From 998330ac2e7c384d2f73c734177ca21f36c06e48 Mon Sep 17 00:00:00 2001 From: SZEDER Gábor Date: Thu, 26 Aug 2021 23:00:02 +0200 Subject: read-cache: look for shared index files next to the index, too MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When reading a split index git always looks for its referenced shared base index in the gitdir of the current repository, even when reading an alternate index specified via GIT_INDEX_FILE, and even when that alternate index file is the "main" '.git/index' file of an other repository. However, if that split index and its referenced shared index files were written by a git command running entirely in that other repository, then, naturally, the shared index file is written to that other repository's gitdir. Consequently, a git command attempting to read that shared index file while running in a different repository won't be able find it and will error out. I'm not sure in what use case it is necessary to read the index of one repository by a git command running in a different repository, but it is certainly possible to do so, and in fact the test 'bare repository: check that --cached honors index' in 't0003-attributes.sh' does exactly that. If GIT_TEST_SPLIT_INDEX=1 were to split the index in just the right moment [1], then this test would indeed fail, because the referenced shared index file could not be found. Let's look for the referenced shared index file not only in the gitdir of the current directory, but, if the shared index is not there, right next to the split index as well. [1] We haven't seen this issue trigger a failure in t0003 yet, because: - While GIT_TEST_SPLIT_INDEX=1 is supposed to trigger index splitting randomly, the first index write has always been deterministic and it has never split the index. - That alternate index file in the other repository is written only once in the entire test script, so it's never split. However, the next patch will fix GIT_TEST_SPLIT_INDEX, and while doing so it will slightly change its behavior to always split the index already on the first index write, and t0003 would always fail without this patch. Signed-off-by: SZEDER Gábor Acked-by: Derrick Stolee Signed-off-by: Junio C Hamano --- read-cache.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'read-cache.c') diff --git a/read-cache.c b/read-cache.c index f5d4385c40..3bf9ed4d43 100644 --- a/read-cache.c +++ b/read-cache.c @@ -2391,9 +2391,21 @@ int read_index_from(struct index_state *istate, const char *path, base_path = xstrfmt("%s/sharedindex.%s", gitdir, base_oid_hex); trace2_region_enter_printf("index", "shared/do_read_index", the_repository, "%s", base_path); - ret = do_read_index(split_index->base, base_path, 1); + ret = do_read_index(split_index->base, base_path, 0); trace2_region_leave_printf("index", "shared/do_read_index", the_repository, "%s", base_path); + if (!ret) { + char *path_copy = xstrdup(path); + const char *base_path2 = xstrfmt("%s/sharedindex.%s", + dirname(path_copy), + base_oid_hex); + free(path_copy); + trace2_region_enter_printf("index", "shared/do_read_index", + the_repository, "%s", base_path2); + ret = do_read_index(split_index->base, base_path2, 1); + trace2_region_leave_printf("index", "shared/do_read_index", + the_repository, "%s", base_path2); + } if (!oideq(&split_index->base_oid, &split_index->base->oid)) die(_("broken index, expect %s in %s, got %s"), base_oid_hex, base_path, -- cgit v1.3 From e8ffd034c8fa43efeeeee60483ca8690498e3085 Mon Sep 17 00:00:00 2001 From: SZEDER Gábor Date: Thu, 26 Aug 2021 23:00:04 +0200 Subject: read-cache: fix GIT_TEST_SPLIT_INDEX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Running tests with GIT_TEST_SPLIT_INDEX=1 is supposed to turn on the split index feature and trigger index splitting (mostly) randomly. Alas, this has been broken since 6e37c8ed3c (read-cache.c: fix writing "link" index ext with null base oid, 2019-02-13), and GIT_TEST_SPLIT_INDEX=1 hasn't triggered any index splitting since then. This patch makes GIT_TEST_SPLIT_INDEX work again, though it doesn't restore the pre-6e37c8ed3c behavior. To understand the bug, the fix, and the behavior change we first have to look at how GIT_TEST_SPLIT_INDEX used to work before 6e37c8ed3c: There are two places where we check the value of GIT_TEST_SPLIT_INDEX, and before 6e37c8ed3c they worked like this: 1) In the lower-level do_write_index(), where, if GIT_TEST_SPLIT_INDEX is enabled, we call init_split_index(). This call merely allocates and zero-initializes 'istate->split_index', but does nothing else (i.e. doesn't fill the base/shared index with cache entries, doesn't actually write a shared index file, etc.). Pertinent to this issue, the hash of the base index remains all zeroed out. 2) In the higher-level write_locked_index(), but only when 'istate->split_index' has already been initialized. Then, if GIT_TEST_SPLIT_INDEX is enabled, it randomly sets the flag that triggers index splitting later in this function. This randomness comes from the first byte of the hash of the base index via an 'if ((first_byte & 15) < 6)' condition. However, if 'istate->split_index' hasn't been initialized (i.e. it is still NULL), then write_locked_index() just calls do_write_locked_index(), which internally calls the above mentioned do_write_index(). This means that while GIT_TEST_SPLIT_INDEX=1 usually triggered index splitting randomly, the first two index writes were always deterministic (though I suspect this was unintentional): - The initial index write never splits the index. During the first index write write_locked_index() is called with 'istate->split_index' still uninitialized, so the check in 2) is not executed. It still calls do_write_index(), though, which then executes the check in 1). The resulting all zero base index hash then leads to the 'link' extension being written to '.git/index', though a shared index file is not written: $ rm .git/index $ GIT_TEST_SPLIT_INDEX=1 git update-index --add file $ test-tool dump-split-index .git/index own c6ef71168597caec8553c83d9d0048f1ef416170 base 0000000000000000000000000000000000000000 100644 d00491fd7e5bb6fa28c517a0bb32b8b506539d4d 0 file replacements: deletions: $ ls -l .git/sharedindex.* ls: cannot access '.git/sharedindex.*': No such file or directory - The second index write always splits the index. When the index written in the previous point is read, 'istate->split_index' is initialized because of the presence of the 'link' extension. So during the second write write_locked_index() does run the check in 2), and the first byte of the all zero base index hash always fulfills the randomness condition, which in turn always triggers the index splitting. - Subsequent index writes will find the 'link' extension with a real non-zero base index hash, so from then on the check in 2) is executed and the first byte of the base index hash is as random as it gets (coming from the SHA-1 of index data including timestamps and inodes...). All this worked until 6e37c8ed3c came along, and stopped writing the 'link' extension if the hash of the base index was all zero: $ rm .git/index $ GIT_TEST_SPLIT_INDEX=1 git update-index --add file $ test-tool dump-split-index .git/index own abbd6f6458d5dee73ae8e210ca15a68a390c6fd7 not a split index $ ls -l .git/sharedindex.* ls: cannot access '.git/sharedindex.*': No such file or directory So, since the first index write with GIT_TEST_SPLIT_INDEX=1 doesn't write a 'link' extension, in the second index write 'istate->split_index' remains uninitialized, and the check in 2) is not executed, and ultimately the index is never split. Fix this by modifying write_locked_index() to make sure to check GIT_TEST_SPLIT_INDEX even if 'istate->split_index' is still uninitialized, and initialize it if necessary. The check for GIT_TEST_SPLIT_INDEX and separate init_split_index() call in do_write_index() thus becomes unnecessary, so remove it. Furthermore, add a test to 't1700-split-index.sh' to make sure that GIT_TEST_SPLIT_INDEX=1 will keep working (though only check the index splitting on the first index write, because after that it will be random). Note that this change does not restore the pre-6e37c8ed3c behaviour, as it will deterministically split the index already on the first index write. Since GIT_TEST_SPLIT_INDEX is purely a developer aid, there is no backwards compatibility issue here. The new behaviour did trigger test failures in 't0003-attributes.sh' and 't1600-index.sh', though, which have been fixed in preparatory patches in this series. Signed-off-by: SZEDER Gábor Acked-by: Derrick Stolee Signed-off-by: Junio C Hamano --- read-cache.c | 23 ++++++++++++++--------- t/t1700-split-index.sh | 11 +++++++++++ 2 files changed, 25 insertions(+), 9 deletions(-) (limited to 'read-cache.c') diff --git a/read-cache.c b/read-cache.c index 3bf9ed4d43..edcb2c5d97 100644 --- a/read-cache.c +++ b/read-cache.c @@ -2824,11 +2824,8 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, } } - if (!istate->version) { + if (!istate->version) istate->version = get_index_format_default(the_repository); - if (git_env_bool("GIT_TEST_SPLIT_INDEX", 0)) - init_split_index(istate); - } /* demote version 3 to version 2 when the latter suffices */ if (istate->version == 3 || istate->version == 2) @@ -3255,7 +3252,7 @@ static int too_many_not_shared_entries(struct index_state *istate) int write_locked_index(struct index_state *istate, struct lock_file *lock, unsigned flags) { - int new_shared_index, ret; + int new_shared_index, ret, test_split_index_env; struct split_index *si = istate->split_index; if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0)) @@ -3270,7 +3267,10 @@ int write_locked_index(struct index_state *istate, struct lock_file *lock, if (istate->fsmonitor_last_update) fill_fsmonitor_bitmap(istate); - if (!si || alternate_index_output || + test_split_index_env = git_env_bool("GIT_TEST_SPLIT_INDEX", 0); + + if ((!si && !test_split_index_env) || + alternate_index_output || (istate->cache_changed & ~EXTMASK)) { if (si) oidclr(&si->base_oid); @@ -3278,10 +3278,15 @@ int write_locked_index(struct index_state *istate, struct lock_file *lock, goto out; } - if (git_env_bool("GIT_TEST_SPLIT_INDEX", 0)) { - int v = si->base_oid.hash[0]; - if ((v & 15) < 6) + if (test_split_index_env) { + if (!si) { + si = init_split_index(istate); istate->cache_changed |= SPLIT_INDEX_ORDERED; + } else { + int v = si->base_oid.hash[0]; + if ((v & 15) < 6) + istate->cache_changed |= SPLIT_INDEX_ORDERED; + } } if (too_many_not_shared_entries(istate)) istate->cache_changed |= SPLIT_INDEX_ORDERED; diff --git a/t/t1700-split-index.sh b/t/t1700-split-index.sh index e2aa0bd949..decd2527ed 100755 --- a/t/t1700-split-index.sh +++ b/t/t1700-split-index.sh @@ -533,4 +533,15 @@ test_expect_success 'reading split index at alternate location' ' test_cmp expect actual ' +test_expect_success 'GIT_TEST_SPLIT_INDEX works' ' + git init git-test-split-index && + ( + cd git-test-split-index && + >file && + GIT_TEST_SPLIT_INDEX=1 git update-index --add file && + ls -l .git/sharedindex.* >actual && + test_line_count = 1 actual + ) +' + test_done -- cgit v1.3