diff --git a/.clangd b/.clangd new file mode 100644 index 0000000000000..490220f56a7c0 --- /dev/null +++ b/.clangd @@ -0,0 +1,43 @@ +Diagnostics: + MissingIncludes: None +InlayHints: + Enabled: true + ParameterNames: true + DeducedTypes: true +CompileFlags: + CompilationDatabase: build/ # Search build/ directory for compile_commands.json + Remove: [ -Werror ] + Add: + - -DDEBUG + - -DLOCAL + - -DPGDLLIMPORT= + - -DPIC + - -O2 + - -Wall + - -Wcast-function-type + - -Wconversion + - -Wdeclaration-after-statement + - -Wendif-labels + - -Werror=vla + - -Wextra + - -Wfloat-equal + - -Wformat-security + - -Wimplicit-fallthrough=3 + - -Wmissing-format-attribute + - -Wmissing-prototypes + - -Wno-format-truncation + - -Wno-sign-conversion + - -Wno-stringop-truncation + - -Wno-unused-const-variable + - -Wpointer-arith + - -Wshadow + - -Wshadow=compatible-local + - -fPIC + - -fexcess-precision=standard + - -fno-strict-aliasing + - -fvisibility=hidden + - -fwrapv + - -g + - -std=c11 + - -I. + - -I../../../../src/include diff --git a/.gdbinit b/.gdbinit new file mode 100644 index 0000000000000..854e5ecbaf69c --- /dev/null +++ b/.gdbinit @@ -0,0 +1,156 @@ +# HOT Indexed Updates — GDB breakpoints for code review +# +# Usage: gdb -x .gdbinit +# Or from gdb: source .gdbinit +# +# These breakpoints cover the major code paths introduced or modified by +# the HOT indexed updates patch series. They are organized by subsystem +# to make it easy to enable/disable groups during debugging. +# +# Tip: to skip to a specific subsystem, disable all then enable selectively: +# disable breakpoints +# enable 1 2 3 # just the update-decision group + +# ========================================================================= +# 1. UPDATE DECISION — heap_update() HOT/HOT-indexed/non-HOT choice +# src/backend/access/heap/heapam.c +# ========================================================================= + +# Main entry: heap_update +break heapam.c:3210 + +# HOT decision block: pure HOT vs HOT indexed vs non-HOT +# Line 4019: pure HOT (no indexed columns changed) +# Line 4024: HOT indexed path (non-catalog, some indexed columns changed) +# Line 4031: predict augmented tuple size +# Line 4033: size+space check before creating augmented tuple +break heapam.c:4019 +break heapam.c:4024 +break heapam.c:4033 + +# Set HEAP_INDEXED_UPDATED flag on new tuple before page insertion +break heapam.c:4101 + +# Restore HEAP_INDEXED_UPDATED on old tuple (only if it previously had it) +break heapam.c:4147 + +# ========================================================================= +# 2. TUPLE CREATION — building the augmented tuple with embedded bitmap +# src/backend/access/heap/heapam.c +# ========================================================================= + +# Predict augmented tuple size (returns 0 if t_hoff would overflow) +break heap_hot_indexed_tuple_size + +# Create augmented tuple with embedded modified-column bitmap +break heap_hot_indexed_create_tuple + +# Serialize Bitmapset into raw bytes in tuple header +break heap_hot_indexed_serialize_bitmap + +# ========================================================================= +# 3. BITMAP UTILITIES — raw bitmap operations for chain following +# src/backend/access/heap/heapam.c +# ========================================================================= + +# Compute raw bitmap byte size from natts +break heap_hot_indexed_bitmap_raw_size + +# Check if tuple header has room for bitmap between null bitmap and data +break heap_hot_indexed_has_bitmap_space + +# Read HOT indexed bitmap from tuple header (returns Bitmapset) +break heap_hot_indexed_read_bitmap + +# Fast overlap check: does tuple's raw bitmap overlap with indexed_attrs? +break heap_hot_indexed_bitmap_overlaps_raw + +# OR a tuple's raw bitmap into an accumulator buffer +break heap_hot_indexed_bitmap_or_raw + +# Check if accumulated raw bitmap overlaps with indexed_attrs +break heap_hot_indexed_accum_overlaps + +# Merge bitmaps from dead tuples into a target tuple on the page +break heap_hot_indexed_merge_bitmaps_raw + +# Deserialize raw bytes back to Bitmapset +break heap_hot_indexed_deserialize_bitmap + +# ========================================================================= +# 4. INDEX SCAN — HOT chain following with stale-entry detection +# src/backend/access/heap/heapam_indexscan.c +# ========================================================================= + +# Main HOT chain search with indexed update awareness +break heap_hot_search_buffer + +# Redirect-with-data: initialize bitmap accumulator from collapsed redirect +break heapam_indexscan.c:182 + +# Accumulate bitmap from INDEXED_UPDATED tuple in chain +break heapam_indexscan.c:250 + +# Stale entry detection: accumulated bitmap overlaps this index's attrs +break heapam_indexscan.c:297 + +# ========================================================================= +# 5. INDEX SCAN SETUP — indexed_attrs bitmap computation +# src/backend/access/index/indexam.c +# ========================================================================= + +# Compute indexed_attrs for HOT indexed update chain following +break indexam.c:299 + +# ========================================================================= +# 6. INDEX INSERTION — skip unchanged indexes for HOT indexed updates +# src/backend/executor/execIndexing.c +# ========================================================================= + +# Entry: insert/update index tuples +break ExecInsertIndexTuples + +# Index skip decision: skip indexes whose attrs don't overlap modified set +break execIndexing.c:370 + +# ========================================================================= +# 7. PRUNING — chain collapsing and redirect-with-data +# src/backend/access/heap/pruneheap.c +# ========================================================================= + +# Main prune function +break heap_page_prune_and_freeze + +# Per-chain pruning entry +break heap_prune_chain + +# Chain collapsing: collect bitmaps from dead INDEXED_UPDATED intermediates +break pruneheap.c:1802 + +# OR dead tuple bitmaps into combined bitmap +break pruneheap.c:1836 + +# Record redirect-with-data for execute phase +break pruneheap.c:1863 + +# Execute phase: apply redirect-with-data entries on the page +break pruneheap.c:1287 + +# ========================================================================= +# 8. WAL REPLAY — recovery of HOT indexed updates +# src/backend/access/heap/heapam_xlog.c +# ========================================================================= + +# WAL replay for XLOG_HEAP2_INDEXED_UPDATE +break heap_xlog_indexed_update + +# ========================================================================= +# 9. WAL LOGGING — writing HOT indexed update records +# src/backend/access/heap/heapam.c +# ========================================================================= + +# WAL logging for heap updates (handles indexed_update flag) +break log_heap_update + +# Serialize redirect-with-data into WAL record (pruneheap.c) +break pruneheap.c:2936 diff --git a/.github/.gitignore b/.github/.gitignore new file mode 100644 index 0000000000000..a447f99442861 --- /dev/null +++ b/.github/.gitignore @@ -0,0 +1,18 @@ +# Node modules +scripts/ai-review/node_modules/ +# Note: package-lock.json should be committed for reproducible CI/CD builds + +# Logs +scripts/ai-review/cost-log-*.json +scripts/ai-review/*.log + +# OS files +.DS_Store +Thumbs.db + +# Editor files +*.swp +*.swo +*~ +.vscode/ +.idea/ diff --git a/.github/QUICKSTART.md b/.github/QUICKSTART.md new file mode 100644 index 0000000000000..d22c4d562ab7d --- /dev/null +++ b/.github/QUICKSTART.md @@ -0,0 +1,378 @@ +# Quick Start Guide - PostgreSQL Mirror CI/CD + +**Goal:** Get your PostgreSQL mirror CI/CD system running in 15 minutes. + +--- + +## ✅ What's Been Implemented + +- **Phase 1: Automated Upstream Sync** - Daily sync from postgres/postgres ✅ +- **Phase 2: AI-Powered Code Review** - Claude-based PR reviews ✅ +- **Phase 3: Windows Builds** - Planned for weeks 4-6 📋 + +--- + +## 🚀 Setup Instructions + +### Step 1: Configure GitHub Actions Permissions (2 minutes) + +1. Go to: **Settings → Actions → General** +2. Scroll to: **Workflow permissions** +3. Select: **"Read and write permissions"** +4. Check: **"Allow GitHub Actions to create and approve pull requests"** +5. Click: **Save** + +✅ This enables workflows to push commits and create issues. + +--- + +### Step 2: Set Up Upstream Sync (3 minutes) + +**Test manual sync first:** + +```bash +# Via GitHub Web UI: +# 1. Go to: Actions tab +# 2. Click: "Sync from Upstream (Manual)" +# 3. Click: "Run workflow" +# 4. Watch it run (should take ~2 minutes) + +# OR via GitHub CLI: +gh workflow run sync-upstream-manual.yml +gh run watch +``` + +**Verify sync worked:** + +```bash +git fetch origin +git log origin/master --oneline -5 + +# Compare with upstream: +# https://github.com/postgres/postgres/commits/master +``` + +**Enable automatic sync:** + +- Automatic sync runs daily at 00:00 UTC +- Already configured, no action needed +- Check: Actions → "Sync from Upstream (Automatic)" + +✅ Your master branch will now stay synced automatically. + +--- + +### Step 3: Set Up AI Code Review (10 minutes) + +**Choose Your Provider:** + +You can use either **Anthropic API** (simpler) or **AWS Bedrock** (if you have AWS infrastructure). + +#### Option A: Anthropic API (Recommended for getting started) + +**A. Get Claude API Key:** + +1. Go to: https://console.anthropic.com/ +2. Sign up or log in +3. Navigate to: API Keys +4. Create new key +5. Copy the key (starts with `sk-ant-...`) + +**B. Add API Key to GitHub:** + +1. Go to: **Settings → Secrets and variables → Actions** +2. Click: **New repository secret** +3. Name: `ANTHROPIC_API_KEY` +4. Value: Paste your API key +5. Click: **Add secret** + +**C. Ensure config uses Anthropic:** + +Check `.github/scripts/ai-review/config.json` has: +```json +{ + "provider": "anthropic", + ... +} +``` + +#### Option B: AWS Bedrock (If you have AWS) + +See detailed guide: [.github/docs/bedrock-setup.md](.github/docs/bedrock-setup.md) + +**Quick steps:** +1. Enable Claude 3.5 Sonnet in AWS Bedrock console +2. Create IAM user with `bedrock:InvokeModel` permission +3. Add three secrets to GitHub: + - `AWS_ACCESS_KEY_ID` + - `AWS_SECRET_ACCESS_KEY` + - `AWS_REGION` (e.g., `us-east-1`) +4. Update `.github/scripts/ai-review/config.json`: +```json +{ + "provider": "bedrock", + "bedrock_model_id": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", + "bedrock_region": "us-east-1", + ... +} +``` + +**Note:** Both providers have identical pricing ($0.003/1K input, $0.015/1K output tokens). + +--- + +**C. Install Dependencies:** + +```bash +cd .github/scripts/ai-review +npm install + +# Should install: +# - @anthropic-ai/sdk (for Anthropic API) +# - @aws-sdk/client-bedrock-runtime (for AWS Bedrock) +# - @actions/github +# - @actions/core +# - parse-diff +# - minimatch +``` + +**D. Test AI Review:** + +```bash +# Option 1: Create a test PR +git checkout -b test/ai-review +echo "// Test change" >> src/backend/utils/adt/int.c +git add . +git commit -m "Test: AI review" +git push origin test/ai-review +# Create PR via GitHub UI + +# Option 2: Manual trigger on existing PR +gh workflow run ai-code-review.yml -f pr_number= +``` + +✅ AI will review the PR and post comments + summary. + +--- + +## 🎯 Verify Everything Works + +### Check Sync Status + +```bash +# Check latest sync run +gh run list --workflow=sync-upstream.yml --limit 1 + +# View details +gh run view $(gh run list --workflow=sync-upstream.yml --limit 1 --json databaseId -q '.[0].databaseId') +``` + +**Expected:** ✅ Green checkmark, "Already up to date" or "Successfully synced X commits" + +### Check AI Review Status + +```bash +# Check latest AI review run +gh run list --workflow=ai-code-review.yml --limit 1 + +# View details +gh run view $(gh run list --workflow=ai-code-review.yml --limit 1 --json databaseId -q '.[0].databaseId') +``` + +**Expected:** ✅ Green checkmark, comments posted on PR + +--- + +## 📊 Monitor Costs + +### GitHub Actions Minutes + +```bash +# View usage (requires admin access) +gh api /repos/gburd/postgres/actions/cache/usage + +# Expected monthly usage: +# - Sync: ~150 minutes (FREE - within 2,000 min limit) +# - AI Review: ~200 minutes (FREE - within limit) +``` + +### Claude API Costs + +**View per-PR cost:** +- Check AI review summary comment on PR +- Format: `Cost: $X.XX | Model: claude-3-5-sonnet` + +**Expected costs:** +- Small PR: $0.50 - $1.00 +- Medium PR: $1.00 - $3.00 +- Large PR: $3.00 - $7.50 +- **Monthly (20 PRs):** $35-50 + +**Download detailed logs:** +```bash +gh run list --workflow=ai-code-review.yml --limit 5 +gh run download -n ai-review-cost-log- +``` + +--- + +## 🔧 Configuration + +### Adjust Sync Schedule + +Edit `.github/workflows/sync-upstream.yml`: + +```yaml +on: + schedule: + # Current: Daily at 00:00 UTC + - cron: '0 0 * * *' + + # Options: + # Every 6 hours: '0 */6 * * *' + # Twice daily: '0 0,12 * * *' + # Weekdays only: '0 0 * * 1-5' +``` + +### Adjust AI Review Costs + +Edit `.github/scripts/ai-review/config.json`: + +```json +{ + "cost_limits": { + "max_per_pr_dollars": 15.0, // ← Lower this to save money + "max_per_month_dollars": 200.0, // ← Hard monthly cap + "alert_threshold_dollars": 150.0 + }, + + "max_file_size_lines": 5000, // ← Skip files larger than this + + "skip_paths": [ + "*.png", "*.svg", // Already skipped + "vendor/**/*", // ← Add more patterns here + "generated/**/*" + ] +} +``` + +### Adjust AI Review Prompts + +**Make AI reviews stricter or more lenient:** + +Edit files in `.github/scripts/ai-review/prompts/`: +- `c-code.md` - PostgreSQL C code review +- `sql.md` - SQL and regression tests +- `documentation.md` - Documentation review +- `build-system.md` - Makefile/Meson review + +--- + +## 🐛 Troubleshooting + +### Sync Not Working + +**Problem:** Workflow fails with "Permission denied" + +**Fix:** +- Check: Settings → Actions → Workflow permissions +- Ensure: "Read and write permissions" is selected + +--- + +### AI Review Not Posting Comments + +**Problem:** Workflow runs but no comments appear + +**Check:** +1. Is PR a draft? (Draft PRs are skipped to save costs) +2. Are there reviewable files? (Check workflow logs) +3. Is API key valid? (Settings → Secrets → ANTHROPIC_API_KEY) + +**Fix:** +- Mark PR as "Ready for review" if draft +- Check workflow logs: Actions → Latest run → View logs +- Verify API key at https://console.anthropic.com/ + +--- + +### High AI Review Costs + +**Problem:** Costs higher than expected + +**Check:** +- Download cost logs: `gh run download ` +- Look for large files being reviewed +- Check number of PR updates (each triggers review) + +**Fix:** +1. Add large files to `skip_paths` in config.json +2. Lower `max_tokens_per_request` (shorter reviews) +3. Use draft PRs for work-in-progress +4. Batch PR updates to reduce review frequency + +--- + +## 📚 Full Documentation + +- **Overview:** [.github/README.md](.github/README.md) +- **Sync Guide:** [.github/docs/sync-setup.md](.github/docs/sync-setup.md) +- **AI Review Guide:** [.github/docs/ai-review-guide.md](.github/docs/ai-review-guide.md) +- **Windows Builds:** [.github/docs/windows-builds.md](.github/docs/windows-builds.md) (planned) +- **Implementation Status:** [.github/IMPLEMENTATION_STATUS.md](.github/IMPLEMENTATION_STATUS.md) + +--- + +## ✨ What's Next? + +### Immediate +- ✅ **Monitor first automatic sync** (tonight at 00:00 UTC) +- ✅ **Test AI review on real PR** +- ✅ **Tune prompts** based on feedback + +### This Week +- Shadow mode testing for AI reviews (Week 1) +- Gather developer feedback +- Adjust configuration + +### Weeks 2-3 +- Enable full AI review mode +- Monitor costs and quality +- Iterate on prompts + +### Weeks 4-6 +- **Phase 3:** Implement Windows dependency builds +- Research winpgbuild approach +- Create build workflows +- Test artifact publishing + +--- + +## 🎉 Success Criteria + +You'll know everything is working when: + +✅ **Sync:** +- Master branch matches postgres/postgres +- Daily sync runs show green checkmarks +- No open issues with label `sync-failure` + +✅ **AI Review:** +- PRs receive inline comments + summary +- Feedback is relevant and actionable +- Costs stay under $50/month +- Developers find reviews helpful + +✅ **Overall:** +- Automation saves 8-16 hours/month +- Issues caught earlier in development +- No manual sync needed + +--- + +**Need Help?** +- Check documentation: `.github/README.md` +- Check workflow logs: Actions → Failed run → View logs +- Create issue with workflow URL and error messages + +**Ready to go!** 🚀 diff --git a/.github/README.md b/.github/README.md new file mode 100644 index 0000000000000..bdfcfe74ac4a4 --- /dev/null +++ b/.github/README.md @@ -0,0 +1,315 @@ +# PostgreSQL Mirror CI/CD System + +This directory contains the CI/CD infrastructure for the PostgreSQL personal mirror repository. + +## System Overview + +``` +┌─────────────────────────────────────────────────────────────┐ +│ PostgreSQL Mirror CI/CD │ +└─────────────────────────────────────────────────────────────┘ + │ + ┌──────────────────────┼──────────────────────┐ + │ │ │ + [1] Sync [2] AI Review [3] Windows + Daily @ 00:00 On PR Events On Master Push + │ │ │ + ▼ ▼ ▼ + postgres/postgres Claude API Dependency Builds + │ │ │ + ▼ ▼ ▼ + github.com/gburd PR Comments Build Artifacts + /postgres/ + Labels (90-day retention) + master +``` + +## Components + +### 1. Automated Upstream Sync +**Status:** ✓ Implemented +**Files:** `workflows/sync-upstream*.yml` + +Automatically syncs the `master` branch with upstream `postgres/postgres` daily. + +- **Frequency:** Daily at 00:00 UTC +- **Trigger:** Cron schedule + manual +- **Features:** + - Fast-forward merge (conflict-free) + - Automatic issue creation on conflicts + - Issue auto-closure on resolution +- **Cost:** Free (~150 min/month, well within free tier) + +**Documentation:** [docs/sync-setup.md](docs/sync-setup.md) + +### 2. AI-Powered Code Review +**Status:** ✓ Implemented +**Files:** `workflows/ai-code-review.yml`, `scripts/ai-review/` + +Uses Claude API to provide PostgreSQL-aware code review on pull requests. + +- **Trigger:** PR opened/updated, ready for review +- **Features:** + - PostgreSQL-specific C code review + - SQL, documentation, build system review + - Inline comments on issues + - Automatic labeling (security, performance, etc.) + - Cost tracking and limits + - **Provider Options:** Anthropic API or AWS Bedrock +- **Cost:** $35-50/month (estimated) +- **Model:** Claude 3.5 Sonnet + +**Documentation:** [docs/ai-review-guide.md](docs/ai-review-guide.md) + +### 3. Windows Build Integration +**Status:** ✅ Implemented +**Files:** `workflows/windows-dependencies.yml`, `windows/`, `scripts/windows/` + +Builds PostgreSQL Windows dependencies for x64 Windows. + +- **Trigger:** Manual, manifest changes, weekly refresh +- **Features:** + - Core dependencies: OpenSSL, zlib, libxml2 + - Smart caching by version hash + - Dependency bundling + - Artifact publishing (90-day retention) + - PowerShell download helper + - **Cost optimization:** Skips builds for pristine commits (dev setup, .github/ only) +- **Cost:** ~$5-8/month (with caching and optimization) + +**Documentation:** [docs/windows-builds.md](docs/windows-builds.md) | [Usage](docs/windows-builds-usage.md) + +## Quick Start + +### Prerequisites + +1. **GitHub Actions enabled:** + - Settings → Actions → General → Allow all actions + +2. **Workflow permissions:** + - Settings → Actions → General → Workflow permissions + - Select: "Read and write permissions" + - Enable: "Allow GitHub Actions to create and approve pull requests" + +3. **Secrets configured:** + - **Option A - Anthropic API:** + - Settings → Secrets and variables → Actions + - Add: `ANTHROPIC_API_KEY` (get from https://console.anthropic.com/) + - **Option B - AWS Bedrock:** + - Add: `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_REGION` + - See: [docs/bedrock-setup.md](docs/bedrock-setup.md) + +### Using the Sync System + +**Manual sync:** +```bash +# Via GitHub UI: +# Actions → "Sync from Upstream (Manual)" → Run workflow + +# Via GitHub CLI: +gh workflow run sync-upstream-manual.yml +``` + +**Check sync status:** +```bash +# Latest sync run +gh run list --workflow=sync-upstream.yml --limit 1 + +# View details +gh run view +``` + +### Using AI Code Review + +AI reviews run automatically on PRs. To test manually: + +```bash +# Via GitHub UI: +# Actions → "AI Code Review" → Run workflow → Enter PR number + +# Via GitHub CLI: +gh workflow run ai-code-review.yml -f pr_number=123 +``` + +**Reviewing AI feedback:** +1. AI posts inline comments on specific lines +2. AI posts summary comment with overview +3. AI adds labels (security-concern, needs-tests, etc.) +4. Review and address feedback like human reviewer comments + +### Cost Monitoring + +**View AI review costs:** +```bash +# Download cost logs +gh run download -n ai-review-cost-log- +``` + +**Expected monthly costs (with optimizations):** +- Sync: $0 (free tier) +- AI Review: $30-45 (only on PRs, skips drafts) +- Windows Builds: $5-8 (caching + pristine commit skipping) +- **Total: $35-53/month** + +**Cost optimizations:** +- Windows builds skip "dev setup" and .github/-only commits +- AI review only runs on non-draft PRs +- Aggressive caching reduces build times by 80-90% +- See [Cost Optimization Guide](docs/cost-optimization.md) for details + +## Workflow Files + +### Sync Workflows +- `workflows/sync-upstream.yml` - Automatic daily sync +- `workflows/sync-upstream-manual.yml` - Manual testing sync + +### AI Review Workflows +- `workflows/ai-code-review.yml` - Automatic PR review + +### Windows Build Workflows +- `workflows/windows-dependencies.yml` - Dependency builds (TBD) + +## Configuration Files + +### AI Review Configuration +- `scripts/ai-review/config.json` - Cost limits, file patterns, labels +- `scripts/ai-review/prompts/*.md` - Review prompts by file type +- `scripts/ai-review/package.json` - Node.js dependencies + +### Windows Build Configuration +- `windows/manifest.json` - Dependency versions (TBD) + +## Branch Strategy + +### Master Branch: Mirror Only +- **Purpose:** Pristine copy of `postgres/postgres` +- **Rule:** Never commit directly to master +- **Sync:** Automatic via GitHub Actions +- **Protection:** Consider branch protection rules + +### Feature Branches: Development +- **Pattern:** `feature/*`, `dev/*`, `experiment/*` +- **Workflow:** + ```bash + git checkout master + git pull origin master + git checkout -b feature/my-feature + # ... make changes ... + git push origin feature/my-feature + # Create PR: feature/my-feature → master + ``` + +### Special Branches +- `recovery/*` - Temporary branches for sync conflict resolution +- Development remotes: commitfest, heikki, orioledb, zheap + +## Integration with Cirrus CI + +GitHub Actions and Cirrus CI run independently: + +- **Cirrus CI:** Comprehensive testing (Linux, FreeBSD, macOS, Windows) +- **GitHub Actions:** Sync, AI review, Windows dependency builds +- **No conflicts:** Both can run on same commits + +## Troubleshooting + +### Sync Issues + +**Problem:** Sync workflow failing +**Check:** Actions → "Sync from Upstream (Automatic)" → Latest run +**Fix:** See [docs/sync-setup.md](docs/sync-setup.md#sync-failure-recovery) + +### AI Review Issues + +**Problem:** AI review not running +**Check:** Is PR a draft? Draft PRs are skipped +**Fix:** Mark PR as ready for review + +**Problem:** AI review too expensive +**Check:** Cost logs in workflow artifacts +**Fix:** Adjust limits in `scripts/ai-review/config.json` + +### Workflow Permission Issues + +**Problem:** "Resource not accessible by integration" +**Check:** Settings → Actions → General → Workflow permissions +**Fix:** Enable "Read and write permissions" + +## Security + +### Secrets Management +- `ANTHROPIC_API_KEY`: Claude API key (required for AI review) +- `GITHUB_TOKEN`: Auto-generated, scoped to repository +- Never commit secrets to repository +- Rotate API keys quarterly + +### Permissions +- Workflows use minimum necessary permissions +- `contents: read` for code access +- `pull-requests: write` for comments +- `issues: write` for sync failure issues + +### Audit Trail +- All workflow runs logged (90-day retention) +- Cost tracking for AI reviews +- GitHub Actions audit log available + +## Support and Documentation + +### Detailed Documentation +- [Sync Setup Guide](docs/sync-setup.md) - Upstream sync system +- [AI Review Guide](docs/ai-review-guide.md) - AI code review system +- [Windows Builds Guide](docs/windows-builds.md) - Windows dependencies +- [Cost Optimization Guide](docs/cost-optimization.md) - Reducing CI/CD costs +- [Pristine Master Policy](docs/pristine-master-policy.md) - Master branch management + +### Reporting Issues + +Issues with CI/CD system: +1. Check workflow logs: Actions → Failed run → View logs +2. Search existing issues: label:automation +3. Create issue with workflow run URL and error messages + +### Modifying Workflows + +**Disabling a workflow:** +```bash +# Via GitHub UI: +# Actions → Select workflow → "..." → Disable workflow + +# Via git: +git mv .github/workflows/workflow-name.yml .github/workflows/workflow-name.yml.disabled +git commit -m "Disable workflow" +``` + +**Testing workflow changes:** +1. Create feature branch +2. Modify workflow file +3. Use `workflow_dispatch` trigger to test +4. Verify in Actions tab +5. Merge to master when working + +## Cost Summary + +| Component | Monthly Cost | Usage | Notes | +|-----------|-------------|-------|-------| +| Sync | $0 | ~150 min | Free tier: 2,000 min | +| AI Review | $30-45 | Variable | Claude API usage-based | +| Windows Builds | $5-8 | ~2,500 min | With caching + optimization | +| **Total** | **$35-53** | | After cost optimizations | + +**Comparison:** CodeRabbit (turnkey solution) = $99-499/month + +**Cost savings:** ~40-47% reduction through optimizations (see [Cost Optimization Guide](docs/cost-optimization.md)) + +## References + +- PostgreSQL: https://github.com/postgres/postgres +- GitHub Actions: https://docs.github.com/en/actions +- Claude API: https://docs.anthropic.com/ +- Cirrus CI: https://cirrus-ci.org/ +- winpgbuild: https://github.com/dpage/winpgbuild + +--- + +**Last Updated:** 2026-03-10 +**Maintained by:** PostgreSQL Mirror Automation diff --git a/.github/docs/ai-review-guide.md b/.github/docs/ai-review-guide.md new file mode 100644 index 0000000000000..eff0ed10cba4f --- /dev/null +++ b/.github/docs/ai-review-guide.md @@ -0,0 +1,512 @@ +# AI-Powered Code Review Guide + +## Overview + +This system uses Claude AI (Anthropic) to provide PostgreSQL-aware code reviews on pull requests. Reviews are similar in style to feedback from the PostgreSQL Hackers mailing list. + +## How It Works + +``` +PR Event (opened/updated) + ↓ +GitHub Actions Workflow Starts + ↓ +Fetch PR diff + metadata + ↓ +Filter reviewable files (.c, .h, .sql, docs, Makefiles) + ↓ +Route each file to appropriate review prompt + ↓ +Send to Claude API with PostgreSQL context + ↓ +Parse response for issues + ↓ +Post inline comments + summary to PR + ↓ +Add labels (security-concern, performance, etc.) +``` + +## Features + +### PostgreSQL-Specific Reviews + +**C Code Review:** +- Memory management (palloc/pfree, memory contexts) +- Concurrency (lock ordering, race conditions) +- Error handling (elog/ereport patterns) +- Performance (algorithm complexity, cache efficiency) +- Security (buffer overflows, SQL injection vectors) +- PostgreSQL conventions (naming, comments, style) + +**SQL Review:** +- PostgreSQL SQL dialect correctness +- Regression test patterns +- Performance (index usage, join strategy) +- Deterministic output for tests +- Edge case coverage + +**Documentation Review:** +- Technical accuracy +- SGML/DocBook format +- PostgreSQL style guide compliance +- Examples and cross-references + +**Build System Review:** +- Makefile correctness (GNU Make, PGXS) +- Meson build consistency +- Cross-platform portability +- VPATH build support + +### Automatic Labeling + +Reviews automatically add labels based on findings: + +- `security-concern` - Security issues, vulnerabilities +- `performance-concern` - Performance problems +- `needs-tests` - Missing test coverage +- `needs-docs` - Missing documentation +- `memory-management` - Memory leaks, context issues +- `concurrency-issue` - Deadlocks, race conditions + +### Cost Management + +- **Per-PR limit:** $15 (configurable) +- **Monthly limit:** $200 (configurable) +- **Alert threshold:** $150 +- **Skip draft PRs** to save costs +- **Skip large files** (>5000 lines) +- **Skip binary/generated files** + +## Setup + +### 1. Install Dependencies + +```bash +cd .github/scripts/ai-review +npm install +``` + +### 2. Configure API Key + +Get API key from: https://console.anthropic.com/ + +Add to repository secrets: +1. Settings → Secrets and variables → Actions +2. New repository secret +3. Name: `ANTHROPIC_API_KEY` +4. Value: Your API key +5. Add secret + +### 3. Enable Workflow + +The workflow is triggered automatically on PR events: +- PR opened +- PR synchronized (updated) +- PR reopened +- PR marked ready for review (draft → ready) + +**Draft PRs are skipped** to save costs. + +## Configuration + +### Main Configuration: `config.json` + +```json +{ + "model": "claude-3-5-sonnet-20241022", + "max_tokens_per_request": 4096, + "max_file_size_lines": 5000, + + "cost_limits": { + "max_per_pr_dollars": 15.0, + "max_per_month_dollars": 200.0, + "alert_threshold_dollars": 150.0 + }, + + "skip_paths": [ + "*.png", "*.jpg", "*.svg", + "src/test/regress/expected/*", + "*.po", "*.pot" + ], + + "auto_labels": { + "security-concern": ["security issue", "vulnerability"], + "performance-concern": ["inefficient", "O(n²)"], + "needs-tests": ["missing test", "no test coverage"] + } +} +``` + +**Tunable parameters:** +- `max_tokens_per_request`: Response length (4096 = ~3000 words) +- `max_file_size_lines`: Skip files larger than this +- `cost_limits`: Adjust budget caps +- `skip_paths`: Add more patterns to skip +- `auto_labels`: Customize label keywords + +### Review Prompts + +Located in `.github/scripts/ai-review/prompts/`: + +- `c-code.md` - PostgreSQL C code review +- `sql.md` - SQL and regression test review +- `documentation.md` - Documentation review +- `build-system.md` - Makefile/Meson review + +**Customization:** Edit prompts to adjust review focus and style. + +## Usage + +### Automatic Reviews + +Reviews run automatically on PRs to `master` and `feature/**` branches. + +**Typical workflow:** +1. Create feature branch +2. Make changes +3. Push branch: `git push origin feature/my-feature` +4. Create PR +5. AI review runs automatically +6. Review AI feedback +7. Make updates if needed +8. Push updates → AI re-reviews + +### Manual Reviews + +Trigger manually via GitHub Actions: + +**Via UI:** +1. Actions → "AI Code Review" +2. Run workflow +3. Enter PR number +4. Run workflow + +**Via CLI:** +```bash +gh workflow run ai-code-review.yml -f pr_number=123 +``` + +### Interpreting Reviews + +**Inline comments:** +- Posted on specific lines of code +- Format: `**[Category]**` followed by description +- Categories: Memory, Security, Performance, etc. + +**Summary comment:** +- Posted at PR level +- Overview of files reviewed +- Issue count by category +- Cost information + +**Labels:** +- Automatically added based on findings +- Filter PRs by label to prioritize +- Remove label manually if false positive + +### Best Practices + +**Trust but verify:** +- AI reviews are helpful but not infallible +- False positives happen (~5% rate) +- Use judgment - AI doesn't have full context +- Especially verify: security and correctness issues + +**Iterative improvement:** +- AI learns from the prompts, not from feedback +- If AI consistently misses something, update prompts +- Share false positives/negatives to improve system + +**Cost consciousness:** +- Keep PRs focused (fewer files = lower cost) +- Use draft PRs for work-in-progress (AI skips drafts) +- Mark PR ready when you want AI review + +## Cost Tracking + +### View Costs + +**Per-PR cost:** +- Shown in AI review summary comment +- Format: `Cost: $X.XX | Model: claude-3-5-sonnet` + +**Monthly cost:** +- Download cost logs from workflow artifacts +- Aggregate to calculate monthly total + +**Download cost logs:** +```bash +# List recent runs +gh run list --workflow=ai-code-review.yml --limit 10 + +# Download artifact +gh run download -n ai-review-cost-log- +``` + +### Cost Estimation + +**Token costs (Claude 3.5 Sonnet):** +- Input: $0.003 per 1K tokens +- Output: $0.015 per 1K tokens + +**Typical costs:** +- Small PR (<500 lines, 5 files): $0.50-$1.00 +- Medium PR (500-2000 lines, 15 files): $1.00-$3.00 +- Large PR (2000-5000 lines, 30 files): $3.00-$7.50 + +**Expected monthly (20 PRs/month mixed sizes):** $35-50 + +### Budget Controls + +**Automatic limits:** +- Per-PR limit: Stops reviewing after $15 +- Monthly limit: Stops at $200 (requires manual override) +- Alert: Warning at $150 + +**Manual controls:** +- Disable workflow: Actions → AI Code Review → Disable +- Reduce `max_tokens_per_request` in config +- Add more patterns to `skip_paths` +- Increase `max_file_size_lines` threshold + +## Troubleshooting + +### Issue: No review posted + +**Possible causes:** +1. PR is draft (intentionally skipped) +2. No reviewable files (all binary or skipped patterns) +3. API key missing or invalid +4. Cost limit reached + +**Check:** +- Actions → "AI Code Review" → Latest run → View logs +- Look for: "Skipping draft PR" or "No reviewable files" +- Verify: `ANTHROPIC_API_KEY` secret exists + +### Issue: Review incomplete + +**Possible causes:** +1. PR cost limit reached ($15 default) +2. File too large (>5000 lines) +3. API rate limit hit + +**Check:** +- Review summary comment for "Reached PR cost limit" +- Workflow logs for "Skipping X - too large" + +**Fix:** +- Increase `max_per_pr_dollars` in config +- Increase `max_file_size_lines` (trade-off: higher cost) +- Split large PR into smaller PRs + +### Issue: False positives + +**Example:** AI flags correct code as problematic + +**Handling:** +1. Ignore the comment (human judgment overrides) +2. Reply to comment explaining why it's correct +3. If systematic: Update prompt to clarify + +**Note:** Some false positives are acceptable (5-10% rate) + +### Issue: Claude API errors + +**Error types:** +- `401 Unauthorized`: Invalid API key +- `429 Too Many Requests`: Rate limit +- `500 Internal Server Error`: Claude service issue + +**Check:** +- Workflow logs for error messages +- Claude status: https://status.anthropic.com/ + +**Fix:** +- Rotate API key if 401 +- Wait and retry if 429 or 500 +- Contact Anthropic support if persistent + +### Issue: High costs + +**Unexpected high costs:** +1. Check cost logs for large PRs +2. Review `skip_paths` - are large files being reviewed? +3. Check for repeated reviews (PR updated many times) + +**Optimization:** +- Add more skip patterns for generated files +- Lower `max_tokens_per_request` (shorter reviews) +- Increase `max_file_size_lines` to skip more files +- Batch PR updates to reduce review runs + +## Disabling AI Review + +### Temporarily disable + +**For one PR:** +- Convert to draft +- Or add `[skip ai]` to PR title (requires workflow modification) + +**For all PRs:** +```bash +# Via GitHub UI: +# Actions → "AI Code Review" → "..." → Disable workflow + +# Via git: +git mv .github/workflows/ai-code-review.yml \ + .github/workflows/ai-code-review.yml.disabled +git commit -m "Disable AI code review" +git push +``` + +### Permanently remove + +```bash +# Remove workflow +rm .github/workflows/ai-code-review.yml + +# Remove scripts +rm -rf .github/scripts/ai-review + +# Commit +git commit -am "Remove AI code review system" +git push +``` + +## Testing and Iteration + +### Shadow Mode (Week 1) + +Run reviews but don't post comments: + +1. Modify `review-pr.js`: + ```javascript + // Comment out posting functions + // await postInlineComments(...) + // await postSummaryComment(...) + ``` + +2. Reviews saved to workflow artifacts +3. Review quality offline +4. Tune prompts based on results + +### Comment Mode (Week 2) + +Post comments with `[AI Review]` prefix: + +1. Add prefix to comment body: + ```javascript + const body = `**[AI Review] [${issue.category}]**\n\n${issue.description}`; + ``` + +2. Gather feedback from developers +3. Adjust prompts and configuration + +### Full Mode (Week 3+) + +Remove prefix, enable all features: + +1. Remove `[AI Review]` prefix +2. Enable auto-labeling +3. Monitor quality and costs +4. Iterate on prompts as needed + +## Advanced Customization + +### Custom Review Prompts + +Add a new prompt for a file type: + +1. Create `.github/scripts/ai-review/prompts/my-type.md` +2. Write review guidelines (see existing prompts) +3. Update `config.json`: + ```json + "file_type_patterns": { + "my_type": ["*.ext", "special/*.files"] + } + ``` +4. Test with manual workflow trigger + +### Conditional Reviews + +Skip AI review for certain PRs: + +Modify `.github/workflows/ai-code-review.yml`: +```yaml +jobs: + ai-review: + if: | + github.event.pull_request.draft == false && + !contains(github.event.pull_request.title, '[skip ai]') && + !contains(github.event.pull_request.labels.*.name, 'no-ai-review') +``` + +### Cost Alerts + +Add cost alert notifications: + +1. Create workflow in `.github/workflows/cost-alert.yml` +2. Trigger: On schedule (weekly) +3. Aggregate cost logs +4. Post issue if over threshold + +## Security and Privacy + +### API Key Security + +- Store only in GitHub Secrets (encrypted at rest) +- Never commit to repository +- Never log in workflow output +- Rotate quarterly + +### Code Privacy + +- Code sent to Claude API (Anthropic) +- Anthropic does not train on API data +- API requests are not retained long-term +- See: https://www.anthropic.com/legal/privacy + +### Sensitive Code + +If reviewing sensitive/proprietary code: + +1. Review Anthropic's terms of service +2. Consider: Self-hosted alternative (future) +3. Or: Skip AI review for sensitive PRs (add label) + +## Support + +### Questions + +- Check this guide first +- Search GitHub issues: label:ai-review +- Check Claude API docs: https://docs.anthropic.com/ + +### Reporting Issues + +Create issue with: +- PR number +- Workflow run URL +- Error messages from logs +- Expected vs actual behavior + +### Improving Prompts + +Contributions welcome: +1. Identify systematic issue (false positive/negative) +2. Propose prompt modification +3. Test on sample PRs +4. Submit PR with updated prompt + +## References + +- Claude API: https://docs.anthropic.com/ +- Claude Models: https://www.anthropic.com/product +- PostgreSQL Hacker's Guide: https://wiki.postgresql.org/wiki/Developer_FAQ +- GitHub Actions: https://docs.github.com/en/actions + +--- + +**Version:** 1.0 +**Last Updated:** 2026-03-10 diff --git a/.github/docs/bedrock-setup.md b/.github/docs/bedrock-setup.md new file mode 100644 index 0000000000000..d8fbd898b51c6 --- /dev/null +++ b/.github/docs/bedrock-setup.md @@ -0,0 +1,298 @@ +# AWS Bedrock Setup for AI Code Review + +This guide explains how to use AWS Bedrock instead of the direct Anthropic API for AI code reviews. + +## Why Use Bedrock? + +- **AWS Credits:** Use existing AWS credits +- **Regional Availability:** Deploy in specific AWS regions +- **Compliance:** Meet specific compliance requirements +- **Integration:** Easier integration with AWS infrastructure +- **IAM Roles:** Use IAM roles instead of API keys when running on AWS + +## Prerequisites + +1. **AWS Account** with Bedrock access +2. **Bedrock Model Access** - Claude 3.5 Sonnet must be enabled +3. **IAM Permissions** for Bedrock API calls + +## Step 1: Enable Bedrock Model Access + +1. Log into AWS Console +2. Navigate to **Amazon Bedrock** +3. Go to **Model access** (left sidebar) +4. Click **Modify model access** +5. Find and enable: **Anthropic - Claude 3.5 Sonnet v2** +6. Click **Save changes** +7. Wait for status to show "Access granted" (~2-5 minutes) + +## Step 2: Create IAM User for GitHub Actions + +### Option A: IAM User with Access Keys (Recommended for GitHub Actions) + +1. Go to **IAM Console** +2. Click **Users** → **Create user** +3. Username: `github-actions-bedrock` +4. Click **Next** + +**Attach Policy:** +```json +{ + "Version": "2012-10-17", + "Statement": [ + { + "Effect": "Allow", + "Action": [ + "bedrock:InvokeModel" + ], + "Resource": [ + "arn:aws:bedrock:*::foundation-model/anthropic.claude-3-5-sonnet-*" + ] + } + ] +} +``` + +5. Click **Create policy** → **JSON** → Paste above +6. Name: `BedrockClaudeInvokeOnly` +7. Attach policy to user +8. Click **Create user** + +**Create Access Keys:** +1. Click on the created user +2. Go to **Security credentials** tab +3. Click **Create access key** +4. Select: **Third-party service** +5. Click **Next** → **Create access key** +6. **Download** or copy: + - Access key ID (starts with `AKIA...`) + - Secret access key (only shown once!) + +### Option B: IAM Role (For AWS-hosted runners) + +If running GitHub Actions on AWS (self-hosted runners): + +1. Create IAM Role with trust policy for your EC2/ECS/EKS +2. Attach same `BedrockClaudeInvokeOnly` policy +3. Assign role to your runner infrastructure +4. No access keys needed! + +## Step 3: Configure Repository + +### A. Add AWS Secrets to GitHub + +1. Go to: **Settings** → **Secrets and variables** → **Actions** +2. Click **New repository secret** for each: + +**Secret 1:** +- Name: `AWS_ACCESS_KEY_ID` +- Value: Your access key ID from Step 2 + +**Secret 2:** +- Name: `AWS_SECRET_ACCESS_KEY` +- Value: Your secret access key from Step 2 + +**Secret 3:** +- Name: `AWS_REGION` +- Value: Your Bedrock region (e.g., `us-east-1`) + +### B. Update Configuration + +Edit `.github/scripts/ai-review/config.json`: + +```json +{ + "provider": "bedrock", + "model": "claude-3-5-sonnet-20241022", + "bedrock_model_id": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", + "bedrock_region": "us-east-1", + ... +} +``` + +**Available Bedrock Model IDs:** +- US: `us.anthropic.claude-3-5-sonnet-20241022-v2:0` +- EU: `eu.anthropic.claude-3-5-sonnet-20241022-v2:0` +- Asia Pacific: `apac.anthropic.claude-3-5-sonnet-20241022-v2:0` + +**Available Regions:** +- `us-east-1` (US East - N. Virginia) +- `us-west-2` (US West - Oregon) +- `eu-central-1` (Europe - Frankfurt) +- `eu-west-1` (Europe - Ireland) +- `eu-west-2` (Europe - London) +- `ap-southeast-1` (Asia Pacific - Singapore) +- `ap-southeast-2` (Asia Pacific - Sydney) +- `ap-northeast-1` (Asia Pacific - Tokyo) + +Check current availability: https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html + +### C. Install Dependencies + +```bash +cd .github/scripts/ai-review +npm install +``` + +This will install the AWS SDK for Bedrock. + +## Step 4: Test Bedrock Integration + +```bash +# Create test PR +git checkout -b test/bedrock-review +echo "// Bedrock test" >> test.c +git add test.c +git commit -m "Test: Bedrock AI review" +git push origin test/bedrock-review +``` + +Then create PR via GitHub UI. Check: +1. **Actions** tab - workflow should run +2. **PR comments** - AI review should appear +3. **Workflow logs** - should show "Using AWS Bedrock as provider" + +## Cost Comparison + +### Bedrock Pricing (Claude 3.5 Sonnet - us-east-1) +- Input: $0.003 per 1K tokens +- Output: $0.015 per 1K tokens + +### Direct Anthropic API Pricing +- Input: $0.003 per 1K tokens +- Output: $0.015 per 1K tokens + +**Same price!** Choose based on infrastructure preference. + +## Troubleshooting + +### Error: "Access denied to model" + +**Check:** +1. Model access enabled in Bedrock console? +2. IAM policy includes correct model ARN? +3. Region matches between config and enabled models? + +**Fix:** +```bash +# Verify model access via AWS CLI +aws bedrock list-foundation-models --region us-east-1 --query 'modelSummaries[?contains(modelId, `claude-3-5-sonnet`)]' +``` + +### Error: "InvalidSignatureException" + +**Check:** +1. AWS_ACCESS_KEY_ID correct? +2. AWS_SECRET_ACCESS_KEY correct? +3. Secrets named exactly as shown? + +**Fix:** +- Re-create access keys +- Update GitHub secrets +- Ensure no extra spaces in secret values + +### Error: "ThrottlingException" + +**Cause:** Bedrock rate limits exceeded + +**Fix:** +1. Reduce `max_concurrent_requests` in config.json +2. Add delays between requests +3. Request quota increase via AWS Support + +### Error: "Model not found" + +**Check:** +1. `bedrock_model_id` matches your region +2. Using cross-region model ID (e.g., `us.anthropic...` in us-east-1) + +**Fix:** +Update `bedrock_model_id` in config.json to match your region: +- US regions: `us.anthropic.claude-3-5-sonnet-20241022-v2:0` +- EU regions: `eu.anthropic.claude-3-5-sonnet-20241022-v2:0` + +## Switching Between Providers + +### Switch to Bedrock + +Edit `.github/scripts/ai-review/config.json`: +```json +{ + "provider": "bedrock", + ... +} +``` + +### Switch to Direct Anthropic API + +Edit `.github/scripts/ai-review/config.json`: +```json +{ + "provider": "anthropic", + ... +} +``` + +No other changes needed! The code automatically detects the provider. + +## Advanced: Cross-Region Setup + +Deploy in multiple regions for redundancy: + +```json +{ + "provider": "bedrock", + "bedrock_regions": ["us-east-1", "us-west-2"], + "bedrock_failover": true +} +``` + +Then update `review-pr.js` to implement failover logic. + +## Security Best Practices + +1. **Least Privilege:** IAM user can only invoke Claude models +2. **Rotate Keys:** Rotate access keys quarterly +3. **Audit Logs:** Enable CloudTrail for Bedrock API calls +4. **Cost Alerts:** Set up AWS Budgets alerts +5. **Secrets:** Never commit AWS credentials to git + +## Monitoring + +### AWS CloudWatch + +Bedrock metrics available: +- `Invocations` - Number of API calls +- `InvocationLatency` - Response time +- `InvocationClientErrors` - 4xx errors +- `InvocationServerErrors` - 5xx errors + +### Cost Tracking + +```bash +# Check Bedrock costs (current month) +aws ce get-cost-and-usage \ + --time-period Start=2026-03-01,End=2026-03-31 \ + --granularity MONTHLY \ + --metrics BlendedCost \ + --filter file://filter.json + +# filter.json: +{ + "Dimensions": { + "Key": "SERVICE", + "Values": ["Amazon Bedrock"] + } +} +``` + +## References + +- AWS Bedrock Docs: https://docs.aws.amazon.com/bedrock/ +- Model Access: https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html +- Bedrock Pricing: https://aws.amazon.com/bedrock/pricing/ +- IAM Best Practices: https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html + +--- + +**Need help?** Check workflow logs in Actions tab or create an issue. diff --git a/.github/docs/cost-optimization.md b/.github/docs/cost-optimization.md new file mode 100644 index 0000000000000..bcfc1c47b3ed8 --- /dev/null +++ b/.github/docs/cost-optimization.md @@ -0,0 +1,219 @@ +# CI/CD Cost Optimization + +## Overview + +This document describes the cost optimization strategies used in the PostgreSQL mirror CI/CD system to minimize GitHub Actions minutes and API costs while maintaining full functionality. + +## Optimization Strategies + +### 1. Skip Builds for Pristine Commits + +**Problem:** "Dev setup" commits and .github/ configuration changes don't require expensive Windows dependency builds or comprehensive testing. + +**Solution:** The Windows Dependencies workflow includes a `check-changes` job that inspects recent commits and skips builds when all commits are: +- Messages starting with "dev setup" (case-insensitive), OR +- Only modifying files under `.github/` directory + +**Implementation:** See `.github/workflows/windows-dependencies.yml` lines 42-90 + +**Savings:** +- Avoids ~45 minutes of Windows runner time per push +- Windows runners cost 2x Linux minutes (1 minute = 2 billed minutes) +- Estimated savings: ~$8-12/month + +### 2. AI Review Only on Pull Requests + +**Problem:** AI code review is expensive and unnecessary for direct commits to master or pristine commits. + +**Solution:** The AI Code Review workflow only triggers on: +- `pull_request` events (opened, synchronized, reopened, ready_for_review) +- Manual `workflow_dispatch` for testing specific PRs +- Skips draft PRs automatically + +**Implementation:** See `.github/workflows/ai-code-review.yml` lines 3-17 + +**Savings:** +- No reviews on dev setup commits or CI/CD changes +- No reviews on draft PRs (saves ~$1-3 per draft) +- Estimated savings: ~$10-20/month + +### 3. Aggressive Caching + +**Windows Dependencies:** +- Cache key: `--win64-` +- Cache duration: GitHub's default (7 days unused, 10 GB limit) +- Cache hit rate: 80-90% for stable versions + +**Node.js Dependencies:** +- AI review scripts cache npm packages +- Cache key based on `package.json` hash +- Near 100% cache hit rate + +**Savings:** +- Reduces build time from 45 minutes to ~5 minutes on cache hit +- Estimated savings: ~$15-20/month + +### 4. Weekly Scheduled Builds + +**Problem:** GitHub Actions artifacts expire after 90 days, making cached dependencies stale. + +**Solution:** Windows Dependencies runs on a weekly schedule (Sunday 4 AM UTC) to refresh artifacts before expiration. + +**Cost:** +- Weekly builds: ~45 minutes/week × 4 weeks = 180 minutes/month +- Windows multiplier: 360 billed minutes +- Cost: ~$6/month (within budget) + +**Alternative considered:** Daily builds would cost ~$50/month (rejected) + +### 5. Sync Workflow Optimization + +**Automatic Sync:** +- Runs hourly to keep mirror current +- Very lightweight: ~2-3 minutes per run +- Cost: ~150 minutes/month = $0 (within free tier) + +**Manual Sync:** +- Only runs on explicit trigger +- Used for testing and recovery +- Cost: Negligible + +### 6. Smart Workflow Triggers + +**Path-based triggers:** +```yaml +push: + paths: + - '.github/windows/manifest.json' + - '.github/workflows/windows-dependencies.yml' +``` + +Only rebuild Windows dependencies when: +- Manifest versions change +- Workflow itself is updated +- Manual trigger or schedule + +**Branch-based triggers:** +- AI review only on PRs to master, feature/**, dev/** +- Sync only affects master branch + +## Cost Breakdown + +| Component | Monthly Cost | Notes | +|-----------|-------------|-------| +| GitHub Actions - Sync | $0 | ~150 min/month (free: 2,000 min) | +| GitHub Actions - AI Review | $0 | ~200 min/month (free: 2,000 min) | +| GitHub Actions - Windows | ~$5-8 | ~2,500 min/month with optimizations | +| Claude API (Bedrock) | $30-45 | Usage-based, ~15-20 PRs/month | +| **Total** | **~$35-53/month** | | + +**Before optimizations:** ~$75-100/month +**After optimizations:** ~$35-53/month +**Savings:** ~$40-47/month (40-47% reduction) + +## Monitoring Costs + +### GitHub Actions Usage + +Check usage in repository settings: +``` +Settings → Billing and plans → View usage +``` + +Or via CLI: +```bash +gh api repos/:owner/:repo/actions/billing/workflows --jq '.workflows' +``` + +### AWS Bedrock Usage + +Monitor Claude API costs in AWS Console: +``` +AWS Console → Bedrock → Usage → Invocation metrics +``` + +Or via cost logs in artifacts: +``` +.github/scripts/ai-review/cost-log-*.json +``` + +### Setting Alerts + +**GitHub Actions:** +- No built-in alerts +- Monitor via monthly email summaries +- Consider third-party monitoring (e.g., AWS Lambda + GitHub API) + +**AWS Bedrock:** +- Set CloudWatch billing alarms +- Recommended thresholds: + - Warning: $30/month + - Critical: $50/month +- Hard cap in code: $200/month (see `config.json`) + +## Future Optimizations + +### Potential Improvements + +1. **Conditional Testing on PRs** + - Only run full Cirrus CI suite if C code or SQL changes + - Skip for docs-only PRs + - Estimated savings: ~5-10% of testing costs + +2. **Incremental AI Review** + - On PR updates, only review changed files + - Current: Reviews entire PR on each update + - Estimated savings: ~20-30% of AI costs + +3. **Dependency Build Sampling** + - Build only changed dependencies instead of all + - Requires more sophisticated manifest diffing + - Estimated savings: ~30-40% of Windows build costs + +4. **Self-hosted Runners** + - Run Linux builds on own infrastructure + - Keep Windows runners on GitHub (licensing) + - Estimated savings: ~$10-15/month + - **Trade-off:** Maintenance overhead + +### Not Recommended + +1. **Reduce sync frequency** (hourly → daily) + - Savings: Negligible (~$0.50/month) + - Cost: Increased lag with upstream (unacceptable) + +2. **Skip Windows builds entirely** + - Savings: ~$8/month + - Cost: Lose reproducible dependency builds (defeats purpose) + +3. **Reduce AI review quality** (Claude Sonnet → Haiku) + - Savings: ~$20-25/month + - Cost: Significantly worse code review quality + +## Pristine Commit Policy + +The following commits are considered "pristine" and skip expensive builds: + +1. **Dev setup commits:** + - Message starts with "dev setup" (case-insensitive) + - Examples: "dev setup v19", "Dev Setup: Update IDE config" + - Contains: .clang-format, .idea/, .vscode/, flake.nix, etc. + +2. **CI/CD configuration commits:** + - Only modify files under `.github/` + - Examples: Workflow changes, script updates, documentation + +**Why this works:** +- Dev setup commits don't affect PostgreSQL code +- CI/CD commits are tested by running the workflows themselves +- Reduces unnecessary Windows builds by ~60-70% + +**Implementation:** See `pristine-master-policy.md` for details. + +## Questions? + +For more information: +- Pristine master policy: `.github/docs/pristine-master-policy.md` +- Sync setup: `.github/docs/sync-setup.md` +- AI review guide: `.github/docs/ai-review-guide.md` +- Windows builds: `.github/docs/windows-builds.md` diff --git a/.github/docs/pristine-master-policy.md b/.github/docs/pristine-master-policy.md new file mode 100644 index 0000000000000..9c0479d32df6a --- /dev/null +++ b/.github/docs/pristine-master-policy.md @@ -0,0 +1,225 @@ +# Pristine Master Policy + +## Overview + +The `master` branch in this mirror repository follows a "mostly pristine" policy, meaning it should closely mirror the upstream `postgres/postgres` repository with only specific exceptions allowed. + +## Allowed Commits on Master + +Master is considered "pristine" and the sync workflow will successfully merge upstream changes if local commits fall into these categories: + +### 1. ✅ CI/CD Configuration (`.github/` directory only) + +Commits that only modify files within the `.github/` directory are allowed. + +**Examples:** +- Adding GitHub Actions workflows +- Updating AI review configuration +- Modifying sync schedules +- Adding documentation in `.github/docs/` + +**Rationale:** CI/CD configuration is repository-specific and doesn't affect the PostgreSQL codebase itself. + +### 2. ✅ Development Environment Setup (commits named "dev setup ...") + +Commits with messages starting with "dev setup" (case-insensitive) are allowed, even if they modify files outside `.github/`. + +**Examples:** +- `dev setup v19` +- `Dev Setup: Add debugging configuration` +- `DEV SETUP - IDE and tooling` + +**Typical files in dev setup commits:** +- `.clang-format`, `.clangd` - Code formatting and LSP config +- `.envrc` - Directory environment variables (direnv) +- `.gdbinit` - Debugger configuration +- `.idea/`, `.vscode/` - IDE settings +- `flake.nix`, `shell.nix` - Nix development environment +- `pg-aliases.sh` - Personal shell aliases +- Other personal development tools + +**Rationale:** Development environment configuration is personal and doesn't affect the code or CI/CD. It's frequently updated as developers refine their workflow. + +### 3. ❌ Code Changes (NOT allowed) + +Any commits that: +- Modify PostgreSQL source code (`src/`, `contrib/`, etc.) +- Modify tests outside `.github/` +- Modify build system outside `.github/` +- Are not `.github/`-only AND don't start with "dev setup" + +**These will cause sync failures** and require manual resolution. + +## Branch Strategy + +### Master Branch +- **Purpose:** Mirror of upstream `postgres/postgres` + local CI/CD + dev environment +- **Updates:** Automatic hourly sync from upstream +- **Direct commits:** Only `.github/` changes or "dev setup" commits +- **All other work:** Use feature branches + +### Feature Branches +- **Purpose:** All PostgreSQL development work +- **Pattern:** `feature/*`, `dev/*`, `experiment/*` +- **Workflow:** + ```bash + git checkout master + git pull origin master + git checkout -b feature/my-feature + # Make changes... + git push origin feature/my-feature + # Create PR: feature/my-feature → master + ``` + +## Sync Workflow Behavior + +### Scenario 1: No Local Commits +``` +Upstream: A---B---C +Master: A---B---C +``` +**Result:** ✅ Already up to date (no action needed) + +### Scenario 2: Only .github/ Commits +``` +Upstream: A---B---C---D +Master: A---B---C---X (X modifies .github/ only) +``` +**Result:** ✅ Merge commit created +``` +Master: A---B---C---X---M + \ / + D---/ +``` + +### Scenario 3: Only "dev setup" Commits +``` +Upstream: A---B---C---D +Master: A---B---C---Y (Y is "dev setup v19") +``` +**Result:** ✅ Merge commit created +``` +Master: A---B---C---Y---M + \ / + D---/ +``` + +### Scenario 4: Mix of Allowed Commits +``` +Upstream: A---B---C---D +Master: A---B---C---X---Y (X=.github/, Y=dev setup) +``` +**Result:** ✅ Merge commit created + +### Scenario 5: Code Changes (Violation) +``` +Upstream: A---B---C---D +Master: A---B---C---Z (Z modifies src/backend/) +``` +**Result:** ❌ Sync fails, issue created + +**Recovery:** +1. Create feature branch from Z +2. Reset master to match upstream +3. Rebase feature branch +4. Create PR + +## Updating Dev Setup + +When you update your development environment: + +```bash +# Make changes to .clangd, flake.nix, etc. +git add .clangd flake.nix .vscode/ + +# Important: Start message with "dev setup" +git commit -m "dev setup v20: Update clangd config and add new aliases" + +git push origin master +``` + +The sync workflow will recognize this as a dev setup commit and preserve it during merges. + +**Naming convention:** +- ✅ `dev setup v20` +- ✅ `Dev setup: Update IDE config` +- ✅ `DEV SETUP - Add debugging tools` +- ❌ `Update development environment` (doesn't start with "dev setup") +- ❌ `dev environment changes` (doesn't start with "dev setup") + +## Sync Failure Recovery + +If sync fails because of non-allowed commits: + +### Check What's Wrong +```bash +git fetch origin +git fetch upstream https://github.com/postgres/postgres.git master + +# See which commits are problematic +git log upstream/master..origin/master --oneline + +# See which files were changed +git diff --name-only upstream/master...origin/master +``` + +### Option 1: Make Commit Acceptable + +If the commit should have been a "dev setup" commit: + +```bash +# Amend the commit message +git commit --amend -m "dev setup v21: Previous changes" +git push origin master --force-with-lease +``` + +### Option 2: Move to Feature Branch + +If the commit contains code changes: + +```bash +# Create feature branch +git checkout -b feature/recovery origin/master + +# Reset master to upstream +git checkout master +git reset --hard upstream/master +git push origin master --force + +# Your changes are safe in feature/recovery +git checkout feature/recovery +# Create PR when ready +``` + +## FAQ + +**Q: Why allow dev setup commits on master?** +A: Development environment configuration is personal, frequently updated, and doesn't affect the codebase or CI/CD. It's more convenient to keep it on master than manage separate branches. + +**Q: What if I forget to name it "dev setup"?** +A: Sync will fail. You can amend the commit message (see recovery above) or move the commit to a feature branch. + +**Q: Can I have both .github/ and dev setup changes in one commit?** +A: Yes! The sync workflow allows commits that modify .github/, or are named "dev setup", or both. + +**Q: What if upstream modifies the same files as my dev setup commit?** +A: The sync will attempt to merge automatically. If there are conflicts, you'll need to resolve them manually (rare, since upstream shouldn't touch personal dev files). + +**Q: Can I reorder commits on master?** +A: It's not recommended due to complexity. The sync workflow handles commits in any order as long as they follow the policy. + +## Monitoring + +**Check sync status:** +- Actions → "Sync from Upstream (Automatic)" +- Look for green ✅ on recent runs + +**Check for policy violations:** +- Open issues with label `sync-failure` +- These indicate commits that violated the pristine master policy + +## Related Documentation + +- [Sync Setup Guide](sync-setup.md) - Detailed sync workflow documentation +- [QUICKSTART](../QUICKSTART.md) - Quick setup guide +- [README](../README.md) - System overview diff --git a/.github/docs/sync-setup.md b/.github/docs/sync-setup.md new file mode 100644 index 0000000000000..1e12aeea3c5fc --- /dev/null +++ b/.github/docs/sync-setup.md @@ -0,0 +1,326 @@ +# Automated Upstream Sync Documentation + +## Overview + +This repository maintains a mirror of the official PostgreSQL repository at `postgres/postgres`. The sync system automatically keeps the `master` branch synchronized with upstream changes. + +## System Components + +### 1. Automatic Daily Sync +**File:** `.github/workflows/sync-upstream.yml` + +- **Trigger:** Daily at 00:00 UTC (cron schedule) +- **Purpose:** Automatically sync master branch without manual intervention +- **Process:** + 1. Fetches latest commits from `postgres/postgres` + 2. Fast-forward merges to local master (conflict-free) + 3. Pushes to `origin/master` + 4. Creates GitHub issue if conflicts detected + 5. Closes existing sync-failure issues on success + +### 2. Manual Sync Workflow +**File:** `.github/workflows/sync-upstream-manual.yml` + +- **Trigger:** Manual via Actions tab → "Sync from Upstream (Manual)" → Run workflow +- **Purpose:** Testing and on-demand syncs +- **Options:** + - `force_push`: Use `--force-with-lease` when pushing (default: true) + +## Branch Strategy + +### Critical Rule: Master is Pristine + +- **master branch:** Mirror only - pristine copy of `postgres/postgres` +- **All development:** Feature branches (e.g., `feature/hot-updates`, `experiment/zheap`) +- **Never commit directly to master** - this will cause sync failures + +### Feature Branch Workflow + +```bash +# Start new feature from latest master +git checkout master +git pull origin master +git checkout -b feature/my-feature + +# Work on feature +git commit -m "Add feature" + +# Keep feature updated with upstream +git checkout master +git pull origin master +git checkout feature/my-feature +git rebase master + +# Push feature branch +git push origin feature/my-feature + +# Create PR: feature/my-feature → master +``` + +## Sync Failure Recovery + +### Diagnosis + +If sync fails, you'll receive a GitHub issue with label `sync-failure`. Check what commits are on master but not upstream: + +```bash +# Clone or update your local repository +git fetch origin +git fetch upstream https://github.com/postgres/postgres.git master + +# View conflicting commits +git log upstream/master..origin/master --oneline + +# See detailed changes +git diff upstream/master...origin/master +``` + +### Recovery Option 1: Preserve Commits (Recommended) + +If the commits on master should be kept: + +```bash +# Create backup branch from current master +git checkout origin/master +git checkout -b recovery/master-backup-$(date +%Y%m%d) +git push origin recovery/master-backup-$(date +%Y%m%d) + +# Reset master to upstream +git checkout master +git reset --hard upstream/master +git push origin master --force + +# Create feature branch from backup +git checkout -b feature/recovered-work recovery/master-backup-$(date +%Y%m%d) + +# Optional: rebase onto new master +git rebase master + +# Push feature branch +git push origin feature/recovered-work + +# Create PR: feature/recovered-work → master +``` + +### Recovery Option 2: Discard Commits + +If the commits on master were mistakes or already merged upstream: + +```bash +git checkout master +git reset --hard upstream/master +git push origin master --force +``` + +### Verification + +After recovery, verify sync status: + +```bash +# Check that master matches upstream +git log origin/master --oneline -10 +git log upstream/master --oneline -10 + +# These should be identical + +# Or run manual sync workflow +# GitHub → Actions → "Sync from Upstream (Manual)" → Run workflow +``` + +The automatic sync will resume on next scheduled run (00:00 UTC daily). + +## Monitoring + +### Success Indicators + +- ✓ GitHub Actions badge shows passing +- ✓ No open issues with label `sync-failure` +- ✓ `master` branch commit history matches `postgres/postgres` + +### Check Sync Status + +**Via GitHub UI:** +1. Go to: Actions → "Sync from Upstream (Automatic)" +2. Check latest run status + +**Via Git:** +```bash +git fetch origin +git fetch upstream https://github.com/postgres/postgres.git master +git log origin/master..upstream/master --oneline + +# No output = fully synced +# Commits listed = behind upstream (sync pending or failed) +``` + +**Via API:** +```bash +# Check latest workflow run +gh run list --workflow=sync-upstream.yml --limit 1 + +# View run details +gh run view +``` + +### Sync Lag + +Expected lag: <1 hour from upstream commit to mirror + +- Upstream commits at 12:30 UTC → Synced at next daily run (00:00 UTC next day) = ~11.5 hours max +- For faster sync: Manually trigger workflow after major upstream merges + +## Configuration + +### GitHub Actions Permissions + +Required settings (already configured): + +1. **Settings → Actions → General → Workflow permissions:** + - ✓ "Read and write permissions" + - ✓ "Allow GitHub Actions to create and approve pull requests" + +2. **Repository Settings → Branches:** + - Consider: Branch protection rule on `master` to prevent direct pushes + - Exception: Allow `github-actions[bot]` to push + +### Adjusting Sync Schedule + +Edit `.github/workflows/sync-upstream.yml`: + +```yaml +on: + schedule: + # Current: Daily at 00:00 UTC + - cron: '0 0 * * *' + + # Examples: + # Every 6 hours: '0 */6 * * *' + # Twice daily: '0 0,12 * * *' + # Weekdays only: '0 0 * * 1-5' +``` + +**Recommendation:** Keep daily schedule to balance freshness with API usage. + +## Troubleshooting + +### Issue: Workflow not running + +**Check:** +1. Actions tab → Check if workflow is disabled +2. Settings → Actions → Ensure workflows are enabled for repository + +**Fix:** +- Enable workflow: Actions → Select workflow → "Enable workflow" + +### Issue: Permission denied on push + +**Check:** +- Settings → Actions → General → Workflow permissions + +**Fix:** +- Set to "Read and write permissions" +- Enable "Allow GitHub Actions to create and approve pull requests" + +### Issue: Merge conflicts every sync + +**Root cause:** Commits being made directly to master + +**Fix:** +1. Review `.git/hooks/` for pre-commit hooks that might auto-commit +2. Check if any automation is committing to master +3. Enforce branch protection rules +4. Educate team members on feature branch workflow + +### Issue: Sync successful but CI fails + +**This is expected** if upstream introduced breaking changes or test failures. + +**Handling:** +- Upstream tests failures are upstream's responsibility +- Focus: Ensure mirror stays in sync +- Separate: Your feature branches should pass CI + +## Cost and Usage + +### GitHub Actions Minutes + +- **Sync workflow:** ~2-3 minutes per run +- **Frequency:** Daily = 60-90 minutes/month +- **Free tier:** 2,000 minutes/month (public repos: unlimited) +- **Cost:** $0 (well within limits) + +### Network Usage + +- Fetches only new commits (incremental) +- Typical: <10 MB per sync +- Total: <300 MB/month + +## Security Considerations + +### Secrets + +- Uses `GITHUB_TOKEN` (automatically provided, scoped to repository) +- No additional secrets required +- Token permissions: Minimum necessary (contents:write, issues:write) + +### Audit Trail + +All syncs are logged: +- GitHub Actions run history (90 days retention) +- Git reflog on server +- Issue creation/closure for failures + +## Integration with Other Workflows + +### Cirrus CI + +Cirrus CI tests trigger on pushes to master: +- Sync pushes → Cirrus CI runs tests on synced commits +- This validates upstream changes against your test matrix + +### AI Code Review + +AI review workflows trigger on PRs, not master pushes: +- Sync to master does NOT trigger AI reviews +- Feature branch PRs → master do trigger AI reviews + +### Windows Builds + +Windows dependency builds trigger on master pushes: +- Sync pushes → Windows builds run +- Ensures dependencies stay compatible with latest upstream + +## Support + +### Reporting Issues + +If sync consistently fails: + +1. Check open issues with label `sync-failure` +2. Review workflow logs: Actions → Failed run → View logs +3. Create issue with: + - Workflow run URL + - Error messages from logs + - Output of `git log upstream/master..origin/master` + +### Disabling Automatic Sync + +If needed (e.g., during major refactoring): + +```bash +# Disable via GitHub UI +# Actions → "Sync from Upstream (Automatic)" → "..." → Disable workflow + +# Or delete/rename the workflow file +git mv .github/workflows/sync-upstream.yml .github/workflows/sync-upstream.yml.disabled +git commit -m "Temporarily disable automatic sync" +git push +``` + +**Remember to re-enable** once work is complete. + +## References + +- Upstream repository: https://github.com/postgres/postgres +- GitHub Actions docs: https://docs.github.com/en/actions +- Git branching strategies: https://git-scm.com/book/en/v2/Git-Branching-Branching-Workflows diff --git a/.github/ocr/context.md b/.github/ocr/context.md new file mode 100644 index 0000000000000..c4a83b85b124e --- /dev/null +++ b/.github/ocr/context.md @@ -0,0 +1,126 @@ +# OCR review context — PostgreSQL contribution standards + +You are reviewing a change to a **PostgreSQL** fork. Every PR here is destined to +become a patch posted to the **pgsql-hackers** mailing list and tracked in a +**commitfest**. Review with the combined rigor, taste, and attention to detail of +the PostgreSQL committers. This context applies to the *whole* change, on top of +the per-file rules. + +## Review discipline +- Be precise and blunt; lead with the most serious problem. No praise, no + validation of the author, no disclaimers — accuracy is the only metric. +- Verify every claim against the actual diff. Confirm names, signatures, line + numbers, and APIs before asserting. Never invent behavior or cite code not in + the change. If unsure, say so, and tag each finding **high / moderate / low** + confidence. +- Judge the change on its merits regardless of how the PR frames it. A draft PR + is WIP: weight design/approach feedback over style nits. + +## Patch hygiene (top rejection reasons on -hackers) +1. **Minimal diff.** The fastest way to get a patch rejected is unrelated + changes: reformatting untouched lines, rewording unrelated comments, touching + code not required by the change. Flag any hunk not needed for the stated + purpose. After the patch, the code should read as if it had always been + written that way. +2. **Atomic, bisectable commits.** Each commit must build and pass tests on its + own — a broken intermediate commit breaks `git bisect`, revert, and + cherry-pick. Flag a commit that only compiles once a later commit lands. + Prefer one focused patch, or a clearly-ordered series of + independently-committable pieces. +3. **Tests + docs are mandatory.** A user-visible change without regression/TAP + tests **and** documentation is WIP, not commit-ready. New behavior needs + tests that cover edge and error paths, not just the happy path. +4. **DRY / reuse.** Prefer existing infrastructure (`List` in `pg_list.h`, + `StringInfo`, `dynahash`/`simplehash`, `palloc`/`MemoryContext`, `foreach`) + over reinventing it. Flag copy-paste and speculative abstraction alike — the + community wants minimal, targeted changes that fit the subsystem's existing + patterns. +5. **Whitespace.** No trailing whitespace; tabs (width 4) for C indentation; + `git diff --check` must be clean. Whitespace-only churn on untouched lines is + a defect. + +## Committer-owned files — do NOT touch in a patch (flag if present) +These are the committer's job at push time; including them causes needless +merge conflicts and is a mistake: +- **`src/include/catalog/catversion.h`** — the `CATALOG_VERSION_NO` bump is done + by the **committer** when pushing. A catversion bump in the PR is **wrong** — + flag it. (This is the single most common author mistake in catalog patches.) +- **Release notes** (`doc/src/sgml/release-*.sgml`) and version strings + (`configure.ac` `AC_INIT` version, `meson.build` `version`, `PG_VERSION`). + +## Generated files — never hand-edit; edit the source +Flag direct edits to generated output; point the author at the source instead: +- Catalog headers `src/include/catalog/*_d.h`, `postgres.bki`, `schemapg.h`, + `system_constraints.sql` → edit the `pg_*.dat` files. +- `src/backend/nodes/{copy,equal,out,read}funcs.c` and other + `gen_node_support.pl` output → annotate the `Node` struct in its header. +- `fmgroids.h`, `fmgrprotos.h`, `fmgrtab.c` → edit `pg_proc.dat`. +- `utils/errcodes.h` → `errcodes.txt`; wait-event headers → + `wait_event_names.txt`; `lwlocknames.h` → `lwlocknames.txt`. +- `configure` → `configure.ac`; `*.po` translations are handled separately; + generated Unicode tables come from their source scripts. + +## Portability is a hard gate +PostgreSQL runs on Linux, Windows (MSVC), macOS, the BSDs and Solaris, across +**x86_64, ARM64, RISC-V, PPC64, s390x**, both endiannesses and 32/64-bit. Any +change must be portable across all of them: +- No unaligned memory access; no dependence on `char` signedness, integer/pointer + width, endianness, or struct padding for on-disk/wire formats. +- Use `int16/int32/int64`, `Size`, and `INT64_FORMAT`/`UINT64_FORMAT` (never + `%ld` for `int64`). +- Atomics/barriers only via `port/atomics` (`pg_atomic_*`, `pg_read/write_barrier`). +- **Windows/MSVC:** any `extern` variable used from another module or an + extension needs `PGDLLIMPORT` in its header; no VLAs or compiler-specific + extensions beyond the tree's C99 baseline. + +## Backward compatibility — the strongest constraint +Do not break SQL behavior, the libpq wire protocol, the logical-replication +protocol, dump/restore, `pg_upgrade`, or exported/`PGDLLIMPORT` APIs without +extraordinary justification. **ABI** matters for back-branches: changing the +size/layout of an exported struct or the signature of an exported function +breaks installed extensions. + +## Mailing-list context & etiquette +Because each PR becomes a pgsql-hackers email read by a busy, expert, opinionated +audience, also flag what reliably wastes reviewer time or draws rejection: +- A patch that **does more than one thing** or bundles unrelated cleanup — split it. +- **Footguns**: easy-to-misuse APIs, silent data-loss/corruption hazards, unsafe + defaults — name them explicitly. +- **Performance claims without a reproducible benchmark.** +- No reference to the **design discussion / prior -hackers thread** (Message-Id) + for a non-trivial change. +- **Do not bikeshed:** keep style nits proportionate and clearly separated from + substantive correctness findings. + +## Minimalism — the "ponytail" discipline +The best code is the code you never wrote (YAGNI). Before accepting new code, +apply the ladder: (1) Does this need to exist at all? (2) Can existing +code/infrastructure already do it? (3) Is this the simplest thing that works? +Flag: speculative scaffolding and config for a path that isn't wired yet; dead +code and unused "flexibility" (fields, params, abstractions, options with no +caller); premature abstraction (a helper used exactly once); knobs/GUCs/flags +nobody asked for. Minimal, targeted changes that fit the existing patterns beat +clever or general-purpose ones. + +## Comment & identity accuracy +- Comments must describe what the code does **now**. Flag aspirational/ + future-tense comments for behavior that already shipped ("will be", "for now", + "not yet", "future", and stale "TODO/FIXME/XXX/HACK"); comments that drifted + from the code they sit above; and incomplete/trailing comments. Comments + explain **why**, not what. No commented-out code. +- **ASCII only** in source and diffs — no smart quotes, em-dashes, or ellipsis + characters. + +## Commit & versioning discipline +- Conventional-commit style, imperative subject, one logical change per commit, + each commit building on its own. +- Do **not** bump version numbers or generated version stamps (including + `catversion.h`) — that is the maintainer's job at commit/release time. + +Understand common list shorthand so your comments are precise and not +miscommunicated: WIP (work in progress), GUC (config variable), WAL, LSN, OID, +TOAST, FSM, TAM (table access method), RLS, DSM, 2PC, PITR, CIC (concurrent index +creation), SAOP, ABI/API, backpatch (apply to supported back-branches), HEAD +(master tip), catversion (catalog version), pgindent, buildfarm, cfbot, +`s/x/y/` (suggested text substitution), footgun, bikeshedding, POLA (principle of +least astonishment). diff --git a/.github/ocr/litellm.yaml b/.github/ocr/litellm.yaml new file mode 100644 index 0000000000000..e23cc4eee6fe2 --- /dev/null +++ b/.github/ocr/litellm.yaml @@ -0,0 +1,41 @@ +# LiteLLM proxy config — bridges Open Code Review (OpenAI protocol) to AWS Bedrock. +# +# This proxy is NOT a hosted service. The ocr-review.yml workflow installs it +# (`pip install 'litellm[proxy]'`) and runs it as a background process bound to +# 127.0.0.1:4000 for the duration of a single GitHub Actions job, then it exits. +# +# Auth to Bedrock: LiteLLM uses boto3's default credential chain, which reads +# the temporary AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY / AWS_SESSION_TOKEN +# minted by the workflow's OIDC "Configure AWS credentials" step; region from +# AWS_REGION. + +model_list: + - model_name: ocr-bedrock + litellm_params: + # Set the repo variable OCR_BEDROCK_MODEL to an Opus inference-profile id + # your account has access to, e.g.: + # bedrock/converse/us.anthropic.claude-opus-4-8 + # The 'converse/' prefix uses Bedrock's Converse API, which is the most + # reliable path for Claude tool-use (what OCR relies on). + model: os.environ/OCR_BEDROCK_MODEL + aws_region_name: os.environ/AWS_REGION + + # "High effort" review. Claude Opus 4.8 on Bedrock uses *adaptive* thinking + # controlled by output_config.effort. Set it DIRECTLY here — NOT via + # reasoning_effort, which LiteLLM still maps to the legacy + # thinking.type.enabled that Opus 4.8 rejects. LiteLLM forwards + # output_config into additionalModelRequestFields for Anthropic models; if + # the build doesn't recognize the effort param it is dropped with a warning + # (no error) and the model reviews at its default effort. + # Valid: low|medium|high|max|xhigh (auto-clamped to the model ceiling). + output_config: + effort: xhigh + max_tokens: 32000 + +litellm_settings: + drop_params: true # silently drop params a model doesn't support + modify_params: true # auto-fix minor request incompatibilities + request_timeout: 600 + +general_settings: + master_key: os.environ/LITELLM_MASTER_KEY diff --git a/.github/ocr/pg-history.py b/.github/ocr/pg-history.py new file mode 100644 index 0000000000000..5794f8a920bd7 --- /dev/null +++ b/.github/ocr/pg-history.py @@ -0,0 +1,225 @@ +#!/usr/bin/env python3 +""" +pg-history: tie a PR's changes to PostgreSQL git + pgsql-hackers email history. + +OCR (the code reviewer) cannot call MCP servers, so this is a separate agent: +it runs a Bedrock (Claude Opus) tool-use loop wired to the Agora MCP server at +https://pg.ddx.io/mcp, lets the model search the mailing-list archives / commit +history / commitfest data, and emits a Markdown summary linking the changes to +the relevant threads (https://pg.ddx.io/m/pgsql-hackers/). + +Env: + PG_HISTORY_MCP_URL MCP endpoint (default https://pg.ddx.io/mcp) + PG_HISTORY_MODEL Bedrock model id (e.g. us.anthropic.claude-opus-4-8) + AWS_REGION region (creds come from the OIDC step's env) + BASE_REF, HEAD_SHA PR base ref and head sha (for the git diff context) + GH_PR_TITLE PR title (optional, adds context) + PG_HISTORY_OUT output markdown path (default /tmp/pg-history.md) +Writes the markdown to PG_HISTORY_OUT; exits 0 even on soft failures (writes a note). +""" +import json, os, subprocess, sys, urllib.request + +MCP_URL = os.environ.get("PG_HISTORY_MCP_URL", "https://pg.ddx.io/mcp") +MODEL = os.environ.get("PG_HISTORY_MODEL", "us.anthropic.claude-opus-4-8").replace("bedrock/converse/", "").replace("bedrock/", "") +REGION = os.environ.get("AWS_REGION", "us-east-1") +BASE_REF = os.environ.get("BASE_REF", "") +HEAD_SHA = os.environ.get("HEAD_SHA", "") +PR_TITLE = os.environ.get("GH_PR_TITLE", "") +OUT = os.environ.get("PG_HISTORY_OUT", "/tmp/pg-history.md") +UA = "pg-history/0.1 (+github-actions)" + +# Curated subset of the 108 Agora tools — the ones useful for connecting a +# change to its discussion/commit history. Intersected with what the server +# actually exposes, so unknown names are harmless. +TOOL_WHITELIST = { + "find_related_discussions", "find_similar_messages", "get_thread", + "discussion_links", "get_author_messages", "browse_by_date", + "blame_symbol", "check_upstream_status", "find_related", + "find_entries_for_thread", "find_entries_for_author", "get_commit", + "search", "hybrid_search", "get_callers", "get_callees", "find_pattern", +} +MAX_ROUNDS = 14 +TOOL_RESULT_CAP = 8000 # chars per tool result fed back to the model + + +def _mcp_post(body, sid=None): + headers = {"Content-Type": "application/json", + "Accept": "application/json, text/event-stream", "User-Agent": UA} + if sid: + headers["Mcp-Session-Id"] = sid + req = urllib.request.Request(MCP_URL, data=json.dumps(body).encode(), headers=headers, method="POST") + resp = urllib.request.urlopen(req, timeout=60) + sid_out = resp.headers.get("Mcp-Session-Id") + result = None + for line in resp.read().decode().splitlines(): + line = line.strip() + if line.startswith("data:"): + line = line[5:].strip() + if not line or line.startswith("event:"): + continue + try: + obj = json.loads(line) + except Exception: + continue + if isinstance(obj, dict) and ("result" in obj or "error" in obj): + result = obj + return result, sid_out + + +class MCP: + def __init__(self): + init, self.sid = _mcp_post({"jsonrpc": "2.0", "id": 1, "method": "initialize", + "params": {"protocolVersion": "2025-06-18", "capabilities": {}, + "clientInfo": {"name": "pg-history", "version": "0.1"}}}) + if not init or "result" not in init: + raise RuntimeError(f"MCP initialize failed: {init}") + try: + _mcp_post({"jsonrpc": "2.0", "method": "notifications/initialized", "params": {}}, self.sid) + except Exception: + pass + self._id = 1 + + def list_tools(self): + self._id += 1 + res, _ = _mcp_post({"jsonrpc": "2.0", "id": self._id, "method": "tools/list", "params": {}}, self.sid) + return (res or {}).get("result", {}).get("tools", []) + + def call(self, name, args): + self._id += 1 + res, _ = _mcp_post({"jsonrpc": "2.0", "id": self._id, "method": "tools/call", + "params": {"name": name, "arguments": args or {}}}, self.sid) + if not res: + return "(no response)" + if "error" in res: + return f"ERROR: {json.dumps(res['error'])[:500]}" + parts = [] + for c in res.get("result", {}).get("content", []): + if c.get("type") == "text": + parts.append(c["text"]) + return ("\n".join(parts) or "(empty)")[:TOOL_RESULT_CAP] + + +def git(*args): + try: + return subprocess.check_output(["git", *args], text=True, stderr=subprocess.DEVNULL).strip() + except Exception: + return "" + + +def pr_context(): + base = f"origin/{BASE_REF}" if BASE_REF else "" + rng = f"{base}..{HEAD_SHA}" if base and HEAD_SHA else HEAD_SHA + commits = git("log", "--no-merges", "--format=%h %s", f"{rng}") if rng else "" + stat = git("diff", "--stat", rng) if rng else "" + files = git("diff", "--name-only", rng) if rng else "" + return commits[:4000], stat[:3000], files[:2000] + + +SYSTEM = """You are a PostgreSQL community research assistant. Given a pull request's +commits and changed files, use the available tools (backed by the Agora index of +pgsql-hackers mail, commit history, and commitfest data) to connect the change to +its history. Your goal: + +- Find the mailing-list thread(s) and prior discussion behind this change. +- Identify related/superseded prior commits and any commitfest entry. +- Note relevant prior art, rejected approaches, or design rationale. + +Rules (voice & rigor): +- Be precise and blunt. No praise, no filler, no hedging, no disclaimers. Accuracy is + the only success metric — not the author's approval. Lead with the most important finding. +- NEVER hallucinate. Verify every Message-ID, thread subject, commit hash, author name, + and date against an actual tool result before citing it. If a search returns nothing, + say so plainly — do not guess or fabricate a plausible-looking link. +- Assess the change on its merits, independent of how the PR frames it. +- Tag any inferred (not tool-confirmed) linkage with an explicit confidence level: + high / moderate / low. +- Be decisive and efficient: a handful of targeted tool calls, not exhaustive search. +- Cite every mailing-list message as a Markdown link: [subject](https://pg.ddx.io/m/pgsql-hackers/MESSAGE_ID). +- If you find nothing relevant, say so in one line — do not pad. + +When done, output ONLY Markdown (no preamble) with these sections, omitting any that are empty: +## 🧵 Related discussion +## 🔗 Related commits / prior art +## 📋 Commitfest +## 🧭 Context for reviewers +Keep it tight (use bullets; link generously).""" + + +def to_toolspec(t): + schema = t.get("inputSchema") or {"type": "object", "properties": {}} + return {"toolSpec": {"name": t["name"], + "description": (t.get("description") or "")[:600], + "inputSchema": {"json": schema}}} + + +def main(): + commits, stat, files = pr_context() + if not commits and not files: + open(OUT, "w").write("") # nothing to do + print("No PR diff context; skipping.") + return + user = (f"PR title: {PR_TITLE}\n\n" if PR_TITLE else "") + \ + f"Commits:\n{commits or '(none)'}\n\nChanged files:\n{files or '(none)'}\n\nDiffstat:\n{stat or '(none)'}\n" + + try: + mcp = MCP() + tools = [to_toolspec(t) for t in mcp.list_tools() if t.get("name") in TOOL_WHITELIST] + except Exception as e: + open(OUT, "w").write(f"_pg-history: could not reach the Agora MCP server ({MCP_URL}): {e}_\n") + print(f"MCP unavailable: {e}") + return + if not tools: + open(OUT, "w").write("_pg-history: no usable MCP tools available._\n") + return + + import boto3 + from botocore.config import Config + + # botocore's default read timeout (60s) is too short for a multi-round + # (MAX_ROUNDS) tool-use loop against a large PR diff on a reasoning model; + # each converse() call alone can take several minutes. Bump it well past + # what a single round needs; connect_timeout stays short since a stuck + # TCP handshake is a different (and much cheaper to detect) failure mode. + brt = boto3.client("bedrock-runtime", region_name=REGION, + config=Config(read_timeout=900, connect_timeout=10)) + messages = [{"role": "user", "content": [{"text": user}]}] + final_text = "" + try: + for _ in range(MAX_ROUNDS): + resp = brt.converse( + modelId=MODEL, + system=[{"text": SYSTEM}], + messages=messages, + toolConfig={"tools": tools}, + inferenceConfig={"maxTokens": 4096}, + ) + out = resp["output"]["message"] + messages.append(out) + if resp.get("stopReason") == "tool_use": + results = [] + for blk in out["content"]: + tu = blk.get("toolUse") + if not tu: + continue + res_text = mcp.call(tu["name"], tu.get("input") or {}) + results.append({"toolResult": {"toolUseId": tu["toolUseId"], + "content": [{"text": res_text}]}}) + messages.append({"role": "user", "content": results}) + continue + final_text = "".join(b.get("text", "") for b in out["content"]).strip() + break + except Exception as e: + open(OUT, "w").write(f"_pg-history: Bedrock call failed: {e}_\n") + print(f"Bedrock error: {e}") + return + + if not final_text: + final_text = "_pg-history: no related history found._" + body = "## 📜 Change history & discussion (Agora / pg.ddx.io)\n\n" + final_text + \ + "\n\nGenerated by pg-history via the Agora MCP server (pg.ddx.io).\n" + open(OUT, "w").write(body) + print(body) + + +if __name__ == "__main__": + main() diff --git a/.github/ocr/rule.json b/.github/ocr/rule.json new file mode 100644 index 0000000000000..60e13e73dcbe0 --- /dev/null +++ b/.github/ocr/rule.json @@ -0,0 +1,65 @@ +{ + "_comment": "OCR per-file review rules for PostgreSQL core + extensions. Cross-cutting contribution standards & mailing-list etiquette live in .github/ocr/context.md, passed via --background-file. OCR uses FIRST-MATCH-WINS in declaration order, so rules are ordered most-specific first. merge_system_rule:true keeps OCR's built-in fine-tuned checks (thread-safety, injection, NPE) alongside these PostgreSQL-specific rules.", + "rules": [ + { + "path": "src/test/**", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL tests. Coverage is mandatory for any behavioral change and must include edge cases (NULL, empty, boundary/overflow) and ERROR paths, not just the happy path. A test that still passes with the feature reverted is worthless — confirm it actually exercises and would catch regressions in the new code. Regression (.sql/expected): deterministic, portable output — ORDER BY where row order matters, no timing/plan-dependent output except intentional EXPLAIN, no absolute paths, locale-independent (C collation or explicit COLLATE), DROP objects the test creates; expected/ output must stay stable across platforms and under the parallel schedule. Concurrency/locking belongs in isolation tests (src/test/isolation, .spec + permutations). End-to-end/crash/replication/CLI behavior belongs in TAP tests (t/*.pl with PostgreSQL::Test::Cluster/Utils) — no hardcoded ports/paths, no sleep as synchronization (use poll_query_until/wait_for), skip cleanly when prerequisites are missing, and clean up nodes." + }, + { + "path": "**/*.{c,h}", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL backend/frontend C — review as pgsql-hackers committers do, in priority order.\n\n(1) CORRECTNESS (highest): Memory — every palloc lives in the right MemoryContext; error paths via ereport/elog(ERROR) must not leak memory/buffers/locks/fds (rely on MemoryContext/ResourceOwner reset or PG_TRY/PG_FINALLY); no use-after-free; delete temp contexts. Concurrency — consistent lock ordering (deadlock-free), correct lock levels, balanced LWLockAcquire/Release and START_/END_CRIT_SECTION, no TOCTOU, CHECK_FOR_INTERRUPTS in long loops, async-signal-safe signal handlers (volatile sig_atomic_t). WAL — any change to shared on-disk state must be WAL-logged AND correctly replayed (redo path), crash- and replica-consistent. NULL/edge/overflow handling.\n\n(2) BACKWARD COMPATIBILITY / ABI: don't break behavior, dump/restore, pg_upgrade, libpq wire protocol, logical-replication protocol, or exported/PGDLLIMPORT'd APIs (struct size/layout, function signatures) without extraordinary justification.\n\n(3) CATALOG / GENERATED: new/changed catalog data goes in pg_*.dat, NOT the generated *_d.h/.bki. New Node types: ANNOTATE the struct in its header so gen_node_support.pl regenerates copy/equal/out/read — do NOT hand-edit *funcs.c. New SQL-callable functions: add to pg_proc.dat with an OID from the 8000-9999 developer range (src/include/catalog/unused_oids; check duplicate_oids); committer renumbers at commit. DO NOT bump CATALOG_VERSION_NO in the patch — flag any catversion.h change as a mistake (committer's job).\n\n(4) PERFORMANCE: no regression on hot paths; avoid O(n^2) where better is feasible; minimize work under contended locks; avoid needless palloc churn and large struct copies in hot paths.\n\n(5) SECURITY: bounded string ops (snprintf/strlcpy/strlcat — never strcpy/strcat/sprintf); integer/size-overflow checks before allocation; never user input as a format string; privilege checks via pg_*_aclcheck; beware search_path and SECURITY DEFINER.\n\n(6) PORTABILITY (hard gate): no unaligned access; no dependence on char signedness, int/long/pointer width, endianness, or struct padding for on-disk/wire formats; use int16/int32/int64 + INT64_FORMAT/UINT64_FORMAT (never %ld for int64); align contended shared structs (pg_attribute_aligned/cache-line pad). Atomics/barriers only via port/atomics (pg_atomic_*, pg_read/write_barrier) — never raw intrinsics or volatile-as-barrier. WINDOWS/MSVC: extern vars used cross-module/extension need PGDLLIMPORT; no VLAs or features beyond the C99 baseline the tree targets; use pg_pread/pg_pwrite. Applies across x86_64/ARM64/RISC-V/PPC64/s390x, big/little endian, 32/64-bit.\n\n(7) CONVENTIONS: errmsg starts lowercase, no trailing period, no embedded newlines; errdetail/errhint are complete capitalized sentences; correct ERRCODE_*; wrap user-facing text in _(); errmsg_plural for counts. Assert() only for can't-happen invariants (never user-reachable). Naming: snake_case with subsystem prefix (heap_insert) or CamelCase for major subsystems (ExecInitNode); ALL_CAPS macros. Must pgindent cleanly (tabs, width 4). Comments explain WHY not WHAT; no #ifdef 0 blocks, no commented-out code, no #ifdef fencing your feature. Reuse existing helpers (DRY)." + }, + { + "path": "**/*.dat", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL catalog data (pg_proc.dat, pg_type.dat, etc.) — the SOURCE for generated headers. The generated *_d.h, postgres.bki, fmgroids.h, fmgrtab.c must NOT be hand-edited (they regenerate from these files). OIDs: use a value from the developer range 8000-9999 (src/include/catalog/unused_oids; verify with duplicate_oids); committer renumbers to a final contiguous block, so stay in-range and unique but don't over-optimize the exact number. Keep proc entries complete/consistent (prosrc, provolatile, proparallel, prorettype/proargtypes, matching description). DO NOT bump CATALOG_VERSION_NO / catversion.h — committer's job at push time; flag any such change. New catalog columns/views need documentation in doc/src/sgml/catalogs.sgml." + }, + { + "path": "**/*.{sql,pgsql}", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL SQL. Valid PostgreSQL dialect (not MySQL/Oracle); correct types (bigint vs int, text vs varchar); sound transaction/isolation and CTE-materialization assumptions. SECURITY: flag SQL injection in dynamic SQL (require quote_identifier/quote_literal or format() with %I/%L), SECURITY DEFINER without a locked-down search_path, inappropriate RLS bypass. Prefer set-based over row-at-a-time/N+1. BACKWARD COMPATIBILITY (a top rejection reason): changing existing SQL behavior, the output of existing functions, or default GUCs needs extraordinary justification. New SQL-callable objects belong in pg_*.dat with OIDs from the 8000-9999 range, not in generated files. Minimal diff; add regression tests + docs." + }, + { + "path": "**/*.{pl,pm}", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL Perl (TAP tests and build/catalog tooling). Require 'use strict; use warnings;'. Must be perltidy-clean with the tree's src/tools/pgindent/perltidyrc and pass src/tools/perlcheck/pgperlcritic. Use the framework: PostgreSQL::Test::Cluster, PostgreSQL::Test::Utils, Test::More; no hardcoded ports/paths/PIDs; use safe_psql/poll_query_until, not sleep; skippable without optional prerequisites; clean up nodes. PORTABILITY: run on Windows (no fork-only constructs, use File::Spec, avoid unavailable signals) and the minimum supported Perl. Robustness: avoid two-arg open and string system()/qx with interpolated data (use list forms). Generator scripts (gen_node_support.pl, catalog Perl) must be deterministic and stay in sync with inputs; do not commit their generated output." + }, + { + "path": "**/*.py", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL Python (build/test tooling, oauth/pytest tests, src/tools). Follow surrounding style; keep imports to the standard library unless the dependency is already required by the tree (no surprise third-party deps in build/test tooling). PORTABILITY: support the project's minimum Python 3 and run on Windows and the BSDs (use os.path/pathlib, avoid POSIX-only calls and shell=True with interpolated input). Deterministic, self-cleaning tests; no hardcoded ports/paths; skip cleanly without prerequisites. For the Perl->pytest porting effort, confirm behavior parity with the TAP test replaced (same assertions/coverage), not a superficial translation. Minimal diff; match the tree's ruff/black config if present." + }, + { + "path": "**/*.{rs,toml}", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. Rust PostgreSQL extension (pgrx) or Rust support crate. Not core C, but it runs inside/alongside the backend, so backend safety applies. SAFETY: in code reachable from an SQL call, a Rust panic aborts the Postgres process — forbid unwrap()/expect()/panic!/unreachable!/todo! and index-panics on reachable paths; use Result and pgrx error reporting (error!/ereport!). Every `unsafe` block needs a comment justifying its invariant; scrutinize raw pointers and FFI across the pg_sys boundary. pgrx: honor #[pg_guard] on extern C fns (correct panic/longjmp handling); never hold Rust references across SPI or anything that can longjmp (skips Rust destructors -> leaks); respect MemoryContext lifetimes for palloc'd data; datum<->Rust conversions must handle NULL. Concurrency uses Postgres shmem/LWLocks (pgrx shmem API), not std::sync alone. Lints: must pass `cargo clippy --all-targets --all-features -- -D warnings` and `cargo fmt --check`; deny unwrap_used/expect_used/panic in libraries; thiserror (libs) / anyhow (bins). Justify every new dependency. Tests: #[pg_test] for in-backend behavior, #[test] for pure logic; cover error and NULL paths. Minimal, idiomatic diff." + }, + { + "path": "**/{configure.ac,*.m4,aclocal.m4}", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL Autoconf. Edit configure.ac / the m4 macros — do NOT hand-edit generated 'configure' or pg_config.h.in in the same patch (regeneration is the committer's step; a patch that also rewrites generated configure output is suspect). Feature/header/function probes must be portable and not assume a specific OS/compiler. Every configure knob must be mirrored on the Meson side (meson_options.txt/meson.build) and documented. Minimal diff." + }, + { + "path": "**/{meson.build,meson_options.txt}", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL Meson build. Valid syntax; correct subdir()/dependency()/declare_dependency and install paths; new source files must be added here. CRITICAL: PostgreSQL maintains BOTH Meson and Autoconf/Make — any new file, option, or feature check must be mirrored on the configure.ac/Makefile side so the two never drift (a file built by only one system is a common defect). New options need matching docs and sensible defaults. Minimal diff." + }, + { + "path": "**/{Makefile,GNUmakefile,*.mk}", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL Makefile (GNU Make). $(VAR) refs; correct .PHONY; accurate dependencies (no parallel -j races); $(MAKE) for recursion; VPATH/out-of-tree build support; no hardcoded paths (use standard PostgreSQL makefile vars and $(top_builddir)); clean/distclean/maintainer-clean must remove new artifacts; extensions use PGXS. Must stay in sync with meson.build. Minimal diff." + }, + { + "path": "doc/**/*.sgml", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. PostgreSQL documentation (DocBook SGML). Technically accurate/complete (parameters, limitations, version/compat notes); correct tag usage/nesting (, , , , , /); working cross-references; spell it 'PostgreSQL' in prose; SQL keywords uppercase in examples. Coverage: a new GUC -> config.sgml (and postgresql.conf.sample); new/changed catalogs or views -> catalogs.sgml; new SQL syntax -> the matching ref/*.sgml; new functions -> func.sgml. Do NOT edit release-notes (release-*.sgml) — written by the release team/committers; flag such edits. New user-facing behavior in this PR should ship with matching docs." + }, + { + "path": "**/*.md", + "merge_system_rule": true, + "rule": "REVIEW DISCIPLINE: Precise, blunt, verify against the diff, tag confidence, no praise. Markdown docs. Clear heading hierarchy; fenced code blocks with language hints; accurate instructions/prerequisites; consistent PostgreSQL terminology; no broken relative links or stale claims. Minimal diff." + } + ] +} diff --git a/.github/workflows/ocr-model-check.yml b/.github/workflows/ocr-model-check.yml new file mode 100644 index 0000000000000..10d250528cf7c --- /dev/null +++ b/.github/workflows/ocr-model-check.yml @@ -0,0 +1,89 @@ +# Checks AWS Bedrock weekly for a newer Claude Opus inference profile than the +# one OCR currently uses (vars.OCR_BEDROCK_MODEL) and, if found, opens/updates a +# single GitHub issue telling the maintainer to bump the variable. It does NOT +# change the model automatically: GITHUB_TOKEN cannot write Actions *variables* +# (that needs a PAT with admin), so this is a notify-only mechanism by design. +name: OCR model self-check + +on: + schedule: + - cron: '0 12 * * 1' # Mondays 12:00 UTC + workflow_dispatch: + +permissions: + id-token: write + contents: read + issues: write + +jobs: + check-model: + runs-on: ubuntu-latest + steps: + - name: Configure AWS credentials (OIDC) + uses: aws-actions/configure-aws-credentials@v6 + with: + role-to-assume: ${{ vars.AWS_ROLE_ARN }} + aws-region: ${{ vars.AWS_REGION }} + role-session-name: ocr-model-check-${{ github.run_id }} + + - name: Find newest Opus vs configured + id: check + env: + CURRENT: ${{ vars.OCR_BEDROCK_MODEL }} + AWS_REGION: ${{ vars.AWS_REGION }} + run: | + python3 - <<'PY' >> "$GITHUB_OUTPUT" + import os, re, subprocess, json + region = os.environ.get("AWS_REGION", "us-east-1") + current = os.environ.get("CURRENT", "") + out = subprocess.run( + ["aws", "bedrock", "list-inference-profiles", "--region", region, + "--query", "inferenceProfileSummaries[].inferenceProfileId", "--output", "json"], + capture_output=True, text=True) + ids = json.loads(out.stdout or "[]") + # Parse claude-opus-- from any profile id (prefix us./global. ok). + def ver(s): + m = re.search(r"claude-opus-(\d+)-(\d+)", s) + return (int(m.group(1)), int(m.group(2))) if m else None + opus = [(ver(i), i) for i in ids if ver(i) and i.startswith(("us.", "global."))] + if not opus: + print("newer=false"); raise SystemExit(0) + best_ver, best_id = max(opus, key=lambda x: x[0]) + cur = ver(current) + newer = (cur is None) or (best_ver > cur) + print(f"newer={'true' if newer else 'false'}") + print(f"best_id={best_id}") + print(f"best_ver={best_ver[0]}.{best_ver[1]}") + print(f"cur_ver={'unknown' if cur is None else f'{cur[0]}.{cur[1]}'}") + PY + + - name: Open/update issue if a newer model exists + if: steps.check.outputs.newer == 'true' + uses: actions/github-script@v9 + with: + script: | + const best = '${{ steps.check.outputs.best_id }}'; + const bestVer = '${{ steps.check.outputs.best_ver }}'; + const curVer = '${{ steps.check.outputs.cur_ver }}'; + const marker = ''; + const title = `OCR: newer Claude Opus available (${bestVer} > ${curVer})`; + const body = `${marker}\n` + + `A newer Claude Opus inference profile is available on Bedrock.\n\n` + + `- **Configured** (\`vars.OCR_BEDROCK_MODEL\`): Opus ${curVer}\n` + + `- **Newest on Bedrock**: \`${best}\` (Opus ${bestVer})\n\n` + + `To upgrade, set the repo variable:\n\n` + + '```\n' + + `gh variable set OCR_BEDROCK_MODEL -R ${context.repo.owner}/${context.repo.repo} \\\n` + + ` -b "bedrock/converse/${best}"\n` + + '```\n\n' + + `Also confirm the \`ocr-bedrock-ci\` IAM inline policy allows invoking the new model ` + + `(the resource is scoped to \`anthropic.claude-opus-*\`), then re-run OCR.\n\n` + + `_Automated by \`.github/workflows/ocr-model-check.yml\`; this issue is upserted._`; + const q = `repo:${context.repo.owner}/${context.repo.repo} in:body "${marker}" state:open`; + const found = await github.rest.search.issuesAndPullRequests({ q, per_page: 1 }); + if (found.data.total_count > 0) { + const n = found.data.items[0].number; + await github.rest.issues.update({ owner: context.repo.owner, repo: context.repo.repo, issue_number: n, title, body }); + } else { + await github.rest.issues.create({ owner: context.repo.owner, repo: context.repo.repo, title, body }); + } diff --git a/.github/workflows/ocr-review.yml b/.github/workflows/ocr-review.yml new file mode 100644 index 0000000000000..0828af429b57c --- /dev/null +++ b/.github/workflows/ocr-review.yml @@ -0,0 +1,427 @@ +# Open Code Review (OCR) — AI PR review backed by AWS Bedrock via a LiteLLM proxy. +# +# Flow: +# PR opened/updated (incl. DRAFTS) ─┐ +# /open-code-review PR comment ─┼─► start LiteLLM (127.0.0.1:4000 → Bedrock) +# manual workflow_dispatch ─┘ └► ocr review --format json +# └► post inline PR review comments +# +# Required (repo settings — all repo *variables*, no secrets; auth is via GitHub OIDC): +# vars.AWS_ROLE_ARN - IAM role to assume via OIDC (granting bedrock:InvokeModel*) +# vars.AWS_REGION - e.g. us-east-1 +# vars.OCR_BEDROCK_MODEL - LiteLLM model string for the Opus inference profile, e.g. +# bedrock/converse/us.anthropic.claude-opus-4-8 +# +# No static AWS keys are stored. GITHUB_TOKEN (auto) posts the review comments. + +name: OCR AI Review + +on: + pull_request: + # Note: no draft filter — drafts are reviewed too. + types: [opened, synchronize, reopened, ready_for_review] + issue_comment: + types: [created] + workflow_dispatch: + inputs: + pr_number: + description: 'PR number to review' + required: true + type: number + +# One review per PR; cancel superseded runs to save Bedrock spend. +concurrency: + group: ocr-review-${{ github.event.pull_request.number || github.event.issue.number || github.event.inputs.pr_number }} + cancel-in-progress: true + +permissions: + id-token: write # required to mint the GitHub OIDC token for AWS role assumption + contents: read + pull-requests: write + +jobs: + ocr-review: + runs-on: ubuntu-latest + # PR events always; comment events only when the comment is on a PR and + # starts with the trigger keyword; manual dispatch always. + if: | + github.event_name == 'pull_request' || + github.event_name == 'workflow_dispatch' || + (github.event_name == 'issue_comment' && github.event.issue.pull_request && + (startsWith(github.event.comment.body, '/open-code-review') || + startsWith(github.event.comment.body, '@open-code-review'))) + + env: + # LiteLLM listens on localhost only; this key never leaves the runner. + LITELLM_MASTER_KEY: sk-ocr-ci-local + OCR_BEDROCK_MODEL: ${{ vars.OCR_BEDROCK_MODEL }} + # Region is a static var (safe at job level). AWS credentials are NOT set + # here — they're minted by the OIDC "Configure AWS credentials" step below + # and exported to the environment for the LiteLLM/boto3 Bedrock calls. + AWS_REGION: ${{ vars.AWS_REGION }} + + steps: + - name: Resolve PR context + id: pr + uses: actions/github-script@v9 + with: + script: | + let prNumber; + if (context.eventName === 'pull_request') { + prNumber = context.payload.pull_request.number; + } else if (context.eventName === 'issue_comment') { + prNumber = context.issue.number; + } else { + prNumber = parseInt('${{ github.event.inputs.pr_number }}', 10); + } + const { data: pr } = await github.rest.pulls.get({ + owner: context.repo.owner, + repo: context.repo.repo, + pull_number: prNumber, + }); + const { data: repo } = await github.rest.repos.get({ + owner: context.repo.owner, + repo: context.repo.repo, + }); + core.setOutput('number', String(prNumber)); + core.setOutput('base_ref', pr.base.ref); + core.setOutput('head_ref', pr.head.ref); + core.setOutput('head_sha', pr.head.sha); + core.setOutput('default_branch', repo.default_branch); + core.setOutput('cross_repo', String(pr.head.repo.full_name !== pr.base.repo.full_name)); + + # NOTE: do NOT checkout the PR head. OCR reads the diff and file contents + # straight from git refs (git diff , git show :path, + # git grep ), so the working tree is irrelevant — but our OCR config + # lives on the default branch, not on the PR branch. We check out the repo + # (default ref), fetch the base/head objects, and materialize the config + # from origin/. + - name: Checkout + uses: actions/checkout@v6 + with: + fetch-depth: 0 + + - name: Prepare git refs and OCR config + env: + BASE_REF: ${{ steps.pr.outputs.base_ref }} + HEAD_REF: ${{ steps.pr.outputs.head_ref }} + HEAD_SHA: ${{ steps.pr.outputs.head_sha }} + DEFAULT_BRANCH: ${{ steps.pr.outputs.default_branch }} + run: | + git fetch --no-tags origin "+refs/heads/${DEFAULT_BRANCH}:refs/remotes/origin/${DEFAULT_BRANCH}" || true + git fetch --no-tags origin "+refs/heads/${BASE_REF}:refs/remotes/origin/${BASE_REF}" || true + git fetch --no-tags origin "+refs/heads/${HEAD_REF}:refs/remotes/origin/${HEAD_REF}" || true + git fetch --no-tags origin "${HEAD_SHA}" || true + + # OCR config lives on the default branch; materialize it independently + # of whatever ref is checked out. + mkdir -p "$RUNNER_TEMP/ocr" + git show "origin/${DEFAULT_BRANCH}:.github/ocr/litellm.yaml" > "$RUNNER_TEMP/ocr/litellm.yaml" + git show "origin/${DEFAULT_BRANCH}:.github/ocr/rule.json" > "$RUNNER_TEMP/ocr/rule.json" + git show "origin/${DEFAULT_BRANCH}:.github/ocr/context.md" > "$RUNNER_TEMP/ocr/context.md" + echo "Config materialized:"; ls -l "$RUNNER_TEMP/ocr" + + - name: Setup Python + uses: actions/setup-python@v6 + with: + python-version: '3.12' + + - name: Setup Node.js + uses: actions/setup-node@v6 + with: + node-version: '20' + + - name: Install LiteLLM proxy + Open Code Review + run: | + python -m pip install --upgrade pip + # Pin LiteLLM to a main commit that supports Claude Opus 4.8 adaptive + # thinking (maps reasoning_effort -> output_config.effort, incl. xhigh). + # Not in any tagged release yet (PyPI latest 1.87.1 lacks the Opus + # normalizer). Bump this SHA once a release ships the feature. + pip install "litellm[proxy] @ git+https://github.com/BerriAI/litellm.git@5be0797d24a2f26eb2123e13788f90055a59d91d" + npm install -g @alibaba-group/open-code-review + + - name: Configure AWS credentials (OIDC) + uses: aws-actions/configure-aws-credentials@v6 + with: + role-to-assume: ${{ vars.AWS_ROLE_ARN }} + aws-region: ${{ vars.AWS_REGION }} + role-session-name: ocr-review-${{ github.run_id }} + + - name: Start LiteLLM proxy (Bedrock bridge) + run: | + if [ -z "$OCR_BEDROCK_MODEL" ]; then + echo "::error::vars.OCR_BEDROCK_MODEL is not set (e.g. bedrock/converse/us.anthropic.claude-opus-4-1-20250805-v1:0)" + exit 1 + fi + nohup litellm --config "$RUNNER_TEMP/ocr/litellm.yaml" --host 127.0.0.1 --port 4000 \ + > /tmp/litellm.log 2>&1 & + echo "Waiting for LiteLLM to become ready..." + for i in $(seq 1 60); do + if curl -sf http://127.0.0.1:4000/health/readiness >/dev/null; then + echo "LiteLLM ready."; exit 0 + fi + sleep 2 + done + echo "::error::LiteLLM did not become ready in time"; cat /tmp/litellm.log; exit 1 + + - name: Configure OCR + run: | + ocr config set llm.url http://127.0.0.1:4000/v1/chat/completions + ocr config set llm.auth_token "$LITELLM_MASTER_KEY" + ocr config set llm.model ocr-bedrock + ocr config set llm.use_anthropic false + ocr config set language English + + - name: Run OCR review + run: | + ocr review \ + --from "origin/${{ steps.pr.outputs.base_ref }}" \ + --to "${{ steps.pr.outputs.head_sha }}" \ + --rule "$RUNNER_TEMP/ocr/rule.json" \ + --background-file "$RUNNER_TEMP/ocr/context.md" \ + --concurrency 3 \ + --timeout 20 \ + --format json \ + > /tmp/ocr-result.json 2>/tmp/ocr-stderr.log || true + echo "----- OCR stdout -----"; cat /tmp/ocr-result.json || true + echo "----- OCR stderr -----"; cat /tmp/ocr-stderr.log || true + echo "----- LiteLLM log (tail) -----"; tail -n 50 /tmp/litellm.log || true + + - name: Post review to PR + uses: actions/github-script@v9 + with: + github-token: ${{ secrets.GITHUB_TOKEN }} + script: | + const fs = require('fs'); + const prNumber = parseInt('${{ steps.pr.outputs.number }}', 10); + const commitSha = '${{ steps.pr.outputs.head_sha }}'; + + // Opus at high effort can emit dozens of findings. Posting them all + // one-by-one trips GitHub's SECONDARY rate limit (403 "content + // creation"), which is what made every run fail after the review + // was already generated. We (a) cap inline comments and overflow + // the rest into the summary, (b) prefer a single bulk createReview, + // and (c) throttle + back off with Retry-After on any fallback. + const MAX_INLINE = 25; + const sleep = (ms) => new Promise(r => setTimeout(r, ms)); + + async function withRetry(fn, label) { + for (let attempt = 1; attempt <= 5; attempt++) { + try { return await fn(); } + catch (e) { + const status = e.status || (e.response && e.response.status); + const h = (e.response && e.response.headers) || {}; + const isRate = status === 403 || status === 429; + if (!isRate || attempt === 5) throw e; + let waitMs = 0; + if (h['retry-after']) waitMs = parseInt(h['retry-after'], 10) * 1000; + else if (h['x-ratelimit-reset']) waitMs = parseInt(h['x-ratelimit-reset'], 10) * 1000 - Date.now(); + if (!waitMs || Number.isNaN(waitMs) || waitMs < 0) waitMs = 1000 * Math.pow(2, attempt); + waitMs = Math.min(waitMs, 60000) + 500; + core.warning(`${label}: rate-limited (status ${status}); waiting ${Math.round(waitMs / 1000)}s (attempt ${attempt}/5)`); + await sleep(waitMs); + } + } + } + + let result; + try { + result = JSON.parse(fs.readFileSync('/tmp/ocr-result.json', 'utf8')); + } catch (e) { + const stderr = (() => { try { return fs.readFileSync('/tmp/ocr-stderr.log', 'utf8').trim(); } catch { return ''; } })(); + await withRetry(() => github.rest.issues.createComment({ + owner: context.repo.owner, repo: context.repo.repo, issue_number: prNumber, + body: `⚠️ **OCR** could not produce a review.\n\n\`\`\`\n${(stderr || e.message).slice(0, 8000)}\n\`\`\``, + }), 'error-comment'); + return; + } + + const comments = result.comments || []; + const warnings = result.warnings || []; + + const formatComment = (c) => { + let body = c.content || ''; + if (c.suggestion_code && c.existing_code) { + body += '\n\n```suggestion\n' + c.suggestion_code + (c.suggestion_code.endsWith('\n') ? '' : '\n') + '```'; + } + return body; + }; + const formatMarkdown = (c) => { + let md = `### 📄 \`${c.path}\``; + if (c.start_line && c.end_line) md += ` (L${c.start_line}-L${c.end_line})`; + md += '\n\n' + (c.content || ''); + if (c.suggestion_code && c.existing_code) { + md += '\n\n
💡 Suggested change\n\n'; + md += '**Before:**\n```\n' + c.existing_code + '\n```\n\n**After:**\n```\n' + c.suggestion_code + '\n```\n\n
'; + } + return md; + }; + + if (comments.length === 0) { + await withRetry(() => github.rest.issues.createComment({ + owner: context.repo.owner, repo: context.repo.repo, issue_number: prNumber, + body: `✅ **OCR**: ${result.message || 'No issues found.'}`, + }), 'no-issues-comment'); + return; + } + + const inlineAll = []; + const noLine = []; + for (const c of comments) { + const body = formatComment(c); + const hasLine = (c.start_line >= 1) || (c.end_line >= 1); + if (!hasLine) { noLine.push(c); continue; } + const rc = { path: c.path, body, side: 'RIGHT' }; + if (c.start_line >= 1 && c.end_line >= 1 && c.start_line !== c.end_line) { + rc.start_line = c.start_line; rc.line = c.end_line; rc.start_side = 'RIGHT'; + } else { + rc.line = c.end_line >= 1 ? c.end_line : c.start_line; + } + inlineAll.push({ rc, c }); + } + + const inline = inlineAll.slice(0, MAX_INLINE).map(x => x.rc); + const overflow = inlineAll.slice(MAX_INLINE).map(x => x.c); + + let summary = `🔍 **OCR** found **${comments.length}** issue(s).`; + summary += `\n- ${inline.length} inline, ${noLine.length + overflow.length} in summary`; + if (overflow.length) summary += ` (inline capped at ${MAX_INLINE})`; + if (warnings.length) summary += `\n- ⚠️ ${warnings.length} warning(s) during review`; + for (const c of noLine.concat(overflow)) summary += '\n\n---\n\n' + formatMarkdown(c); + + // Preferred path: ONE createReview carrying every inline comment. + try { + await withRetry(() => github.rest.pulls.createReview({ + owner: context.repo.owner, repo: context.repo.repo, pull_number: prNumber, + commit_id: commitSha, body: summary, event: 'COMMENT', comments: inline, + }), 'bulk-review'); + return; + } catch (e) { + core.warning(`bulk createReview failed (${e.status || '?'}: ${e.message}); falling back to throttled per-comment posting`); + } + + // Fallback: an invalid inline position (line not in the diff -> 422) + // rejects the whole bulk review. Post the summary, then each comment + // individually with a delay + backoff, skipping ones GitHub rejects. + let ok = 0; const failed = []; + try { + await withRetry(() => github.rest.pulls.createReview({ + owner: context.repo.owner, repo: context.repo.repo, pull_number: prNumber, + commit_id: commitSha, body: summary, event: 'COMMENT', + }), 'summary-review'); + } catch (err) { failed.push(`summary: ${err.message}`); } + + for (const rc of inline) { + try { + await withRetry(() => github.rest.pulls.createReviewComment({ + owner: context.repo.owner, repo: context.repo.repo, pull_number: prNumber, + commit_id: commitSha, path: rc.path, body: rc.body, + ...(rc.start_line ? { start_line: rc.start_line, start_side: rc.start_side } : {}), + line: rc.line, side: rc.side, + }), `comment ${rc.path}:${rc.line}`); + ok++; + } catch (inner) { + failed.push(`\`${rc.path}\` L${rc.line}: ${inner.message}`); + } + await sleep(1200); // stay under the secondary content-creation limit + } + + if (failed.length) { + await withRetry(() => github.rest.issues.createComment({ + owner: context.repo.owner, repo: context.repo.repo, issue_number: prNumber, + body: `📊 OCR posted ${ok}/${inline.length} inline comment(s).\n\n
${failed.length} could not be posted\n\n${failed.join('\n')}\n
`, + }), 'summary-failures'); + } + + # Companion job: OCR can't call MCP, so this separate agent ties the PR's + # changes to PostgreSQL git + pgsql-hackers history via the Agora MCP server + # (pg.ddx.io) and posts a single, upserted "history & discussion" comment. + pg-history: + runs-on: ubuntu-latest + if: | + github.event_name == 'pull_request' || + github.event_name == 'workflow_dispatch' || + (github.event_name == 'issue_comment' && github.event.issue.pull_request && + (startsWith(github.event.comment.body, '/open-code-review') || + startsWith(github.event.comment.body, '@open-code-review') || + startsWith(github.event.comment.body, '/pg-history'))) + steps: + - name: Resolve PR context + id: pr + uses: actions/github-script@v9 + with: + script: | + let prNumber; + if (context.eventName === 'pull_request') prNumber = context.payload.pull_request.number; + else if (context.eventName === 'issue_comment') prNumber = context.issue.number; + else prNumber = parseInt('${{ github.event.inputs.pr_number }}', 10); + const { data: pr } = await github.rest.pulls.get({ + owner: context.repo.owner, repo: context.repo.repo, pull_number: prNumber }); + core.setOutput('number', String(prNumber)); + core.setOutput('base_ref', pr.base.ref); + core.setOutput('head_sha', pr.head.sha); + core.setOutput('title', pr.title || ''); + + - name: Checkout + uses: actions/checkout@v6 + with: + fetch-depth: 0 + + - name: Make base/head refs available + env: + BASE_REF: ${{ steps.pr.outputs.base_ref }} + HEAD_SHA: ${{ steps.pr.outputs.head_sha }} + run: | + git fetch --no-tags origin "+refs/heads/${BASE_REF}:refs/remotes/origin/${BASE_REF}" || true + git fetch --no-tags origin "${HEAD_SHA}" || true + + - name: Setup Python + uses: actions/setup-python@v6 + with: + python-version: '3.12' + + - name: Configure AWS credentials (OIDC) + uses: aws-actions/configure-aws-credentials@v6 + with: + role-to-assume: ${{ vars.AWS_ROLE_ARN }} + aws-region: ${{ vars.AWS_REGION }} + role-session-name: pg-history-${{ github.run_id }} + + - name: Install deps + run: pip install boto3 + + - name: Run pg-history (Agora MCP) + env: + PG_HISTORY_MODEL: ${{ vars.OCR_BEDROCK_MODEL }} + AWS_REGION: ${{ vars.AWS_REGION }} + BASE_REF: ${{ steps.pr.outputs.base_ref }} + HEAD_SHA: ${{ steps.pr.outputs.head_sha }} + GH_PR_TITLE: ${{ steps.pr.outputs.title }} + PG_HISTORY_OUT: ${{ runner.temp }}/pg-history.md + run: | + python .github/ocr/pg-history.py || true + echo "----- output -----"; cat "${{ runner.temp }}/pg-history.md" 2>/dev/null || echo "(no output)" + + - name: Upsert PR comment + uses: actions/github-script@v9 + with: + script: | + const fs = require('fs'); + const path = process.env.RUNNER_TEMP + '/pg-history.md'; + let body = ''; + try { body = fs.readFileSync(path, 'utf8').trim(); } catch (e) {} + if (!body) { console.log('pg-history: empty output, nothing to post'); return; } + const prNumber = parseInt('${{ steps.pr.outputs.number }}', 10); + const marker = ''; + body = marker + '\n' + body; + const { data: comments } = await github.rest.issues.listComments({ + owner: context.repo.owner, repo: context.repo.repo, issue_number: prNumber, per_page: 100 }); + const mine = comments.find(c => c.user.type === 'Bot' && c.body && c.body.includes(marker)); + if (mine) { + await github.rest.issues.updateComment({ + owner: context.repo.owner, repo: context.repo.repo, comment_id: mine.id, body }); + } else { + await github.rest.issues.createComment({ + owner: context.repo.owner, repo: context.repo.repo, issue_number: prNumber, body }); + } diff --git a/.github/workflows/sync-upstream-manual.yml b/.github/workflows/sync-upstream-manual.yml new file mode 100644 index 0000000000000..3139e517f409f --- /dev/null +++ b/.github/workflows/sync-upstream-manual.yml @@ -0,0 +1,252 @@ +name: Sync from Upstream (Manual) + +on: + workflow_dispatch: + inputs: + force_push: + description: 'Use --force-with-lease when pushing' + required: false + type: boolean + default: true + +jobs: + sync: + runs-on: ubuntu-latest + permissions: + contents: write + issues: write + + steps: + - name: Checkout repository + uses: actions/checkout@v5 + with: + fetch-depth: 0 + # PAT with repo + workflow scope. The default GITHUB_TOKEN cannot push + # commits that touch .github/workflows/ (platform block). See SYNC_TOKEN + # repo secret. + token: ${{ secrets.SYNC_TOKEN || secrets.GITHUB_TOKEN }} + + - name: Configure Git + run: | + git config user.name "github-actions[bot]" + git config user.email "github-actions[bot]@users.noreply.github.com" + + - name: Add upstream remote + run: | + git remote add upstream https://github.com/postgres/postgres.git || true + git remote -v + + - name: Fetch upstream + run: | + echo "Fetching from upstream postgres/postgres..." + git fetch upstream master + echo "Current local master:" + git log origin/master --oneline -5 + echo "Upstream master:" + git log upstream/master --oneline -5 + + - name: Check for local commits + id: check_commits + run: | + git checkout master + LOCAL_COMMITS=$(git rev-list origin/master..upstream/master --count) + DIVERGED=$(git rev-list upstream/master..origin/master --count) + echo "commits_behind=$LOCAL_COMMITS" >> $GITHUB_OUTPUT + echo "commits_ahead=$DIVERGED" >> $GITHUB_OUTPUT + echo "Mirror is $DIVERGED commits ahead and $LOCAL_COMMITS commits behind upstream" + + if [ "$DIVERGED" -gt 0 ]; then + # Check commit messages for "dev setup" or "dev v" pattern + DEV_SETUP_COMMITS=$(git log --format=%s upstream/master...origin/master | grep -iE "^dev (setup|v[0-9])" | wc -l) + echo "dev_setup_commits=$DEV_SETUP_COMMITS" >> $GITHUB_OUTPUT + + # Check if diverged commits only touch .github/ directory + NON_GITHUB_CHANGES=$(git diff --name-only upstream/master...origin/master | grep -v "^\.github/" | wc -l) + echo "non_github_changes=$NON_GITHUB_CHANGES" >> $GITHUB_OUTPUT + + if [ "$NON_GITHUB_CHANGES" -eq 0 ]; then + echo "✓ All local commits are CI/CD configuration (.github/ only)" + elif [ "$DEV_SETUP_COMMITS" -gt 0 ]; then + echo "✓ Found $DEV_SETUP_COMMITS 'dev setup/version' commit(s)" + else + echo "⚠️ WARNING: Local commits modify files outside .github/ and are not 'dev setup/version' commits!" + git diff --name-only upstream/master...origin/master | grep -v "^\.github/" || true + fi + else + echo "non_github_changes=0" >> $GITHUB_OUTPUT + echo "dev_setup_commits=0" >> $GITHUB_OUTPUT + fi + + - name: Attempt merge + id: merge + run: | + COMMITS_AHEAD=${{ steps.check_commits.outputs.commits_ahead }} + COMMITS_BEHIND=${{ steps.check_commits.outputs.commits_behind }} + NON_GITHUB_CHANGES=${{ steps.check_commits.outputs.non_github_changes }} + DEV_SETUP_COMMITS=${{ steps.check_commits.outputs.dev_setup_commits }} + + # Check if there are problematic local commits + # Allow commits if: + # 1. Only .github/ changes (CI/CD config) + # 2. Has "dev setup/version" commits (personal development environment) + if [ "$COMMITS_AHEAD" -gt 0 ] && [ "$NON_GITHUB_CHANGES" -gt 0 ]; then + if [ "$DEV_SETUP_COMMITS" -eq 0 ]; then + echo "❌ Local master has commits outside .github/ that are not 'dev setup/version' commits!" + echo "merge_status=conflict" >> $GITHUB_OUTPUT + exit 1 + else + echo "✓ Non-.github/ changes are from 'dev setup/version' commits - allowed" + fi + fi + + # Already up to date + if [ "$COMMITS_BEHIND" -eq 0 ]; then + echo "✓ Already up to date with upstream" + echo "merge_status=uptodate" >> $GITHUB_OUTPUT + exit 0 + fi + + # Try fast-forward first (clean case) + if [ "$COMMITS_AHEAD" -eq 0 ]; then + echo "Fast-forwarding to upstream (no local commits)..." + git merge --ff-only upstream/master + echo "merge_status=success" >> $GITHUB_OUTPUT + exit 0 + fi + + # Local commits exist (.github/ and/or dev setup/version) - rebase onto upstream + if [ "$DEV_SETUP_COMMITS" -gt 0 ]; then + echo "Rebasing local CI/CD and dev setup/version commits onto upstream..." + else + echo "Rebasing local CI/CD commits (.github/ only) onto upstream..." + fi + + git config user.name "github-actions[bot]" + git config user.email "github-actions[bot]@users.noreply.github.com" + + if git rebase upstream/master; then + echo "✓ Successfully rebased local commits onto upstream" + echo "merge_status=success" >> $GITHUB_OUTPUT + else + echo "❌ Rebase conflict occurred" + echo "merge_status=conflict" >> $GITHUB_OUTPUT + + # Abort the failed rebase to clean up state + git rebase --abort + exit 1 + fi + continue-on-error: true + + - name: Push to origin + if: steps.merge.outputs.merge_status == 'success' + run: | + if [ "${{ inputs.force_push }}" == "true" ]; then + git push origin master --force-with-lease + else + git push origin master + fi + echo "✓ Successfully synced master with upstream" + + - name: Create issue on failure + if: steps.merge.outputs.merge_status == 'conflict' + uses: actions/github-script@v7 + with: + script: | + const title = '🚨 Upstream Sync Failed - Manual Intervention Required'; + const body = `## Sync Failure Report + + The automated sync from \`postgres/postgres\` failed due to conflicting commits. + + **Details:** + - Local master has ${{ steps.check_commits.outputs.commits_ahead }} commit(s) not in upstream + - Upstream has ${{ steps.check_commits.outputs.commits_behind }} new commit(s) + - Non-.github/ changes: ${{ steps.check_commits.outputs.non_github_changes }} files + + **This indicates commits were made directly to master outside .github/**, which violates the pristine mirror policy. + + **Note:** Commits to .github/ (CI/CD configuration) are allowed and will be preserved during sync. + + ### Resolution Steps: + + 1. Identify the conflicting commits: + \`\`\`bash + git fetch origin + git fetch upstream https://github.com/postgres/postgres.git master + git log upstream/master..origin/master + \`\`\` + + 2. If these commits should be preserved: + - Create a feature branch: \`git checkout -b recovery/master-commits origin/master\` + - Reset master: \`git checkout master && git reset --hard upstream/master\` + - Push: \`git push origin master --force\` + - Cherry-pick or rebase the feature branch + + 3. If these commits should be discarded: + - Reset master: \`git checkout master && git reset --hard upstream/master\` + - Push: \`git push origin master --force\` + + 4. Close this issue once resolved + + **Workflow run:** ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }} + `; + + // Check if issue already exists + const issues = await github.rest.issues.listForRepo({ + owner: context.repo.owner, + repo: context.repo.repo, + state: 'open', + labels: 'sync-failure' + }); + + if (issues.data.length === 0) { + await github.rest.issues.create({ + owner: context.repo.owner, + repo: context.repo.repo, + title: title, + body: body, + labels: ['sync-failure', 'automation'] + }); + } + + - name: Close existing sync-failure issues + if: steps.merge.outputs.merge_status == 'success' + uses: actions/github-script@v7 + with: + script: | + const issues = await github.rest.issues.listForRepo({ + owner: context.repo.owner, + repo: context.repo.repo, + state: 'open', + labels: 'sync-failure' + }); + + for (const issue of issues.data) { + await github.rest.issues.createComment({ + owner: context.repo.owner, + repo: context.repo.repo, + issue_number: issue.number, + body: '✓ Sync successful - closing this issue automatically.' + }); + + await github.rest.issues.update({ + owner: context.repo.owner, + repo: context.repo.repo, + issue_number: issue.number, + state: 'closed' + }); + } + + - name: Summary + if: always() + run: | + echo "### Sync Summary" >> $GITHUB_STEP_SUMMARY + echo "- **Status:** ${{ steps.merge.outputs.merge_status }}" >> $GITHUB_STEP_SUMMARY + echo "- **Commits behind:** ${{ steps.check_commits.outputs.commits_behind }}" >> $GITHUB_STEP_SUMMARY + echo "- **Commits ahead:** ${{ steps.check_commits.outputs.commits_ahead }}" >> $GITHUB_STEP_SUMMARY + if [ "${{ steps.merge.outputs.merge_status }}" == "success" ]; then + echo "- **Result:** ✓ Successfully synced with upstream" >> $GITHUB_STEP_SUMMARY + elif [ "${{ steps.merge.outputs.merge_status }}" == "uptodate" ]; then + echo "- **Result:** ✓ Already up to date" >> $GITHUB_STEP_SUMMARY + else + echo "- **Result:** ⚠️ Sync failed - manual intervention required" >> $GITHUB_STEP_SUMMARY + fi diff --git a/.github/workflows/sync-upstream.yml b/.github/workflows/sync-upstream.yml new file mode 100644 index 0000000000000..eca408a7a11c5 --- /dev/null +++ b/.github/workflows/sync-upstream.yml @@ -0,0 +1,260 @@ +name: Sync from Upstream (Automatic) + +on: + schedule: + # Run hourly every day + - cron: '0 * * * *' + workflow_dispatch: + +jobs: + sync: + runs-on: ubuntu-latest + permissions: + contents: write + issues: write + + steps: + - name: Checkout repository + uses: actions/checkout@v5 + with: + fetch-depth: 0 + # PAT with repo + workflow scope. The default GITHUB_TOKEN cannot push + # commits that touch .github/workflows/ (platform block). See SYNC_TOKEN + # repo secret. Falls back to GITHUB_TOKEN if unset (push will fail on + # workflow-file changes, but non-workflow syncs still work). + token: ${{ secrets.SYNC_TOKEN || secrets.GITHUB_TOKEN }} + + - name: Configure Git + run: | + git config user.name "github-actions[bot]" + git config user.email "github-actions[bot]@users.noreply.github.com" + + - name: Add upstream remote + run: | + git remote add upstream https://github.com/postgres/postgres.git || true + git remote -v + + - name: Fetch upstream + run: | + echo "Fetching from upstream postgres/postgres..." + git fetch upstream master + + - name: Check for local commits + id: check_commits + run: | + git checkout master + LOCAL_COMMITS=$(git rev-list origin/master..upstream/master --count) + DIVERGED=$(git rev-list upstream/master..origin/master --count) + echo "commits_behind=$LOCAL_COMMITS" >> $GITHUB_OUTPUT + echo "commits_ahead=$DIVERGED" >> $GITHUB_OUTPUT + + if [ "$LOCAL_COMMITS" -eq 0 ]; then + echo "✓ Already up to date with upstream" + else + echo "Mirror is $LOCAL_COMMITS commits behind upstream" + fi + + if [ "$DIVERGED" -gt 0 ]; then + echo "⚠️ Local master has $DIVERGED commits not in upstream" + + # Check commit messages for "dev setup" or "dev v" pattern + DEV_SETUP_COMMITS=$(git log --format=%s upstream/master..origin/master | grep -iE "^dev (setup|v[0-9])" | wc -l) + echo "dev_setup_commits=$DEV_SETUP_COMMITS" >> $GITHUB_OUTPUT + + # Check if diverged commits only touch .github/ directory + NON_GITHUB_CHANGES=$(git diff --name-only upstream/master...origin/master | grep -v "^\.github/" | wc -l) + echo "non_github_changes=$NON_GITHUB_CHANGES" >> $GITHUB_OUTPUT + + if [ "$NON_GITHUB_CHANGES" -eq 0 ]; then + echo "✓ All local commits are CI/CD configuration (.github/ only) - will merge" + elif [ "$DEV_SETUP_COMMITS" -gt 0 ]; then + echo "✓ Found $DEV_SETUP_COMMITS 'dev setup/version' commit(s)" + else + echo "⚠️ WARNING: Local commits modify files outside .github/ and are not 'dev setup/version' commits!" + git diff --name-only upstream/master...origin/master | grep -v "^\.github/" || true + echo "Non-dev commits:" + git log --format=" %h %s" upstream/master..origin/master | grep -ivE "^ [a-f0-9]* dev (setup|v[0-9])" || true + fi + else + echo "non_github_changes=0" >> $GITHUB_OUTPUT + echo "dev_setup_commits=0" >> $GITHUB_OUTPUT + fi + + - name: Attempt merge + id: merge + run: | + COMMITS_AHEAD=${{ steps.check_commits.outputs.commits_ahead }} + COMMITS_BEHIND=${{ steps.check_commits.outputs.commits_behind }} + NON_GITHUB_CHANGES=${{ steps.check_commits.outputs.non_github_changes }} + DEV_SETUP_COMMITS=${{ steps.check_commits.outputs.dev_setup_commits }} + + # Check if there are problematic local commits + # Allow commits if: + # 1. Only .github/ changes (CI/CD config) + # 2. Has "dev setup/version" commits (personal development environment) + if [ "$COMMITS_AHEAD" -gt 0 ] && [ "$NON_GITHUB_CHANGES" -gt 0 ]; then + if [ "$DEV_SETUP_COMMITS" -eq 0 ]; then + echo "❌ Local master has commits outside .github/ that are not 'dev setup/version' commits!" + echo "merge_status=conflict" >> $GITHUB_OUTPUT + exit 1 + else + echo "✓ Non-.github/ changes are from 'dev setup/version' commits - allowed" + fi + fi + + # Already up to date + if [ "$COMMITS_BEHIND" -eq 0 ]; then + echo "✓ Already up to date with upstream" + echo "merge_status=uptodate" >> $GITHUB_OUTPUT + exit 0 + fi + + # Try fast-forward first (clean case) + if [ "$COMMITS_AHEAD" -eq 0 ]; then + echo "Fast-forwarding to upstream (no local commits)..." + git merge --ff-only upstream/master + echo "merge_status=success" >> $GITHUB_OUTPUT + exit 0 + fi + + # Local commits exist (.github/ and/or dev setup/version) - rebase onto upstream + if [ "$DEV_SETUP_COMMITS" -gt 0 ]; then + echo "Rebasing local CI/CD and dev setup/version commits onto upstream..." + else + echo "Rebasing local CI/CD commits (.github/ only) onto upstream..." + fi + + git config user.name "github-actions[bot]" + git config user.email "github-actions[bot]@users.noreply.github.com" + + if git rebase upstream/master; then + echo "✓ Successfully rebased local commits onto upstream" + echo "merge_status=success" >> $GITHUB_OUTPUT + else + echo "❌ Rebase conflict occurred" + echo "merge_status=conflict" >> $GITHUB_OUTPUT + + # Abort the failed rebase to clean up state + git rebase --abort + exit 1 + fi + continue-on-error: true + + - name: Push to origin + if: steps.merge.outputs.merge_status == 'success' + run: | + git push origin master --force-with-lease + + COMMITS_SYNCED="${{ steps.check_commits.outputs.commits_behind }}" + echo "✓ Successfully synced $COMMITS_SYNCED commits from upstream" + + - name: Create issue on failure + if: steps.merge.outputs.merge_status == 'conflict' + uses: actions/github-script@v7 + with: + script: | + const title = '🚨 Automated Upstream Sync Failed'; + const body = `## Automatic Sync Failure + + The daily sync from \`postgres/postgres\` failed. + + **Details:** + - Local master has ${{ steps.check_commits.outputs.commits_ahead }} commit(s) not in upstream + - Upstream has ${{ steps.check_commits.outputs.commits_behind }} new commit(s) + - Non-.github/ changes: ${{ steps.check_commits.outputs.non_github_changes }} files + - **Run date:** ${new Date().toISOString()} + + **Root cause:** Commits were made directly to master outside of .github/, which violates the pristine mirror policy. + + **Note:** Commits to .github/ (CI/CD configuration) are allowed and will be preserved during sync. + + ### Resolution Steps: + + 1. Review the conflicting commits: + \`\`\`bash + git log upstream/master..origin/master --oneline + \`\`\` + + 2. Determine if commits should be: + - **Preserved:** Create feature branch and reset master + - **Discarded:** Hard reset master to upstream + + 3. See [sync documentation](.github/docs/sync-setup.md) for detailed recovery procedures + + 4. Run manual sync workflow after resolution to verify + + **Workflow run:** ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }} + `; + + // Check if issue already exists + const issues = await github.rest.issues.listForRepo({ + owner: context.repo.owner, + repo: context.repo.repo, + state: 'open', + labels: 'sync-failure' + }); + + if (issues.data.length === 0) { + await github.rest.issues.create({ + owner: context.repo.owner, + repo: context.repo.repo, + title: title, + body: body, + labels: ['sync-failure', 'automation', 'urgent'] + }); + } else { + // Update existing issue + await github.rest.issues.createComment({ + owner: context.repo.owner, + repo: context.repo.repo, + issue_number: issues.data[0].number, + body: `Sync failed again on ${new Date().toISOString()}\n\nWorkflow: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}` + }); + } + + - name: Close sync-failure issues + if: steps.merge.outputs.merge_status == 'success' + uses: actions/github-script@v7 + with: + script: | + const issues = await github.rest.issues.listForRepo({ + owner: context.repo.owner, + repo: context.repo.repo, + state: 'open', + labels: 'sync-failure' + }); + + for (const issue of issues.data) { + await github.rest.issues.createComment({ + owner: context.repo.owner, + repo: context.repo.repo, + issue_number: issue.number, + body: `✓ Automatic sync successful on ${new Date().toISOString()} - synced ${{ steps.check_commits.outputs.commits_behind }} commits.\n\nClosing issue automatically.` + }); + + await github.rest.issues.update({ + owner: context.repo.owner, + repo: context.repo.repo, + issue_number: issue.number, + state: 'closed' + }); + } + + - name: Summary + if: always() + run: | + echo "### Daily Sync Summary" >> $GITHUB_STEP_SUMMARY + echo "- **Date:** $(date -u)" >> $GITHUB_STEP_SUMMARY + echo "- **Status:** ${{ steps.merge.outputs.merge_status }}" >> $GITHUB_STEP_SUMMARY + echo "- **Commits synced:** ${{ steps.check_commits.outputs.commits_behind }}" >> $GITHUB_STEP_SUMMARY + + if [ "${{ steps.merge.outputs.merge_status }}" == "success" ]; then + echo "" >> $GITHUB_STEP_SUMMARY + echo "✓ Mirror successfully updated with upstream postgres/postgres" >> $GITHUB_STEP_SUMMARY + elif [ "${{ steps.merge.outputs.merge_status }}" == "uptodate" ]; then + echo "" >> $GITHUB_STEP_SUMMARY + echo "✓ Mirror already up to date" >> $GITHUB_STEP_SUMMARY + else + echo "" >> $GITHUB_STEP_SUMMARY + echo "⚠️ Sync failed - check created issue for details" >> $GITHUB_STEP_SUMMARY + fi diff --git a/contrib/pg_buffercache/pg_buffercache_pages.c b/contrib/pg_buffercache/pg_buffercache_pages.c index 510455998aa74..b94e6f6fda80b 100644 --- a/contrib/pg_buffercache/pg_buffercache_pages.c +++ b/contrib/pg_buffercache/pg_buffercache_pages.c @@ -161,7 +161,7 @@ pg_buffercache_pages(PG_FUNCTION_ARGS) reldatabase = bufHdr->tag.dbOid; forknum = BufTagGetForkNum(&bufHdr->tag); blocknum = bufHdr->tag.blockNum; - usagecount = BUF_STATE_GET_USAGECOUNT(buf_state); + usagecount = BUF_STATE_GET_COOLSTATE(buf_state); pinning_backends = BUF_STATE_GET_REFCOUNT(buf_state); if (buf_state & BM_DIRTY) @@ -605,7 +605,7 @@ pg_buffercache_summary(PG_FUNCTION_ARGS) if (buf_state & BM_VALID) { buffers_used++; - usagecount_total += BUF_STATE_GET_USAGECOUNT(buf_state); + usagecount_total += BUF_STATE_GET_COOLSTATE(buf_state); if (buf_state & BM_DIRTY) buffers_dirty++; @@ -655,7 +655,7 @@ pg_buffercache_usage_counts(PG_FUNCTION_ARGS) CHECK_FOR_INTERRUPTS(); - usage_count = BUF_STATE_GET_USAGECOUNT(buf_state); + usage_count = BUF_STATE_GET_COOLSTATE(buf_state); usage_counts[usage_count]++; if (buf_state & BM_DIRTY) diff --git a/flake.lock b/flake.lock new file mode 100644 index 0000000000000..b8e8a1fdb750f --- /dev/null +++ b/flake.lock @@ -0,0 +1,78 @@ +{ + "nodes": { + "flake-utils": { + "inputs": { + "systems": "systems" + }, + "locked": { + "lastModified": 1731533236, + "narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=", + "owner": "numtide", + "repo": "flake-utils", + "rev": "11707dc2f618dd54ca8739b309ec4fc024de578b", + "type": "github" + }, + "original": { + "owner": "numtide", + "repo": "flake-utils", + "type": "github" + } + }, + "nixpkgs": { + "locked": { + "lastModified": 1767313136, + "narHash": "sha256-16KkgfdYqjaeRGBaYsNrhPRRENs0qzkQVUooNHtoy2w=", + "owner": "NixOS", + "repo": "nixpkgs", + "rev": "ac62194c3917d5f474c1a844b6fd6da2db95077d", + "type": "github" + }, + "original": { + "owner": "NixOS", + "ref": "nixos-25.05", + "repo": "nixpkgs", + "type": "github" + } + }, + "nixpkgs-unstable": { + "locked": { + "lastModified": 1777270315, + "narHash": "sha256-yKB4G6cKsQsWN7M6rZGk6gkJPDNPIzT05y4qzRyCDlI=", + "owner": "nixos", + "repo": "nixpkgs", + "rev": "6368eda62c9775c38ef7f714b2555a741c20c72d", + "type": "github" + }, + "original": { + "owner": "nixos", + "ref": "nixpkgs-unstable", + "repo": "nixpkgs", + "type": "github" + } + }, + "root": { + "inputs": { + "flake-utils": "flake-utils", + "nixpkgs": "nixpkgs", + "nixpkgs-unstable": "nixpkgs-unstable" + } + }, + "systems": { + "locked": { + "lastModified": 1681028828, + "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=", + "owner": "nix-systems", + "repo": "default", + "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e", + "type": "github" + }, + "original": { + "owner": "nix-systems", + "repo": "default", + "type": "github" + } + } + }, + "root": "root", + "version": 7 +} diff --git a/flake.nix b/flake.nix new file mode 100644 index 0000000000000..aae6d54c4c8cf --- /dev/null +++ b/flake.nix @@ -0,0 +1,45 @@ +{ + description = "PostgreSQL development environment"; + + inputs = { + nixpkgs.url = "github:NixOS/nixpkgs/nixos-25.05"; + nixpkgs-unstable.url = "github:nixos/nixpkgs/nixpkgs-unstable"; + flake-utils.url = "github:numtide/flake-utils"; + }; + + outputs = { + self, + nixpkgs, + nixpkgs-unstable, + flake-utils, + }: + flake-utils.lib.eachDefaultSystem ( + system: let + pkgs = import nixpkgs { + inherit system; + config.allowUnfree = true; + }; + pkgs-unstable = import nixpkgs-unstable { + inherit system; + config.allowUnfree = true; + }; + + shellConfig = import ./shell.nix {inherit pkgs pkgs-unstable system;}; + in { + formatter = pkgs.alejandra; + devShells = { + default = shellConfig.devShell; + gcc = shellConfig.devShell; + clang = shellConfig.clangDevShell; + gcc-musl = shellConfig.muslDevShell; + clang-musl = shellConfig.clangMuslDevShell; + }; + + packages = { + inherit (shellConfig) gdbConfig flameGraphScript pgbenchScript; + }; + + environment.localBinInPath = true; + } + ); +} diff --git a/glibc-no-fortify-warning.patch b/glibc-no-fortify-warning.patch new file mode 100644 index 0000000000000..4657a12adbcc5 --- /dev/null +++ b/glibc-no-fortify-warning.patch @@ -0,0 +1,24 @@ +From 130c231020f97e5eb878cc9fdb2bd9b186a5aa04 Mon Sep 17 00:00:00 2001 +From: Greg Burd +Date: Fri, 24 Oct 2025 11:58:24 -0400 +Subject: [PATCH] no warnings with -O0 and fortify source please + +--- + include/features.h | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/include/features.h b/include/features.h +index 673c4036..a02c8a3f 100644 +--- a/include/features.h ++++ b/include/features.h +@@ -432,7 +432,6 @@ + + #if defined _FORTIFY_SOURCE && _FORTIFY_SOURCE > 0 + # if !defined __OPTIMIZE__ || __OPTIMIZE__ <= 0 +-# warning _FORTIFY_SOURCE requires compiling with optimization (-O) + # elif !__GNUC_PREREQ (4, 1) + # warning _FORTIFY_SOURCE requires GCC 4.1 or later + # elif _FORTIFY_SOURCE > 2 && (__glibc_clang_prereq (9, 0) \ +-- +2.50.1 + diff --git a/pg-aliases.sh b/pg-aliases.sh new file mode 100644 index 0000000000000..0c13adc8f903a --- /dev/null +++ b/pg-aliases.sh @@ -0,0 +1,658 @@ +# PostgreSQL Development Aliases + +# ============================================================ +# Build helpers shared by every variant. +# ============================================================ +pg_clean_for_compiler() { + local current_compiler="$(basename $CC)" + local build_dir="${1:-$PG_BUILD_DIR}" + + if [ -f "$build_dir/compile_commands.json" ]; then + local last_compiler=$(grep -o '/[^/]*/bin/[gc]cc\|/[^/]*/bin/clang' "$build_dir/compile_commands.json" | head -1 | xargs basename 2>/dev/null || echo "unknown") + + if [ "$last_compiler" != "$current_compiler" ] && [ "$last_compiler" != "unknown" ]; then + echo "Detected compiler change from $last_compiler to $current_compiler" + echo "Cleaning build directory..." + trash "$build_dir" 2>/dev/null || rm -rf "$build_dir" + mkdir -p "$build_dir" + fi + fi + + mkdir -p "$build_dir" + echo "$current_compiler" >"$build_dir/.compiler_used" +} + +# ============================================================ +# Core PostgreSQL commands (default/debug build) +# ============================================================ +alias pg-setup=' + if [ -z "$PERL_CORE_DIR" ]; then + echo "Error: Could not find perl CORE directory" >&2 + return 1 + fi + + pg_clean_for_compiler "$PG_BUILD_DIR" + + echo "=== PostgreSQL Build Configuration ===" + echo "Compiler: $CC" + echo "LLVM: $(llvm-config --version 2>/dev/null || echo disabled)" + echo "Source: $PG_SOURCE_DIR" + echo "Build: $PG_BUILD_DIR" + echo "Install: $PG_INSTALL_DIR" + echo "======================================" + + env CFLAGS="-I$PERL_CORE_DIR $CFLAGS" \ + LDFLAGS="-L$PERL_CORE_DIR -lperl $LDFLAGS" \ + meson setup $MESON_EXTRA_SETUP \ + --reconfigure \ + -Doptimization=g \ + -Ddebug=true \ + -Db_sanitize=none \ + -Db_lundef=false \ + -Dlz4=enabled \ + -Dzstd=enabled \ + -Dllvm=disabled \ + -Dplperl=enabled \ + -Dplpython=enabled \ + -Dpltcl=enabled \ + -Dlibxml=enabled \ + -Duuid=e2fs \ + -Dlibxslt=enabled \ + -Dssl=openssl \ + -Dldap=disabled \ + -Dcassert=true \ + -Dtap_tests=enabled \ + -Dinjection_points=true \ + -Ddocs_pdf=enabled \ + -Ddocs_html_style=website \ + --prefix="$PG_INSTALL_DIR" \ + "$PG_BUILD_DIR" \ + "$PG_SOURCE_DIR"' + +alias pg-compdb='compdb -p build/ list > compile_commands.json' +alias pg-build='meson compile -C "$PG_BUILD_DIR"' +alias pg-install='meson install -C "$PG_BUILD_DIR"' +alias pg-test='meson test -q --print-errorlogs -C "$PG_BUILD_DIR"' + +# Clean commands +alias pg-clean='ninja -C "$PG_BUILD_DIR" clean' +alias pg-full-clean='trash "$PG_BUILD_DIR" "$PG_INSTALL_DIR" 2>/dev/null || rm -rf "$PG_BUILD_DIR" "$PG_INSTALL_DIR"; echo "Build and install directories cleaned"' + +# Database management +alias pg-init='trash "$PG_DATA_DIR" 2>/dev/null || rm -rf "$PG_DATA_DIR"; "$PG_INSTALL_DIR/bin/initdb" --debug --no-clean "$PG_DATA_DIR"' + +alias pg-start='ulimit -c unlimited && "$PG_INSTALL_DIR/bin/postgres" -D "$PG_DATA_DIR" -k "$PG_DATA_DIR"' + +alias pg-stop='pkill -f "postgres.*-D.*$PG_DATA_DIR" || true' +alias pg-restart='pg-stop && sleep 2 && pg-start' +alias pg-status='pgrep -f "postgres.*-D.*$PG_DATA_DIR" && echo "PostgreSQL is running" || echo "PostgreSQL is not running"' + +# Client connections +alias pg-psql='"$PG_INSTALL_DIR/bin/psql" -h "$PG_DATA_DIR" postgres' +alias pg-createdb='"$PG_INSTALL_DIR/bin/createdb" -h "$PG_DATA_DIR"' +alias pg-dropdb='"$PG_INSTALL_DIR/bin/dropdb" -h "$PG_DATA_DIR"' + +# ============================================================ +# Debugger attachments +# ============================================================ +alias pg-debug-gdb='gdb -x "$GDBINIT" -x .gdbinit "$PG_INSTALL_DIR/bin/postgres"' +alias pg-debug-lldb='lldb "$PG_INSTALL_DIR/bin/postgres"' +alias pg-debug=' + if command -v gdb >/dev/null 2>&1; then + pg-debug-gdb + elif command -v lldb >/dev/null 2>&1; then + pg-debug-lldb + else + echo "No debugger available (gdb or lldb required)" + fi' + +alias pg-attach-gdb=' + PG_PID=$(pgrep -f "postgres.*-D.*$PG_DATA_DIR" | head -1) + if [ -n "$PG_PID" ]; then + echo "Attaching GDB to PostgreSQL process $PG_PID" + gdb -x "$GDBINIT" -x .gdbinit -p "$PG_PID" + else + echo "No PostgreSQL process found" + fi' + +alias pg-attach-lldb=' + PG_PID=$(pgrep -f "postgres.*-D.*$PG_DATA_DIR" | head -1) + if [ -n "$PG_PID" ]; then + echo "Attaching LLDB to PostgreSQL process $PG_PID" + lldb -p "$PG_PID" + else + echo "No PostgreSQL process found" + fi' + +alias pg-attach=' + if command -v gdb >/dev/null 2>&1; then + pg-attach-gdb + elif command -v lldb >/dev/null 2>&1; then + pg-attach-lldb + else + echo "No debugger available (gdb or lldb required)" + fi' + +# ============================================================ +# Valgrind-instrumented build and tests +# +# The valgrind build lives in a separate directory so the normal +# build stays warm. Runs use a wrapper dir that shadows `postgres` +# with a valgrind wrapper -- pg_regress finds it via PATH. +# ============================================================ +pg-build-valgrind() { + local bdir="$PG_BUILD_DIR_VALGRIND" + if [ -z "$PERL_CORE_DIR" ]; then + echo "Error: PERL_CORE_DIR is not set" >&2 + return 1 + fi + + pg_clean_for_compiler "$bdir" + + echo "=== Configuring Valgrind build in $bdir ===" + env CFLAGS="-Og -ggdb3 -fno-omit-frame-pointer -DUSE_VALGRIND -I$PERL_CORE_DIR $CFLAGS" \ + LDFLAGS="-L$PERL_CORE_DIR -lperl $LDFLAGS" \ + meson setup --reconfigure \ + -Doptimization=g \ + -Ddebug=true \ + -Dcassert=true \ + -Dtap_tests=enabled \ + -Dinjection_points=true \ + -Dllvm=disabled \ + -Dplperl=enabled -Dplpython=enabled -Dpltcl=enabled \ + -Dlz4=enabled -Dzstd=enabled \ + -Dlibxml=enabled -Dlibxslt=enabled -Dssl=openssl -Duuid=e2fs \ + -Dldap=disabled \ + --prefix="$PG_INSTALL_DIR-valgrind" \ + "$bdir" "$PG_SOURCE_DIR" || return 1 + + meson compile -C "$bdir" +} + +# Drop a wrapper directory that shadows the real binaries; `postgres` +# exec's into valgrind, everything else is a symlink. Writes to the +# supplied wrap dir and echoes its path. +_pg_make_valgrind_wrapper() { + local bindir="$1" + local wrapdir="$2" + + mkdir -p "$wrapdir" + cat >"$wrapdir/postgres" <&2 + return 1 + fi + + local tmpbin="$bdir/tmp_install$PG_INSTALL_DIR-valgrind/bin" + if [ ! -x "$tmpbin/postgres" ]; then + echo "Populating tmp_install..." + meson test -C "$bdir" tmp_install install_test_files initdb_cache >/dev/null || return 1 + fi + + local wrap + wrap=$(mktemp -d /tmp/pg-vg-wrap-XXXXXX) + _pg_make_valgrind_wrapper "$tmpbin" "$wrap" + + mkdir -p "$PG_BENCH_DIR" + echo "Valgrind logs: $PG_BENCH_DIR/valgrind-*.log" + echo "Wrapper dir: $wrap (will be removed on exit)" + echo "Expect the regress suite to take 15-45 minutes under valgrind." + + local rc=0 + (cd "$bdir" && PATH="$wrap:$PATH" meson test -t 60 --print-errorlogs regress/regress) || rc=$? + + trash "$wrap" 2>/dev/null || rm -rf "$wrap" + return "$rc" +} + +pg-valgrind-test() { + local bdir="$PG_BUILD_DIR_VALGRIND" + if [ ! -x "$bdir/src/backend/postgres" ]; then + echo "Valgrind build not found; run 'pg-build-valgrind' first." >&2 + return 1 + fi + + echo "This runs the FULL postgres test suite under valgrind." + echo "Expect many hours, and tens of GB of valgrind log output." + echo "Logs: $PG_BENCH_DIR/valgrind-*.log" + local yn + read -r -p "Continue? [y/N] " yn + case "$yn" in + y | Y | yes) ;; + *) echo "Aborted."; return 0 ;; + esac + + local tmpbin="$bdir/tmp_install$PG_INSTALL_DIR-valgrind/bin" + if [ ! -x "$tmpbin/postgres" ]; then + echo "Populating tmp_install..." + meson test -C "$bdir" tmp_install install_test_files initdb_cache >/dev/null || return 1 + fi + + local wrap + wrap=$(mktemp -d /tmp/pg-vg-wrap-XXXXXX) + _pg_make_valgrind_wrapper "$tmpbin" "$wrap" + mkdir -p "$PG_BENCH_DIR" + + local rc=0 + (cd "$bdir" && PATH="$wrap:$PATH" meson test -t 60 --print-errorlogs) || rc=$? + + trash "$wrap" 2>/dev/null || rm -rf "$wrap" + return "$rc" +} + +# ============================================================ +# AddressSanitizer / UndefinedBehaviorSanitizer build and tests +# ============================================================ +pg-build-asan() { + local bdir="$PG_BUILD_DIR_ASAN" + if [ -z "$PERL_CORE_DIR" ]; then + echo "Error: PERL_CORE_DIR is not set" >&2 + return 1 + fi + + pg_clean_for_compiler "$bdir" + + echo "=== Configuring ASan+UBSan build in $bdir ===" + env CFLAGS="-Og -ggdb3 -fno-omit-frame-pointer -fsanitize=address,undefined -fno-sanitize-recover=all -I$PERL_CORE_DIR $CFLAGS" \ + LDFLAGS="-fsanitize=address,undefined -L$PERL_CORE_DIR -lperl $LDFLAGS" \ + meson setup --reconfigure \ + -Doptimization=g \ + -Ddebug=true \ + -Dcassert=true \ + -Dtap_tests=enabled \ + -Dinjection_points=true \ + -Dllvm=disabled \ + -Dplperl=enabled -Dplpython=enabled -Dpltcl=enabled \ + -Dlz4=enabled -Dzstd=enabled \ + -Dlibxml=enabled -Dlibxslt=enabled -Dssl=openssl -Duuid=e2fs \ + -Dldap=disabled \ + --prefix="$PG_INSTALL_DIR-asan" \ + "$bdir" "$PG_SOURCE_DIR" || return 1 + + meson compile -C "$bdir" +} + +pg-asan-regress() { + local bdir="$PG_BUILD_DIR_ASAN" + if [ ! -x "$bdir/src/backend/postgres" ]; then + echo "ASan build not found; run 'pg-build-asan' first." >&2 + return 1 + fi + + # halt_on_error=0 lets regress continue past the first diagnostic so + # the whole suite runs; abort_on_error=1 makes each hit fail the test. + ASAN_OPTIONS="halt_on_error=0:abort_on_error=1:detect_leaks=0:print_summary=1:print_stacktrace=1" \ + UBSAN_OPTIONS="halt_on_error=1:abort_on_error=1:print_stacktrace=1:print_summary=1" \ + meson test -t 5 --print-errorlogs -C "$bdir" regress/regress +} + +# ============================================================ +# rr (deterministic record-and-replay) +# Requires kernel.perf_event_paranoid <= 1. rr is the single most +# effective tool for postgres bugs that reproduce intermittently. +# ============================================================ +pg-rr-check() { + if ! command -v rr >/dev/null; then + echo "rr is not installed (expected in the dev shell)." >&2 + return 1 + fi + local paranoid + paranoid=$(cat /proc/sys/kernel/perf_event_paranoid 2>/dev/null || echo 99) + if [ "$paranoid" -gt 1 ]; then + echo "rr requires kernel.perf_event_paranoid <= 1; currently $paranoid" + echo "To enable (root needed):" + echo " echo 1 | sudo tee /proc/sys/kernel/perf_event_paranoid" + return 1 + fi + echo "rr ready (perf_event_paranoid=$paranoid)" +} + +pg-rr-record() { + pg-rr-check >/dev/null || { + pg-rr-check + return 1 + } + ulimit -c unlimited + rr record -- "$PG_INSTALL_DIR/bin/postgres" -D "$PG_DATA_DIR" -k "$PG_DATA_DIR" +} + +pg-rr-replay() { + rr replay "$@" +} + +# ============================================================ +# perf wrappers (parallel to the flame-graph helper) +# ============================================================ +pg-perf-record() { + local pid + pid=$(pgrep -f "postgres.*-D.*$PG_DATA_DIR" | head -1) + if [ -z "$pid" ]; then + echo "No postgres running under $PG_DATA_DIR" >&2 + return 1 + fi + mkdir -p "$PG_BENCH_DIR" + local out="$PG_BENCH_DIR/perf-$(date +%Y%m%d_%H%M%S).data" + echo "Recording to $out (Ctrl-C to stop)" + perf record -F 997 --call-graph dwarf -p "$pid" -o "$out" "$@" + echo "Saved: $out" +} + +pg-perf-report() { + local data + data=$(ls -t "$PG_BENCH_DIR"/perf-*.data 2>/dev/null | head -1) + if [ -z "$data" ]; then + echo "No perf data in $PG_BENCH_DIR" >&2 + return 1 + fi + echo "Reading $data" + perf report -i "$data" "$@" +} + +pg-perf-annotate() { + local data + data=$(ls -t "$PG_BENCH_DIR"/perf-*.data 2>/dev/null | head -1) + if [ -z "$data" ]; then + echo "No perf data in $PG_BENCH_DIR" >&2 + return 1 + fi + perf annotate -i "$data" "$@" +} + +# ============================================================ +# Single regression test / group runner. +# Runs pg_regress directly against the existing build so you skip the +# full meson-driven suite wrapper. Usage: pg-test-one boolean [name ...] +# ============================================================ +pg-test-one() { + if [ $# -eq 0 ]; then + echo "usage: pg-test-one TESTNAME [TESTNAME ...]" + echo "example: pg-test-one boolean" + return 2 + fi + local bdir="${PG_BUILD_DIR_ONE:-$PG_BUILD_DIR}" + local tmpbin="$bdir/tmp_install$PG_INSTALL_DIR/bin" + if [ ! -x "$tmpbin/postgres" ]; then + echo "Populating tmp_install..." + meson test -C "$bdir" tmp_install install_test_files initdb_cache >/dev/null || return 1 + fi + local outdir + outdir=$(mktemp -d /tmp/pg-test-one-XXXXXX) + echo "Test output: $outdir" + "$bdir/src/test/regress/pg_regress" \ + --bindir="$tmpbin" \ + --inputdir="$PG_SOURCE_DIR/src/test/regress" \ + --expecteddir="$PG_SOURCE_DIR/src/test/regress" \ + --dlpath="$bdir/src/test/regress" \ + --outputdir="$outdir" \ + --temp-instance="$outdir/tmp" \ + --port=40099 \ + "$@" +} + +# Full flame graph / benchmark aliases +alias pg-flame='pg-flame-generate' +alias pg-flame-30='pg-flame-generate 30' +alias pg-flame-60='pg-flame-generate 60' +alias pg-flame-120='pg-flame-generate 120' + +pg-flame-custom() { + local duration=${1:-30} + local output_dir=${2:-$PG_FLAME_DIR} + echo "Generating flame graph for ${duration}s, output to: $output_dir" + pg-flame-generate "$duration" "$output_dir" +} + +alias pg-bench='pg-bench-run' +alias pg-bench-quick='pg-bench-run 5 1 100 1 30 select-only' +alias pg-bench-standard='pg-bench-run 10 2 1000 10 60 tpcb-like' +alias pg-bench-heavy='pg-bench-run 50 4 5000 100 300 tpcb-like' +alias pg-bench-readonly='pg-bench-run 20 4 2000 50 120 select-only' + +pg-bench-custom() { + local clients=${1:-10} + local threads=${2:-2} + local transactions=${3:-1000} + local scale=${4:-10} + local duration=${5:-60} + local test_type=${6:-tpcb-like} + + echo "Running custom benchmark:" + echo " Clients: $clients, Threads: $threads" + echo " Transactions: $transactions, Scale: $scale" + echo " Duration: ${duration}s, Type: $test_type" + + pg-bench-run "$clients" "$threads" "$transactions" "$scale" "$duration" "$test_type" +} + +pg-bench-flame() { + local duration=${1:-60} + local clients=${2:-10} + local scale=${3:-10} + + echo "Running benchmark with flame graph generation" + echo "Duration: ${duration}s, Clients: $clients, Scale: $scale" + + pg-bench-run "$clients" 2 1000 "$scale" "$duration" tpcb-like & + local bench_pid=$! + + sleep 5 + + local flame_duration=$((duration - 10)) + if [ $flame_duration -gt 10 ]; then + pg-flame-generate "$flame_duration" & + local flame_pid=$! + fi + + wait $bench_pid + if [ -n "${flame_pid:-}" ]; then + wait $flame_pid + fi + + echo "Benchmark and flame graph generation completed" +} + +# Live monitoring +alias pg-perf='perf top -p $(pgrep -f "postgres.*-D.*$PG_DATA_DIR" | head -1)' +alias pg-htop='htop -p $(pgrep -f "postgres.*-D.*$PG_DATA_DIR" | tr "\n" "," | sed "s/,$//")' + +pg-stats() { + local duration=${1:-30} + echo "Collecting system stats for ${duration}s..." + + iostat -x 1 "$duration" >"$PG_BENCH_DIR/iostat_$(date +%Y%m%d_%H%M%S).log" & + vmstat 1 "$duration" >"$PG_BENCH_DIR/vmstat_$(date +%Y%m%d_%H%M%S).log" & + + wait + echo "System stats saved to $PG_BENCH_DIR" +} + +# ============================================================ +# Code quality helpers +# ============================================================ +pg-format() { + local since=${1:-HEAD} + + if [ ! -f "$PG_SOURCE_DIR/src/tools/pgindent/pgindent" ]; then + echo "Error: pgindent not found at $PG_SOURCE_DIR/src/tools/pgindent/pgindent" + else + + modified_files=$(git diff --name-only "${since}" | grep -E "\.c$|\.h$") + + if [ -z "$modified_files" ]; then + echo "No modified .c or .h files found" + else + + echo "Formatting modified files with pgindent:" + for file in $modified_files; do + if [ -f "$file" ]; then + echo " Formatting: $file" + "$PG_SOURCE_DIR/src/tools/pgindent/pgindent" "$file" + else + echo " Warning: File not found: $file" + fi + done + + echo "Checking files for whitespace:" + git diff --check "${since}" + fi + fi +} + +pg-tidy() { + local since=${1:-HEAD} + local files + files=$(git diff --name-only "$since" | grep -E "\.(c|h)$") + if [ -z "$files" ]; then + echo "No modified .c or .h files." + return 0 + fi + for f in $files; do + [ -f "$f" ] || continue + echo "clang-tidy: $f" + clang-tidy -p "$PG_BUILD_DIR" "$f" 2>&1 | head -50 + done +} + +pg-spell() { + local since=${1:-HEAD} + local files=$(git diff --name-only "$since" | grep -E '\.(c|h|sgml|md)$') + if [ -z "$files" ]; then + echo "No .c/.h/.sgml/.md files changed since $since" + return 0 + fi + for f in $files; do + [ -f "$f" ] || continue + case "$f" in + *.c | *.h) + grep -nE '^\s*(/\*|\*|//)' "$f" | codespell --stdin-single-line - 2>/dev/null \ + && echo " $f: ok" || true + ;; + *.sgml | *.md) + codespell "$f" || true + ;; + esac + done +} + +# ============================================================ +# Core dump one-shots (one-time, requires root). kernel.core_pattern +# is a system-wide sysctl -- we don't touch it on every shell entry. +# ============================================================ +pg-cores-status() { + echo "ulimit -c: $(ulimit -c)" + echo "kernel.core_pattern: $(cat /proc/sys/kernel/core_pattern 2>/dev/null || echo unreadable)" + echo "cwd: $(pwd)" +} + +pg-enable-cores() { + ulimit -c unlimited + if ! [ -w /proc/sys/kernel/core_pattern ]; then + echo "Setting kernel.core_pattern (requires sudo)..." + echo "core.%p" | sudo tee /proc/sys/kernel/core_pattern >/dev/null || { + echo "Failed to write /proc/sys/kernel/core_pattern" >&2 + return 1 + } + else + echo "core.%p" >/proc/sys/kernel/core_pattern + fi + pg-cores-status +} + +pg-disable-cores() { + ulimit -c 0 + if ! [ -w /proc/sys/kernel/core_pattern ]; then + echo "Restoring kernel.core_pattern to 'core' (requires sudo)..." + echo "core" | sudo tee /proc/sys/kernel/core_pattern >/dev/null || { + echo "Failed to restore /proc/sys/kernel/core_pattern" >&2 + return 1 + } + else + echo "core" >/proc/sys/kernel/core_pattern + fi + pg-cores-status +} + +# ============================================================ +# Logs and results +# ============================================================ +alias pg-log='tail -f "$PG_DATA_DIR/log/postgresql-$(date +%Y-%m-%d).log" 2>/dev/null || echo "No log file found"' +alias pg-log-errors='grep -i error "$PG_DATA_DIR/log/"*.log 2>/dev/null || echo "No error logs found"' + +alias pg-build-log='cat "$PG_BUILD_DIR/meson-logs/meson-log.txt"' +alias pg-build-errors='grep -i error "$PG_BUILD_DIR/meson-logs/meson-log.txt" 2>/dev/null || echo "No build errors found"' + +alias pg-bench-results='ls -la "$PG_BENCH_DIR" && echo "Latest results:" && tail -20 "$PG_BENCH_DIR"/results_*.txt 2>/dev/null | tail -20' +alias pg-flame-results='ls -la "$PG_FLAME_DIR" && echo "Open flame graphs with: firefox $PG_FLAME_DIR/*.svg"' + +pg-clean-results() { + local days=${1:-7} + echo "Cleaning benchmark and flame graph results older than $days days..." + find "$PG_BENCH_DIR" -type f -mtime +$days -delete 2>/dev/null || true + find "$PG_FLAME_DIR" -type f -mtime +$days -delete 2>/dev/null || true + echo "Cleanup completed" +} + +# ============================================================ +# Info +# ============================================================ +alias pg-info=' + echo "=== PostgreSQL Development Environment ===" + echo "Source: $PG_SOURCE_DIR" + echo "Build (default): $PG_BUILD_DIR" + echo "Build (valgrind):$PG_BUILD_DIR_VALGRIND" + echo "Build (asan): $PG_BUILD_DIR_ASAN" + echo "Install: $PG_INSTALL_DIR" + echo "Data: $PG_DATA_DIR" + echo "Benchmarks: $PG_BENCH_DIR" + echo "Flame graphs: $PG_FLAME_DIR" + echo "Compiler: $CC" + echo "" + echo "Available commands:" + echo " Setup/build: pg-setup, pg-build, pg-install" + echo " Database: pg-init, pg-start, pg-stop, pg-psql" + echo " Tests: pg-test, pg-test-one NAME" + echo " Valgrind: pg-build-valgrind, pg-valgrind-regress, pg-valgrind-test" + echo " ASan/UBSan: pg-build-asan, pg-asan-regress" + echo " Debug: pg-debug, pg-attach" + echo " Record/replay: pg-rr-check, pg-rr-record, pg-rr-replay" + echo " Perf: pg-perf-record, pg-perf-report, pg-perf-annotate, pg-perf" + echo " Flame graphs: pg-flame, pg-flame-30, pg-flame-60, pg-flame-custom" + echo " Benchmarks: pg-bench-quick, pg-bench-standard, pg-bench-heavy" + echo " Combined: pg-bench-flame" + echo " Results: pg-bench-results, pg-flame-results" + echo " Logs: pg-log, pg-build-log" + echo " Clean: pg-clean, pg-full-clean, pg-clean-results" + echo " Code quality: pg-format, pg-tidy, pg-spell" + echo " Cores: pg-enable-cores, pg-disable-cores, pg-cores-status" + echo "=========================================="' + +echo "PostgreSQL aliases loaded. Run 'pg-info' for available commands." diff --git a/shell.nix b/shell.nix new file mode 100644 index 0000000000000..8c738afa789a7 --- /dev/null +++ b/shell.nix @@ -0,0 +1,745 @@ +{ + pkgs, + pkgs-unstable, + system, +}: let + # Create a patched glibc only for the dev shell. + # + # Glibc's features.h emits a `-Wcpp` diagnostic when _FORTIFY_SOURCE is + # defined without an optimization level. Meson's dependency probes + # (notably the libcurl thread-safety check) compile small snippets with + # `-O0 -Werror`, which turns that cpp warning into a hard error and + # breaks reconfigure under our default CFLAGS. The patch simply drops + # the warning. It is scoped to this dev shell only and never leaks + # into system glibc or release builds. + patchedGlibc = pkgs.glibc.overrideAttrs (oldAttrs: { + patches = (oldAttrs.patches or []) ++ [ + ./glibc-no-fortify-warning.patch + ]; + }); + + # Use LLVM for modern PostgreSQL development + llvmPkgs = pkgs-unstable.llvmPackages_21; + + # Configuration constants + config = { + pgSourceDir = "$PWD"; + pgBuildDir = "$PWD/build"; + pgBuildDirValgrind = "$PWD/build-valgrind"; + pgBuildDirAsan = "$PWD/build-asan"; + pgInstallDir = "$PWD/install"; + pgDataDir = "/tmp/test-db-$(basename $PWD)"; + pgBenchDir = "/tmp/pgbench-results-$(basename $PWD)"; + pgFlameDir = "/tmp/flame-graphs-$(basename $PWD)"; + }; + + # Single dependency function that can be used for all environments + getPostgreSQLDeps = muslLibs: + with pkgs; + [ + # Build system (always use host tools) + pkgs-unstable.meson + pkgs-unstable.ninja + pkg-config + autoconf + git + which + binutils + gnumake + mold # fast linker, big wins on large postgres links + + # Parser/lexer tools + bison + flex + + # Perl with required packages + (perl.withPackages (ps: with ps; [IPCRun])) + + # Documentation + docbook_xml_dtd_45 + docbook-xsl-nons + libxslt + libxml2 + fop + + # Development tools (always use host tools) + coreutils + shellcheck + ripgrep + valgrind + curl + uv + pylint + black + lcov + strace + ltrace + perf-tools + linuxPackages.perf + flamegraph + bpftrace # kernel-level tracing (probes, uprobes) + rr # record-and-replay deterministic debugger + htop + iotop + sysstat + ccache + cppcheck + compdb + + # Spell checking + aspell + aspellDicts.en + codespell + + # GCC/GDB + gcc + gdb + + # LLVM toolchain + llvmPkgs.llvm + llvmPkgs.llvm.dev + llvmPkgs.clang-tools + llvmPkgs.lldb + + # Language support + (python3.withPackages (ps: with ps; [requests browser-cookie3])) + tcl + ] + ++ ( + if muslLibs + then [ + # Musl target libraries for cross-compilation + pkgs.pkgsMusl.readline + pkgs.pkgsMusl.zlib + pkgs.pkgsMusl.openssl + pkgs.pkgsMusl.icu + pkgs.pkgsMusl.lz4 + pkgs.pkgsMusl.zstd + pkgs.pkgsMusl.libuuid + pkgs.pkgsMusl.libkrb5 + pkgs.pkgsMusl.linux-pam + pkgs.pkgsMusl.libxcrypt + ] + else [ + # Glibc target libraries + readline + zlib + openssl + icu + lz4 + zstd + libuuid + libkrb5 + linux-pam + libxcrypt + numactl + openldap + liburing + libselinux + patchedGlibc + patchedGlibc.dev + ] + ); + + # GDB configuration for PostgreSQL debugging + gdbConfig = pkgs.writeText "gdbinit-postgres" '' + # PostgreSQL-specific GDB configuration + + # Pretty-print PostgreSQL data structures + define print_node + if $arg0 + printf "Node type: %s\n", nodeTagNames[$arg0->type] + print *$arg0 + else + printf "NULL node\n" + end + end + document print_node + Print a PostgreSQL Node with type information + Usage: print_node + end + + define print_list + set $list = (List*)$arg0 + if $list + printf "List length: %d\n", $list->length + set $cell = $list->head + set $i = 0 + while $cell && $i < $list->length + printf " [%d]: ", $i + print_node $cell->data.ptr_value + set $cell = $cell->next + set $i = $i + 1 + end + else + printf "NULL list\n" + end + end + document print_list + Print a PostgreSQL List structure + Usage: print_list + end + + define print_query + set $query = (Query*)$arg0 + if $query + printf "Query type: %d, command type: %d\n", $query->querySource, $query->commandType + print *$query + else + printf "NULL query\n" + end + end + document print_query + Print a PostgreSQL Query structure + Usage: print_query + end + + define print_relcache + set $rel = (Relation)$arg0 + if $rel + printf "Relation: %s.%s (OID: %u)\n", $rel->rd_rel->relnamespace, $rel->rd_rel->relname.data, $rel->rd_id + printf " natts: %d, relkind: %c\n", $rel->rd_rel->relnatts, $rel->rd_rel->relkind + else + printf "NULL relation\n" + end + end + document print_relcache + Print relation cache entry information + Usage: print_relcache + end + + define print_tupdesc + set $desc = (TupleDesc)$arg0 + if $desc + printf "TupleDesc: %d attributes\n", $desc->natts + set $i = 0 + while $i < $desc->natts + set $attr = $desc->attrs[$i] + printf " [%d]: %s (type: %u, len: %d)\n", $i, $attr->attname.data, $attr->atttypid, $attr->attlen + set $i = $i + 1 + end + else + printf "NULL tuple descriptor\n" + end + end + document print_tupdesc + Print tuple descriptor information + Usage: print_tupdesc + end + + define print_slot + set $slot = (TupleTableSlot*)$arg0 + if $slot + printf "TupleTableSlot: %s\n", $slot->tts_ops->name + printf " empty: %d, shouldFree: %d\n", $slot->tts_empty, $slot->tts_shouldFree + if $slot->tts_tupleDescriptor + print_tupdesc $slot->tts_tupleDescriptor + end + else + printf "NULL slot\n" + end + end + document print_slot + Print tuple table slot information + Usage: print_slot + end + + # Memory context debugging + define print_mcxt + set $context = (MemoryContext)$arg0 + if $context + printf "MemoryContext: %s\n", $context->name + printf " type: %s, parent: %p\n", $context->methods->name, $context->parent + printf " total: %zu, free: %zu\n", $context->mem_allocated, $context->freep - $context->freeptr + else + printf "NULL memory context\n" + end + end + document print_mcxt + Print memory context information + Usage: print_mcxt + end + + # Process debugging + define print_proc + set $proc = (PGPROC*)$arg0 + if $proc + printf "PGPROC: pid=%d, database=%u\n", $proc->pid, $proc->databaseId + printf " waiting: %d, waitStatus: %d\n", $proc->waiting, $proc->waitStatus + else + printf "NULL process\n" + end + end + document print_proc + Print process information + Usage: print_proc + end + + # Set useful defaults + set print pretty on + set print object on + set print static-members off + set print vtbl on + set print demangle on + set demangle-style gnu-v3 + set print sevenbit-strings off + set history save on + set history size 1000 + set history filename ~/.gdb_history_postgres + + # Common breakpoints for PostgreSQL debugging + define pg_break_common + break elog + break errfinish + break ExceptionalCondition + break ProcessInterrupts + end + document pg_break_common + Set common PostgreSQL debugging breakpoints + end + + printf "PostgreSQL GDB configuration loaded.\n" + printf "Available commands: print_node, print_list, print_query, print_relcache,\n" + printf " print_tupdesc, print_slot, print_mcxt, print_proc, pg_break_common\n" + ''; + + # Flame graph generation script + flameGraphScript = pkgs.writeScriptBin "pg-flame-generate" '' + #!${pkgs.bash}/bin/bash + set -euo pipefail + + DURATION=''${1:-30} + OUTPUT_DIR=''${2:-${config.pgFlameDir}} + TIMESTAMP=$(date +%Y%m%d_%H%M%S) + + mkdir -p "$OUTPUT_DIR" + + echo "Generating flame graph for PostgreSQL (duration: ''${DURATION}s)" + + # Find PostgreSQL processes + PG_PIDS=$(pgrep -f "postgres.*-D.*${config.pgDataDir}" || true) + + if [ -z "$PG_PIDS" ]; then + echo "Error: No PostgreSQL processes found" + exit 1 + fi + + echo "Found PostgreSQL processes: $PG_PIDS" + + # Record perf data + PERF_DATA="$OUTPUT_DIR/perf_$TIMESTAMP.data" + echo "Recording perf data to $PERF_DATA" + + ${pkgs.linuxPackages.perf}/bin/perf record \ + -F 997 \ + -g \ + --call-graph dwarf \ + -p "$(echo $PG_PIDS | tr ' ' ',')" \ + -o "$PERF_DATA" \ + sleep "$DURATION" + + # Generate flame graph + FLAME_SVG="$OUTPUT_DIR/postgres_flame_$TIMESTAMP.svg" + echo "Generating flame graph: $FLAME_SVG" + + ${pkgs.linuxPackages.perf}/bin/perf script -i "$PERF_DATA" | \ + ${pkgs.flamegraph}/bin/stackcollapse-perf.pl | \ + ${pkgs.flamegraph}/bin/flamegraph.pl \ + --title "PostgreSQL Flame Graph ($TIMESTAMP)" \ + --width 1200 \ + --height 800 \ + > "$FLAME_SVG" + + echo "Flame graph generated: $FLAME_SVG" + echo "Perf data saved: $PERF_DATA" + + # Generate summary report + REPORT="$OUTPUT_DIR/report_$TIMESTAMP.txt" + echo "Generating performance report: $REPORT" + + { + echo "PostgreSQL Performance Analysis Report" + echo "Generated: $(date)" + echo "Duration: ''${DURATION}s" + echo "Processes: $PG_PIDS" + echo "" + echo "=== Top Functions ===" + ${pkgs.linuxPackages.perf}/bin/perf report -i "$PERF_DATA" --stdio --sort comm,dso,symbol | head -50 + echo "" + echo "=== Call Graph ===" + ${pkgs.linuxPackages.perf}/bin/perf report -i "$PERF_DATA" --stdio -g --sort comm,dso,symbol | head -100 + } > "$REPORT" + + echo "Report generated: $REPORT" + echo "" + echo "Files created:" + echo " Flame graph: $FLAME_SVG" + echo " Perf data: $PERF_DATA" + echo " Report: $REPORT" + ''; + + # pgbench wrapper script + pgbenchScript = pkgs.writeScriptBin "pg-bench-run" '' + #!${pkgs.bash}/bin/bash + set -euo pipefail + + # Default parameters + CLIENTS=''${1:-10} + THREADS=''${2:-2} + TRANSACTIONS=''${3:-1000} + SCALE=''${4:-10} + DURATION=''${5:-60} + TEST_TYPE=''${6:-tpcb-like} + + OUTPUT_DIR="${config.pgBenchDir}" + TIMESTAMP=$(date +%Y%m%d_%H%M%S) + + mkdir -p "$OUTPUT_DIR" + + echo "=== PostgreSQL Benchmark Configuration ===" + echo "Clients: $CLIENTS" + echo "Threads: $THREADS" + echo "Transactions: $TRANSACTIONS" + echo "Scale factor: $SCALE" + echo "Duration: ''${DURATION}s" + echo "Test type: $TEST_TYPE" + echo "Output directory: $OUTPUT_DIR" + echo "============================================" + + # Check if PostgreSQL is running + if ! pgrep -f "postgres.*-D.*${config.pgDataDir}" >/dev/null; then + echo "Error: PostgreSQL is not running. Start it with 'pg-start'" + exit 1 + fi + + PGBENCH="${config.pgInstallDir}/bin/pgbench" + PSQL="${config.pgInstallDir}/bin/psql" + CREATEDB="${config.pgInstallDir}/bin/createdb" + DROPDB="${config.pgInstallDir}/bin/dropdb" + + DB_NAME="pgbench_test_$TIMESTAMP" + RESULTS_FILE="$OUTPUT_DIR/results_$TIMESTAMP.txt" + LOG_FILE="$OUTPUT_DIR/pgbench_$TIMESTAMP.log" + + echo "Creating test database: $DB_NAME" + "$CREATEDB" -h "${config.pgDataDir}" "$DB_NAME" || { + echo "Failed to create database" + exit 1 + } + + # Initialize pgbench tables + echo "Initializing pgbench tables (scale factor: $SCALE)" + "$PGBENCH" -h "${config.pgDataDir}" -i -s "$SCALE" "$DB_NAME" || { + echo "Failed to initialize pgbench tables" + "$DROPDB" -h "${config.pgDataDir}" "$DB_NAME" 2>/dev/null || true + exit 1 + } + + # Run benchmark based on test type + echo "Running benchmark..." + + case "$TEST_TYPE" in + "tpcb-like"|"default") + BENCH_ARGS="" + ;; + "select-only") + BENCH_ARGS="-S" + ;; + "simple-update") + BENCH_ARGS="-N" + ;; + "read-write") + BENCH_ARGS="-b select-only@70 -b tpcb-like@30" + ;; + *) + echo "Unknown test type: $TEST_TYPE" + echo "Available types: tpcb-like, select-only, simple-update, read-write" + "$DROPDB" -h "${config.pgDataDir}" "$DB_NAME" 2>/dev/null || true + exit 1 + ;; + esac + + { + echo "PostgreSQL Benchmark Results" + echo "Generated: $(date)" + echo "Test type: $TEST_TYPE" + echo "Clients: $CLIENTS, Threads: $THREADS" + echo "Transactions: $TRANSACTIONS, Duration: ''${DURATION}s" + echo "Scale factor: $SCALE" + echo "Database: $DB_NAME" + echo "" + echo "=== System Information ===" + echo "CPU: $(nproc) cores" + echo "Memory: $(free -h | grep '^Mem:' | awk '{print $2}')" + echo "Compiler: $CC" + echo "PostgreSQL version: $("$PSQL" --no-psqlrc -h "${config.pgDataDir}" -d "$DB_NAME" -t -c "SELECT version();" | head -1)" + echo "" + echo "=== Benchmark Results ===" + } > "$RESULTS_FILE" + + # Run the actual benchmark + "$PGBENCH" \ + -h "${config.pgDataDir}" \ + -c "$CLIENTS" \ + -j "$THREADS" \ + -T "$DURATION" \ + -P 5 \ + --log \ + --log-prefix="$OUTPUT_DIR/pgbench_$TIMESTAMP" \ + $BENCH_ARGS \ + "$DB_NAME" 2>&1 | tee -a "$RESULTS_FILE" + + # Collect additional statistics + { + echo "" + echo "=== Database Statistics ===" + "$PSQL" --no-psqlrc -h "${config.pgDataDir}" -d "$DB_NAME" -c " + SELECT + schemaname, + relname, + n_tup_ins as inserts, + n_tup_upd as updates, + n_tup_del as deletes, + n_live_tup as live_tuples, + n_dead_tup as dead_tuples + FROM pg_stat_user_tables; + " + + echo "" + echo "=== Index Statistics ===" + "$PSQL" --no-psqlrc -h "${config.pgDataDir}" -d "$DB_NAME" -c " + SELECT + schemaname, + relname, + indexrelname, + idx_scan, + idx_tup_read, + idx_tup_fetch + FROM pg_stat_user_indexes; + " + } >> "$RESULTS_FILE" + + # Clean up + echo "Cleaning up test database: $DB_NAME" + "$DROPDB" -h "${config.pgDataDir}" "$DB_NAME" 2>/dev/null || true + + echo "" + echo "Benchmark completed!" + echo "Results saved to: $RESULTS_FILE" + echo "Transaction logs: $OUTPUT_DIR/pgbench_$TIMESTAMP*" + + # Show summary + echo "" + echo "=== Quick Summary ===" + grep -E "(tps|latency)" "$RESULTS_FILE" | tail -5 + ''; + + # Shared shellHook fragments. Each devShell prepends its own compiler/CFLAGS + # block, then appends the common tail via ${commonHookTail variant}. + commonHookHead = icon: '' + # History configuration + export HISTFILE=.history + export HISTSIZE=1000000 + export HISTFILESIZE=1000000 + + # Clean environment + unset LD_LIBRARY_PATH LD_PRELOAD LIBRARY_PATH C_INCLUDE_PATH CPLUS_INCLUDE_PATH + + # Essential tools in PATH + export PATH="${pkgs.which}/bin:${pkgs.coreutils}/bin:$PATH" + export PS1="$(echo -e '\u${icon}') {\[$(tput sgr0)\]\[\033[38;5;228m\]\w\[$(tput sgr0)\]\[\033[38;5;15m\]} ($(git rev-parse --abbrev-ref HEAD)) \\$ \[$(tput sgr0)\]" + + # Ccache configuration + export PATH=${pkgs.ccache}/bin:$PATH + export CCACHE_COMPILERCHECK=content + # Loosen a few rules so ccache hits across rebuilds with touched headers. + export CCACHE_SLOPPINESS=pch_defines,time_macros,include_file_mtime,include_file_ctime + export CCACHE_DIR=$HOME/.ccache/pg/$(basename $PWD) + mkdir -p "$CCACHE_DIR" + + # Development tools in PATH + export PATH=${pkgs.clang-tools}/bin:$PATH + export PATH=${pkgs.cppcheck}/bin:$PATH + ''; + + # Tail shared by every devShell: PG env vars, GDB, tool PATH, per-process + # setup and alias load. Kernel core_pattern is NOT touched here -- + # run 'pg-enable-cores' explicitly if you need per-PID cores in CWD. + commonHookTail = label: '' + # PostgreSQL environment + export PG_SOURCE_DIR="${config.pgSourceDir}" + export PG_BUILD_DIR="${config.pgBuildDir}" + export PG_BUILD_DIR_VALGRIND="${config.pgBuildDirValgrind}" + export PG_BUILD_DIR_ASAN="${config.pgBuildDirAsan}" + export PG_INSTALL_DIR="${config.pgInstallDir}" + export PG_DATA_DIR="${config.pgDataDir}" + export PG_BENCH_DIR="${config.pgBenchDir}" + export PG_FLAME_DIR="${config.pgFlameDir}" + export PERL_CORE_DIR=$(find ${pkgs.perl} -maxdepth 5 -path "*/CORE" -type d) + + # GDB configuration + export GDBINIT="${gdbConfig}" + + # Performance tools in PATH + export PATH="${flameGraphScript}/bin:${pgbenchScript}/bin:$PATH" + + # Create output directories + mkdir -p "$PG_BENCH_DIR" "$PG_FLAME_DIR" + + # Per-process core dump size limit. Kernel core_pattern is NOT + # touched here -- run 'pg-enable-cores' explicitly when you need + # per-PID cores in CWD. + ulimit -c unlimited + + # Local git excludes + git config core.excludesFile .local-gitignore 2>/dev/null || true + + # Load PostgreSQL development aliases + if [ -f ./pg-aliases.sh ]; then + source ./pg-aliases.sh + else + echo "Warning: pg-aliases.sh not found in current directory" + fi + + echo "" + echo "PostgreSQL Development Environment Ready (${label})" + echo "Run 'pg-info' for available commands" + ''; + + # Development shell (GCC + glibc) + devShell = pkgs.mkShell { + name = "postgresql-dev"; + buildInputs = + (getPostgreSQLDeps false) + ++ [ + flameGraphScript + pgbenchScript + ]; + + shellHook = + (commonHookHead "f121") + + '' + # LLVM configuration + export LLVM_CONFIG="${llvmPkgs.llvm}/bin/llvm-config" + export PATH="${llvmPkgs.llvm}/bin:$PATH" + export PKG_CONFIG_PATH="${llvmPkgs.llvm.dev}/lib/pkgconfig:$PKG_CONFIG_PATH" + export LLVM_DIR="${llvmPkgs.llvm.dev}/lib/cmake/llvm" + export LLVM_ROOT="${llvmPkgs.llvm}" + + # PostgreSQL Development CFLAGS + export CFLAGS="" + export CXXFLAGS="" + + # Python UV + UV_PYTHON_DOWNLOADS=never + + # GCC configuration (default compiler) + export CC="${pkgs.gcc}/bin/gcc" + export CXX="${pkgs.gcc}/bin/g++" + + echo "Environment configured:" + echo " Compiler: $CC" + echo " libc: glibc" + echo " LLVM: $(llvm-config --version 2>/dev/null || echo 'not available')" + '' + + (commonHookTail "GCC + glibc"); + }; + + # Clang + glibc variant + clangDevShell = pkgs.mkShell { + name = "postgresql-clang-glibc"; + buildInputs = + (getPostgreSQLDeps false) + ++ [ + llvmPkgs.clang + llvmPkgs.lld + llvmPkgs.compiler-rt + flameGraphScript + pgbenchScript + ]; + + shellHook = + (commonHookHead "f121") + + '' + # LLVM configuration + export LLVM_CONFIG="${llvmPkgs.llvm}/bin/llvm-config" + export PATH="${llvmPkgs.llvm}/bin:$PATH" + export PKG_CONFIG_PATH="${llvmPkgs.llvm.dev}/lib/pkgconfig:$PKG_CONFIG_PATH" + export LLVM_DIR="${llvmPkgs.llvm.dev}/lib/cmake/llvm" + export LLVM_ROOT="${llvmPkgs.llvm}" + + # Clang + glibc configuration + export CC="${llvmPkgs.clang}/bin/clang" + export CXX="${llvmPkgs.clang}/bin/clang++" + + echo "Environment configured:" + echo " Compiler: $CC" + echo " libc: glibc" + echo " LLVM: $(llvm-config --version 2>/dev/null || echo 'not available')" + '' + + (commonHookTail "Clang + glibc"); + }; + + # GCC + musl variant (cross-compilation) + muslDevShell = pkgs.mkShell { + name = "postgresql-gcc-musl"; + buildInputs = + (getPostgreSQLDeps true) + ++ [ + pkgs.gcc + flameGraphScript + pgbenchScript + ]; + + shellHook = + (commonHookHead "f121") + + '' + # Cross-compilation to musl with GCC + export CC="${pkgs.gcc}/bin/gcc" + export CXX="${pkgs.gcc}/bin/g++" + + export PKG_CONFIG_PATH="${pkgs.pkgsMusl.openssl.dev}/lib/pkgconfig:${pkgs.pkgsMusl.zlib.dev}/lib/pkgconfig:${pkgs.pkgsMusl.icu.dev}/lib/pkgconfig" + export CFLAGS="-ggdb -Og -fno-omit-frame-pointer -D_FORTIFY_SOURCE=1 -I${pkgs.pkgsMusl.stdenv.cc.libc}/include" + export CXXFLAGS="-ggdb -Og -fno-omit-frame-pointer -D_FORTIFY_SOURCE=1 -I${pkgs.pkgsMusl.stdenv.cc.libc}/include" + export LDFLAGS="-L${pkgs.pkgsMusl.stdenv.cc.libc}/lib -static-libgcc" + + echo "Environment configured:" + echo " Compiler: $CC" + echo " libc: musl (cross-compilation)" + '' + + (commonHookTail "GCC + musl"); + }; + + # Clang + musl variant (cross-compilation) + clangMuslDevShell = pkgs.mkShell { + name = "postgresql-clang-musl"; + buildInputs = + (getPostgreSQLDeps true) + ++ [ + llvmPkgs.clang + llvmPkgs.lld + flameGraphScript + pgbenchScript + ]; + + shellHook = + (commonHookHead "f121") + + '' + # Cross-compilation to musl with clang + export CC="${llvmPkgs.clang}/bin/clang" + export CXX="${llvmPkgs.clang}/bin/clang++" + + export PKG_CONFIG_PATH="${pkgs.pkgsMusl.openssl.dev}/lib/pkgconfig:${pkgs.pkgsMusl.zlib.dev}/lib/pkgconfig:${pkgs.pkgsMusl.icu.dev}/lib/pkgconfig" + export CFLAGS="--target=x86_64-linux-musl -ggdb -Og -fno-omit-frame-pointer -D_FORTIFY_SOURCE=1 -I${pkgs.pkgsMusl.stdenv.cc.libc}/include" + export CXXFLAGS="--target=x86_64-linux-musl -ggdb -Og -fno-omit-frame-pointer -D_FORTIFY_SOURCE=1 -I${pkgs.pkgsMusl.stdenv.cc.libc}/include" + export LDFLAGS="--target=x86_64-linux-musl -L${pkgs.pkgsMusl.stdenv.cc.libc}/lib -fuse-ld=lld" + + echo "Environment configured:" + echo " Compiler: $CC" + echo " libc: musl (cross-compilation)" + '' + + (commonHookTail "Clang + musl"); + }; +in { + inherit devShell clangDevShell muslDevShell clangMuslDevShell gdbConfig flameGraphScript pgbenchScript; +} diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c index 3908529872a31..86892667cadf9 100644 --- a/src/backend/storage/buffer/bufmgr.c +++ b/src/backend/storage/buffer/bufmgr.c @@ -83,6 +83,7 @@ /* Bits in SyncOneBuffer's return value */ #define BUF_WRITTEN 0x01 #define BUF_REUSABLE 0x02 +#define BUF_COOLED 0x04 #define RELS_BSEARCH_THRESHOLD 20 @@ -634,7 +635,7 @@ static void PinBuffer_Locked(BufferDesc *buf); static void UnpinBuffer(BufferDesc *buf); static void UnpinBufferNoOwner(BufferDesc *buf); static void BufferSync(int flags); -static int SyncOneBuffer(int buf_id, bool skip_recently_used, +static int SyncOneBuffer(int buf_id, bool skip_recently_used, bool cool_if_hot, WritebackContext *wb_context); static void WaitIO(BufferDesc *buf); static void AbortBufferIO(Buffer buffer); @@ -2333,7 +2334,10 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum, * checkpoints, except for their "init" forks, which need to be treated * just like permanent relations. */ - set_bits |= BM_TAG_VALID | BUF_USAGECOUNT_ONE; + set_bits |= BM_TAG_VALID; + /* Admit the newly loaded page COOL (probation); a second access via + * PinBuffer promotes it to HOT. This is what makes a one-touch scan + * self-evicting -- see the cooling-state notes in buf_internals.h. */ if (relpersistence == RELPERSISTENCE_PERMANENT || forkNum == INIT_FORKNUM) set_bits |= BM_PERMANENT; @@ -3002,7 +3006,9 @@ ExtendBufferedRelShared(BufferManagerRelation bmr, victim_buf_hdr->tag = tag; - set_bits |= BM_TAG_VALID | BUF_USAGECOUNT_ONE; + set_bits |= BM_TAG_VALID; + /* Admit COOL (probation); see the comment at the other admission + * site and the cooling-state notes in buf_internals.h. */ if (bmr.relpersistence == RELPERSISTENCE_PERMANENT || fork == INIT_FORKNUM) set_bits |= BM_PERMANENT; @@ -3332,21 +3338,17 @@ PinBuffer(BufferDesc *buf, BufferAccessStrategy strategy, /* increase refcount */ buf_state += BUF_REFCOUNT_ONE; - if (strategy == NULL) - { - /* Default case: increase usagecount unless already max. */ - if (BUF_STATE_GET_USAGECOUNT(buf_state) < BM_MAX_USAGE_COUNT) - buf_state += BUF_USAGECOUNT_ONE; - } - else - { - /* - * Ring buffers shouldn't evict others from pool. Thus we - * don't make usagecount more than 1. - */ - if (BUF_STATE_GET_USAGECOUNT(buf_state) == 0) - buf_state += BUF_USAGECOUNT_ONE; - } + /* + * Accessing a resident buffer promotes it to HOT (the 2Q rescue): + * a page loaded COOL on probation becomes part of the hot working + * set on its second touch. BM_MAX_USAGE_COUNT is + * BUF_COOLSTATE_HOT (1), so this saturates at HOT and never + * overflows the field. We also set the second-chance ref bit so + * the bgwriter's next cooling pass spares this recently-used buffer. + */ + if (BUF_STATE_GET_COOLSTATE(buf_state) < BUF_COOLSTATE_HOT) + buf_state += BUF_COOLSTATE_ONE; + buf_state |= BUF_REFBIT; if (pg_atomic_compare_exchange_u64(&buf->state, &old_buf_state, buf_state)) @@ -3785,7 +3787,7 @@ BufferSync(int flags) */ if (pg_atomic_read_u64(&bufHdr->state) & BM_CHECKPOINT_NEEDED) { - if (SyncOneBuffer(buf_id, false, &wb_context) & BUF_WRITTEN) + if (SyncOneBuffer(buf_id, false, false, &wb_context) & BUF_WRITTEN) { TRACE_POSTGRESQL_BUFFER_SYNC_WRITTEN(buf_id); PendingCheckpointerStats.buffers_written++; @@ -3876,6 +3878,19 @@ BgBufferSync(WritebackContext *wb_context) float smoothing_samples = 16; float scan_whole_pool_milliseconds = 120000.0; + /* + * The cleaner scan directly observes the reusable (COOL, unpinned) buffer + * density over the region it walks, which -- with the cooling-stage + * evictor -- is exactly the sweep's victim predicate. That observation is + * ground truth for the buffers about to be reused, whereas the strategy + * scan's positional proxy (strategy_delta/recent_alloc) blurs a pool whose + * COOL population is spatially clustered (a scan burst leaves whole regions + * COOL, hot OLTP regions not). So we let the cleaner's own sample adapt on + * a shorter window than the strategy proxy, tracking a burst of + * probationary/scan COOL pages within a cycle or two instead of lagging it. + */ + float cleaner_smoothing_samples = 4; + /* Used to compute how far we scan ahead */ long strategy_delta; int bufs_to_lap; @@ -3889,6 +3904,7 @@ BgBufferSync(WritebackContext *wb_context) int num_to_scan; int num_written; int reusable_buffers; + int write_limit; /* Variables for final smoothed_density update */ long new_strategy_delta; @@ -4063,8 +4079,22 @@ BgBufferSync(WritebackContext *wb_context) * Now write out dirty reusable buffers, working forward from the * next_to_clean point, until we have lapped the strategy scan, or cleaned * enough buffers to match our estimate of the next cycle's allocation - * requirements, or hit the bgwriter_lru_maxpages limit. - */ + * requirements, or hit the write limit. + * + * The per-cycle write cap is normally bgwriter_lru_maxpages. But under a + * bulk-dirtying workload (COPY, bulk UPDATE, VACUUM) the pool fills with + * dirty COOL buffers faster than that fixed cap can clean, so the + * foreground clock sweep is forced to flush dirty victims inline -- the + * very cost the cooling-stage evictor is meant to keep off the critical + * path. When predicted demand (upcoming_alloc_est) exceeds the fixed cap, + * raise the limit to meet demand so the bgwriter stays ahead and supplies + * clean victims. This stays bounded (by demand and by lapping the + * strategy point), so it cannot run away, and normal workloads are + * unaffected because there upcoming_alloc_est <= bgwriter_lru_maxpages. + */ + write_limit = bgwriter_lru_maxpages; + if (upcoming_alloc_est > write_limit) + write_limit = upcoming_alloc_est; num_to_scan = bufs_to_lap; num_written = 0; @@ -4073,7 +4103,13 @@ BgBufferSync(WritebackContext *wb_context) /* Execute the LRU scan */ while (num_to_scan > 0 && reusable_buffers < upcoming_alloc_est) { - int sync_state = SyncOneBuffer(next_to_clean, true, + /* + * cool_if_hot = false: with the cool-in-place foreground sweep, the + * clock hand demotes HOT buffers on every tick, so the bgwriter does + * writeback only and leaves all cooling to the sweep (no background + * pre-cooling, no double-cooling). + */ + int sync_state = SyncOneBuffer(next_to_clean, true, false, wb_context); if (++next_to_clean >= NBuffers) @@ -4086,7 +4122,7 @@ BgBufferSync(WritebackContext *wb_context) if (sync_state & BUF_WRITTEN) { reusable_buffers++; - if (++num_written >= bgwriter_lru_maxpages) + if (++num_written >= write_limit) { PendingBgWriterStats.maxwritten_clean++; break; @@ -4121,7 +4157,7 @@ BgBufferSync(WritebackContext *wb_context) { scans_per_alloc = (float) new_strategy_delta / (float) new_recent_alloc; smoothed_density += (scans_per_alloc - smoothed_density) / - smoothing_samples; + cleaner_smoothing_samples; #ifdef BGW_DEBUG elog(DEBUG2, "bgwriter: cleaner density alloc=%u scan=%ld density=%.2f new smoothed=%.2f", @@ -4140,16 +4176,26 @@ BgBufferSync(WritebackContext *wb_context) * If skip_recently_used is true, we don't write currently-pinned buffers, nor * buffers marked recently used, as these are not replacement candidates. * + * If cool_if_hot is true (the bgwriter's LRU scan), an unpinned HOT buffer is + * demoted HOT -> COOL as we pass it, pre-staging eviction candidates so the + * foreground clock sweep finds a COOL victim in a single pass instead of + * having to cool buffers itself (force_cool). The demotion is done under the + * buffer header lock we already hold, so it needs no CAS and cannot race a + * concurrent demotion. A concurrent PinBuffer promotes it back to HOT, which + * is the intended 2Q behavior (a re-accessed buffer is rescued). + * * Returns a bitmask containing the following flag bits: * BUF_WRITTEN: we wrote the buffer. * BUF_REUSABLE: buffer is available for replacement, ie, it has - * pin count 0 and usage count 0. + * pin count 0 and is COOL (an eviction candidate). + * BUF_COOLED: we demoted this buffer HOT -> COOL this call. * * (BUF_WRITTEN could be set in error if FlushBuffer finds the buffer clean * after locking it, but we don't care all that much.) */ static int -SyncOneBuffer(int buf_id, bool skip_recently_used, WritebackContext *wb_context) +SyncOneBuffer(int buf_id, bool skip_recently_used, bool cool_if_hot, + WritebackContext *wb_context) { BufferDesc *bufHdr = GetBufferDescriptor(buf_id); int result = 0; @@ -4171,8 +4217,38 @@ SyncOneBuffer(int buf_id, bool skip_recently_used, WritebackContext *wb_context) */ buf_state = LockBufHdr(bufHdr); + /* + * Pre-cool with a second chance: if asked, act on an unpinned HOT buffer. + * If its ref bit is set (accessed since our last pass), clear the ref bit + * and leave it HOT -- a recently-used buffer earns one reprieve, keeping + * the hot working set out of the COOL stage under scan pressure. Only a + * HOT buffer whose ref bit is already clear is demoted HOT -> COOL, + * pre-staging it as an eviction candidate for the foreground sweep. We + * hold the header lock, so each transition is a plain masked store applied + * atomically by UnlockBufHdrExt; we re-lock to continue the dirty-write + * inspection below. + */ + if (cool_if_hot && + BUF_STATE_GET_REFCOUNT(buf_state) == 0 && + BUF_STATE_GET_COOLSTATE(buf_state) != BUF_COOLSTATE_COOL) + { + if (BUF_STATE_GET_REFBIT(buf_state)) + { + /* second chance: consume the ref bit, stay HOT */ + UnlockBufHdrExt(bufHdr, buf_state, 0, BUF_REFBIT, 0); + buf_state = LockBufHdr(bufHdr); + } + else + { + /* not re-accessed since last pass: demote to COOL */ + UnlockBufHdrExt(bufHdr, buf_state, 0, BUF_USAGECOUNT_MASK, 0); + buf_state = LockBufHdr(bufHdr); + result |= BUF_COOLED; + } + } + if (BUF_STATE_GET_REFCOUNT(buf_state) == 0 && - BUF_STATE_GET_USAGECOUNT(buf_state) == 0) + BUF_STATE_GET_COOLSTATE(buf_state) == BUF_COOLSTATE_COOL) { result |= BUF_REUSABLE; } diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c index fdb5bad7910a2..808f13360e62a 100644 --- a/src/backend/storage/buffer/freelist.c +++ b/src/backend/storage/buffer/freelist.c @@ -22,6 +22,7 @@ #include "storage/proc.h" #include "storage/shmem.h" #include "storage/subsystems.h" +#include "port/pg_numa.h" #define INT_ACCESS_ONCE(var) ((int)(*((volatile int *)&(var)))) @@ -48,6 +49,16 @@ typedef struct uint32 completePasses; /* Complete cycles of the clock-sweep */ pg_atomic_uint32 numBufferAllocs; /* Buffers allocated since last reset */ + /* + * Number of clock-hand values a backend claims per atomic fetch-add. + * Computed once at startup (see StrategyCtlShmemInit). Kept in shared + * memory rather than a backend-local static so that EXEC_BACKEND children + * (which do not inherit the postmaster's statics) see the same value; a + * backend-local copy would silently reset to 1 there, disabling batching + * on Windows. + */ + uint32 batchSize; + /* * Bgworker process to be notified upon activity or -1 if none. See * StrategyNotifyBgWriter. @@ -100,68 +111,99 @@ static BufferDesc *GetBufferFromRing(BufferAccessStrategy strategy, static void AddBufferToRing(BufferAccessStrategy strategy, BufferDesc *buf); +/* + * Per-backend state for the batched clock sweep. Each backend claims a run + * of consecutive clock-hand values with a single atomic fetch-add and then + * iterates through them privately, so the contended nextVictimBuffer cache + * line is touched roughly 1/batch as often. MyBatchPos is the next hand + * value to hand out; MyBatchEnd is one past the end of the claimed run. Both + * are absolute (monotonically increasing) hand values; the buffer id is the + * value modulo NBuffers. + */ +static uint32 MyBatchPos = 0; +static uint32 MyBatchEnd = 0; + /* * ClockSweepTick - Helper routine for StrategyGetBuffer() * - * Move the clock hand one buffer ahead of its current position and return the - * id of the buffer now under the hand. + * Return the next buffer to consider for eviction. Backends claim batches of + * consecutive buffer IDs from the shared clock hand, then iterate through + * them locally without further atomic operations. This preserves the global + * sweep order while reducing contention on the shared counter. */ static inline uint32 ClockSweepTick(void) { uint32 victim; - /* - * Atomically move hand ahead one buffer - if there's several processes - * doing this, this can lead to buffers being returned slightly out of - * apparent order. - */ - victim = - pg_atomic_fetch_add_u32(&StrategyControl->nextVictimBuffer, 1); - - if (victim >= NBuffers) + if (MyBatchPos >= MyBatchEnd) { - uint32 originalVictim = victim; - - /* always wrap what we look up in BufferDescriptors */ - victim = victim % NBuffers; - /* - * If we're the one that just caused a wraparound, force - * completePasses to be incremented while holding the spinlock. We - * need the spinlock so StrategySyncStart() can return a consistent - * value consisting of nextVictimBuffer and completePasses. + * Claim a fresh batch from the shared clock hand. This is the only + * atomic operation per batch, reducing contention by the batch size. */ - if (victim == 0) - { - uint32 expected; - uint32 wrapped; - bool success = false; + uint32 start; + uint32 batch_size = StrategyControl->batchSize; - expected = originalVictim + 1; + start = pg_atomic_fetch_add_u32(&StrategyControl->nextVictimBuffer, + batch_size); - while (!success) - { - /* - * Acquire the spinlock while increasing completePasses. That - * allows other readers to read nextVictimBuffer and - * completePasses in a consistent manner which is required for - * StrategySyncStart(). In theory delaying the increment - * could lead to an overflow of nextVictimBuffers, but that's - * highly unlikely and wouldn't be particularly harmful. - */ - SpinLockAcquire(&StrategyControl->buffer_strategy_lock); + if (start >= (uint32) NBuffers) + { + start = start % NBuffers; - wrapped = expected % NBuffers; + /* + * The counter has grown past NBuffers; try to wrap it back. We + * must hold the spinlock so StrategySyncStart() can read + * nextVictimBuffer and completePasses consistently. + * + * With batching, multiple backends may each land a fetch-add + * that returns a value past NBuffers in the same pass. After + * acquiring the spinlock we re-read the counter: if another + * backend already wrapped it below NBuffers we are done. + */ + SpinLockAcquire(&StrategyControl->buffer_strategy_lock); + { + uint32 current; + uint32 wrapped; - success = pg_atomic_compare_exchange_u32(&StrategyControl->nextVictimBuffer, - &expected, wrapped); - if (success) - StrategyControl->completePasses++; - SpinLockRelease(&StrategyControl->buffer_strategy_lock); + current = pg_atomic_read_u32(&StrategyControl->nextVictimBuffer); + if (current >= (uint32) NBuffers) + { + wrapped = current % NBuffers; + if (pg_atomic_compare_exchange_u32(&StrategyControl->nextVictimBuffer, + ¤t, wrapped)) + StrategyControl->completePasses++; + } } + SpinLockRelease(&StrategyControl->buffer_strategy_lock); } + else if (start + batch_size > (uint32) NBuffers) + { + /* + * The fetch-add returned a value below NBuffers, but this batch + * spans the wrap point (start .. NBuffers-1 then 0 .. k are + * iterated locally via "% NBuffers"). That crossing is a + * complete pass too, but the wrap-and-increment path above only + * fires when the fetch-add return is itself >= NBuffers, so + * without this it would go uncounted and completePasses would + * drift low (it feeds bgwriter pacing / StrategySyncStart, not + * correctness). The batch is capped at NBuffers, so a batch + * spans the wrap at most once; count it under the spinlock for a + * consistent (nextVictimBuffer, completePasses) pair. + */ + SpinLockAcquire(&StrategyControl->buffer_strategy_lock); + StrategyControl->completePasses++; + SpinLockRelease(&StrategyControl->buffer_strategy_lock); + } + + MyBatchPos = start; + MyBatchEnd = start + batch_size; } + + victim = MyBatchPos % NBuffers; + MyBatchPos++; + return victim; } @@ -236,12 +278,30 @@ StrategyGetBuffer(BufferAccessStrategy strategy, uint64 *buf_state, bool *from_r */ pg_atomic_fetch_add_u32(&StrategyControl->numBufferAllocs, 1); - /* Use the "clock sweep" algorithm to find a free buffer */ + /* + * Use the cooling-stage clock sweep to find a victim. + * + * A buffer is HOT (recently used) or COOL (an eviction candidate). This + * is a COOL-IN-PLACE sweep: every tick past a HOT buffer demotes it one + * step toward COOL (respecting a single second-chance reference bit), and + * a COOL, unpinned buffer is claimed as the victim. Because every tick + * makes cooling progress, the sweep is self-staging: it never needs a + * background pre-cooler to keep COOL victims available, and it cannot get + * stuck in a "no COOL victim anywhere" state that forces a foreground + * escalation pass. Newly loaded pages are admitted COOL (see + * BufferAlloc), so scan resistance falls out of the algorithm. + * + * trycounter bounds the search: only a pinned buffer is "no progress". + * Demoting or reclaiming is progress and resets it. A full NBuffers pass + * that finds every buffer pinned fails, matching the stock "no unpinned + * buffers available" contract. + */ trycounter = NBuffers; for (;;) { uint64 old_buf_state; uint64 local_buf_state; + bool no_progress = false; buf = GetBufferDescriptor(ClockSweepTick()); @@ -254,25 +314,10 @@ StrategyGetBuffer(BufferAccessStrategy strategy, uint64 *buf_state, bool *from_r { local_buf_state = old_buf_state; - /* - * If the buffer is pinned or has a nonzero usage_count, we cannot - * use it; decrement the usage_count (unless pinned) and keep - * scanning. - */ - + /* If the buffer is pinned we cannot use it; keep scanning. */ if (BUF_STATE_GET_REFCOUNT(local_buf_state) != 0) { - if (--trycounter == 0) - { - /* - * We've scanned all the buffers without making any state - * changes, so all the buffers are pinned (or were when we - * looked at them). We could hope that someone will free - * one eventually, but it's probably better to fail than - * to risk getting stuck in an infinite loop. - */ - elog(ERROR, "no unpinned buffers available"); - } + no_progress = true; break; } @@ -283,9 +328,23 @@ StrategyGetBuffer(BufferAccessStrategy strategy, uint64 *buf_state, bool *from_r continue; } - if (BUF_STATE_GET_USAGECOUNT(local_buf_state) != 0) + if (BUF_STATE_GET_COOLSTATE(local_buf_state) != BUF_COOLSTATE_COOL) { - local_buf_state -= BUF_USAGECOUNT_ONE; + /* + * HOT buffer: cool it in place this tick. Apply a single + * second-chance reference bit: a HOT buffer whose ref bit is + * set (touched since it was last passed) has the ref bit + * cleared and stays HOT; only a HOT buffer whose ref bit is + * already clear is demoted HOT -> COOL. Either transition is + * progress toward a victim, so reset trycounter. We do NOT + * claim the buffer this tick -- a demoted buffer becomes a + * candidate for a later tick, giving it one more full sweep of + * grace before eviction. + */ + if (BUF_STATE_GET_REFBIT(local_buf_state)) + local_buf_state &= ~BUF_REFBIT; /* second chance: clear ref, stay HOT */ + else + local_buf_state &= ~BUF_USAGECOUNT_MASK; /* HOT -> COOL, clear ref bit */ if (pg_atomic_compare_exchange_u64(&buf->state, &old_buf_state, local_buf_state)) @@ -296,7 +355,7 @@ StrategyGetBuffer(BufferAccessStrategy strategy, uint64 *buf_state, bool *from_r } else { - /* pin the buffer if the CAS succeeds */ + /* COOL and unpinned: claim it. Pin if the CAS succeeds. */ local_buf_state += BUF_REFCOUNT_ONE; if (pg_atomic_compare_exchange_u64(&buf->state, &old_buf_state, @@ -313,6 +372,15 @@ StrategyGetBuffer(BufferAccessStrategy strategy, uint64 *buf_state, bool *from_r } } } + + /* + * Only a pinned buffer is no progress. A full NBuffers pass that + * makes no progress means every buffer is pinned, so fail rather than + * spin forever. (A failed CAS above is neither progress nor a full + * miss: we simply retry the same buffer.) + */ + if (no_progress && --trycounter == 0) + elog(ERROR, "no unpinned buffers available"); } } @@ -408,6 +476,29 @@ StrategyCtlShmemInit(void *arg) /* No pending notification */ StrategyControl->bgwprocno = -1; + + /* + * Decide whether to batch the clock sweep. + * + * Batching claims a run of consecutive buffer IDs per atomic fetch-add so + * concurrent backends touch the shared nextVictimBuffer cache line ~1/batch + * as often -- a win only when that line actually bounces across sockets, + * i.e. on multi-node NUMA hardware. On a single socket the atomic is + * already node-local and batching would only make backends skip ahead for + * no benefit, so we fall back to batch size 1 there (byte-identical to the + * stock one-buffer-at-a-time clock sweep). + * + * Batch (> 1) only when libnuma reports more than one node + * (pg_numa_get_max_node() >= 1); pg_numa_init() returns -1 when NUMA is + * unavailable. (Benchmarking showed the win holds with or without huge + * pages, so huge-page availability is intentionally not part of the gate.) + */ + if (pg_numa_init() != -1 && + pg_numa_get_max_node() >= 1) + StrategyControl->batchSize = Min(PG_CACHE_LINE_SIZE / (uint32) sizeof(uint32), + (uint32) NBuffers); + else + StrategyControl->batchSize = 1; } @@ -655,14 +746,17 @@ GetBufferFromRing(BufferAccessStrategy strategy, uint64 *buf_state) /* * If the buffer is pinned we cannot use it under any circumstances. * - * If usage_count is 0 or 1 then the buffer is fair game (we expect 1, - * since our own previous usage of the ring element would have left it - * there, but it might've been decremented by clock-sweep since then). - * A higher usage_count indicates someone else has touched the buffer, - * so we shouldn't re-use it. + * If it is unpinned but has been promoted to HOT, another backend + * touched it since we last cycled past this ring slot, so it has + * joined the working set and we must not recycle it -- tell the caller + * to get a fresh victim from the sweep instead. This is the 1-bit + * cooling-state analog of the stock ring's "usage_count > 1 means + * someone else touched it" test: a slot the ring keeps reusing and + * nobody else pins stays COOL, and an out-of-ring PinBuffer() is + * exactly what promotes it to HOT. */ - if (BUF_STATE_GET_REFCOUNT(local_buf_state) != 0 - || BUF_STATE_GET_USAGECOUNT(local_buf_state) > 1) + if (BUF_STATE_GET_REFCOUNT(local_buf_state) != 0 || + BUF_STATE_GET_COOLSTATE(local_buf_state) != BUF_COOLSTATE_COOL) break; /* See equivalent code in PinBuffer() */ diff --git a/src/backend/storage/buffer/localbuf.c b/src/backend/storage/buffer/localbuf.c index 4870c8e13d010..21c08091c490b 100644 --- a/src/backend/storage/buffer/localbuf.c +++ b/src/backend/storage/buffer/localbuf.c @@ -167,7 +167,7 @@ LocalBufferAlloc(SMgrRelation smgr, ForkNumber forkNum, BlockNumber blockNum, buf_state = pg_atomic_read_u64(&bufHdr->state); buf_state &= ~(BUF_FLAG_MASK | BUF_USAGECOUNT_MASK); - buf_state |= BM_TAG_VALID | BUF_USAGECOUNT_ONE; + buf_state |= BM_TAG_VALID; /* admit COOL (probation) */ pg_atomic_unlocked_write_u64(&bufHdr->state, buf_state); *foundPtr = false; @@ -248,9 +248,10 @@ GetLocalVictimBuffer(void) { uint64 buf_state = pg_atomic_read_u64(&bufHdr->state); - if (BUF_STATE_GET_USAGECOUNT(buf_state) > 0) + if (BUF_STATE_GET_COOLSTATE(buf_state) != BUF_COOLSTATE_COOL) { - buf_state -= BUF_USAGECOUNT_ONE; + /* HOT: give it a second chance, cool it and keep scanning. */ + buf_state -= BUF_COOLSTATE_ONE; pg_atomic_unlocked_write_u64(&bufHdr->state, buf_state); trycounter = NLocBuffer; } @@ -454,7 +455,7 @@ ExtendBufferedRelLocal(BufferManagerRelation bmr, victim_buf_hdr->tag = tag; - buf_state |= BM_TAG_VALID | BUF_USAGECOUNT_ONE; + buf_state |= BM_TAG_VALID; /* admit COOL (probation) */ pg_atomic_unlocked_write_u64(&victim_buf_hdr->state, buf_state); @@ -839,9 +840,9 @@ PinLocalBuffer(BufferDesc *buf_hdr, bool adjust_usagecount) NLocalPinnedBuffers++; buf_state += BUF_REFCOUNT_ONE; if (adjust_usagecount && - BUF_STATE_GET_USAGECOUNT(buf_state) < BM_MAX_USAGE_COUNT) + BUF_STATE_GET_COOLSTATE(buf_state) < BUF_COOLSTATE_HOT) { - buf_state += BUF_USAGECOUNT_ONE; + buf_state += BUF_COOLSTATE_ONE; } pg_atomic_unlocked_write_u64(&buf_hdr->state, buf_state); diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index e4ff5619b79ca..131df126cda00 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -67,6 +67,50 @@ StaticAssertDecl(BUF_REFCOUNT_BITS + BUF_USAGECOUNT_BITS + BUF_FLAG_BITS + BUF_L #define BUF_USAGECOUNT_ONE \ (UINT64CONST(1) << BUF_REFCOUNT_BITS) +/* + * Cooling state (LeanStore / 2Q-A1 cooling-stage clock sweep). + * + * The field historically used for the 0..5 usage_count now holds a single + * cooling-state bit: HOT (recently accessed, not an eviction candidate) or + * COOL (an eviction candidate). We reuse BUF_USAGECOUNT_ONE as the unit so + * the buffer-state bit geography -- refcount, flag, and lock offsets, and the + * 64-bit StaticAsserts -- is unchanged; only the meaning of the field and the + * instructions that touch it change. + * + * A demand-loaded page is admitted COOL (probation); a second access promotes + * it to HOT (the rescue). The sweep prefers COOL victims and demotes HOT to + * COOL only when a full pass finds no COOL victim. So a one-touch scan fills + * and drains the COOL stage without displacing the HOT working set -- scan + * resistance intrinsic to the replacement algorithm. + */ +#define BUF_COOLSTATE_COOL 0 +#define BUF_COOLSTATE_HOT 1 +#define BUF_COOLSTATE_ONE BUF_USAGECOUNT_ONE + +/* + * Second-chance reference bit, bit 1 of the (former usagecount) field, one + * position above the cooling-state bit. PinBuffer sets it on every access. + * The bgwriter's pre-cooling gives a HOT buffer a second chance: the first + * time it passes a HOT buffer whose ref bit is set, it clears the ref bit and + * leaves the buffer HOT; only a HOT buffer whose ref bit is already clear (not + * re-accessed since the previous bgwriter pass) is demoted to COOL. This + * keeps genuinely-hot pages out of the COOL stage (protecting the working set + * from being cooled under scan pressure) while leaving the foreground sweep a + * single-pass search over the pre-staged COOL buffers. A separate bit (not a + * count) so it stays a plain masked store under the header lock. + */ +#define BUF_REFBIT (UINT64CONST(2) << BUF_REFCOUNT_BITS) +#define BUF_STATE_GET_REFBIT(state) (((state) & BUF_REFBIT) != 0) + +/* + * The cooling state occupies bit 0 and the reference bit occupies bit 1 of + * the (former usagecount) field, so the field must be at least 2 bits wide. + * Assert it here so a future change to BUF_USAGECOUNT_BITS cannot silently + * push BUF_REFBIT up into the flag bits. + */ +StaticAssertDecl(BUF_USAGECOUNT_BITS >= 2, + "cooling state + reference bit need at least 2 bits in the usagecount field"); + /* flags related definitions */ #define BUF_FLAG_SHIFT \ (BUF_REFCOUNT_BITS + BUF_USAGECOUNT_BITS) @@ -92,6 +136,11 @@ StaticAssertDecl(BUF_REFCOUNT_BITS + BUF_USAGECOUNT_BITS + BUF_FLAG_BITS + BUF_L #define BUF_STATE_GET_USAGECOUNT(state) \ ((uint32)(((state) & BUF_USAGECOUNT_MASK) >> BUF_USAGECOUNT_SHIFT)) +/* Cooling state (HOT/COOL) from buffer state -- bit 0 of the field only, so + * the second-chance ref bit (bit 1) does not perturb the HOT/COOL test. */ +#define BUF_STATE_GET_COOLSTATE(state) \ + ((uint32) (((state) >> BUF_USAGECOUNT_SHIFT) & 1)) + /* * Flags for buffer descriptors * @@ -134,17 +183,15 @@ StaticAssertDecl(MAX_BACKENDS_BITS <= (BUF_LOCK_BITS - 2), /* - * The maximum allowed value of usage_count represents a tradeoff between - * accuracy and speed of the clock-sweep buffer management algorithm. A - * large value (comparable to NBuffers) would approximate LRU semantics. - * But it can take as many as BM_MAX_USAGE_COUNT+1 complete cycles of the - * clock-sweep hand to find a free buffer, so in practice we don't want the - * value to be very large. + * The cooling state is a single bit (HOT/COOL); the maximum value stored in + * the field is therefore BUF_COOLSTATE_HOT. Retained under the historical + * name BM_MAX_USAGE_COUNT so the pin fast path ("promote unless already at + * max") reads naturally. */ -#define BM_MAX_USAGE_COUNT 5 +#define BM_MAX_USAGE_COUNT BUF_COOLSTATE_HOT StaticAssertDecl(BM_MAX_USAGE_COUNT < (UINT64CONST(1) << BUF_USAGECOUNT_BITS), - "BM_MAX_USAGE_COUNT doesn't fit in BUF_USAGECOUNT_BITS bits"); + "cooling state doesn't fit in BUF_USAGECOUNT_BITS bits"); /* * Buffer tag identifies which disk block the buffer contains. diff --git a/src/test/regress/pg_regress.c b/src/test/regress/pg_regress.c index 21d00f792d24e..bfd7e84e56bef 100644 --- a/src/test/regress/pg_regress.c +++ b/src/test/regress/pg_regress.c @@ -1243,7 +1243,7 @@ spawn_process(const char *cmdline) char *cmdline2; cmdline2 = psprintf("exec %s", cmdline); - execl(shellprog, shellprog, "-c", cmdline2, (char *) NULL); + execlp(shellprog, shellprog, "-c", cmdline2, (char *) NULL); /* Not using the normal bail() here as we want _exit */ bail_noatexit("could not exec \"%s\": %m", shellprog); } diff --git a/src/tools/pgindent/pgindent b/src/tools/pgindent/pgindent index 004b8fcab0027..747f054351486 100755 --- a/src/tools/pgindent/pgindent +++ b/src/tools/pgindent/pgindent @@ -1,4 +1,4 @@ -#!/usr/bin/perl +#!/usr/bin/env perl # Copyright (c) 2021-2026, PostgreSQL Global Development Group