From c195ecda7703098f28c160cc63306ca0e1488236 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Thu, 6 Jun 2024 18:19:25 -0400 Subject: [PATCH 1/2] commit-graph.c: remove temporary graph layers on exit Since the introduction of split commit graph layers in 92b1ea66b9a (Merge branch 'ds/commit-graph-incremental', 2019-07-19), the function write_commit_graph_file() has done the following when writing an incremental commit-graph layer: - used a lock_file to control access to the commit-graph-chain file - used an auxiliary file (whose descriptor was stored in 'fd') to write the new commit-graph layer itself Using a lock_file to control access to the commit-graph-chain is sensible, since only one writer may modify it at a time. Likewise, when the commit-graph machinery is writing out a single layer, the lock_file structure is used to modify the commit-graph itself. This is also sensible, since the non-incremental commit-graph may also have at most one writer. However, using an auxiliary temporary file without using the tempfile.h API means that writes that fail after the temporary graph layer has been created will leave around a file in $GIT_DIR/objects/info/commit-graphs/tmp_graph_XXXXXX The commit-graph-chain file and non-incremental commit-graph do not suffer from this problem as the lockfile.h API uses the tempfile.h API transparently, so processes that died before moving those finals into their final location cleaned up after themselves. Ensure that the temporary file used to write incremental commit-graphs is also managed with the tempfile.h API, to ensure that we do not ever leave tmp_graph_XXXXXX files laying around. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- commit-graph.c | 19 ++++++++----------- t/t5324-split-commit-graph.sh | 26 +++++++++++++++++++++++++- 2 files changed, 33 insertions(+), 12 deletions(-) diff --git a/commit-graph.c b/commit-graph.c index e5dd3553df..92c7163714 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -2002,8 +2002,8 @@ static int write_graph_chunk_base(struct hashfile *f, static int write_commit_graph_file(struct write_commit_graph_context *ctx) { uint32_t i; - int fd; struct hashfile *f; + struct tempfile *graph_layer; /* when ctx->split is non-zero */ struct lock_file lk = LOCK_INIT; const unsigned hashsz = the_hash_algo->rawsz; struct strbuf progress_title = STRBUF_INIT; @@ -2035,24 +2035,23 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) LOCK_DIE_ON_ERROR, 0444); free(lock_name); - fd = git_mkstemp_mode(ctx->graph_name, 0444); - if (fd < 0) { + graph_layer = mks_tempfile_m(ctx->graph_name, 0444); + if (!graph_layer) { error(_("unable to create temporary graph layer")); return -1; } - if (adjust_shared_perm(ctx->graph_name)) { + if (adjust_shared_perm(get_tempfile_path(graph_layer))) { error(_("unable to adjust shared permissions for '%s'"), - ctx->graph_name); + get_tempfile_path(graph_layer)); return -1; } - f = hashfd(fd, ctx->graph_name); + f = hashfd(get_tempfile_fd(graph_layer), get_tempfile_path(graph_layer)); } else { hold_lock_file_for_update_mode(&lk, ctx->graph_name, LOCK_DIE_ON_ERROR, 0444); - fd = get_lock_file_fd(&lk); - f = hashfd(fd, get_lock_file_path(&lk)); + f = hashfd(get_lock_file_fd(&lk), get_lock_file_path(&lk)); } cf = init_chunkfile(f); @@ -2133,8 +2132,6 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) char *final_graph_name; int result; - close(fd); - if (!chainf) { error(_("unable to open commit-graph chain file")); return -1; @@ -2169,7 +2166,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) free(ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 1]); ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 1] = final_graph_name; - result = rename(ctx->graph_name, final_graph_name); + result = rename_tempfile(&graph_layer, final_graph_name); for (i = 0; i < ctx->num_commit_graphs_after; i++) fprintf(get_lock_file_fp(&lk), "%s\n", ctx->commit_graph_hash_after[i]); diff --git a/t/t5324-split-commit-graph.sh b/t/t5324-split-commit-graph.sh index 281266f788..77e91547ea 100755 --- a/t/t5324-split-commit-graph.sh +++ b/t/t5324-split-commit-graph.sh @@ -13,7 +13,8 @@ test_expect_success 'setup repo' ' git init && git config core.commitGraph true && git config gc.writeCommitGraph false && - infodir=".git/objects/info" && + objdir=".git/objects" && + infodir="$objdir/info" && graphdir="$infodir/commit-graphs" && test_oid_cache <<-EOM shallow sha1:2132 @@ -718,4 +719,27 @@ test_expect_success 'write generation data chunk when commit-graph chain is repl ) ' +test_expect_success 'temporary graph layer is discarded upon failure' ' + git init layer-discard && + ( + cd layer-discard && + + test_commit A && + test_commit B && + + # Intentionally remove commit "A" from the object store + # so that the commit-graph machinery fails to parse the + # parents of "B". + # + # This takes place after the commit-graph machinery has + # initialized a new temporary file to store the contents + # of the new graph layer, so will allow us to ensure + # that the temporary file is discarded upon failure. + rm $objdir/$(test_oid_to_path $(git rev-parse HEAD^)) && + + test_must_fail git commit-graph write --reachable --split && + test_dir_is_empty $graphdir + ) +' + test_done From 8981dca8bc717d7656f28fc375b513b91b365360 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Thu, 6 Jun 2024 18:19:31 -0400 Subject: [PATCH 2/2] server-info.c: remove temporary info files on exit The update_info_file() function within server-info.c is responsible for moving the info/refs and info/packs files around when updating server info. These updates are staged into a temporary file and then moved into place atomically to avoid race conditions when reading those files. However, the temporary file used to stage these changes is managed outside of the tempfile.h API, and thus survives process death. Manage these files instead with the tempfile.h API so that they are automatically cleaned up upon abnormal process death. Unfortunately, and unlike in the previous step, there isn't a straightforward way to inject a failure into the update-server-info step that causes us to die() rather than take the cleanup path in label 'out', hence the lack of a test here. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- server-info.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/server-info.c b/server-info.c index 6feaa457c5..37d1085982 100644 --- a/server-info.c +++ b/server-info.c @@ -13,6 +13,7 @@ #include "object-store-ll.h" #include "server-info.h" #include "strbuf.h" +#include "tempfile.h" struct update_info_ctx { FILE *cur_fp; @@ -75,9 +76,8 @@ static int update_info_file(char *path, int force) { char *tmp = mkpathdup("%s_XXXXXX", path); + struct tempfile *f = NULL; int ret = -1; - int fd = -1; - FILE *to_close; struct update_info_ctx uic = { .cur_fp = NULL, .old_fp = NULL, @@ -86,13 +86,12 @@ static int update_info_file(char *path, }; safe_create_leading_directories(path); - fd = git_mkstemp_mode(tmp, 0666); - if (fd < 0) + f = mks_tempfile_m(tmp, 0666); + if (!f) goto out; - to_close = uic.cur_fp = fdopen(fd, "w"); + uic.cur_fp = fdopen_tempfile(f, "w"); if (!uic.cur_fp) goto out; - fd = -1; /* no problem on ENOENT and old_fp == NULL, it's stale, now */ if (!force) @@ -121,27 +120,22 @@ static int update_info_file(char *path, } uic.cur_fp = NULL; - if (fclose(to_close)) - goto out; if (uic_is_stale(&uic)) { - if (adjust_shared_perm(tmp) < 0) + if (adjust_shared_perm(get_tempfile_path(f)) < 0) goto out; - if (rename(tmp, path) < 0) + if (rename_tempfile(&f, path) < 0) goto out; } else { - unlink(tmp); + delete_tempfile(&f); } ret = 0; out: if (ret) { error_errno("unable to update %s", path); - if (uic.cur_fp) - fclose(uic.cur_fp); - else if (fd >= 0) - close(fd); - unlink(tmp); + if (f) + delete_tempfile(&f); } free(tmp); if (uic.old_fp)