fix(engine): retry passes rsync exit 23, a dangling symlink under -L

README.md

@@ -255,7 +255,7 @@ and `smoke-mirror` do nothing until a mirror fills them.
 | `smoke` | A sample of the run's keys read back through `HOST`, sizes against the listing; the tlpdb sha512 when `TL` is set; then `smoke-mirror` |
 | `smoke-mirror` | Hook. Nothing here; a mirror with more to read back defines it |
 | `report-engine` | Hook. The engine's rows of the run summary |
-| `retry` | Run a command, retrying rsync's transport exit codes with backoff; 24 is a success |
+| `retry` | Run a command, retrying rsync's transport exit codes with backoff; 23 (an unreadable path, skipped) and 24 (a file vanished mid-transfer) are successes |
 
 `normalise`, `pull`, `push`, `batch`, `merge` and `remove` are the verbs those call;
 `pull` and `push` move an xz-compressed key between the bucket and `.run`, and a

engines/rsync.yml

@@ -106,6 +106,9 @@ tasks:
       # the report count old lines.
       - rm -f {{.RUN}}/publish.txt {{.RUN}}/orphans.txt
       - mkdir -p {{.RUN}} {{.STAGING}}
+      # -L lists every symlink as its file. One whose target is gone upstream is reported
+      # and skipped, and rsync exits 23 with the rest of the listing intact; retry passes
+      # that. A listing cut short is caught by LIST_FLOOR, not by the exit code.
       - task: retry
         vars: {CMD: '{{.RSYNC}}{{if .FILTER}} {{.FILTER}}{{end}} -rL --list-only {{.SOURCE}} > {{.RUN}}/listing.txt'}
       - {task: normalise}
@@ -487,12 +490,12 @@ tasks:
       - test ! -d {{.RUN}}/tl || echo "| Signature | $(test -f {{.RUN}}/tl/tlpkg/texlive.tlpdb && echo "tlpdb signed by {{.TL_KEY}}; $(test -f {{.RUN}}/tl/missing.txt && wc -l < {{.RUN}}/tl/missing.txt || echo 0) named containers missing from the bucket" || echo "the tlpdb did not verify") |" >> "${GITHUB_STEP_SUMMARY:-/dev/stdout}"
 
   retry:
-    desc: Run CMD, retrying rsync's transport exit codes (5 10 12 30 35) five times with backoff and jitter; exit 24 (file vanished mid-transfer) is a success
+    desc: Run CMD, retrying rsync's transport exit codes (5 10 12 30 35) five times with backoff and jitter; 23 (a path it could not read, a dangling symlink under -L) and 24 (file vanished mid-transfer) are successes
     cmds:
       - |
         for i in 1 2 3 4 5; do
           rc=0; ( {{.CMD}} ) || rc=$?   # subshell so CMD's exit cannot end the loop; || so Task's errexit cannot
-          case $rc in 0|24) exit 0;; 5|10|12|30|35) ;; *) exit $rc;; esac
+          case $rc in 0|23|24) exit 0;; 5|10|12|30|35) ;; *) exit $rc;; esac
           test $i -lt 5 || break
           s=$(({{.RETRY_S}} * 2 ** i + RANDOM % (2 * {{.RETRY_S}} + 1))); echo "rsync exit $rc, retry $i in ${s}s" >&2; sleep $s
         done; exit $rc

examples/rsync/Taskfile.yml

@@ -62,7 +62,8 @@ tasks:
       - {task: diff, vars: {RUN: '{{.F}}/run-empty'}}
       - {task: merge, vars: {RUN: '{{.F}}/run-empty', STAGING: '{{.F}}/run-empty/staging', B: '{{.F}}/run-empty/changed.txt'}}
       - cmp {{.F}}/run-empty/applied.new {{.F}}/run-empty/applied.txt
-      # retry: 24 is a success, a transport code is retried five times, anything else is final.
+      # retry: 23 and 24 are successes, a transport code is retried five times, anything else is final.
+      - task retry CMD='exit 23' RETRY_BASE=0
       - task retry CMD='exit 24' RETRY_BASE=0
       - '! task retry CMD=''exit 5'' RETRY_BASE=0 2>/dev/null'
       - '! task retry CMD=''exit 3'' RETRY_BASE=0 2>/dev/null'

examples/rsync/render.txt

@@ -3,7 +3,7 @@ task: [list] rm -f /work/examples/rsync/.run/publish.txt /work/examples/rsync/.r
 task: [list] mkdir -p /work/examples/rsync/.run /work/examples/rsync/staging
 task: [retry] for i in 1 2 3 4 5; do
   rc=0; ( rsync --timeout=300 --contimeout=60 --no-h -rL --list-only rsync://rsync.example.org/pub/ > /work/examples/rsync/.run/listing.txt ) || rc=$?   # subshell so CMD's exit cannot end the loop; || so Task's errexit cannot
-  case $rc in 0|24) exit 0;; 5|10|12|30|35) ;; *) exit $rc;; esac
+  case $rc in 0|23|24) exit 0;; 5|10|12|30|35) ;; *) exit $rc;; esac
   test $i -lt 5 || break
   s=$((15 * 2 ** i + RANDOM % (2 * 15 + 1))); echo "rsync exit $rc, retry $i in ${s}s" >&2; sleep $s
 done; exit $rc
@@ -53,7 +53,7 @@ task: [prepare] mkdir -p /work/examples/rsync/.run/tl
 task: [prepare] printf '%s\n' tlpkg/texlive.tlpdb.xz tlpkg/texlive.tlpdb.sha512 tlpkg/texlive.tlpdb.sha512.asc tlpkg/gpg/pubring.gpg > /work/examples/rsync/.run/tl/files.txt
 task: [retry] for i in 1 2 3 4 5; do
   rc=0; ( rsync --timeout=300 --contimeout=60 --no-h -Lt --files-from=/work/examples/rsync/.run/tl/files.txt rsync://rsync.example.org/pub// /work/examples/rsync/.run/tl/ ) || rc=$?   # subshell so CMD's exit cannot end the loop; || so Task's errexit cannot
-  case $rc in 0|24) exit 0;; 5|10|12|30|35) ;; *) exit $rc;; esac
+  case $rc in 0|23|24) exit 0;; 5|10|12|30|35) ;; *) exit $rc;; esac
   test $i -lt 5 || break
   s=$((15 * 2 ** i + RANDOM % (2 * 15 + 1))); echo "rsync exit $rc, retry $i in ${s}s" >&2; sleep $s
 done; exit $rc
@@ -64,7 +64,7 @@ task: [fetch] find /work/examples/rsync/staging -mindepth 1 -delete
 task: [fetch] cut -f1  > /work/examples/rsync/.run/files.txt
 task: [retry] for i in 1 2 3 4 5; do
   rc=0; ( rsync --timeout=300 --contimeout=60 --no-h -Lt --files-from=/work/examples/rsync/.run/files.txt --ignore-missing-args rsync://rsync.example.org/pub/ /work/examples/rsync/staging/ ) || rc=$?   # subshell so CMD's exit cannot end the loop; || so Task's errexit cannot
-  case $rc in 0|24) exit 0;; 5|10|12|30|35) ;; *) exit $rc;; esac
+  case $rc in 0|23|24) exit 0;; 5|10|12|30|35) ;; *) exit $rc;; esac
   test $i -lt 5 || break
   s=$((15 * 2 ** i + RANDOM % (2 * 15 + 1))); echo "rsync exit $rc, retry $i in ${s}s" >&2; sleep $s
 done; exit $rc