From 4d35bb2abaeff3965024b0f1599641641bcb17a6 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:17:54 +0200 Subject: [PATCH 01/11] reftable: consistently refer to `reftable_write_options` as `opts` Throughout the reftable library the `reftable_write_options` are sometimes referred to as `cfg` and sometimes as `opts`. Unify these to consistently use `opts` to avoid confusion. While at it, touch up the coding style a bit by removing unneeded braces around one-line statements and newlines between variable declarations. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/dump.c | 4 +- reftable/reftable-stack.h | 2 +- reftable/stack.c | 41 +++++++------- reftable/stack.h | 2 +- reftable/stack_test.c | 114 +++++++++++++++++--------------------- 5 files changed, 74 insertions(+), 89 deletions(-) diff --git a/reftable/dump.c b/reftable/dump.c index 26e0393c7d..9c770a10cc 100644 --- a/reftable/dump.c +++ b/reftable/dump.c @@ -27,9 +27,9 @@ https://developers.google.com/open-source/licenses/bsd static int compact_stack(const char *stackdir) { struct reftable_stack *stack = NULL; - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; - int err = reftable_new_stack(&stack, stackdir, cfg); + int err = reftable_new_stack(&stack, stackdir, opts); if (err < 0) goto done; diff --git a/reftable/reftable-stack.h b/reftable/reftable-stack.h index 1b602dda58..9c8e4eef49 100644 --- a/reftable/reftable-stack.h +++ b/reftable/reftable-stack.h @@ -29,7 +29,7 @@ struct reftable_stack; * stored in 'dir'. Typically, this should be .git/reftables. */ int reftable_new_stack(struct reftable_stack **dest, const char *dir, - struct reftable_write_options config); + struct reftable_write_options opts); /* returns the update_index at which a next table should be written. */ uint64_t reftable_stack_next_update_index(struct reftable_stack *st); diff --git a/reftable/stack.c b/reftable/stack.c index a59ebe038d..54e7473f3a 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -54,15 +54,14 @@ static int reftable_fd_flush(void *arg) } int reftable_new_stack(struct reftable_stack **dest, const char *dir, - struct reftable_write_options config) + struct reftable_write_options opts) { struct reftable_stack *p = reftable_calloc(1, sizeof(*p)); struct strbuf list_file_name = STRBUF_INIT; int err = 0; - if (config.hash_id == 0) { - config.hash_id = GIT_SHA1_FORMAT_ID; - } + if (opts.hash_id == 0) + opts.hash_id = GIT_SHA1_FORMAT_ID; *dest = NULL; @@ -73,7 +72,7 @@ int reftable_new_stack(struct reftable_stack **dest, const char *dir, p->list_file = strbuf_detach(&list_file_name, NULL); p->list_fd = -1; p->reftable_dir = xstrdup(dir); - p->config = config; + p->opts = opts; err = reftable_stack_reload_maybe_reuse(p, 1); if (err < 0) { @@ -255,7 +254,7 @@ static int reftable_stack_reload_once(struct reftable_stack *st, char **names, /* success! */ err = reftable_new_merged_table(&new_merged, new_tables, - new_readers_len, st->config.hash_id); + new_readers_len, st->opts.hash_id); if (err < 0) goto done; @@ -578,8 +577,8 @@ static int reftable_stack_init_addition(struct reftable_addition *add, } goto done; } - if (st->config.default_permissions) { - if (chmod(add->lock_file->filename.buf, st->config.default_permissions) < 0) { + if (st->opts.default_permissions) { + if (chmod(add->lock_file->filename.buf, st->opts.default_permissions) < 0) { err = REFTABLE_IO_ERROR; goto done; } @@ -678,7 +677,7 @@ int reftable_addition_commit(struct reftable_addition *add) if (err) goto done; - if (!add->stack->config.disable_auto_compact) { + if (!add->stack->opts.disable_auto_compact) { /* * Auto-compact the stack to keep the number of tables in * control. It is possible that a concurrent writer is already @@ -756,9 +755,9 @@ int reftable_addition_add(struct reftable_addition *add, err = REFTABLE_IO_ERROR; goto done; } - if (add->stack->config.default_permissions) { + if (add->stack->opts.default_permissions) { if (chmod(get_tempfile_path(tab_file), - add->stack->config.default_permissions)) { + add->stack->opts.default_permissions)) { err = REFTABLE_IO_ERROR; goto done; } @@ -766,7 +765,7 @@ int reftable_addition_add(struct reftable_addition *add, tab_fd = get_tempfile_fd(tab_file); wr = reftable_new_writer(reftable_fd_write, reftable_fd_flush, &tab_fd, - &add->stack->config); + &add->stack->opts); err = write_table(wr, arg); if (err < 0) goto done; @@ -849,14 +848,14 @@ static int stack_compact_locked(struct reftable_stack *st, } tab_fd = get_tempfile_fd(tab_file); - if (st->config.default_permissions && - chmod(get_tempfile_path(tab_file), st->config.default_permissions) < 0) { + if (st->opts.default_permissions && + chmod(get_tempfile_path(tab_file), st->opts.default_permissions) < 0) { err = REFTABLE_IO_ERROR; goto done; } wr = reftable_new_writer(reftable_fd_write, reftable_fd_flush, - &tab_fd, &st->config); + &tab_fd, &st->opts); err = stack_write_compact(st, wr, first, last, config); if (err < 0) goto done; @@ -904,7 +903,7 @@ static int stack_write_compact(struct reftable_stack *st, st->readers[last]->max_update_index); err = reftable_new_merged_table(&mt, subtabs, subtabs_len, - st->config.hash_id); + st->opts.hash_id); if (err < 0) { reftable_free(subtabs); goto done; @@ -1094,9 +1093,9 @@ static int stack_compact_range(struct reftable_stack *st, goto done; } - if (st->config.default_permissions) { + if (st->opts.default_permissions) { if (chmod(get_lock_file_path(&tables_list_lock), - st->config.default_permissions) < 0) { + st->opts.default_permissions) < 0) { err = REFTABLE_IO_ERROR; goto done; } @@ -1286,7 +1285,7 @@ static uint64_t *stack_table_sizes_for_compaction(struct reftable_stack *st) { uint64_t *sizes = reftable_calloc(st->merged->stack_len, sizeof(*sizes)); - int version = (st->config.hash_id == GIT_SHA1_FORMAT_ID) ? 1 : 2; + int version = (st->opts.hash_id == GIT_SHA1_FORMAT_ID) ? 1 : 2; int overhead = header_size(version) - 1; int i = 0; for (i = 0; i < st->merged->stack_len; i++) { @@ -1435,11 +1434,11 @@ done: int reftable_stack_print_directory(const char *stackdir, uint32_t hash_id) { struct reftable_stack *stack = NULL; - struct reftable_write_options cfg = { .hash_id = hash_id }; + struct reftable_write_options opts = { .hash_id = hash_id }; struct reftable_merged_table *merged = NULL; struct reftable_table table = { NULL }; - int err = reftable_new_stack(&stack, stackdir, cfg); + int err = reftable_new_stack(&stack, stackdir, opts); if (err < 0) goto done; diff --git a/reftable/stack.h b/reftable/stack.h index d43efa4760..97d7ebc043 100644 --- a/reftable/stack.h +++ b/reftable/stack.h @@ -20,7 +20,7 @@ struct reftable_stack { char *reftable_dir; - struct reftable_write_options config; + struct reftable_write_options opts; struct reftable_reader **readers; size_t readers_len; diff --git a/reftable/stack_test.c b/reftable/stack_test.c index 7889f818d1..e17ad4dc62 100644 --- a/reftable/stack_test.c +++ b/reftable/stack_test.c @@ -150,7 +150,7 @@ static void test_reftable_stack_add_one(void) char *dir = get_tmp_dir(__LINE__); struct strbuf scratch = STRBUF_INIT; int mask = umask(002); - struct reftable_write_options cfg = { + struct reftable_write_options opts = { .default_permissions = 0660, }; struct reftable_stack *st = NULL; @@ -163,7 +163,7 @@ static void test_reftable_stack_add_one(void) }; struct reftable_ref_record dest = { NULL }; struct stat stat_result = { 0 }; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); err = reftable_stack_add(st, &write_test_ref, &ref); @@ -186,7 +186,7 @@ static void test_reftable_stack_add_one(void) strbuf_addstr(&scratch, "/tables.list"); err = stat(scratch.buf, &stat_result); EXPECT(!err); - EXPECT((stat_result.st_mode & 0777) == cfg.default_permissions); + EXPECT((stat_result.st_mode & 0777) == opts.default_permissions); strbuf_reset(&scratch); strbuf_addstr(&scratch, dir); @@ -195,7 +195,7 @@ static void test_reftable_stack_add_one(void) strbuf_addstr(&scratch, st->readers[0]->name); err = stat(scratch.buf, &stat_result); EXPECT(!err); - EXPECT((stat_result.st_mode & 0777) == cfg.default_permissions); + EXPECT((stat_result.st_mode & 0777) == opts.default_permissions); #else (void) stat_result; #endif @@ -209,7 +209,7 @@ static void test_reftable_stack_add_one(void) static void test_reftable_stack_uptodate(void) { - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st1 = NULL; struct reftable_stack *st2 = NULL; char *dir = get_tmp_dir(__LINE__); @@ -232,10 +232,10 @@ static void test_reftable_stack_uptodate(void) /* simulate multi-process access to the same stack by creating two stacks for the same directory. */ - err = reftable_new_stack(&st1, dir, cfg); + err = reftable_new_stack(&st1, dir, opts); EXPECT_ERR(err); - err = reftable_new_stack(&st2, dir, cfg); + err = reftable_new_stack(&st2, dir, opts); EXPECT_ERR(err); err = reftable_stack_add(st1, &write_test_ref, &ref1); @@ -257,8 +257,7 @@ static void test_reftable_stack_uptodate(void) static void test_reftable_stack_transaction_api(void) { char *dir = get_tmp_dir(__LINE__); - - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st = NULL; int err; struct reftable_addition *add = NULL; @@ -271,8 +270,7 @@ static void test_reftable_stack_transaction_api(void) }; struct reftable_ref_record dest = { NULL }; - - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); reftable_addition_destroy(add); @@ -301,12 +299,12 @@ static void test_reftable_stack_transaction_api(void) static void test_reftable_stack_transaction_api_performs_auto_compaction(void) { char *dir = get_tmp_dir(__LINE__); - struct reftable_write_options cfg = {0}; + struct reftable_write_options opts = {0}; struct reftable_addition *add = NULL; struct reftable_stack *st = NULL; int i, n = 20, err; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); for (i = 0; i <= n; i++) { @@ -325,7 +323,7 @@ static void test_reftable_stack_transaction_api_performs_auto_compaction(void) * we can ensure that we indeed honor this setting and have * better control over when exactly auto compaction runs. */ - st->config.disable_auto_compact = i != n; + st->opts.disable_auto_compact = i != n; err = reftable_stack_new_addition(&add, st); EXPECT_ERR(err); @@ -361,13 +359,13 @@ static void test_reftable_stack_auto_compaction_fails_gracefully(void) .value_type = REFTABLE_REF_VAL1, .value.val1 = {0x01}, }; - struct reftable_write_options cfg = {0}; + struct reftable_write_options opts = {0}; struct reftable_stack *st; struct strbuf table_path = STRBUF_INIT; char *dir = get_tmp_dir(__LINE__); int err; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); err = reftable_stack_add(st, write_test_ref, &ref); @@ -404,8 +402,7 @@ static int write_error(struct reftable_writer *wr, void *arg) static void test_reftable_stack_update_index_check(void) { char *dir = get_tmp_dir(__LINE__); - - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st = NULL; int err; struct reftable_ref_record ref1 = { @@ -421,7 +418,7 @@ static void test_reftable_stack_update_index_check(void) .value.symref = "master", }; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); err = reftable_stack_add(st, &write_test_ref, &ref1); @@ -436,12 +433,11 @@ static void test_reftable_stack_update_index_check(void) static void test_reftable_stack_lock_failure(void) { char *dir = get_tmp_dir(__LINE__); - - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st = NULL; int err, i; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); for (i = -1; i != REFTABLE_EMPTY_TABLE_ERROR; i--) { err = reftable_stack_add(st, &write_error, &i); @@ -456,7 +452,7 @@ static void test_reftable_stack_add(void) { int i = 0; int err = 0; - struct reftable_write_options cfg = { + struct reftable_write_options opts = { .exact_log_message = 1, .default_permissions = 0660, .disable_auto_compact = 1, @@ -469,7 +465,7 @@ static void test_reftable_stack_add(void) struct stat stat_result; int N = ARRAY_SIZE(refs); - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); for (i = 0; i < N; i++) { @@ -528,7 +524,7 @@ static void test_reftable_stack_add(void) strbuf_addstr(&path, "/tables.list"); err = stat(path.buf, &stat_result); EXPECT(!err); - EXPECT((stat_result.st_mode & 0777) == cfg.default_permissions); + EXPECT((stat_result.st_mode & 0777) == opts.default_permissions); strbuf_reset(&path); strbuf_addstr(&path, dir); @@ -537,7 +533,7 @@ static void test_reftable_stack_add(void) strbuf_addstr(&path, st->readers[0]->name); err = stat(path.buf, &stat_result); EXPECT(!err); - EXPECT((stat_result.st_mode & 0777) == cfg.default_permissions); + EXPECT((stat_result.st_mode & 0777) == opts.default_permissions); #else (void) stat_result; #endif @@ -555,7 +551,7 @@ static void test_reftable_stack_add(void) static void test_reftable_stack_log_normalize(void) { int err = 0; - struct reftable_write_options cfg = { + struct reftable_write_options opts = { 0, }; struct reftable_stack *st = NULL; @@ -579,7 +575,7 @@ static void test_reftable_stack_log_normalize(void) .update_index = 1, }; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); input.value.update.message = "one\ntwo"; @@ -612,8 +608,7 @@ static void test_reftable_stack_tombstone(void) { int i = 0; char *dir = get_tmp_dir(__LINE__); - - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st = NULL; int err; struct reftable_ref_record refs[2] = { { NULL } }; @@ -622,8 +617,7 @@ static void test_reftable_stack_tombstone(void) struct reftable_ref_record dest = { NULL }; struct reftable_log_record log_dest = { NULL }; - - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); /* even entries add the refs, odd entries delete them. */ @@ -691,8 +685,7 @@ static void test_reftable_stack_tombstone(void) static void test_reftable_stack_hash_id(void) { char *dir = get_tmp_dir(__LINE__); - - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st = NULL; int err; @@ -702,24 +695,24 @@ static void test_reftable_stack_hash_id(void) .value.symref = "target", .update_index = 1, }; - struct reftable_write_options cfg32 = { .hash_id = GIT_SHA256_FORMAT_ID }; + struct reftable_write_options opts32 = { .hash_id = GIT_SHA256_FORMAT_ID }; struct reftable_stack *st32 = NULL; - struct reftable_write_options cfg_default = { 0 }; + struct reftable_write_options opts_default = { 0 }; struct reftable_stack *st_default = NULL; struct reftable_ref_record dest = { NULL }; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); err = reftable_stack_add(st, &write_test_ref, &ref); EXPECT_ERR(err); /* can't read it with the wrong hash ID. */ - err = reftable_new_stack(&st32, dir, cfg32); + err = reftable_new_stack(&st32, dir, opts32); EXPECT(err == REFTABLE_FORMAT_ERROR); - /* check that we can read it back with default config too. */ - err = reftable_new_stack(&st_default, dir, cfg_default); + /* check that we can read it back with default opts too. */ + err = reftable_new_stack(&st_default, dir, opts_default); EXPECT_ERR(err); err = reftable_stack_read_ref(st_default, "master", &dest); @@ -752,8 +745,7 @@ static void test_suggest_compaction_segment_nothing(void) static void test_reflog_expire(void) { char *dir = get_tmp_dir(__LINE__); - - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st = NULL; struct reftable_log_record logs[20] = { { NULL } }; int N = ARRAY_SIZE(logs) - 1; @@ -764,8 +756,7 @@ static void test_reflog_expire(void) }; struct reftable_log_record log = { NULL }; - - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); for (i = 1; i <= N; i++) { @@ -828,21 +819,19 @@ static int write_nothing(struct reftable_writer *wr, void *arg) static void test_empty_add(void) { - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st = NULL; int err; char *dir = get_tmp_dir(__LINE__); - struct reftable_stack *st2 = NULL; - - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); err = reftable_stack_add(st, &write_nothing, NULL); EXPECT_ERR(err); - err = reftable_new_stack(&st2, dir, cfg); + err = reftable_new_stack(&st2, dir, opts); EXPECT_ERR(err); clear_dir(dir); reftable_stack_destroy(st); @@ -861,16 +850,15 @@ static int fastlog2(uint64_t sz) static void test_reftable_stack_auto_compaction(void) { - struct reftable_write_options cfg = { + struct reftable_write_options opts = { .disable_auto_compact = 1, }; struct reftable_stack *st = NULL; char *dir = get_tmp_dir(__LINE__); - int err, i; int N = 100; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); for (i = 0; i < N; i++) { @@ -900,13 +888,13 @@ static void test_reftable_stack_auto_compaction(void) static void test_reftable_stack_add_performs_auto_compaction(void) { - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st = NULL; struct strbuf refname = STRBUF_INIT; char *dir = get_tmp_dir(__LINE__); int err, i, n = 20; - err = reftable_new_stack(&st, dir, cfg); + err = reftable_new_stack(&st, dir, opts); EXPECT_ERR(err); for (i = 0; i <= n; i++) { @@ -921,7 +909,7 @@ static void test_reftable_stack_add_performs_auto_compaction(void) * we can ensure that we indeed honor this setting and have * better control over when exactly auto compaction runs. */ - st->config.disable_auto_compact = i != n; + st->opts.disable_auto_compact = i != n; strbuf_reset(&refname); strbuf_addf(&refname, "branch-%04d", i); @@ -948,14 +936,13 @@ static void test_reftable_stack_add_performs_auto_compaction(void) static void test_reftable_stack_compaction_concurrent(void) { - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st1 = NULL, *st2 = NULL; char *dir = get_tmp_dir(__LINE__); - int err, i; int N = 3; - err = reftable_new_stack(&st1, dir, cfg); + err = reftable_new_stack(&st1, dir, opts); EXPECT_ERR(err); for (i = 0; i < N; i++) { @@ -972,7 +959,7 @@ static void test_reftable_stack_compaction_concurrent(void) EXPECT_ERR(err); } - err = reftable_new_stack(&st2, dir, cfg); + err = reftable_new_stack(&st2, dir, opts); EXPECT_ERR(err); err = reftable_stack_compact_all(st1, NULL); @@ -998,14 +985,13 @@ static void unclean_stack_close(struct reftable_stack *st) static void test_reftable_stack_compaction_concurrent_clean(void) { - struct reftable_write_options cfg = { 0 }; + struct reftable_write_options opts = { 0 }; struct reftable_stack *st1 = NULL, *st2 = NULL, *st3 = NULL; char *dir = get_tmp_dir(__LINE__); - int err, i; int N = 3; - err = reftable_new_stack(&st1, dir, cfg); + err = reftable_new_stack(&st1, dir, opts); EXPECT_ERR(err); for (i = 0; i < N; i++) { @@ -1022,7 +1008,7 @@ static void test_reftable_stack_compaction_concurrent_clean(void) EXPECT_ERR(err); } - err = reftable_new_stack(&st2, dir, cfg); + err = reftable_new_stack(&st2, dir, opts); EXPECT_ERR(err); err = reftable_stack_compact_all(st1, NULL); @@ -1031,7 +1017,7 @@ static void test_reftable_stack_compaction_concurrent_clean(void) unclean_stack_close(st1); unclean_stack_close(st2); - err = reftable_new_stack(&st3, dir, cfg); + err = reftable_new_stack(&st3, dir, opts); EXPECT_ERR(err); err = reftable_stack_clean(st3); From 799237852bd265feb1e1a8d4a19780e20991b4fd Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:17:59 +0200 Subject: [PATCH 02/11] reftable: pass opts as constant pointer We sometimes pass the refatble write options as value and sometimes as a pointer. This is quite confusing and makes the reader wonder whether the options get modified sometimes. In fact, `reftable_new_writer()` does cause the caller-provided options to get updated when some values aren't set up. This is quite unexpected, but didn't cause any harm until now. Adapt the code so that we do not modify the caller-provided values anymore. While at it, refactor the code to code to consistently pass the options as a constant pointer to clarify that the caller-provided opts will not ever get modified. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- refs/reftable-backend.c | 6 ++--- reftable/dump.c | 2 +- reftable/reftable-stack.h | 2 +- reftable/reftable-writer.h | 2 +- reftable/stack.c | 7 ++++-- reftable/stack_test.c | 48 +++++++++++++++++++------------------- reftable/writer.c | 17 +++++++++----- 7 files changed, 46 insertions(+), 38 deletions(-) diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index 010ef811b6..f8f930380d 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -129,7 +129,7 @@ static struct reftable_stack *stack_for(struct reftable_ref_store *store, store->base.repo->commondir, wtname_buf.buf); store->err = reftable_new_stack(&stack, wt_dir.buf, - store->write_options); + &store->write_options); assert(store->err != REFTABLE_API_ERROR); strmap_put(&store->worktree_stacks, wtname_buf.buf, stack); } @@ -263,7 +263,7 @@ static struct ref_store *reftable_be_init(struct repository *repo, } strbuf_addstr(&path, "/reftable"); refs->err = reftable_new_stack(&refs->main_stack, path.buf, - refs->write_options); + &refs->write_options); if (refs->err) goto done; @@ -280,7 +280,7 @@ static struct ref_store *reftable_be_init(struct repository *repo, strbuf_addf(&path, "%s/reftable", gitdir); refs->err = reftable_new_stack(&refs->worktree_stack, path.buf, - refs->write_options); + &refs->write_options); if (refs->err) goto done; } diff --git a/reftable/dump.c b/reftable/dump.c index 9c770a10cc..586f3eb288 100644 --- a/reftable/dump.c +++ b/reftable/dump.c @@ -29,7 +29,7 @@ static int compact_stack(const char *stackdir) struct reftable_stack *stack = NULL; struct reftable_write_options opts = { 0 }; - int err = reftable_new_stack(&stack, stackdir, opts); + int err = reftable_new_stack(&stack, stackdir, &opts); if (err < 0) goto done; diff --git a/reftable/reftable-stack.h b/reftable/reftable-stack.h index 9c8e4eef49..c15632c401 100644 --- a/reftable/reftable-stack.h +++ b/reftable/reftable-stack.h @@ -29,7 +29,7 @@ struct reftable_stack; * stored in 'dir'. Typically, this should be .git/reftables. */ int reftable_new_stack(struct reftable_stack **dest, const char *dir, - struct reftable_write_options opts); + const struct reftable_write_options *opts); /* returns the update_index at which a next table should be written. */ uint64_t reftable_stack_next_update_index(struct reftable_stack *st); diff --git a/reftable/reftable-writer.h b/reftable/reftable-writer.h index b601a69a40..03df3a4963 100644 --- a/reftable/reftable-writer.h +++ b/reftable/reftable-writer.h @@ -88,7 +88,7 @@ struct reftable_stats { struct reftable_writer * reftable_new_writer(ssize_t (*writer_func)(void *, const void *, size_t), int (*flush_func)(void *), - void *writer_arg, struct reftable_write_options *opts); + void *writer_arg, const struct reftable_write_options *opts); /* Set the range of update indices for the records we will add. When writing a table into a stack, the min should be at least diff --git a/reftable/stack.c b/reftable/stack.c index 54e7473f3a..d2e68be7e8 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -54,12 +54,15 @@ static int reftable_fd_flush(void *arg) } int reftable_new_stack(struct reftable_stack **dest, const char *dir, - struct reftable_write_options opts) + const struct reftable_write_options *_opts) { struct reftable_stack *p = reftable_calloc(1, sizeof(*p)); struct strbuf list_file_name = STRBUF_INIT; + struct reftable_write_options opts = {0}; int err = 0; + if (_opts) + opts = *_opts; if (opts.hash_id == 0) opts.hash_id = GIT_SHA1_FORMAT_ID; @@ -1438,7 +1441,7 @@ int reftable_stack_print_directory(const char *stackdir, uint32_t hash_id) struct reftable_merged_table *merged = NULL; struct reftable_table table = { NULL }; - int err = reftable_new_stack(&stack, stackdir, opts); + int err = reftable_new_stack(&stack, stackdir, &opts); if (err < 0) goto done; diff --git a/reftable/stack_test.c b/reftable/stack_test.c index e17ad4dc62..d15f11d712 100644 --- a/reftable/stack_test.c +++ b/reftable/stack_test.c @@ -163,7 +163,7 @@ static void test_reftable_stack_add_one(void) }; struct reftable_ref_record dest = { NULL }; struct stat stat_result = { 0 }; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); err = reftable_stack_add(st, &write_test_ref, &ref); @@ -232,10 +232,10 @@ static void test_reftable_stack_uptodate(void) /* simulate multi-process access to the same stack by creating two stacks for the same directory. */ - err = reftable_new_stack(&st1, dir, opts); + err = reftable_new_stack(&st1, dir, &opts); EXPECT_ERR(err); - err = reftable_new_stack(&st2, dir, opts); + err = reftable_new_stack(&st2, dir, &opts); EXPECT_ERR(err); err = reftable_stack_add(st1, &write_test_ref, &ref1); @@ -270,7 +270,7 @@ static void test_reftable_stack_transaction_api(void) }; struct reftable_ref_record dest = { NULL }; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); reftable_addition_destroy(add); @@ -304,7 +304,7 @@ static void test_reftable_stack_transaction_api_performs_auto_compaction(void) struct reftable_stack *st = NULL; int i, n = 20, err; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); for (i = 0; i <= n; i++) { @@ -365,7 +365,7 @@ static void test_reftable_stack_auto_compaction_fails_gracefully(void) char *dir = get_tmp_dir(__LINE__); int err; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); err = reftable_stack_add(st, write_test_ref, &ref); @@ -418,7 +418,7 @@ static void test_reftable_stack_update_index_check(void) .value.symref = "master", }; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); err = reftable_stack_add(st, &write_test_ref, &ref1); @@ -437,7 +437,7 @@ static void test_reftable_stack_lock_failure(void) struct reftable_stack *st = NULL; int err, i; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); for (i = -1; i != REFTABLE_EMPTY_TABLE_ERROR; i--) { err = reftable_stack_add(st, &write_error, &i); @@ -465,7 +465,7 @@ static void test_reftable_stack_add(void) struct stat stat_result; int N = ARRAY_SIZE(refs); - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); for (i = 0; i < N; i++) { @@ -575,7 +575,7 @@ static void test_reftable_stack_log_normalize(void) .update_index = 1, }; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); input.value.update.message = "one\ntwo"; @@ -617,7 +617,7 @@ static void test_reftable_stack_tombstone(void) struct reftable_ref_record dest = { NULL }; struct reftable_log_record log_dest = { NULL }; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); /* even entries add the refs, odd entries delete them. */ @@ -701,18 +701,18 @@ static void test_reftable_stack_hash_id(void) struct reftable_stack *st_default = NULL; struct reftable_ref_record dest = { NULL }; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); err = reftable_stack_add(st, &write_test_ref, &ref); EXPECT_ERR(err); /* can't read it with the wrong hash ID. */ - err = reftable_new_stack(&st32, dir, opts32); + err = reftable_new_stack(&st32, dir, &opts32); EXPECT(err == REFTABLE_FORMAT_ERROR); /* check that we can read it back with default opts too. */ - err = reftable_new_stack(&st_default, dir, opts_default); + err = reftable_new_stack(&st_default, dir, &opts_default); EXPECT_ERR(err); err = reftable_stack_read_ref(st_default, "master", &dest); @@ -756,7 +756,7 @@ static void test_reflog_expire(void) }; struct reftable_log_record log = { NULL }; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); for (i = 1; i <= N; i++) { @@ -825,13 +825,13 @@ static void test_empty_add(void) char *dir = get_tmp_dir(__LINE__); struct reftable_stack *st2 = NULL; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); err = reftable_stack_add(st, &write_nothing, NULL); EXPECT_ERR(err); - err = reftable_new_stack(&st2, dir, opts); + err = reftable_new_stack(&st2, dir, &opts); EXPECT_ERR(err); clear_dir(dir); reftable_stack_destroy(st); @@ -858,7 +858,7 @@ static void test_reftable_stack_auto_compaction(void) int err, i; int N = 100; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); for (i = 0; i < N; i++) { @@ -894,7 +894,7 @@ static void test_reftable_stack_add_performs_auto_compaction(void) char *dir = get_tmp_dir(__LINE__); int err, i, n = 20; - err = reftable_new_stack(&st, dir, opts); + err = reftable_new_stack(&st, dir, &opts); EXPECT_ERR(err); for (i = 0; i <= n; i++) { @@ -942,7 +942,7 @@ static void test_reftable_stack_compaction_concurrent(void) int err, i; int N = 3; - err = reftable_new_stack(&st1, dir, opts); + err = reftable_new_stack(&st1, dir, &opts); EXPECT_ERR(err); for (i = 0; i < N; i++) { @@ -959,7 +959,7 @@ static void test_reftable_stack_compaction_concurrent(void) EXPECT_ERR(err); } - err = reftable_new_stack(&st2, dir, opts); + err = reftable_new_stack(&st2, dir, &opts); EXPECT_ERR(err); err = reftable_stack_compact_all(st1, NULL); @@ -991,7 +991,7 @@ static void test_reftable_stack_compaction_concurrent_clean(void) int err, i; int N = 3; - err = reftable_new_stack(&st1, dir, opts); + err = reftable_new_stack(&st1, dir, &opts); EXPECT_ERR(err); for (i = 0; i < N; i++) { @@ -1008,7 +1008,7 @@ static void test_reftable_stack_compaction_concurrent_clean(void) EXPECT_ERR(err); } - err = reftable_new_stack(&st2, dir, opts); + err = reftable_new_stack(&st2, dir, &opts); EXPECT_ERR(err); err = reftable_stack_compact_all(st1, NULL); @@ -1017,7 +1017,7 @@ static void test_reftable_stack_compaction_concurrent_clean(void) unclean_stack_close(st1); unclean_stack_close(st2); - err = reftable_new_stack(&st3, dir, opts); + err = reftable_new_stack(&st3, dir, &opts); EXPECT_ERR(err); err = reftable_stack_clean(st3); diff --git a/reftable/writer.c b/reftable/writer.c index 10eccaaa07..4cc6e2ebd8 100644 --- a/reftable/writer.c +++ b/reftable/writer.c @@ -122,20 +122,25 @@ static struct strbuf reftable_empty_strbuf = STRBUF_INIT; struct reftable_writer * reftable_new_writer(ssize_t (*writer_func)(void *, const void *, size_t), int (*flush_func)(void *), - void *writer_arg, struct reftable_write_options *opts) + void *writer_arg, const struct reftable_write_options *_opts) { struct reftable_writer *wp = reftable_calloc(1, sizeof(*wp)); - strbuf_init(&wp->block_writer_data.last_key, 0); - options_set_defaults(opts); - if (opts->block_size >= (1 << 24)) { + struct reftable_write_options opts = {0}; + + if (_opts) + opts = *_opts; + options_set_defaults(&opts); + if (opts.block_size >= (1 << 24)) { /* TODO - error return? */ abort(); } + + strbuf_init(&wp->block_writer_data.last_key, 0); wp->last_key = reftable_empty_strbuf; - REFTABLE_CALLOC_ARRAY(wp->block, opts->block_size); + REFTABLE_CALLOC_ARRAY(wp->block, opts.block_size); wp->write = writer_func; wp->write_arg = writer_arg; - wp->opts = *opts; + wp->opts = opts; wp->flush = flush_func; writer_reinit_block_writer(wp, BLOCK_TYPE_REF); From e0cf3d8f8bc0480e67ac83502c10d6e6c38e1e11 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:04 +0200 Subject: [PATCH 03/11] reftable/writer: drop static variable used to initialize strbuf We have a static variable in the reftable writer code that is merely used to initialize the `last_key` of the writer. Convert the code to instead use `strbuf_init()` and drop the variable. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/writer.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/reftable/writer.c b/reftable/writer.c index 4cc6e2ebd8..a043025b01 100644 --- a/reftable/writer.c +++ b/reftable/writer.c @@ -117,8 +117,6 @@ static void writer_reinit_block_writer(struct reftable_writer *w, uint8_t typ) w->block_writer->restart_interval = w->opts.restart_interval; } -static struct strbuf reftable_empty_strbuf = STRBUF_INIT; - struct reftable_writer * reftable_new_writer(ssize_t (*writer_func)(void *, const void *, size_t), int (*flush_func)(void *), @@ -136,7 +134,7 @@ reftable_new_writer(ssize_t (*writer_func)(void *, const void *, size_t), } strbuf_init(&wp->block_writer_data.last_key, 0); - wp->last_key = reftable_empty_strbuf; + strbuf_init(&wp->last_key, 0); REFTABLE_CALLOC_ARRAY(wp->block, opts.block_size); wp->write = writer_func; wp->write_arg = writer_arg; From c22d75b02784baa1713e0c007fcd0cb675dd9f43 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:09 +0200 Subject: [PATCH 04/11] reftable/writer: improve error when passed an invalid block size The reftable format only supports block sizes up to 16MB. When the writer is being passed a value bigger than that it simply calls abort(3P), which isn't all that helpful due to the lack of a proper error message. Improve this by calling `BUG()` instead. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/writer.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/reftable/writer.c b/reftable/writer.c index a043025b01..45b3e9ce1f 100644 --- a/reftable/writer.c +++ b/reftable/writer.c @@ -128,10 +128,8 @@ reftable_new_writer(ssize_t (*writer_func)(void *, const void *, size_t), if (_opts) opts = *_opts; options_set_defaults(&opts); - if (opts.block_size >= (1 << 24)) { - /* TODO - error return? */ - abort(); - } + if (opts.block_size >= (1 << 24)) + BUG("configured block size exceeds 16MB"); strbuf_init(&wp->block_writer_data.last_key, 0); strbuf_init(&wp->last_key, 0); From fcf341890ef583f519bc2746940c048bb8261d3d Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:13 +0200 Subject: [PATCH 05/11] reftable/dump: support dumping a table's block structure We're about to introduce new configs that will allow users to have more control over how exactly reftables are written. To verify that these configs are effective we will need to take a peak into the actual blocks written by the reftable backend. Introduce a new mode to the dumping logic that prints out the block structure. This logic can be invoked via `test-tool dump-reftables -b`. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/dump.c | 8 ++- reftable/reader.c | 63 ++++++++++++++++++ reftable/reftable-reader.h | 2 + t/t0613-reftable-write-options.sh | 102 ++++++++++++++++++++++++++++++ 4 files changed, 174 insertions(+), 1 deletion(-) create mode 100755 t/t0613-reftable-write-options.sh diff --git a/reftable/dump.c b/reftable/dump.c index 586f3eb288..41abbb8ecf 100644 --- a/reftable/dump.c +++ b/reftable/dump.c @@ -48,6 +48,7 @@ static void print_help(void) printf("usage: dump [-cst] arg\n\n" "options: \n" " -c compact\n" + " -b dump blocks\n" " -t dump table\n" " -s dump stack\n" " -6 sha256 hash format\n" @@ -58,6 +59,7 @@ static void print_help(void) int reftable_dump_main(int argc, char *const *argv) { int err = 0; + int opt_dump_blocks = 0; int opt_dump_table = 0; int opt_dump_stack = 0; int opt_compact = 0; @@ -67,6 +69,8 @@ int reftable_dump_main(int argc, char *const *argv) for (; argc > 1; argv++, argc--) if (*argv[1] != '-') break; + else if (!strcmp("-b", argv[1])) + opt_dump_blocks = 1; else if (!strcmp("-t", argv[1])) opt_dump_table = 1; else if (!strcmp("-6", argv[1])) @@ -88,7 +92,9 @@ int reftable_dump_main(int argc, char *const *argv) arg = argv[1]; - if (opt_dump_table) { + if (opt_dump_blocks) { + err = reftable_reader_print_blocks(arg); + } else if (opt_dump_table) { err = reftable_reader_print_file(arg); } else if (opt_dump_stack) { err = reftable_stack_print_directory(arg, opt_hash_id); diff --git a/reftable/reader.c b/reftable/reader.c index 481dff10d4..f23c8523db 100644 --- a/reftable/reader.c +++ b/reftable/reader.c @@ -856,3 +856,66 @@ done: reftable_reader_free(r); return err; } + +int reftable_reader_print_blocks(const char *tablename) +{ + struct { + const char *name; + int type; + } sections[] = { + { + .name = "ref", + .type = BLOCK_TYPE_REF, + }, + { + .name = "obj", + .type = BLOCK_TYPE_OBJ, + }, + { + .name = "log", + .type = BLOCK_TYPE_LOG, + }, + }; + struct reftable_block_source src = { 0 }; + struct table_iter ti = TABLE_ITER_INIT; + struct reftable_reader *r = NULL; + size_t i; + int err; + + err = reftable_block_source_from_file(&src, tablename); + if (err < 0) + goto done; + + err = reftable_new_reader(&r, &src, tablename); + if (err < 0) + goto done; + + printf("header:\n"); + printf(" block_size: %d\n", r->block_size); + + for (i = 0; i < ARRAY_SIZE(sections); i++) { + err = reader_start(r, &ti, sections[i].type, 0); + if (err < 0) + goto done; + if (err > 0) + continue; + + printf("%s:\n", sections[i].name); + + while (1) { + printf(" - length: %u\n", ti.br.block_len); + printf(" restarts: %u\n", ti.br.restart_count); + + err = table_iter_next_block(&ti); + if (err < 0) + goto done; + if (err > 0) + break; + } + } + +done: + reftable_reader_free(r); + table_iter_close(&ti); + return err; +} diff --git a/reftable/reftable-reader.h b/reftable/reftable-reader.h index 4a4bc2fdf8..4a04857773 100644 --- a/reftable/reftable-reader.h +++ b/reftable/reftable-reader.h @@ -97,5 +97,7 @@ void reftable_table_from_reader(struct reftable_table *tab, /* print table onto stdout for debugging. */ int reftable_reader_print_file(const char *tablename); +/* print blocks onto stdout for debugging. */ +int reftable_reader_print_blocks(const char *tablename); #endif diff --git a/t/t0613-reftable-write-options.sh b/t/t0613-reftable-write-options.sh new file mode 100755 index 0000000000..462980c37c --- /dev/null +++ b/t/t0613-reftable-write-options.sh @@ -0,0 +1,102 @@ +#!/bin/sh + +test_description='reftable write options' + +GIT_TEST_DEFAULT_REF_FORMAT=reftable +export GIT_TEST_DEFAULT_REF_FORMAT +# Disable auto-compaction for all tests as we explicitly control repacking of +# refs. +GIT_TEST_REFTABLE_AUTOCOMPACTION=false +export GIT_TEST_REFTABLE_AUTOCOMPACTION +# Block sizes depend on the hash function, so we force SHA1 here. +GIT_TEST_DEFAULT_HASH=sha1 +export GIT_TEST_DEFAULT_HASH +# Block sizes also depend on the actual refs we write, so we force "master" to +# be the default initial branch name. +GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=master +export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME + +. ./test-lib.sh + +test_expect_success 'default write options' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + git pack-refs && + cat >expect <<-EOF && + header: + block_size: 4096 + ref: + - length: 129 + restarts: 2 + log: + - length: 262 + restarts: 2 + EOF + test-tool dump-reftable -b .git/reftable/*.ref >actual && + test_cmp expect actual + ) +' + +test_expect_success 'disabled reflog writes no log blocks' ' + test_config_global core.logAllRefUpdates false && + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + git pack-refs && + cat >expect <<-EOF && + header: + block_size: 4096 + ref: + - length: 129 + restarts: 2 + EOF + test-tool dump-reftable -b .git/reftable/*.ref >actual && + test_cmp expect actual + ) +' + +test_expect_success 'many refs results in multiple blocks' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + for i in $(test_seq 200) + do + printf "update refs/heads/branch-%d HEAD\n" "$i" || + return 1 + done >input && + git update-ref --stdin expect <<-EOF && + header: + block_size: 4096 + ref: + - length: 4049 + restarts: 11 + - length: 1136 + restarts: 3 + log: + - length: 4041 + restarts: 4 + - length: 4015 + restarts: 3 + - length: 4014 + restarts: 3 + - length: 4012 + restarts: 3 + - length: 3289 + restarts: 3 + EOF + test-tool dump-reftable -b .git/reftable/*.ref >actual && + test_cmp expect actual + ) +' + +test_done From 831b366c243ecaa450289d76926bb687c746d495 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:19 +0200 Subject: [PATCH 06/11] refs/reftable: allow configuring block size Add a new option `reftable.blockSize` that allows the user to control the block size used by the reftable library. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- Documentation/config.txt | 2 + Documentation/config/reftable.txt | 14 ++++++ refs/reftable-backend.c | 31 ++++++++++++- t/t0613-reftable-write-options.sh | 72 +++++++++++++++++++++++++++++++ 4 files changed, 118 insertions(+), 1 deletion(-) create mode 100644 Documentation/config/reftable.txt diff --git a/Documentation/config.txt b/Documentation/config.txt index 6f649c997c..cbf0b99c44 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -498,6 +498,8 @@ include::config/rebase.txt[] include::config/receive.txt[] +include::config/reftable.txt[] + include::config/remote.txt[] include::config/remotes.txt[] diff --git a/Documentation/config/reftable.txt b/Documentation/config/reftable.txt new file mode 100644 index 0000000000..fa7c4be014 --- /dev/null +++ b/Documentation/config/reftable.txt @@ -0,0 +1,14 @@ +reftable.blockSize:: + The size in bytes used by the reftable backend when writing blocks. + The block size is determined by the writer, and does not have to be a + power of 2. The block size must be larger than the longest reference + name or log entry used in the repository, as references cannot span + blocks. ++ +Powers of two that are friendly to the virtual memory system or +filesystem (such as 4kB or 8kB) are recommended. Larger sizes (64kB) can +yield better compression, with a possible increased cost incurred by +readers during access. ++ +The largest block size is `16777215` bytes (15.99 MiB). The default value is +`4096` bytes (4kB). A value of `0` will use the default value. diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index f8f930380d..8d0ae9e285 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -1,6 +1,7 @@ #include "../git-compat-util.h" #include "../abspath.h" #include "../chdir-notify.h" +#include "../config.h" #include "../environment.h" #include "../gettext.h" #include "../hash.h" @@ -228,6 +229,22 @@ done: return ret; } +static int reftable_be_config(const char *var, const char *value, + const struct config_context *ctx, + void *_opts) +{ + struct reftable_write_options *opts = _opts; + + if (!strcmp(var, "reftable.blocksize")) { + unsigned long block_size = git_config_ulong(var, value, ctx->kvi); + if (block_size > 16777215) + die("reftable block size cannot exceed 16MB"); + opts->block_size = block_size; + } + + return 0; +} + static struct ref_store *reftable_be_init(struct repository *repo, const char *gitdir, unsigned int store_flags) @@ -243,12 +260,24 @@ static struct ref_store *reftable_be_init(struct repository *repo, base_ref_store_init(&refs->base, repo, gitdir, &refs_be_reftable); strmap_init(&refs->worktree_stacks); refs->store_flags = store_flags; - refs->write_options.block_size = 4096; + refs->write_options.hash_id = repo->hash_algo->format_id; refs->write_options.default_permissions = calc_shared_perm(0666 & ~mask); refs->write_options.disable_auto_compact = !git_env_bool("GIT_TEST_REFTABLE_AUTOCOMPACTION", 1); + git_config(reftable_be_config, &refs->write_options); + + /* + * It is somewhat unfortunate that we have to mirror the default block + * size of the reftable library here. But given that the write options + * wouldn't be updated by the library here, and given that we require + * the proper block size to trim reflog message so that they fit, we + * must set up a proper value here. + */ + if (!refs->write_options.block_size) + refs->write_options.block_size = 4096; + /* * Set up the main reftable stack that is hosted in GIT_COMMON_DIR. * This stack contains both the shared and the main worktree refs. diff --git a/t/t0613-reftable-write-options.sh b/t/t0613-reftable-write-options.sh index 462980c37c..8bdbc6ec70 100755 --- a/t/t0613-reftable-write-options.sh +++ b/t/t0613-reftable-write-options.sh @@ -99,4 +99,76 @@ test_expect_success 'many refs results in multiple blocks' ' ) ' +test_expect_success 'tiny block size leads to error' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + cat >expect <<-EOF && + error: unable to compact stack: entry too large + EOF + test_must_fail git -c reftable.blockSize=50 pack-refs 2>err && + test_cmp expect err + ) +' + +test_expect_success 'small block size leads to multiple ref blocks' ' + test_config_global core.logAllRefUpdates false && + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit A && + test_commit B && + git -c reftable.blockSize=100 pack-refs && + + cat >expect <<-EOF && + header: + block_size: 100 + ref: + - length: 53 + restarts: 1 + - length: 74 + restarts: 1 + - length: 38 + restarts: 1 + EOF + test-tool dump-reftable -b .git/reftable/*.ref >actual && + test_cmp expect actual + ) +' + +test_expect_success 'small block size fails with large reflog message' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit A && + perl -e "print \"a\" x 500" >logmsg && + cat >expect <<-EOF && + fatal: update_ref failed for ref ${SQ}refs/heads/logme${SQ}: reftable: transaction failure: entry too large + EOF + test_must_fail git -c reftable.blockSize=100 \ + update-ref -m "$(cat logmsg)" refs/heads/logme HEAD 2>err && + test_cmp expect err + ) +' + +test_expect_success 'block size exceeding maximum supported size' ' + test_config_global core.logAllRefUpdates false && + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit A && + test_commit B && + cat >expect <<-EOF && + fatal: reftable block size cannot exceed 16MB + EOF + test_must_fail git -c reftable.blockSize=16777216 pack-refs 2>err && + test_cmp expect err + ) +' + test_done From 8e9e136d6172824dd77f8f83569ec3e5f7bc08cd Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:23 +0200 Subject: [PATCH 07/11] reftable: use `uint16_t` to track restart interval The restart interval can at most be `UINT16_MAX` as specified in the technical documentation of the reftable format. Furthermore, it cannot ever be negative. Regardless of that we use an `int` to track the restart interval. Change the type to use an `uint16_t` instead. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/block.h | 2 +- reftable/reftable-writer.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/reftable/block.h b/reftable/block.h index e91f3d2790..1c8f25ee6e 100644 --- a/reftable/block.h +++ b/reftable/block.h @@ -29,7 +29,7 @@ struct block_writer { uint32_t header_off; /* How often to restart keys. */ - int restart_interval; + uint16_t restart_interval; int hash_size; /* Offset of next uint8_t to write. */ diff --git a/reftable/reftable-writer.h b/reftable/reftable-writer.h index 03df3a4963..94804eaa68 100644 --- a/reftable/reftable-writer.h +++ b/reftable/reftable-writer.h @@ -28,7 +28,7 @@ struct reftable_write_options { unsigned skip_index_objects : 1; /* how often to write complete keys in each block. */ - int restart_interval; + uint16_t restart_interval; /* 4-byte identifier ("sha1", "s256") of the hash. * Defaults to SHA1 if unset From 90db611c2a1f4ca2123ef5a8d7e592fa348bb23b Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:28 +0200 Subject: [PATCH 08/11] refs/reftable: allow configuring restart interval Add a new option `reftable.restartInterval` that allows the user to control the restart interval when writing reftable records used by the reftable library. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- Documentation/config/reftable.txt | 18 +++++++++++++ refs/reftable-backend.c | 5 ++++ t/t0613-reftable-write-options.sh | 43 +++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+) diff --git a/Documentation/config/reftable.txt b/Documentation/config/reftable.txt index fa7c4be014..2374be71d7 100644 --- a/Documentation/config/reftable.txt +++ b/Documentation/config/reftable.txt @@ -12,3 +12,21 @@ readers during access. + The largest block size is `16777215` bytes (15.99 MiB). The default value is `4096` bytes (4kB). A value of `0` will use the default value. + +reftable.restartInterval:: + The interval at which to create restart points. The reftable backend + determines the restart points at file creation. Every 16 may be + more suitable for smaller block sizes (4k or 8k), every 64 for larger + block sizes (64k). ++ +More frequent restart points reduces prefix compression and increases +space consumed by the restart table, both of which increase file size. ++ +Less frequent restart points makes prefix compression more effective, +decreasing overall file size, with increased penalties for readers +walking through more records after the binary search step. ++ +A maximum of `65535` restart points per block is supported. ++ +The default value is to create restart points every 16 records. A value of `0` +will use the default value. diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index 8d0ae9e285..a2880aabce 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -240,6 +240,11 @@ static int reftable_be_config(const char *var, const char *value, if (block_size > 16777215) die("reftable block size cannot exceed 16MB"); opts->block_size = block_size; + } else if (!strcmp(var, "reftable.restartinterval")) { + unsigned long restart_interval = git_config_ulong(var, value, ctx->kvi); + if (restart_interval > UINT16_MAX) + die("reftable block size cannot exceed %u", (unsigned)UINT16_MAX); + opts->restart_interval = restart_interval; } return 0; diff --git a/t/t0613-reftable-write-options.sh b/t/t0613-reftable-write-options.sh index 8bdbc6ec70..e0a5b26f58 100755 --- a/t/t0613-reftable-write-options.sh +++ b/t/t0613-reftable-write-options.sh @@ -171,4 +171,47 @@ test_expect_success 'block size exceeding maximum supported size' ' ) ' +test_expect_success 'restart interval at every single record' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + for i in $(test_seq 10) + do + printf "update refs/heads/branch-%d HEAD\n" "$i" || + return 1 + done >input && + git update-ref --stdin expect <<-EOF && + header: + block_size: 4096 + ref: + - length: 566 + restarts: 13 + log: + - length: 1393 + restarts: 12 + EOF + test-tool dump-reftable -b .git/reftable/*.ref >actual && + test_cmp expect actual + ) +' + +test_expect_success 'restart interval exceeding maximum supported interval' ' + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + cat >expect <<-EOF && + fatal: reftable block size cannot exceed 65535 + EOF + test_must_fail git -c reftable.restartInterval=65536 pack-refs 2>err && + test_cmp expect err + ) +' + test_done From afbdbfae0b44efe470c6c7998822900c61f71e39 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:33 +0200 Subject: [PATCH 09/11] refs/reftable: allow disabling writing the object index Besides the expected "ref" and "log" records, the reftable library also writes "obj" records. These are basically a reverse mapping of object IDs to their respective ref records so that it becomes efficient to figure out which references point to a specific object. The motivation for this data structure is the "uploadpack.allowTipSHA1InWant" config, which allows a client to fetch any object by its hash that has a ref pointing to it. This reverse index is not used by Git at all though, and the expectation is that most hosters nowadays use "uploadpack.allowAnySHA1InWant". It may thus be preferable for many users to disable writing these optional object indices altogether to safe some precious disk space. Add a new config "reftable.indexObjects" that allows the user to disable the object index altogether. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- Documentation/config/reftable.txt | 6 +++ refs/reftable-backend.c | 2 + t/t0613-reftable-write-options.sh | 69 +++++++++++++++++++++++++++++++ 3 files changed, 77 insertions(+) diff --git a/Documentation/config/reftable.txt b/Documentation/config/reftable.txt index 2374be71d7..68083876fa 100644 --- a/Documentation/config/reftable.txt +++ b/Documentation/config/reftable.txt @@ -30,3 +30,9 @@ A maximum of `65535` restart points per block is supported. + The default value is to create restart points every 16 records. A value of `0` will use the default value. + +reftable.indexObjects:: + Whether the reftable backend shall write object blocks. Object blocks + are a reverse mapping of object ID to the references pointing to them. ++ +The default value is `true`. diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index a2880aabce..5ffb36770a 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -245,6 +245,8 @@ static int reftable_be_config(const char *var, const char *value, if (restart_interval > UINT16_MAX) die("reftable block size cannot exceed %u", (unsigned)UINT16_MAX); opts->restart_interval = restart_interval; + } else if (!strcmp(var, "reftable.indexobjects")) { + opts->skip_index_objects = !git_config_bool(var, value); } return 0; diff --git a/t/t0613-reftable-write-options.sh b/t/t0613-reftable-write-options.sh index e0a5b26f58..e2708e11d5 100755 --- a/t/t0613-reftable-write-options.sh +++ b/t/t0613-reftable-write-options.sh @@ -214,4 +214,73 @@ test_expect_success 'restart interval exceeding maximum supported interval' ' ) ' +test_expect_success 'object index gets written by default with ref index' ' + test_config_global core.logAllRefUpdates false && + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + for i in $(test_seq 5) + do + printf "update refs/heads/branch-%d HEAD\n" "$i" || + return 1 + done >input && + git update-ref --stdin expect <<-EOF && + header: + block_size: 100 + ref: + - length: 53 + restarts: 1 + - length: 95 + restarts: 1 + - length: 71 + restarts: 1 + - length: 80 + restarts: 1 + obj: + - length: 11 + restarts: 1 + EOF + test-tool dump-reftable -b .git/reftable/*.ref >actual && + test_cmp expect actual + ) +' + +test_expect_success 'object index can be disabled' ' + test_config_global core.logAllRefUpdates false && + test_when_finished "rm -rf repo" && + git init repo && + ( + cd repo && + test_commit initial && + for i in $(test_seq 5) + do + printf "update refs/heads/branch-%d HEAD\n" "$i" || + return 1 + done >input && + git update-ref --stdin expect <<-EOF && + header: + block_size: 100 + ref: + - length: 53 + restarts: 1 + - length: 95 + restarts: 1 + - length: 71 + restarts: 1 + - length: 80 + restarts: 1 + EOF + test-tool dump-reftable -b .git/reftable/*.ref >actual && + test_cmp expect actual + ) +' + test_done From f663d34306d414bca27cf6b5dc7affb00e8603fe Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:38 +0200 Subject: [PATCH 10/11] reftable: make the compaction factor configurable When auto-compacting, the reftable library packs references such that the sizes of the tables form a geometric sequence. The factor for this geometric sequence is hardcoded to 2 right now. We're about to expose this as a config option though, so let's expose the factor via write options. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/constants.h | 1 + reftable/reftable-writer.h | 6 ++++++ reftable/stack.c | 14 ++++++++++---- reftable/stack.h | 3 ++- reftable/stack_test.c | 4 ++-- 5 files changed, 21 insertions(+), 7 deletions(-) diff --git a/reftable/constants.h b/reftable/constants.h index 5eee72c4c1..f6beb843eb 100644 --- a/reftable/constants.h +++ b/reftable/constants.h @@ -17,5 +17,6 @@ https://developers.google.com/open-source/licenses/bsd #define MAX_RESTARTS ((1 << 16) - 1) #define DEFAULT_BLOCK_SIZE 4096 +#define DEFAULT_GEOMETRIC_FACTOR 2 #endif diff --git a/reftable/reftable-writer.h b/reftable/reftable-writer.h index 94804eaa68..189b1f4144 100644 --- a/reftable/reftable-writer.h +++ b/reftable/reftable-writer.h @@ -45,6 +45,12 @@ struct reftable_write_options { /* boolean: Prevent auto-compaction of tables. */ unsigned disable_auto_compact : 1; + + /* + * Geometric sequence factor used by auto-compaction to decide which + * tables to compact. Defaults to 2 if unset. + */ + uint8_t auto_compaction_factor; }; /* reftable_block_stats holds statistics for a single block type */ diff --git a/reftable/stack.c b/reftable/stack.c index d2e68be7e8..0ebe69e81d 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -10,6 +10,7 @@ https://developers.google.com/open-source/licenses/bsd #include "../write-or-die.h" #include "system.h" +#include "constants.h" #include "merged.h" #include "reader.h" #include "reftable-error.h" @@ -1212,12 +1213,16 @@ static int segment_size(struct segment *s) return s->end - s->start; } -struct segment suggest_compaction_segment(uint64_t *sizes, size_t n) +struct segment suggest_compaction_segment(uint64_t *sizes, size_t n, + uint8_t factor) { struct segment seg = { 0 }; uint64_t bytes; size_t i; + if (!factor) + factor = DEFAULT_GEOMETRIC_FACTOR; + /* * If there are no tables or only a single one then we don't have to * compact anything. The sequence is geometric by definition already. @@ -1249,7 +1254,7 @@ struct segment suggest_compaction_segment(uint64_t *sizes, size_t n) * 64, 32, 16, 8, 4, 3, 1 */ for (i = n - 1; i > 0; i--) { - if (sizes[i - 1] < sizes[i] * 2) { + if (sizes[i - 1] < sizes[i] * factor) { seg.end = i + 1; bytes = sizes[i]; break; @@ -1275,7 +1280,7 @@ struct segment suggest_compaction_segment(uint64_t *sizes, size_t n) uint64_t curr = bytes; bytes += sizes[i - 1]; - if (sizes[i - 1] < curr * 2) { + if (sizes[i - 1] < curr * factor) { seg.start = i - 1; seg.bytes = bytes; } @@ -1301,7 +1306,8 @@ int reftable_stack_auto_compact(struct reftable_stack *st) { uint64_t *sizes = stack_table_sizes_for_compaction(st); struct segment seg = - suggest_compaction_segment(sizes, st->merged->stack_len); + suggest_compaction_segment(sizes, st->merged->stack_len, + st->opts.auto_compaction_factor); reftable_free(sizes); if (segment_size(&seg) > 0) return stack_compact_range_stats(st, seg.start, seg.end - 1, diff --git a/reftable/stack.h b/reftable/stack.h index 97d7ebc043..5b45cff4f7 100644 --- a/reftable/stack.h +++ b/reftable/stack.h @@ -35,6 +35,7 @@ struct segment { uint64_t bytes; }; -struct segment suggest_compaction_segment(uint64_t *sizes, size_t n); +struct segment suggest_compaction_segment(uint64_t *sizes, size_t n, + uint8_t factor); #endif diff --git a/reftable/stack_test.c b/reftable/stack_test.c index d15f11d712..0f7b1453e6 100644 --- a/reftable/stack_test.c +++ b/reftable/stack_test.c @@ -729,7 +729,7 @@ static void test_suggest_compaction_segment(void) { uint64_t sizes[] = { 512, 64, 17, 16, 9, 9, 9, 16, 2, 16 }; struct segment min = - suggest_compaction_segment(sizes, ARRAY_SIZE(sizes)); + suggest_compaction_segment(sizes, ARRAY_SIZE(sizes), 2); EXPECT(min.start == 1); EXPECT(min.end == 10); } @@ -738,7 +738,7 @@ static void test_suggest_compaction_segment_nothing(void) { uint64_t sizes[] = { 64, 32, 16, 8, 4, 2 }; struct segment result = - suggest_compaction_segment(sizes, ARRAY_SIZE(sizes)); + suggest_compaction_segment(sizes, ARRAY_SIZE(sizes), 2); EXPECT(result.start == result.end); } From f518d91a2b6465c9951f4ee1ab316ee81894000c Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 13 May 2024 10:18:43 +0200 Subject: [PATCH 11/11] refs/reftable: allow configuring geometric factor Allow configuring the geometric factor used by the auto-compaction algorithm whenever a new table is appended to the stack of tables. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- Documentation/config/reftable.txt | 10 ++++++++++ refs/reftable-backend.c | 5 +++++ 2 files changed, 15 insertions(+) diff --git a/Documentation/config/reftable.txt b/Documentation/config/reftable.txt index 68083876fa..0515727977 100644 --- a/Documentation/config/reftable.txt +++ b/Documentation/config/reftable.txt @@ -36,3 +36,13 @@ reftable.indexObjects:: are a reverse mapping of object ID to the references pointing to them. + The default value is `true`. + +reftable.geometricFactor:: + Whenever the reftable backend appends a new table to the stack, it + performs auto compaction to ensure that there is only a handful of + tables. The backend does this by ensuring that tables form a geometric + sequence regarding the respective sizes of each table. ++ +By default, the geometric sequence uses a factor of 2, meaning that for any +table, the next-biggest table must at least be twice as big. A maximum factor +of 256 is supported. diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index 5ffb36770a..da620fd598 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -247,6 +247,11 @@ static int reftable_be_config(const char *var, const char *value, opts->restart_interval = restart_interval; } else if (!strcmp(var, "reftable.indexobjects")) { opts->skip_index_objects = !git_config_bool(var, value); + } else if (!strcmp(var, "reftable.geometricfactor")) { + unsigned long factor = git_config_ulong(var, value, ctx->kvi); + if (factor > UINT8_MAX) + die("reftable geometric factor cannot exceed %u", (unsigned)UINT8_MAX); + opts->auto_compaction_factor = factor; } return 0;