From 78de1c6c327b00ec9ed97c478e5f9e56d03c1db8 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Mon, 2 Oct 2023 20:44:26 -0400 Subject: [PATCH 1/5] t7700: split cruft-related tests to t7704 A small handful of the tests in t7700 (the main script for testing functionality of 'git repack') are specifically related to cruft pack operations. Prepare for adding new cruft pack-related tests by moving the existing set into a new test script. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- t/t7700-repack.sh | 121 ------------------------------------- t/t7704-repack-cruft.sh | 130 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 130 insertions(+), 121 deletions(-) create mode 100755 t/t7704-repack-cruft.sh diff --git a/t/t7700-repack.sh b/t/t7700-repack.sh index 27b66807cd..55ee3eb8ae 100755 --- a/t/t7700-repack.sh +++ b/t/t7700-repack.sh @@ -633,125 +633,4 @@ test_expect_success '-n overrides repack.updateServerInfo=true' ' test_server_info_missing ' -test_expect_success '--expire-to stores pruned objects (now)' ' - git init expire-to-now && - ( - cd expire-to-now && - - git branch -M main && - - test_commit base && - - git checkout -b cruft && - test_commit --no-tag cruft && - - git rev-list --objects --no-object-names main..cruft >moved.raw && - sort moved.raw >moved.want && - - git rev-list --all --objects --no-object-names >expect.raw && - sort expect.raw >expect && - - git checkout main && - git branch -D cruft && - git reflog expire --all --expire=all && - - git init --bare expired.git && - git repack -d \ - --cruft --cruft-expiration="now" \ - --expire-to="expired.git/objects/pack/pack" && - - expired="$(ls expired.git/objects/pack/pack-*.idx)" && - test_path_is_file "${expired%.idx}.mtimes" && - - # Since the `--cruft-expiration` is "now", the effective - # behavior is to move _all_ unreachable objects out to - # the location in `--expire-to`. - git show-index <$expired >expired.raw && - cut -d" " -f2 expired.raw | sort >expired.objects && - git rev-list --all --objects --no-object-names \ - >remaining.objects && - - # ...in other words, the combined contents of this - # repository and expired.git should be the same as the - # set of objects we started with. - cat expired.objects remaining.objects | sort >actual && - test_cmp expect actual && - - # The "moved" objects (i.e., those in expired.git) - # should be the same as the cruft objects which were - # expired in the previous step. - test_cmp moved.want expired.objects - ) -' - -test_expect_success '--expire-to stores pruned objects (5.minutes.ago)' ' - git init expire-to-5.minutes.ago && - ( - cd expire-to-5.minutes.ago && - - git branch -M main && - - test_commit base && - - # Create two classes of unreachable objects, one which - # is older than 5 minutes (stale), and another which is - # newer (recent). - for kind in stale recent - do - git checkout -b $kind main && - test_commit --no-tag $kind || return 1 - done && - - git rev-list --objects --no-object-names main..stale >in && - stale="$(git pack-objects $objdir/pack/pack expect.raw && - sort expect.raw >expect && - - # moved.want holds the set of objects we expect to find - # in expired.git - git rev-list --objects --no-object-names main..stale >out && - sort out >moved.want && - - git checkout main && - git branch -D stale recent && - git reflog expire --all --expire=all && - git prune-packed && - - git init --bare expired.git && - git repack -d \ - --cruft --cruft-expiration=5.minutes.ago \ - --expire-to="expired.git/objects/pack/pack" && - - # Some of the remaining objects in this repository are - # unreachable, so use `cat-file --batch-all-objects` - # instead of `rev-list` to get their names - git cat-file --batch-all-objects --batch-check="%(objectname)" \ - >remaining.objects && - sort remaining.objects >actual && - test_cmp expect actual && - - ( - cd expired.git && - - expired="$(ls objects/pack/pack-*.mtimes)" && - test-tool pack-mtimes $(basename $expired) >out && - cut -d" " -f1 out | sort >../moved.got && - - # Ensure that there are as many objects with the - # expected mtime as were moved to expired.git. - # - # In other words, ensure that the recorded - # mtimes of any moved objects was written - # correctly. - grep " $mtime$" out >matching && - test_line_count = $(wc -l <../moved.want) matching - ) && - test_cmp moved.want moved.got - ) -' - test_done diff --git a/t/t7704-repack-cruft.sh b/t/t7704-repack-cruft.sh new file mode 100755 index 0000000000..d91fcf1af1 --- /dev/null +++ b/t/t7704-repack-cruft.sh @@ -0,0 +1,130 @@ +#!/bin/sh + +test_description='git repack works correctly' + +. ./test-lib.sh + +objdir=.git/objects + +test_expect_success '--expire-to stores pruned objects (now)' ' + git init expire-to-now && + ( + cd expire-to-now && + + git branch -M main && + + test_commit base && + + git checkout -b cruft && + test_commit --no-tag cruft && + + git rev-list --objects --no-object-names main..cruft >moved.raw && + sort moved.raw >moved.want && + + git rev-list --all --objects --no-object-names >expect.raw && + sort expect.raw >expect && + + git checkout main && + git branch -D cruft && + git reflog expire --all --expire=all && + + git init --bare expired.git && + git repack -d \ + --cruft --cruft-expiration="now" \ + --expire-to="expired.git/objects/pack/pack" && + + expired="$(ls expired.git/objects/pack/pack-*.idx)" && + test_path_is_file "${expired%.idx}.mtimes" && + + # Since the `--cruft-expiration` is "now", the effective + # behavior is to move _all_ unreachable objects out to + # the location in `--expire-to`. + git show-index <$expired >expired.raw && + cut -d" " -f2 expired.raw | sort >expired.objects && + git rev-list --all --objects --no-object-names \ + >remaining.objects && + + # ...in other words, the combined contents of this + # repository and expired.git should be the same as the + # set of objects we started with. + cat expired.objects remaining.objects | sort >actual && + test_cmp expect actual && + + # The "moved" objects (i.e., those in expired.git) + # should be the same as the cruft objects which were + # expired in the previous step. + test_cmp moved.want expired.objects + ) +' + +test_expect_success '--expire-to stores pruned objects (5.minutes.ago)' ' + git init expire-to-5.minutes.ago && + ( + cd expire-to-5.minutes.ago && + + git branch -M main && + + test_commit base && + + # Create two classes of unreachable objects, one which + # is older than 5 minutes (stale), and another which is + # newer (recent). + for kind in stale recent + do + git checkout -b $kind main && + test_commit --no-tag $kind || return 1 + done && + + git rev-list --objects --no-object-names main..stale >in && + stale="$(git pack-objects $objdir/pack/pack expect.raw && + sort expect.raw >expect && + + # moved.want holds the set of objects we expect to find + # in expired.git + git rev-list --objects --no-object-names main..stale >out && + sort out >moved.want && + + git checkout main && + git branch -D stale recent && + git reflog expire --all --expire=all && + git prune-packed && + + git init --bare expired.git && + git repack -d \ + --cruft --cruft-expiration=5.minutes.ago \ + --expire-to="expired.git/objects/pack/pack" && + + # Some of the remaining objects in this repository are + # unreachable, so use `cat-file --batch-all-objects` + # instead of `rev-list` to get their names + git cat-file --batch-all-objects --batch-check="%(objectname)" \ + >remaining.objects && + sort remaining.objects >actual && + test_cmp expect actual && + + ( + cd expired.git && + + expired="$(ls objects/pack/pack-*.mtimes)" && + test-tool pack-mtimes $(basename $expired) >out && + cut -d" " -f1 out | sort >../moved.got && + + # Ensure that there are as many objects with the + # expected mtime as were moved to expired.git. + # + # In other words, ensure that the recorded + # mtimes of any moved objects was written + # correctly. + grep " $mtime$" out >matching && + test_line_count = $(wc -l <../moved.want) matching + ) && + test_cmp moved.want moved.got + ) +' + +test_done From b5b1f4c0ecf20c069d0301732edfdbfec167aa0c Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Mon, 2 Oct 2023 20:44:29 -0400 Subject: [PATCH 2/5] builtin/repack.c: parse `--max-pack-size` with OPT_MAGNITUDE The repack builtin takes a `--max-pack-size` command-line argument which it uses to feed into any of the pack-objects children that it may spawn when generating a new pack. This option is parsed with OPT_STRING, meaning that we'll accept anything as input, punting on more fine-grained validation until we get down into pack-objects. This is fine, but it's wasteful to spend an entire sub-process just to figure out that one of its option is bogus. Instead, parse the value of `--max-pack-size` with OPT_MAGNITUDE in 'git repack', and then pass the known-good result down to pack-objects. Suggested-by: Junio C Hamano Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- builtin/repack.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/builtin/repack.c b/builtin/repack.c index 529e13120d..8a5bbb9cba 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -51,7 +51,7 @@ struct pack_objects_args { const char *window_memory; const char *depth; const char *threads; - const char *max_pack_size; + unsigned long max_pack_size; int no_reuse_delta; int no_reuse_object; int quiet; @@ -242,7 +242,7 @@ static void prepare_pack_objects(struct child_process *cmd, if (args->threads) strvec_pushf(&cmd->args, "--threads=%s", args->threads); if (args->max_pack_size) - strvec_pushf(&cmd->args, "--max-pack-size=%s", args->max_pack_size); + strvec_pushf(&cmd->args, "--max-pack-size=%lu", args->max_pack_size); if (args->no_reuse_delta) strvec_pushf(&cmd->args, "--no-reuse-delta"); if (args->no_reuse_object) @@ -946,7 +946,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) N_("limits the maximum delta depth")), OPT_STRING(0, "threads", &po_args.threads, N_("n"), N_("limits the maximum number of threads")), - OPT_STRING(0, "max-pack-size", &po_args.max_pack_size, N_("bytes"), + OPT_MAGNITUDE(0, "max-pack-size", &po_args.max_pack_size, N_("maximum size of each packfile")), OPT_BOOL(0, "pack-kept-objects", &pack_kept_objects, N_("repack objects in packs marked with .keep")), From 37dc6d81042ac41437163264e7a29d3bf50c8d90 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Mon, 2 Oct 2023 20:44:32 -0400 Subject: [PATCH 3/5] builtin/repack.c: implement support for `--max-cruft-size` Cruft packs are an alternative mechanism for storing a collection of unreachable objects whose mtimes are recent enough to avoid being pruned out of the repository. When cruft packs were first introduced back in b757353676 (builtin/pack-objects.c: --cruft without expiration, 2022-05-20) and a7d493833f (builtin/pack-objects.c: --cruft with expiration, 2022-05-20), the recommended workflow consisted of: - Repacking periodically, either by packing anything loose in the repository (via `git repack -d`) or producing a geometric sequence of packs (via `git repack --geometric= -d`). - Every so often, splitting the repository into two packs, one cruft to store the unreachable objects, and another non-cruft pack to store the reachable objects. Repositories may (out of band with the above) choose periodically to prune out some unreachable objects which have aged out of the grace period by generating a pack with `--cruft-expiration=`. This allowed repositories to maintain relatively few packs on average, and quarantine unreachable objects together in a cruft pack, avoiding the pitfalls of holding unreachable objects as loose while they age out (for more, see some of the details in 3d89a8c118 (Documentation/technical: add cruft-packs.txt, 2022-05-20)). This all works, but can be costly from an I/O-perspective when frequently repacking a repository that has many unreachable objects. This problem is exacerbated when those unreachable objects are rarely (if every) pruned. Since there is at most one cruft pack in the above scheme, each time we update the cruft pack it must be rewritten from scratch. Because much of the pack is reused, this is a relatively inexpensive operation from a CPU-perspective, but is very costly in terms of I/O since we end up rewriting basically the same pack (plus any new unreachable objects that have entered the repository since the last time a cruft pack was generated). At the time, we decided against implementing more robust support for multiple cruft packs. This patch implements that support which we were lacking. Introduce a new option `--max-cruft-size` which allows repositories to accumulate cruft packs up to a given size, after which point a new generation of cruft packs can accumulate until it reaches the maximum size, and so on. To generate a new cruft pack, the process works like so: - Sort a list of any existing cruft packs in ascending order of pack size. - Starting from the beginning of the list, group cruft packs together while the accumulated size is smaller than the maximum specified pack size. - Combine the objects in these cruft packs together into a new cruft pack, along with any other unreachable objects which have since entered the repository. Once a cruft pack grows beyond the size specified via `--max-cruft-size` the pack is effectively frozen. This limits the I/O churn up to a quadratic function of the value specified by the `--max-cruft-size` option, instead of behaving quadratically in the number of total unreachable objects. When pruning unreachable objects, we bypass the new code paths which combine small cruft packs together, and instead start from scratch, passing in the appropriate `--max-pack-size` down to `pack-objects`, putting it in charge of keeping the resulting set of cruft packs sized correctly. This may seem like further I/O churn, but in practice it isn't so bad. We could prune old cruft packs for whom all or most objects are removed, and then generate a new cruft pack with just the remaining set of objects. But this additional complexity buys us relatively little, because most objects end up being pruned anyway, so the I/O churn is well contained. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- Documentation/config/gc.txt | 6 + Documentation/git-gc.txt | 7 + Documentation/git-repack.txt | 11 ++ builtin/gc.c | 7 + builtin/repack.c | 134 +++++++++++++++++-- t/t6500-gc.sh | 27 ++++ t/t7704-repack-cruft.sh | 245 +++++++++++++++++++++++++++++++++++ 7 files changed, 426 insertions(+), 11 deletions(-) diff --git a/Documentation/config/gc.txt b/Documentation/config/gc.txt index ca47eb2008..83ebc2de55 100644 --- a/Documentation/config/gc.txt +++ b/Documentation/config/gc.txt @@ -86,6 +86,12 @@ gc.cruftPacks:: linkgit:git-repack[1]) instead of as loose objects. The default is `true`. +gc.maxCruftSize:: + Limit the size of new cruft packs when repacking. When + specified in addition to `--max-cruft-size`, the command line + option takes priority. See the `--max-cruft-size` option of + linkgit:git-repack[1]. + gc.pruneExpire:: When 'git gc' is run, it will call 'prune --expire 2.weeks.ago' (and 'repack --cruft --cruft-expiration 2.weeks.ago' if using diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt index 90806fd26a..b5561c458a 100644 --- a/Documentation/git-gc.txt +++ b/Documentation/git-gc.txt @@ -59,6 +59,13 @@ be performed as well. cruft pack instead of storing them as loose objects. `--cruft` is on by default. +--max-cruft-size=:: + When packing unreachable objects into a cruft pack, limit the + size of new cruft packs to be at most `` bytes. Overrides any + value specified via the `gc.maxCruftSize` configuration. See + the `--max-cruft-size` option of linkgit:git-repack[1] for + more. + --prune=:: Prune loose objects older than date (default is 2 weeks ago, overridable by the config variable `gc.pruneExpire`). diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt index 4017157949..fbfc72e1b2 100644 --- a/Documentation/git-repack.txt +++ b/Documentation/git-repack.txt @@ -74,6 +74,17 @@ to the new separate pack will be written. immediately instead of waiting for the next `git gc` invocation. Only useful with `--cruft -d`. +--max-cruft-size=:: + Repack cruft objects into packs as large as `` bytes before + creating new packs. As long as there are enough cruft packs + smaller than ``, repacking will cause a new cruft pack to + be created containing objects from any combined cruft packs, + along with any new unreachable objects. Cruft packs larger than + `` will not be modified. When the new cruft pack is larger + than `` bytes, it will be split into multiple packs, all of + which are guaranteed to be at most `` bytes in size. Only + useful with `--cruft -d`. + --expire-to=:: Write a cruft pack containing pruned objects (if any) to the directory ``. This option is useful for keeping a copy of diff --git a/builtin/gc.c b/builtin/gc.c index 00192ae5d3..c97c9fb046 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -52,6 +52,7 @@ static const char * const builtin_gc_usage[] = { static int pack_refs = 1; static int prune_reflogs = 1; static int cruft_packs = 1; +static unsigned long max_cruft_size; static int aggressive_depth = 50; static int aggressive_window = 250; static int gc_auto_threshold = 6700; @@ -163,6 +164,7 @@ static void gc_config(void) git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit); git_config_get_bool("gc.autodetach", &detach_auto); git_config_get_bool("gc.cruftpacks", &cruft_packs); + git_config_get_ulong("gc.maxcruftsize", &max_cruft_size); git_config_get_expiry("gc.pruneexpire", &prune_expire); git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire); git_config_get_expiry("gc.logexpiry", &gc_log_expire); @@ -347,6 +349,9 @@ static void add_repack_all_option(struct string_list *keep_pack) strvec_push(&repack, "--cruft"); if (prune_expire) strvec_pushf(&repack, "--cruft-expiration=%s", prune_expire); + if (max_cruft_size) + strvec_pushf(&repack, "--max-cruft-size=%lu", + max_cruft_size); } else { strvec_push(&repack, "-A"); if (prune_expire) @@ -575,6 +580,8 @@ int cmd_gc(int argc, const char **argv, const char *prefix) N_("prune unreferenced objects"), PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire }, OPT_BOOL(0, "cruft", &cruft_packs, N_("pack unreferenced objects separately")), + OPT_MAGNITUDE(0, "max-cruft-size", &max_cruft_size, + N_("with --cruft, limit the size of new cruft packs")), OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")), OPT_BOOL_F(0, "auto", &auto_gc, N_("enable auto-gc mode"), PARSE_OPT_NOCOMPLETE), diff --git a/builtin/repack.c b/builtin/repack.c index 8a5bbb9cba..04770b15fe 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -27,6 +27,7 @@ #define PACK_CRUFT 4 #define DELETE_PACK 1 +#define RETAIN_PACK 2 static int pack_everything; static int delta_base_offset = 1; @@ -116,11 +117,26 @@ static void pack_mark_for_deletion(struct string_list_item *item) item->util = (void*)((uintptr_t)item->util | DELETE_PACK); } +static void pack_unmark_for_deletion(struct string_list_item *item) +{ + item->util = (void*)((uintptr_t)item->util & ~DELETE_PACK); +} + static int pack_is_marked_for_deletion(struct string_list_item *item) { return (uintptr_t)item->util & DELETE_PACK; } +static void pack_mark_retained(struct string_list_item *item) +{ + item->util = (void*)((uintptr_t)item->util | RETAIN_PACK); +} + +static int pack_is_retained(struct string_list_item *item) +{ + return (uintptr_t)item->util & RETAIN_PACK; +} + static void mark_packs_for_deletion_1(struct string_list *names, struct string_list *list) { @@ -133,17 +149,39 @@ static void mark_packs_for_deletion_1(struct string_list *names, if (len < hexsz) continue; sha1 = item->string + len - hexsz; - /* - * Mark this pack for deletion, which ensures that this - * pack won't be included in a MIDX (if `--write-midx` - * was given) and that we will actually delete this pack - * (if `-d` was given). - */ - if (!string_list_has_string(names, sha1)) + + if (pack_is_retained(item)) { + pack_unmark_for_deletion(item); + } else if (!string_list_has_string(names, sha1)) { + /* + * Mark this pack for deletion, which ensures + * that this pack won't be included in a MIDX + * (if `--write-midx` was given) and that we + * will actually delete this pack (if `-d` was + * given). + */ pack_mark_for_deletion(item); + } } } +static void retain_cruft_pack(struct existing_packs *existing, + struct packed_git *cruft) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list_item *item; + + strbuf_addstr(&buf, pack_basename(cruft)); + strbuf_strip_suffix(&buf, ".pack"); + + item = string_list_lookup(&existing->cruft_packs, buf.buf); + if (!item) + BUG("could not find cruft pack '%s'", pack_basename(cruft)); + + pack_mark_retained(item); + strbuf_release(&buf); +} + static void mark_packs_for_deletion(struct existing_packs *existing, struct string_list *names) @@ -225,6 +263,8 @@ static void collect_pack_filenames(struct existing_packs *existing, } string_list_sort(&existing->kept_packs); + string_list_sort(&existing->non_kept_packs); + string_list_sort(&existing->cruft_packs); strbuf_release(&buf); } @@ -806,6 +846,72 @@ static void remove_redundant_bitmaps(struct string_list *include, strbuf_release(&path); } +static int existing_cruft_pack_cmp(const void *va, const void *vb) +{ + struct packed_git *a = *(struct packed_git **)va; + struct packed_git *b = *(struct packed_git **)vb; + + if (a->pack_size < b->pack_size) + return -1; + if (a->pack_size > b->pack_size) + return 1; + return 0; +} + +static void collapse_small_cruft_packs(FILE *in, size_t max_size, + struct existing_packs *existing) +{ + struct packed_git **existing_cruft, *p; + struct strbuf buf = STRBUF_INIT; + size_t total_size = 0; + size_t existing_cruft_nr = 0; + size_t i; + + ALLOC_ARRAY(existing_cruft, existing->cruft_packs.nr); + + for (p = get_all_packs(the_repository); p; p = p->next) { + if (!(p->is_cruft && p->pack_local)) + continue; + + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + + if (!string_list_has_string(&existing->cruft_packs, buf.buf)) + continue; + + if (existing_cruft_nr >= existing->cruft_packs.nr) + BUG("too many cruft packs (found %"PRIuMAX", but knew " + "of %"PRIuMAX")", + (uintmax_t)existing_cruft_nr + 1, + (uintmax_t)existing->cruft_packs.nr); + existing_cruft[existing_cruft_nr++] = p; + } + + QSORT(existing_cruft, existing_cruft_nr, existing_cruft_pack_cmp); + + for (i = 0; i < existing_cruft_nr; i++) { + size_t proposed; + + p = existing_cruft[i]; + proposed = st_add(total_size, p->pack_size); + + if (proposed <= max_size) { + total_size = proposed; + fprintf(in, "-%s\n", pack_basename(p)); + } else { + retain_cruft_pack(existing, p); + fprintf(in, "%s\n", pack_basename(p)); + } + } + + for (i = 0; i < existing->non_kept_packs.nr; i++) + fprintf(in, "-%s.pack\n", + existing->non_kept_packs.items[i].string); + + strbuf_release(&buf); +} + static int write_cruft_pack(const struct pack_objects_args *args, const char *destination, const char *pack_prefix, @@ -853,10 +959,14 @@ static int write_cruft_pack(const struct pack_objects_args *args, in = xfdopen(cmd.in, "w"); for_each_string_list_item(item, names) fprintf(in, "%s-%s.pack\n", pack_prefix, item->string); - for_each_string_list_item(item, &existing->non_kept_packs) - fprintf(in, "-%s.pack\n", item->string); - for_each_string_list_item(item, &existing->cruft_packs) - fprintf(in, "-%s.pack\n", item->string); + if (args->max_pack_size && !cruft_expiration) { + collapse_small_cruft_packs(in, args->max_pack_size, existing); + } else { + for_each_string_list_item(item, &existing->non_kept_packs) + fprintf(in, "-%s.pack\n", item->string); + for_each_string_list_item(item, &existing->cruft_packs) + fprintf(in, "-%s.pack\n", item->string); + } for_each_string_list_item(item, &existing->kept_packs) fprintf(in, "%s.pack\n", item->string); fclose(in); @@ -919,6 +1029,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix) PACK_CRUFT), OPT_STRING(0, "cruft-expiration", &cruft_expiration, N_("approxidate"), N_("with --cruft, expire objects older than this")), + OPT_MAGNITUDE(0, "max-cruft-size", &cruft_po_args.max_pack_size, + N_("with --cruft, limit the size of new cruft packs")), OPT_BOOL('d', NULL, &delete_redundant, N_("remove redundant packs, and run git-prune-packed")), OPT_BOOL('f', NULL, &po_args.no_reuse_delta, diff --git a/t/t6500-gc.sh b/t/t6500-gc.sh index 69509d0c11..0d6b5c3b27 100755 --- a/t/t6500-gc.sh +++ b/t/t6500-gc.sh @@ -303,6 +303,33 @@ test_expect_success 'gc.bigPackThreshold ignores cruft packs' ' ) ' +cruft_max_size_opts="git repack -d -l --cruft --cruft-expiration=2.weeks.ago" + +test_expect_success 'setup for --max-cruft-size tests' ' + git init cruft--max-size && + ( + cd cruft--max-size && + prepare_cruft_history + ) +' + +test_expect_success '--max-cruft-size sets appropriate repack options' ' + GIT_TRACE2_EVENT=$(pwd)/trace2.txt git -C cruft--max-size \ + gc --cruft --max-cruft-size=1M && + test_subcommand $cruft_max_size_opts --max-cruft-size=1048576 blob && + git hash-object -w -t blob blob && + rm blob +} + +pack_random_blob () { + generate_random_blob "$@" && + git repack -d -q >/dev/null +} + +generate_cruft_pack () { + pack_random_blob "$@" >/dev/null && + + ls $packdir/pack-*.pack | xargs -n 1 basename >in && + pack="$(git pack-objects --cruft $packdir/pack foo.objects && + test-tool pack-mtimes $(basename "$cruft_bar") >bar.objects && + + grep "^$foo" foo.objects && + test_line_count = 1 foo.objects && + grep "^$bar" bar.objects && + test_line_count = 1 bar.objects + ) +' + +test_expect_success '--max-cruft-size combines existing packs when below threshold' ' + git init max-cruft-size-small && + ( + cd max-cruft-size-small && + test_commit base && + + foo="$(pack_random_blob foo $((1*1024*1024)))" && + git repack --cruft -d && + + bar="$(pack_random_blob bar $((1*1024*1024)))" && + git repack --cruft -d --max-cruft-size=10M && + + cruft=$(ls $packdir/pack-*.mtimes) && + test-tool pack-mtimes $(basename "$cruft") >cruft.objects && + + grep "^$foo" cruft.objects && + grep "^$bar" cruft.objects && + test_line_count = 2 cruft.objects + ) +' + +test_expect_success '--max-cruft-size combines smaller packs first' ' + git init max-cruft-size-consume-small && + ( + cd max-cruft-size-consume-small && + + test_commit base && + git repack -ad && + + cruft_foo="$(generate_cruft_pack foo 524288)" && # 0.5 MiB + cruft_bar="$(generate_cruft_pack bar 524288)" && # 0.5 MiB + cruft_baz="$(generate_cruft_pack baz 1048576)" && # 1.0 MiB + cruft_quux="$(generate_cruft_pack quux 1572864)" && # 1.5 MiB + + test-tool pack-mtimes "$(basename $cruft_foo)" >expect.raw && + test-tool pack-mtimes "$(basename $cruft_bar)" >>expect.raw && + sort expect.raw >expect.objects && + + # repacking with `--max-cruft-size=2M` should combine + # both 0.5 MiB packs together, instead of, say, one of + # the 0.5 MiB packs with the 1.0 MiB pack + ls $packdir/pack-*.mtimes | sort >cruft.before && + git repack -d --cruft --max-cruft-size=2M && + ls $packdir/pack-*.mtimes | sort >cruft.after && + + comm -13 cruft.before cruft.after >cruft.new && + comm -23 cruft.before cruft.after >cruft.removed && + + test_line_count = 1 cruft.new && + test_line_count = 2 cruft.removed && + + # the two smaller packs should be rolled up first + printf "%s\n" $cruft_foo $cruft_bar | sort >expect.removed && + test_cmp expect.removed cruft.removed && + + # ...and contain the set of objects rolled up + test-tool pack-mtimes "$(basename $(cat cruft.new))" >actual.raw && + sort actual.raw >actual.objects && + + test_cmp expect.objects actual.objects + ) +' + +test_expect_success 'setup --max-cruft-size with freshened objects' ' + git init max-cruft-size-freshen && + ( + cd max-cruft-size-freshen && + + test_commit base && + git repack -ad && + + foo="$(generate_random_blob foo 64)" && + test-tool chmtime --get -10000 \ + "$objdir/$(test_oid_to_path "$foo")" >foo.mtime && + + git repack --cruft -d && + + cruft="$(ls $packdir/pack-*.mtimes)" && + test-tool pack-mtimes "$(basename $cruft)" >actual && + echo "$foo $(cat foo.mtime)" >expect && + test_cmp expect actual + ) +' + +test_expect_success '--max-cruft-size with freshened objects (loose)' ' + ( + cd max-cruft-size-freshen && + + # regenerate the object, setting its mtime to be more recent + foo="$(generate_random_blob foo 64)" && + test-tool chmtime --get -100 \ + "$objdir/$(test_oid_to_path "$foo")" >foo.mtime && + + git repack --cruft -d && + + cruft="$(ls $packdir/pack-*.mtimes)" && + test-tool pack-mtimes "$(basename $cruft)" >actual && + echo "$foo $(cat foo.mtime)" >expect && + test_cmp expect actual + ) +' + +test_expect_success '--max-cruft-size with freshened objects (packed)' ' + ( + cd max-cruft-size-freshen && + + # regenerate the object and store it in a packfile, + # setting its mtime to be more recent + # + # store it alongside another cruft object so that we + # do not create an identical copy of the existing + # cruft pack (which contains $foo). + foo="$(generate_random_blob foo 64)" && + bar="$(generate_random_blob bar 64)" && + foo_pack="$(printf "%s\n" $foo $bar | git pack-objects $packdir/pack)" && + git prune-packed && + + test-tool chmtime --get -10 \ + "$packdir/pack-$foo_pack.pack" >foo.mtime && + + git repack --cruft -d && + + cruft="$(ls $packdir/pack-*.mtimes)" && + test-tool pack-mtimes "$(basename $cruft)" >actual && + echo "$foo $(cat foo.mtime)" >expect.raw && + echo "$bar $(cat foo.mtime)" >>expect.raw && + sort expect.raw >expect && + test_cmp expect actual + ) +' + +test_expect_success '--max-cruft-size with pruning' ' + git init max-cruft-size-prune && + ( + cd max-cruft-size-prune && + + test_commit base && + foo="$(generate_random_blob foo $((1024*1024)))" && + bar="$(generate_random_blob bar $((1024*1024)))" && + baz="$(generate_random_blob baz $((1024*1024)))" && + + test-tool chmtime -10000 "$objdir/$(test_oid_to_path "$foo")" && + + git repack -d --cruft --max-cruft-size=1M && + + # backdate the mtimes of all cruft packs to validate + # that they were rewritten as a result of pruning + ls $packdir/pack-*.mtimes | sort >cruft.before && + for cruft in $(cat cruft.before) + do + mtime="$(test-tool chmtime --get -10000 "$cruft")" && + echo $cruft $mtime >>mtimes || return 1 + done && + + # repack (and prune) with a --max-cruft-size to ensure + # that we appropriately split the resulting set of packs + git repack -d --cruft --max-cruft-size=1M \ + --cruft-expiration=10.seconds.ago && + ls $packdir/pack-*.mtimes | sort >cruft.after && + + for cruft in $(cat cruft.after) + do + old_mtime="$(grep $cruft mtimes | cut -d" " -f2)" && + new_mtime="$(test-tool chmtime --get $cruft)" && + test $old_mtime -lt $new_mtime || return 1 + done && + + test_line_count = 3 cruft.before && + test_line_count = 2 cruft.after && + test_must_fail git cat-file -e $foo && + git cat-file -e $bar && + git cat-file -e $baz + ) +' + +test_expect_success '--max-cruft-size ignores non-local packs' ' + repo="max-cruft-size-non-local" && + git init $repo && + ( + cd $repo && + test_commit base && + generate_random_blob foo 64 && + git repack --cruft -d + ) && + + git clone --reference=$repo $repo $repo-alt && + ( + cd $repo-alt && + + test_commit other && + generate_random_blob bar 64 && + + # ensure that we do not attempt to pick up packs from + # the non-alternated repository, which would result in a + # crash + git repack --cruft --max-cruft-size=1M -d + ) +' + test_done From 3c1e2c2113842b8462803ef8c9aca596eacfd3af Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Tue, 3 Oct 2023 17:54:19 -0400 Subject: [PATCH 4/5] builtin/repack.c: avoid making cruft packs preferred When doing a `--geometric` repack, we make sure that the preferred pack (if writing a MIDX) is the largest pack that we *didn't* repack. That has the effect of keeping the preferred pack in sync with the pack containing a majority of the repository's reachable objects. But if the repository happens to double in size, we'll repack everything. Here we don't specify any `--preferred-pack`, and instead let the MIDX code choose. In the past, that worked fine, since there would only be one pack to choose from: the one we just wrote. But it's no longer necessarily the case that there is one pack to choose from. It's possible that the repository also has a cruft pack, too. If the cruft pack happens to come earlier in lexical order (and has an earlier mtime than any non-cruft pack), we'll pick that pack as preferred. This makes it impossible to reuse chunks of the reachable pack verbatim from pack-objects, so is sub-optimal. Luckily, this is a somewhat rare circumstance to be in, since we would have to repack the entire repository during a `--geometric` repack, and the cruft pack would have to sort ahead of the pack we just created. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- builtin/repack.c | 47 ++++++++++++++++++++++++++++++++++++++++- t/t7704-repack-cruft.sh | 39 ++++++++++++++++++++++++++++++++++ 2 files changed, 85 insertions(+), 1 deletion(-) diff --git a/builtin/repack.c b/builtin/repack.c index 04770b15fe..a1a893d952 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -355,6 +355,18 @@ static struct generated_pack_data *populate_pack_exts(const char *name) return data; } +static int has_pack_ext(const struct generated_pack_data *data, + const char *ext) +{ + int i; + for (i = 0; i < ARRAY_SIZE(exts); i++) { + if (strcmp(exts[i].name, ext)) + continue; + return !!data->tempfiles[i]; + } + BUG("unknown pack extension: '%s'", ext); +} + static void repack_promisor_objects(const struct pack_objects_args *args, struct string_list *names) { @@ -772,6 +784,7 @@ static void midx_included_packs(struct string_list *include, static int write_midx_included_packs(struct string_list *include, struct pack_geometry *geometry, + struct string_list *names, const char *refs_snapshot, int show_progress, int write_bitmaps) { @@ -801,6 +814,38 @@ static int write_midx_included_packs(struct string_list *include, if (preferred) strvec_pushf(&cmd.args, "--preferred-pack=%s", pack_basename(preferred)); + else if (names->nr) { + /* The largest pack was repacked, meaning that either + * one or two packs exist depending on whether the + * repository has a cruft pack or not. + * + * Select the non-cruft one as preferred to encourage + * pack-reuse among packs containing reachable objects + * over unreachable ones. + * + * (Note we could write multiple packs here if + * `--max-pack-size` was given, but any one of them + * will suffice, so pick the first one.) + */ + for_each_string_list_item(item, names) { + struct generated_pack_data *data = item->util; + if (has_pack_ext(data, ".mtimes")) + continue; + + strvec_pushf(&cmd.args, "--preferred-pack=pack-%s.pack", + item->string); + break; + } + } else { + /* + * No packs were kept, and no packs were written. The + * only thing remaining are .keep packs (unless + * --pack-kept-objects was given). + * + * Set the `--preferred-pack` arbitrarily here. + */ + ; + } if (refs_snapshot) strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot); @@ -1360,7 +1405,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) struct string_list include = STRING_LIST_INIT_NODUP; midx_included_packs(&include, &existing, &names, &geometry); - ret = write_midx_included_packs(&include, &geometry, + ret = write_midx_included_packs(&include, &geometry, &names, refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL, show_progress, write_bitmaps > 0); diff --git a/t/t7704-repack-cruft.sh b/t/t7704-repack-cruft.sh index dc86ca8269..be3735dff0 100755 --- a/t/t7704-repack-cruft.sh +++ b/t/t7704-repack-cruft.sh @@ -372,4 +372,43 @@ test_expect_success '--max-cruft-size ignores non-local packs' ' ) ' +test_expect_success 'reachable packs are preferred over cruft ones' ' + repo="cruft-preferred-packs" && + git init "$repo" && + ( + cd "$repo" && + + # This test needs to exercise careful control over when a MIDX + # is and is not written. Unset the corresponding TEST variable + # accordingly. + sane_unset GIT_TEST_MULTI_PACK_INDEX && + + test_commit base && + test_commit --no-tag cruft && + + non_cruft="$(echo base | git pack-objects --revs $packdir/pack)" && + # Write a cruft pack which both (a) sorts ahead of the non-cruft + # pack in lexical order, and (b) has an older mtime to appease + # the MIDX preferred pack selection routine. + cruft="$(echo pack-$non_cruft.pack | git pack-objects --cruft $packdir/pack-A)" && + test-tool chmtime -1000 $packdir/pack-A-$cruft.pack && + + test_commit other && + git repack -d && + + git repack --geometric 2 -d --write-midx --write-bitmap-index && + + # After repacking, there are two packs left: one reachable one + # (which is the result of combining both of the existing two + # non-cruft packs), and one cruft pack. + find .git/objects/pack -type f -name "*.pack" >packs && + test_line_count = 2 packs && + + # Make sure that the pack we just wrote is marked as preferred, + # not the cruft one. + pack="$(test-tool read-midx --preferred-pack $objdir)" && + test_path_is_missing "$packdir/$(basename "$pack" ".idx").mtimes" + ) +' + test_done From c1b754d0597be83439ecc8de2a59a90f35cd4040 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sat, 7 Oct 2023 13:20:31 -0400 Subject: [PATCH 5/5] repack: free existing_cruft array after use We allocate an array of packed_git pointers so that we can sort the list of cruft packs, but we never free the array, causing a small leak. Note that we don't need to free the packed_git structs themselves; they're owned by the repository object. Signed-off-by: Jeff King Acked-by: Taylor Blau Signed-off-by: Junio C Hamano --- builtin/repack.c | 1 + 1 file changed, 1 insertion(+) diff --git a/builtin/repack.c b/builtin/repack.c index a1a893d952..69e8f302c0 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -955,6 +955,7 @@ static void collapse_small_cruft_packs(FILE *in, size_t max_size, existing->non_kept_packs.items[i].string); strbuf_release(&buf); + free(existing_cruft); } static int write_cruft_pack(const struct pack_objects_args *args,