rerere: keep a background gc from killing a rebase

Since 2.54 unscheduled maintenance uses the "geometric" strategy, so
the "git maintenance run --auto --detach" behind every "git commit"
runs "git rerere gc" in the background whenever rr-cache has an entry.
That includes the "git commit" the sequencer runs for a resolved pick
on "git rebase --continue".

rerere_gc() takes MERGE_RR.lock through setup_rerere(), which uses
LOCK_DIE_ON_ERROR, and so does the sequencer's repo_rerere() at the
next conflict a few milliseconds later. Whichever comes second dies.
When it is the rebase, it dies in do_pick_commit() with the index
written but before make_patch() writes rebase-merge/{message,patch,
stopped-sha}, and every later "git rebase --continue" refuses with
"you have staged changes in your working tree". When it is the "git
commit" of a later continue, that one dies in its post-commit
repo_rerere() after the commit was made. Before 2.54 the same
collision needed an auto gc to actually run, since gc runs
"rerere gc" at its end.

A rebase with two conflicts in a row shows it. The filler makes the
pick slower than the ~5 ms the background task needs to take the
lock, and keeps the lock held for about 0.4 s. It hit 6 of 6 runs
here on 2.55.0, and a test suite driving rebases on toy repositories
with a single rr-cache entry hit it in both runs that were traced:

    git init -q -b main r && cd r
    git config rerere.enabled true
    git config maintenance.auto false
    mkdir pad && seq 20000 | (cd pad && split -l 1 -a 5)
    echo base >f && git add -A && git commit -qm base
    git checkout -q -b topic
    echo b >f && git commit -qam B
    echo c >f && git commit -qam C
    git checkout -q main
    echo a >f && git commit -qam A
    git repack -adq
    seq 20000 | awk '{printf ".git/rr-cache/%040x\n", $1}' \
        | xargs mkdir -p
    for d in .git/rr-cache/*/; do echo x >$d/preimage; done
    git config --unset maintenance.auto
    git checkout -q topic
    git rebase main
    echo ab >f && git add f
    GIT_EDITOR=true git rebase --continue

The second continue dies with "Unable to create '.git/MERGE_RR.lock':
File exists" while the gc spawned by its own commit holds the lock,
and after resolving C every further continue refuses. Maintenance
stays off during the setup so that no repack is pending: a repack due
at that commit runs ahead of rerere-gc in the task list and would
spend the window.

The gc needs the lock: it removes every rr-cache directory it finds
empty, and a rerere that has just created its directory but not yet
written the preimage looks exactly like that. So keep the lock and fix
both orders. When the gc finds the lock busy, let it warn and do
nothing this time, the way "maintenance run" treats its own lock, so a
manual "git rerere gc" sees the warning and the maintenance task and
"git gc" see a clean exit. When the gc holds the lock, let every other
caller wait it out instead of dying at once, for rerere.lockTimeout
milliseconds with the semantics of core.packedRefsTimeout: 1000 by
default, 0 for the old behaviour, -1 for an unbounded wait. Walking a
20000-entry rr-cache takes about 0.4 s here.

That rebase now completes. The tests cover the gc under a held lock,
directly and through the maintenance task, a merge that waits a lock
out within a five second rerere.lockTimeout, and one that fails at
once with a timeout of 0.

Assisted-by: Claude Fable 5.1
Signed-off-by: Thomas Bachem <mail@thomasbachem.com>

Author: thomasbachem

Documentation/config/rerere.adoc

@@ -10,3 +10,11 @@ rerere.enabled::
 	enabled if there is an `rr-cache` directory under the
 	`$GIT_DIR`, e.g. if "rerere" was previously used in the
 	repository.
+
+rerere.lockTimeout::
+	The length of time, in milliseconds, to retry when trying to
+	take the rerere lock while another process holds it, typically
+	a background `git rerere gc`.  Value 0 means not to retry at
+	all; -1 means to try indefinitely.  Default is 1000 (i.e.,
+	retry for 1 second).  `git rerere gc` itself does not wait and
+	skips its run instead.

Documentation/git-rerere.adoc

@@ -70,7 +70,9 @@ occurred a long time ago.  By default, unresolved conflicts older
 than 15 days and resolved conflicts older than 60
 days are pruned.  These defaults are controlled via the
 `gc.rerereUnresolved` and `gc.rerereResolved` configuration
-variables respectively.
+variables respectively.  If another process holds the lock on the
+recorded resolutions, for example a merge or rebase that is recording
+a conflict, `gc` does nothing and reports so.
 
 
 DISCUSSION

rerere.c

@@ -32,6 +32,7 @@ static int rerere_enabled = -1;
 
 /* automatically update cleanly resolved paths to the index */
 static int rerere_autoupdate;
+static int rerere_lock_timeout_ms = 1000;
 
 #define RR_HAS_POSTIMAGE 1
 #define RR_HAS_PREIMAGE 2
@@ -876,6 +877,8 @@ static void git_rerere_config(void)
 {
 	repo_config_get_bool(the_repository, "rerere.enabled", &rerere_enabled);
 	repo_config_get_bool(the_repository, "rerere.autoupdate", &rerere_autoupdate);
+	repo_config_get_int(the_repository, "rerere.locktimeout",
+			    &rerere_lock_timeout_ms);
 	repo_config(the_repository, git_default_config, NULL);
 }
 
@@ -908,12 +911,26 @@ int setup_rerere(struct repository *r, struct string_list *merge_rr, int flags)
 
 	if (flags & (RERERE_AUTOUPDATE|RERERE_NOAUTOUPDATE))
 		rerere_autoupdate = !!(flags & RERERE_AUTOUPDATE);
-	if (flags & RERERE_READONLY)
+	if (flags & RERERE_READONLY) {
 		fd = 0;
-	else
+	} else if (flags & RERERE_SKIP_LOCKED) {
 		fd = hold_lock_file_for_update(&write_lock,
-					       git_path_merge_rr(r),
-					       LOCK_DIE_ON_ERROR);
+					       git_path_merge_rr(r), 0);
+		if (fd < 0) {
+			warning_errno(_("unable to lock '%s', skipping"),
+				      git_path_merge_rr(r));
+			return -1;
+		}
+	} else {
+		/*
+		 * A background "rerere gc" holds the lock for as long as it
+		 * takes to walk rr-cache, so wait it out rather than die.
+		 */
+		fd = hold_lock_file_for_update_timeout(&write_lock,
+						       git_path_merge_rr(r),
+						       LOCK_DIE_ON_ERROR,
+						       rerere_lock_timeout_ms);
+	}
 	read_rr(r, merge_rr);
 	return fd;
 }
@@ -1237,7 +1254,7 @@ void rerere_gc(struct repository *r, struct string_list *rr)
 	timestamp_t cutoff_resolve = now - 60 * 86400;
 	struct strbuf buf = STRBUF_INIT;
 
-	if (setup_rerere(r, rr, 0) < 0)
+	if (setup_rerere(r, rr, RERERE_SKIP_LOCKED) < 0)
 		return;
 
 	repo_config_get_expiry_in_days(the_repository, "gc.rerereresolved",

rerere.h

@@ -10,6 +10,7 @@ struct repository;
 #define RERERE_AUTOUPDATE   01
 #define RERERE_NOAUTOUPDATE 02
 #define RERERE_READONLY     04
+#define RERERE_SKIP_LOCKED  010
 
 /*
  * Marks paths that have been hand-resolved and added to the

t/t4200-rerere.sh

@@ -242,6 +242,46 @@ test_expect_success 'old records rest in peace' '
 	test_path_is_missing $rr2/preimage
 '
 
+test_expect_success 'gc does nothing while MERGE_RR is locked' '
+	mkdir -p $rr2 &&
+	echo Hello >$rr2/preimage &&
+	test-tool chmtime =$just_over_15_days_ago $rr2/preimage &&
+
+	test_when_finished "rm -f .git/MERGE_RR.lock" &&
+	>.git/MERGE_RR.lock &&
+	git rerere gc 2>err &&
+	test_grep "MERGE_RR" err &&
+	test_path_is_file $rr2/preimage &&
+
+	rm .git/MERGE_RR.lock &&
+	git rerere gc &&
+	test_path_is_missing $rr2/preimage
+'
+
+test_expect_success 'a held lock is waited out within rerere.lockTimeout' '
+	git reset --hard &&
+	rm -rf $rr &&
+	test_when_finished "rm -f .git/MERGE_RR.lock" &&
+	>.git/MERGE_RR.lock &&
+	{
+		(sleep 1 && rm -f .git/MERGE_RR.lock) &
+	} &&
+	test_must_fail git -c rerere.lockTimeout=5000 merge first 2>err &&
+	wait &&
+	test_grep ! "Unable to create" err &&
+	grep "^=======\$" $rr/preimage
+'
+
+test_expect_success 'rerere.lockTimeout=0 fails at once on a held lock' '
+	git reset --hard &&
+	rm -rf $rr &&
+	test_when_finished "rm -f .git/MERGE_RR.lock" &&
+	>.git/MERGE_RR.lock &&
+	test_must_fail git -c rerere.lockTimeout=0 merge first 2>err &&
+	test_grep "Unable to create" err &&
+	test_path_is_missing $rr/preimage
+'
+
 rerere_gc_custom_expiry_test () {
 	five_days="$1" right_now="$2"
 	test_expect_success "rerere gc with custom expiry ($five_days, $right_now)" '

t/t7900-maintenance.sh

@@ -885,6 +885,14 @@ test_expect_success 'rerere-gc task with --auto honors maintenance.rerere-gc.aut
 	test_expect_rerere_gc ! git -c maintenance.rerere-gc.auto=0 maintenance run --auto --task=rerere-gc
 '
 
+test_expect_success 'rerere-gc task succeeds while MERGE_RR is locked' '
+	test_when_finished "rm -rf .git/rr-cache .git/MERGE_RR.lock" &&
+	mkdir .git/rr-cache &&
+	: >.git/rr-cache/entry &&
+	>.git/MERGE_RR.lock &&
+	test_expect_rerere_gc git maintenance run --task=rerere-gc
+'
+
 test_expect_success '--auto and --schedule incompatible' '
 	test_must_fail git maintenance run --auto --schedule=daily 2>err &&
 	test_grep "cannot be used together" err