From f4c78d70e8ee4a5fefa3e21dc311f4e88142b34b Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:39 +0000 Subject: [PATCH 01/11] tmp-objdir: new API for creating temporary writable databases The tmp_objdir API provides the ability to create temporary object directories, but was designed with the goal of having subprocesses access these object stores, followed by the main process migrating objects from it to the main object store or just deleting it. The subprocesses would view it as their primary datastore and write to it. Here we add the tmp_objdir_replace_primary_odb function that replaces the current process's writable "main" object directory with the specified one. The previous main object directory is restored in either tmp_objdir_migrate or tmp_objdir_destroy. For the --remerge-diff usecase, add a new `will_destroy` flag in `struct object_database` to mark ephemeral object databases that do not require fsync durability. Add 'git prune' support for removing temporary object databases, and make sure that they have a name starting with tmp_ and containing an operation-specific name. Based-on-patch-by: Elijah Newren Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- builtin/prune.c | 23 +++++++++++++++--- builtin/receive-pack.c | 2 +- environment.c | 5 ++++ object-file.c | 44 +++++++++++++++++++++++++++++++-- object-store.h | 19 +++++++++++++++ object.c | 2 +- tmp-objdir.c | 55 +++++++++++++++++++++++++++++++++++++++--- tmp-objdir.h | 29 +++++++++++++++++++--- 8 files changed, 165 insertions(+), 14 deletions(-) diff --git a/builtin/prune.c b/builtin/prune.c index 02c6ab7cbaafba..6b6b0c7b011836 100644 --- a/builtin/prune.c +++ b/builtin/prune.c @@ -18,6 +18,7 @@ static int show_only; static int verbose; static timestamp_t expire; static int show_progress = -1; +static struct strbuf remove_dir_buf = STRBUF_INIT; static int prune_tmp_file(const char *fullpath) { @@ -26,10 +27,20 @@ static int prune_tmp_file(const char *fullpath) return error("Could not stat '%s'", fullpath); if (st.st_mtime > expire) return 0; - if (show_only || verbose) - printf("Removing stale temporary file %s\n", fullpath); - if (!show_only) - unlink_or_warn(fullpath); + if (S_ISDIR(st.st_mode)) { + if (show_only || verbose) + printf("Removing stale temporary directory %s\n", fullpath); + if (!show_only) { + strbuf_reset(&remove_dir_buf); + strbuf_addstr(&remove_dir_buf, fullpath); + remove_dir_recursively(&remove_dir_buf, 0); + } + } else { + if (show_only || verbose) + printf("Removing stale temporary file %s\n", fullpath); + if (!show_only) + unlink_or_warn(fullpath); + } return 0; } @@ -97,6 +108,9 @@ static int prune_cruft(const char *basename, const char *path, void *data) static int prune_subdir(unsigned int nr, const char *path, void *data) { + if (verbose) + printf("Removing directory %s\n", path); + if (!show_only) rmdir(path); return 0; @@ -185,5 +199,6 @@ int cmd_prune(int argc, const char **argv, const char *prefix) prune_shallow(show_only ? PRUNE_SHOW_ONLY : 0); } + strbuf_release(&remove_dir_buf); return 0; } diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index 2d1f97e1ca7b53..34626b978e5952 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -2211,7 +2211,7 @@ static const char *unpack(int err_fd, struct shallow_info *si) strvec_push(&child.args, alt_shallow_file); } - tmp_objdir = tmp_objdir_create(); + tmp_objdir = tmp_objdir_create("incoming"); if (!tmp_objdir) { if (err_fd > 0) close(err_fd); diff --git a/environment.c b/environment.c index b4ba4fa22dbe41..b39cc75cdfa769 100644 --- a/environment.c +++ b/environment.c @@ -17,6 +17,7 @@ #include "commit.h" #include "strvec.h" #include "object-store.h" +#include "tmp-objdir.h" #include "chdir-notify.h" #include "shallow.h" @@ -340,10 +341,14 @@ static void update_relative_gitdir(const char *name, void *data) { char *path = reparent_relative_path(old_cwd, new_cwd, get_git_dir()); + struct tmp_objdir *tmp_objdir = tmp_objdir_unapply_primary_odb(); trace_printf_key(&trace_setup_key, "setup: move $GIT_DIR to '%s'", path); + set_git_dir_1(path); + if (tmp_objdir) + tmp_objdir_reapply_primary_odb(tmp_objdir, old_cwd, new_cwd); free(path); } diff --git a/object-file.c b/object-file.c index a8be8994814933..f2d27d0f011498 100644 --- a/object-file.c +++ b/object-file.c @@ -750,6 +750,43 @@ void add_to_alternates_memory(const char *reference) '\n', NULL, 0); } +struct object_directory *set_temporary_primary_odb(const char *dir, int will_destroy) +{ + struct object_directory *new_odb; + + /* + * Make sure alternates are initialized, or else our entry may be + * overwritten when they are. + */ + prepare_alt_odb(the_repository); + + /* + * Make a new primary odb and link the old primary ODB in as an + * alternate + */ + new_odb = xcalloc(1, sizeof(*new_odb)); + new_odb->path = xstrdup(dir); + new_odb->will_destroy = will_destroy; + new_odb->next = the_repository->objects->odb; + the_repository->objects->odb = new_odb; + return new_odb->next; +} + +void restore_primary_odb(struct object_directory *restore_odb, const char *old_path) +{ + struct object_directory *cur_odb = the_repository->objects->odb; + + if (strcmp(old_path, cur_odb->path)) + BUG("expected %s as primary object store; found %s", + old_path, cur_odb->path); + + if (cur_odb->next != restore_odb) + BUG("we expect the old primary object store to be the first alternate"); + + the_repository->objects->odb = restore_odb; + free_object_directory(cur_odb); +} + /* * Compute the exact path an alternate is at and returns it. In case of * error NULL is returned and the human readable error is added to `err` @@ -1862,8 +1899,11 @@ int hash_object_file(const struct git_hash_algo *algo, const void *buf, /* Finalize a file on disk, and close it. */ static void close_loose_object(int fd) { - if (fsync_object_files) - fsync_or_die(fd, "loose object file"); + if (!the_repository->objects->odb->will_destroy) { + if (fsync_object_files) + fsync_or_die(fd, "loose object file"); + } + if (close(fd) != 0) die_errno(_("error when closing loose object file")); } diff --git a/object-store.h b/object-store.h index d24915ced1b2dd..36a9da8f50e54c 100644 --- a/object-store.h +++ b/object-store.h @@ -26,6 +26,11 @@ struct object_directory { uint32_t loose_objects_subdir_seen[8]; /* 256 bits */ struct oidtree *loose_objects_cache; + /* + * This object store is ephemeral, so there is no need to fsync. + */ + int will_destroy; + /* * Path to the alternative object store. If this is a relative path, * it is relative to the current working directory. @@ -56,6 +61,17 @@ void add_to_alternates_file(const char *dir); */ void add_to_alternates_memory(const char *dir); +/* + * Replace the current writable object directory with the specified temporary + * object directory; returns the former primary object directory. + */ +struct object_directory *set_temporary_primary_odb(const char *dir, int will_destroy); + +/* + * Restore a previous ODB replaced by set_temporary_main_odb. + */ +void restore_primary_odb(struct object_directory *restore_odb, const char *old_path); + /* * Populate and return the loose object cache array corresponding to the * given object ID. @@ -66,6 +82,9 @@ struct oidtree *odb_loose_cache(struct object_directory *odb, /* Empty the loose object cache for the specified object directory. */ void odb_clear_loose_cache(struct object_directory *odb); +/* Clear and free the specified object directory */ +void free_object_directory(struct object_directory *odb); + struct packed_git { struct hashmap_entry packmap_ent; struct packed_git *next; diff --git a/object.c b/object.c index 4e85955a941168..98635bc4043625 100644 --- a/object.c +++ b/object.c @@ -513,7 +513,7 @@ struct raw_object_store *raw_object_store_new(void) return o; } -static void free_object_directory(struct object_directory *odb) +void free_object_directory(struct object_directory *odb) { free(odb->path); odb_clear_loose_cache(odb); diff --git a/tmp-objdir.c b/tmp-objdir.c index b8d880e3626a9c..3d38eeab66bfb0 100644 --- a/tmp-objdir.c +++ b/tmp-objdir.c @@ -1,5 +1,6 @@ #include "cache.h" #include "tmp-objdir.h" +#include "chdir-notify.h" #include "dir.h" #include "sigchain.h" #include "string-list.h" @@ -11,6 +12,8 @@ struct tmp_objdir { struct strbuf path; struct strvec env; + struct object_directory *prev_odb; + int will_destroy; }; /* @@ -38,6 +41,9 @@ static int tmp_objdir_destroy_1(struct tmp_objdir *t, int on_signal) if (t == the_tmp_objdir) the_tmp_objdir = NULL; + if (!on_signal && t->prev_odb) + restore_primary_odb(t->prev_odb, t->path.buf); + /* * This may use malloc via strbuf_grow(), but we should * have pre-grown t->path sufficiently so that this @@ -52,6 +58,7 @@ static int tmp_objdir_destroy_1(struct tmp_objdir *t, int on_signal) */ if (!on_signal) tmp_objdir_free(t); + return err; } @@ -121,7 +128,7 @@ static int setup_tmp_objdir(const char *root) return ret; } -struct tmp_objdir *tmp_objdir_create(void) +struct tmp_objdir *tmp_objdir_create(const char *prefix) { static int installed_handlers; struct tmp_objdir *t; @@ -129,11 +136,16 @@ struct tmp_objdir *tmp_objdir_create(void) if (the_tmp_objdir) BUG("only one tmp_objdir can be used at a time"); - t = xmalloc(sizeof(*t)); + t = xcalloc(1, sizeof(*t)); strbuf_init(&t->path, 0); strvec_init(&t->env); - strbuf_addf(&t->path, "%s/incoming-XXXXXX", get_object_directory()); + /* + * Use a string starting with tmp_ so that the builtin/prune.c code + * can recognize any stale objdirs left behind by a crash and delete + * them. + */ + strbuf_addf(&t->path, "%s/tmp_objdir-%s-XXXXXX", get_object_directory(), prefix); /* * Grow the strbuf beyond any filename we expect to be placed in it. @@ -269,6 +281,13 @@ int tmp_objdir_migrate(struct tmp_objdir *t) if (!t) return 0; + if (t->prev_odb) { + if (the_repository->objects->odb->will_destroy) + BUG("migrating an ODB that was marked for destruction"); + restore_primary_odb(t->prev_odb, t->path.buf); + t->prev_odb = NULL; + } + strbuf_addbuf(&src, &t->path); strbuf_addstr(&dst, get_object_directory()); @@ -292,3 +311,33 @@ void tmp_objdir_add_as_alternate(const struct tmp_objdir *t) { add_to_alternates_memory(t->path.buf); } + +void tmp_objdir_replace_primary_odb(struct tmp_objdir *t, int will_destroy) +{ + if (t->prev_odb) + BUG("the primary object database is already replaced"); + t->prev_odb = set_temporary_primary_odb(t->path.buf, will_destroy); + t->will_destroy = will_destroy; +} + +struct tmp_objdir *tmp_objdir_unapply_primary_odb(void) +{ + if (!the_tmp_objdir || !the_tmp_objdir->prev_odb) + return NULL; + + restore_primary_odb(the_tmp_objdir->prev_odb, the_tmp_objdir->path.buf); + the_tmp_objdir->prev_odb = NULL; + return the_tmp_objdir; +} + +void tmp_objdir_reapply_primary_odb(struct tmp_objdir *t, const char *old_cwd, + const char *new_cwd) +{ + char *path; + + path = reparent_relative_path(old_cwd, new_cwd, t->path.buf); + strbuf_reset(&t->path); + strbuf_addstr(&t->path, path); + free(path); + tmp_objdir_replace_primary_odb(t, t->will_destroy); +} diff --git a/tmp-objdir.h b/tmp-objdir.h index b1e45b4c75d2d8..a3145051f25bf6 100644 --- a/tmp-objdir.h +++ b/tmp-objdir.h @@ -10,7 +10,7 @@ * * Example: * - * struct tmp_objdir *t = tmp_objdir_create(); + * struct tmp_objdir *t = tmp_objdir_create("incoming"); * if (!run_command_v_opt_cd_env(cmd, 0, NULL, tmp_objdir_env(t)) && * !tmp_objdir_migrate(t)) * printf("success!\n"); @@ -22,9 +22,10 @@ struct tmp_objdir; /* - * Create a new temporary object directory; returns NULL on failure. + * Create a new temporary object directory with the specified prefix; + * returns NULL on failure. */ -struct tmp_objdir *tmp_objdir_create(void); +struct tmp_objdir *tmp_objdir_create(const char *prefix); /* * Return a list of environment strings, suitable for use with @@ -51,4 +52,26 @@ int tmp_objdir_destroy(struct tmp_objdir *); */ void tmp_objdir_add_as_alternate(const struct tmp_objdir *); +/* + * Replaces the main object store in the current process with the temporary + * object directory and makes the former main object store an alternate. + * If will_destroy is nonzero, the object directory may not be migrated. + */ +void tmp_objdir_replace_primary_odb(struct tmp_objdir *, int will_destroy); + +/* + * If the primary object database was replaced by a temporary object directory, + * restore it to its original value while keeping the directory contents around. + * Returns NULL if the primary object database was not replaced. + */ +struct tmp_objdir *tmp_objdir_unapply_primary_odb(void); + +/* + * Reapplies the former primary temporary object database, after protentially + * changing its relative path. + */ +void tmp_objdir_reapply_primary_odb(struct tmp_objdir *, const char *old_cwd, + const char *new_cwd); + + #endif /* TMP_OBJDIR_H */ From 4c785a60bb606a76c781f2e0d338403d1497150e Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:40 +0000 Subject: [PATCH 02/11] tmp-objdir: disable ref updates when replacing the primary odb When creating a subprocess with a temporary ODB, we set the GIT_QUARANTINE_ENVIRONMENT env var to tell child Git processes not to update refs, since the tmp-objdir may go away. Introduce a similar mechanism for in-process temporary ODBs when we call tmp_objdir_replace_primary_odb. Now both mechanisms set the disable_ref_updates flag on the odb, which is queried by the ref_transaction_prepare function. Note: This change adds an assumption that the state of the_repository is relevant for any ref transaction that might be initiated. Unwinding this assumption should be straightforward by saving the relevant repository to query in the transaction or the ref_store. Peff's test case was invoking ref updates via the cachetextconv setting. That particular code silently does nothing when a ref update is forbidden. See the call to notes_cache_put in fill_textconv where errors are ignored. Reported-by: Jeff King Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- environment.c | 4 ++++ object-file.c | 6 ++++++ object-store.h | 9 ++++++++- refs.c | 2 +- repository.c | 2 ++ repository.h | 1 + 6 files changed, 22 insertions(+), 2 deletions(-) diff --git a/environment.c b/environment.c index b39cc75cdfa769..7ba5ae06c71669 100644 --- a/environment.c +++ b/environment.c @@ -177,6 +177,10 @@ void setup_git_env(const char *git_dir) args.graft_file = getenv_safe(&to_free, GRAFT_ENVIRONMENT); args.index_file = getenv_safe(&to_free, INDEX_ENVIRONMENT); args.alternate_db = getenv_safe(&to_free, ALTERNATE_DB_ENVIRONMENT); + if (getenv(GIT_QUARANTINE_ENVIRONMENT)) { + args.disable_ref_updates = 1; + } + repo_set_gitdir(the_repository, git_dir, &args); strvec_clear(&to_free); diff --git a/object-file.c b/object-file.c index f2d27d0f011498..9ec1794c367e38 100644 --- a/object-file.c +++ b/object-file.c @@ -766,6 +766,12 @@ struct object_directory *set_temporary_primary_odb(const char *dir, int will_des */ new_odb = xcalloc(1, sizeof(*new_odb)); new_odb->path = xstrdup(dir); + + /* + * Disable ref updates while a temporary odb is active, since + * the objects in the database may roll back. + */ + new_odb->disable_ref_updates = 1; new_odb->will_destroy = will_destroy; new_odb->next = the_repository->objects->odb; the_repository->objects->odb = new_odb; diff --git a/object-store.h b/object-store.h index 36a9da8f50e54c..b205aad8438983 100644 --- a/object-store.h +++ b/object-store.h @@ -26,10 +26,17 @@ struct object_directory { uint32_t loose_objects_subdir_seen[8]; /* 256 bits */ struct oidtree *loose_objects_cache; + /* + * This is a temporary object store created by the tmp_objdir + * facility. Disable ref updates since the objects in the store + * might be discarded on rollback. + */ + unsigned int disable_ref_updates : 1; + /* * This object store is ephemeral, so there is no need to fsync. */ - int will_destroy; + unsigned int will_destroy : 1; /* * Path to the alternative object store. If this is a relative path, diff --git a/refs.c b/refs.c index 8b9f7c3a80a0f6..7c182607dcffb4 100644 --- a/refs.c +++ b/refs.c @@ -2126,7 +2126,7 @@ int ref_transaction_prepare(struct ref_transaction *transaction, break; } - if (getenv(GIT_QUARANTINE_ENVIRONMENT)) { + if (the_repository->objects->odb->disable_ref_updates) { strbuf_addstr(err, _("ref updates forbidden inside quarantine environment")); return -1; diff --git a/repository.c b/repository.c index b2bf44c6fafec8..0a7b3c30c6cad9 100644 --- a/repository.c +++ b/repository.c @@ -80,6 +80,8 @@ void repo_set_gitdir(struct repository *repo, expand_base_dir(&repo->objects->odb->path, o->object_dir, repo->commondir, "objects"); + repo->objects->odb->disable_ref_updates = o->disable_ref_updates; + free(repo->objects->alternate_db); repo->objects->alternate_db = xstrdup_or_null(o->alternate_db); expand_base_dir(&repo->graft_file, o->graft_file, diff --git a/repository.h b/repository.h index 3740c93bc0fe27..77316367d998a3 100644 --- a/repository.h +++ b/repository.h @@ -162,6 +162,7 @@ struct set_gitdir_args { const char *graft_file; const char *index_file; const char *alternate_db; + int disable_ref_updates; }; void repo_set_gitdir(struct repository *repo, const char *root, From c9aa8b3fea14df5f049b4be74a21d3f5a3496049 Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:41 +0000 Subject: [PATCH 03/11] bulk-checkin: rename 'state' variable and separate 'plugged' boolean Preparation for adding bulk-fsync to the bulk-checkin.c infrastructure. * Rename 'state' variable to 'bulk_checkin_state', since we will later be adding 'bulk_fsync_state'. This also makes the variable easier to find in the debugger, since the name is more unique. * Move the 'plugged' data member of 'bulk_checkin_state' into a separate static variable. Doing this avoids resetting the variable in finish_bulk_checkin when zeroing the 'bulk_checkin_state'. As-is, we seem to unintentionally disable the plugging functionality the first time a new packfile must be created due to packfile size limits. While disabling the plugging state only results in suboptimal behavior for the current code, it would be fatal for the bulk-fsync functionality later in this patch series. Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- bulk-checkin.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/bulk-checkin.c b/bulk-checkin.c index 8785b2ac806992..6ae18401e04ecd 100644 --- a/bulk-checkin.c +++ b/bulk-checkin.c @@ -10,9 +10,9 @@ #include "packfile.h" #include "object-store.h" -static struct bulk_checkin_state { - unsigned plugged:1; +static int bulk_checkin_plugged; +static struct bulk_checkin_state { char *pack_tmp_name; struct hashfile *f; off_t offset; @@ -21,7 +21,7 @@ static struct bulk_checkin_state { struct pack_idx_entry **written; uint32_t alloc_written; uint32_t nr_written; -} state; +} bulk_checkin_state; static void finish_tmp_packfile(struct strbuf *basename, const char *pack_tmp_name, @@ -277,21 +277,23 @@ int index_bulk_checkin(struct object_id *oid, int fd, size_t size, enum object_type type, const char *path, unsigned flags) { - int status = deflate_to_pack(&state, oid, fd, size, type, + int status = deflate_to_pack(&bulk_checkin_state, oid, fd, size, type, path, flags); - if (!state.plugged) - finish_bulk_checkin(&state); + if (!bulk_checkin_plugged) + finish_bulk_checkin(&bulk_checkin_state); return status; } void plug_bulk_checkin(void) { - state.plugged = 1; + assert(!bulk_checkin_plugged); + bulk_checkin_plugged = 1; } void unplug_bulk_checkin(void) { - state.plugged = 0; - if (state.f) - finish_bulk_checkin(&state); + assert(bulk_checkin_plugged); + bulk_checkin_plugged = 0; + if (bulk_checkin_state.f) + finish_bulk_checkin(&bulk_checkin_state); } From 173e51914d3ba781b58daf4d0cf3e4f7d080d459 Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:42 +0000 Subject: [PATCH 04/11] core.fsyncobjectfiles: batched disk flushes When adding many objects to a repo with core.fsyncObjectFiles set to true, the cost of fsync'ing each object file can become prohibitive. One major source of the cost of fsync is the implied flush of the hardware writeback cache within the disk drive. Fortunately, Windows, and macOS offer mechanisms to write data from the filesystem page cache without initiating a hardware flush. Linux has the sync_file_range API, which issues a pagecache writeback request reliably after version 5.2. This patch introduces a new 'core.fsyncObjectFiles = batch' option that batches up hardware flushes. It hooks into the bulk-checkin plugging and unplugging functionality and takes advantage of tmp-objdir. When the new mode is enabled do the following for each new object: 1. Create the object in a tmp-objdir. 2. Issue a pagecache writeback request and wait for it to complete. At the end of the entire transaction when unplugging bulk checkin: 1. Issue an fsync against a dummy file to flush the hardware writeback cache, which should by now have processed the tmp-objdir writes. 2. Rename all of the tmp-objdir files to their final names. 3. When updating the index and/or refs, we assume that Git will issue another fsync internal to that operation. This is not the case today, but may be a good extension to those components. On a filesystem with a singular journal that is updated during name operations (e.g. create, link, rename, etc), such as NTFS, HFS+, or XFS we would expect the fsync to trigger a journal writeout so that this sequence is enough to ensure that the user's data is durable by the time the git command returns. This change also updates the macOS code to trigger a real hardware flush via fnctl(fd, F_FULLFSYNC) when fsync_or_die is called. Previously, on macOS there was no guarantee of durability since a simple fsync(2) call does not flush any hardware caches. _Performance numbers_: Linux - Hyper-V VM running Kernel 5.11 (Ubuntu 20.04) on a fast SSD. Mac - macOS 11.5.1 running on a Mac mini on a 1TB Apple SSD. Windows - Same host as Linux, a preview version of Windows 11. This number is from a patch later in the series. Adding 500 files to the repo with 'git add' Times reported in seconds. core.fsyncObjectFiles | Linux | Mac | Windows ----------------------|-------|-------|-------- false | 0.06 | 0.35 | 0.61 true | 1.88 | 11.18 | 2.47 batch | 0.15 | 0.41 | 1.53 Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- Documentation/config/core.txt | 29 +++++++++++---- Makefile | 6 ++++ bulk-checkin.c | 68 +++++++++++++++++++++++++++++++++++ bulk-checkin.h | 2 ++ cache.h | 8 ++++- config.c | 7 +++- config.mak.uname | 1 + configure.ac | 8 +++++ environment.c | 2 +- git-compat-util.h | 7 ++++ object-file.c | 12 ++++++- wrapper.c | 44 +++++++++++++++++++++++ write-or-die.c | 2 +- 13 files changed, 185 insertions(+), 11 deletions(-) diff --git a/Documentation/config/core.txt b/Documentation/config/core.txt index c04f62a54a154c..200b4d9f06ea65 100644 --- a/Documentation/config/core.txt +++ b/Documentation/config/core.txt @@ -548,12 +548,29 @@ core.whitespace:: errors. The default tab width is 8. Allowed values are 1 to 63. core.fsyncObjectFiles:: - This boolean will enable 'fsync()' when writing object files. -+ -This is a total waste of time and effort on a filesystem that orders -data writes properly, but can be useful for filesystems that do not use -journalling (traditional UNIX filesystems) or that only journal metadata -and not file contents (OS X's HFS+, or Linux ext3 with "data=writeback"). + A value indicating the level of effort Git will expend in + trying to make objects added to the repo durable in the event + of an unclean system shutdown. This setting currently only + controls loose objects in the object store, so updates to any + refs or the index may not be equally durable. ++ +* `false` allows data to remain in file system caches according to + operating system policy, whence it may be lost if the system loses power + or crashes. +* `true` triggers a data integrity flush for each loose object added to the + object store. This is the safest setting that is likely to ensure durability + across all operating systems and file systems that honor the 'fsync' system + call. However, this setting comes with a significant performance cost on + common hardware. Git does not currently fsync parent directories for + newly-added files, so some filesystems may still allow data to be lost on + system crash. +* `batch` enables an experimental mode that uses interfaces available in some + operating systems to write loose object data with a minimal set of FLUSH + CACHE (or equivalent) commands sent to the storage controller. If the + operating system interfaces are not available, this mode behaves the same as + `true`. This mode is expected to be as safe as `true` on macOS for repos + stored on HFS+ or APFS filesystems and on Windows for repos stored on NTFS or + ReFS. core.preloadIndex:: Enable parallel index preload for operations like 'git diff' diff --git a/Makefile b/Makefile index 3df0ab5c765119..7a2e20acf15f88 100644 --- a/Makefile +++ b/Makefile @@ -406,6 +406,8 @@ all:: # # Define HAVE_CLOCK_MONOTONIC if your platform has CLOCK_MONOTONIC. # +# Define HAVE_SYNC_FILE_RANGE if your platform has sync_file_range. +# # Define NEEDS_LIBRT if your platform requires linking with librt (glibc version # before 2.17) for clock_gettime and CLOCK_MONOTONIC. # @@ -1896,6 +1898,10 @@ ifdef HAVE_CLOCK_MONOTONIC BASIC_CFLAGS += -DHAVE_CLOCK_MONOTONIC endif +ifdef HAVE_SYNC_FILE_RANGE + BASIC_CFLAGS += -DHAVE_SYNC_FILE_RANGE +endif + ifdef NEEDS_LIBRT EXTLIBS += -lrt endif diff --git a/bulk-checkin.c b/bulk-checkin.c index 6ae18401e04ecd..4deee1af46e946 100644 --- a/bulk-checkin.c +++ b/bulk-checkin.c @@ -3,14 +3,20 @@ */ #include "cache.h" #include "bulk-checkin.h" +#include "lockfile.h" #include "repository.h" #include "csum-file.h" #include "pack.h" #include "strbuf.h" +#include "string-list.h" +#include "tmp-objdir.h" #include "packfile.h" #include "object-store.h" static int bulk_checkin_plugged; +static int needs_batch_fsync; + +static struct tmp_objdir *bulk_fsync_objdir; static struct bulk_checkin_state { char *pack_tmp_name; @@ -79,6 +85,34 @@ static void finish_bulk_checkin(struct bulk_checkin_state *state) reprepare_packed_git(the_repository); } +/* + * Cleanup after batch-mode fsync_object_files. + */ +static void do_batch_fsync(void) +{ + /* + * Issue a full hardware flush against a temporary file to ensure + * that all objects are durable before any renames occur. The code in + * fsync_loose_object_bulk_checkin has already issued a writeout + * request, but it has not flushed any writeback cache in the storage + * hardware. + */ + + if (needs_batch_fsync) { + struct strbuf temp_path = STRBUF_INIT; + struct tempfile *temp; + + strbuf_addf(&temp_path, "%s/bulk_fsync_XXXXXX", get_object_directory()); + temp = xmks_tempfile(temp_path.buf); + fsync_or_die(get_tempfile_fd(temp), get_tempfile_path(temp)); + delete_tempfile(&temp); + strbuf_release(&temp_path); + } + + if (bulk_fsync_objdir) + tmp_objdir_migrate(bulk_fsync_objdir); +} + static int already_written(struct bulk_checkin_state *state, struct object_id *oid) { int i; @@ -273,6 +307,25 @@ static int deflate_to_pack(struct bulk_checkin_state *state, return 0; } +void fsync_loose_object_bulk_checkin(int fd) +{ + assert(fsync_object_files == FSYNC_OBJECT_FILES_BATCH); + + /* + * If we have a plugged bulk checkin, we issue a call that + * cleans the filesystem page cache but avoids a hardware flush + * command. Later on we will issue a single hardware flush + * before as part of do_batch_fsync. + */ + if (bulk_checkin_plugged && + git_fsync(fd, FSYNC_WRITEOUT_ONLY) >= 0) { + if (!needs_batch_fsync) + needs_batch_fsync = 1; + } else { + fsync_or_die(fd, "loose object file"); + } +} + int index_bulk_checkin(struct object_id *oid, int fd, size_t size, enum object_type type, const char *path, unsigned flags) @@ -287,6 +340,19 @@ int index_bulk_checkin(struct object_id *oid, void plug_bulk_checkin(void) { assert(!bulk_checkin_plugged); + + /* + * A temporary object directory is used to hold the files + * while they are not fsynced. + */ + if (fsync_object_files == FSYNC_OBJECT_FILES_BATCH) { + bulk_fsync_objdir = tmp_objdir_create("bulk-fsync"); + if (!bulk_fsync_objdir) + die(_("Could not create temporary object directory for core.fsyncobjectfiles=batch")); + + tmp_objdir_replace_primary_odb(bulk_fsync_objdir, 0); + } + bulk_checkin_plugged = 1; } @@ -296,4 +362,6 @@ void unplug_bulk_checkin(void) bulk_checkin_plugged = 0; if (bulk_checkin_state.f) finish_bulk_checkin(&bulk_checkin_state); + + do_batch_fsync(); } diff --git a/bulk-checkin.h b/bulk-checkin.h index b26f3dc3b74cb9..08f292379b6cf9 100644 --- a/bulk-checkin.h +++ b/bulk-checkin.h @@ -6,6 +6,8 @@ #include "cache.h" +void fsync_loose_object_bulk_checkin(int fd); + int index_bulk_checkin(struct object_id *oid, int fd, size_t size, enum object_type type, const char *path, unsigned flags); diff --git a/cache.h b/cache.h index 0a8d44ce71d89e..b85ed61abc3bfd 100644 --- a/cache.h +++ b/cache.h @@ -984,7 +984,13 @@ void reset_shared_repository(void); extern int read_replace_refs; extern char *git_replace_ref_base; -extern int fsync_object_files; +enum fsync_object_files_mode { + FSYNC_OBJECT_FILES_OFF, + FSYNC_OBJECT_FILES_ON, + FSYNC_OBJECT_FILES_BATCH +}; + +extern enum fsync_object_files_mode fsync_object_files; extern int core_preload_index; extern int precomposed_unicode; extern int protect_hfs; diff --git a/config.c b/config.c index 7a6ff18ffa6c46..881e6467407de6 100644 --- a/config.c +++ b/config.c @@ -1506,7 +1506,12 @@ static int git_default_core_config(const char *var, const char *value, void *cb) } if (!strcmp(var, "core.fsyncobjectfiles")) { - fsync_object_files = git_config_bool(var, value); + if (value && !strcmp(value, "batch")) + fsync_object_files = FSYNC_OBJECT_FILES_BATCH; + else if (git_config_bool(var, value)) + fsync_object_files = FSYNC_OBJECT_FILES_ON; + else + fsync_object_files = FSYNC_OBJECT_FILES_OFF; return 0; } diff --git a/config.mak.uname b/config.mak.uname index 69413fb3dc0ad8..7ba731a646f255 100644 --- a/config.mak.uname +++ b/config.mak.uname @@ -53,6 +53,7 @@ ifeq ($(uname_S),Linux) HAVE_CLOCK_MONOTONIC = YesPlease # -lrt is needed for clock_gettime on glibc <= 2.16 NEEDS_LIBRT = YesPlease + HAVE_SYNC_FILE_RANGE = YesPlease HAVE_GETDELIM = YesPlease SANE_TEXT_GREP=-a FREAD_READS_DIRECTORIES = UnfortunatelyYes diff --git a/configure.ac b/configure.ac index 031e8d3fee8f22..c711037d625da7 100644 --- a/configure.ac +++ b/configure.ac @@ -1090,6 +1090,14 @@ AC_COMPILE_IFELSE([CLOCK_MONOTONIC_SRC], [AC_MSG_RESULT([no]) HAVE_CLOCK_MONOTONIC=]) GIT_CONF_SUBST([HAVE_CLOCK_MONOTONIC]) + +# +# Define HAVE_SYNC_FILE_RANGE=YesPlease if sync_file_range is available. +GIT_CHECK_FUNC(sync_file_range, + [HAVE_SYNC_FILE_RANGE=YesPlease], + [HAVE_SYNC_FILE_RANGE]) +GIT_CONF_SUBST([HAVE_SYNC_FILE_RANGE]) + # # Define NO_SETITIMER if you don't have setitimer. GIT_CHECK_FUNC(setitimer, diff --git a/environment.c b/environment.c index 7ba5ae06c71669..41a19809be1f2b 100644 --- a/environment.c +++ b/environment.c @@ -43,7 +43,7 @@ const char *git_attributes_file; const char *git_hooks_path; int zlib_compression_level = Z_BEST_SPEED; int pack_compression_level = Z_DEFAULT_COMPRESSION; -int fsync_object_files; +enum fsync_object_files_mode fsync_object_files; size_t packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE; size_t packed_git_limit = DEFAULT_PACKED_GIT_LIMIT; size_t delta_base_cache_limit = 96 * 1024 * 1024; diff --git a/git-compat-util.h b/git-compat-util.h index b46605300abf81..d14e243627645f 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -1210,6 +1210,13 @@ __attribute__((format (printf, 1, 2))) NORETURN void BUG(const char *fmt, ...); #endif +enum fsync_action { + FSYNC_WRITEOUT_ONLY, + FSYNC_HARDWARE_FLUSH +}; + +int git_fsync(int fd, enum fsync_action action); + /* * Preserves errno, prints a message, but gives no warning for ENOENT. * Returns 0 on success, which includes trying to unlink an object that does diff --git a/object-file.c b/object-file.c index 9ec1794c367e38..9aec225c68cf88 100644 --- a/object-file.c +++ b/object-file.c @@ -1906,8 +1906,18 @@ int hash_object_file(const struct git_hash_algo *algo, const void *buf, static void close_loose_object(int fd) { if (!the_repository->objects->odb->will_destroy) { - if (fsync_object_files) + switch (fsync_object_files) { + case FSYNC_OBJECT_FILES_OFF: + break; + case FSYNC_OBJECT_FILES_ON: fsync_or_die(fd, "loose object file"); + break; + case FSYNC_OBJECT_FILES_BATCH: + fsync_loose_object_bulk_checkin(fd); + break; + default: + BUG("Invalid fsync_object_files mode."); + } } if (close(fd) != 0) diff --git a/wrapper.c b/wrapper.c index 7c6586af321000..bb4f9f043cedad 100644 --- a/wrapper.c +++ b/wrapper.c @@ -540,6 +540,50 @@ int xmkstemp_mode(char *filename_template, int mode) return fd; } +int git_fsync(int fd, enum fsync_action action) +{ + switch (action) { + case FSYNC_WRITEOUT_ONLY: + +#ifdef __APPLE__ + /* + * on macOS, fsync just causes filesystem cache writeback but does not + * flush hardware caches. + */ + return fsync(fd); +#endif + +#ifdef HAVE_SYNC_FILE_RANGE + /* + * On linux 2.6.17 and above, sync_file_range is the way to issue + * a writeback without a hardware flush. An offset of 0 and size of 0 + * indicates writeout of the entire file and the wait flags ensure that all + * dirty data is written to the disk (potentially in a disk-side cache) + * before we continue. + */ + + return sync_file_range(fd, 0, 0, SYNC_FILE_RANGE_WAIT_BEFORE | + SYNC_FILE_RANGE_WRITE | + SYNC_FILE_RANGE_WAIT_AFTER); +#endif + + errno = ENOSYS; + return -1; + + case FSYNC_HARDWARE_FLUSH: + +#ifdef __APPLE__ + return fcntl(fd, F_FULLFSYNC); +#else + return fsync(fd); +#endif + + default: + BUG("unexpected git_fsync(%d) call", action); + } + +} + static int warn_if_unremovable(const char *op, const char *file, int rc) { int err; diff --git a/write-or-die.c b/write-or-die.c index d33e68f6abb30a..8f53953d4ababb 100644 --- a/write-or-die.c +++ b/write-or-die.c @@ -57,7 +57,7 @@ void fprintf_or_die(FILE *f, const char *fmt, ...) void fsync_or_die(int fd, const char *msg) { - while (fsync(fd) < 0) { + while (git_fsync(fd, FSYNC_HARDWARE_FLUSH) < 0) { if (errno != EINTR) die_errno("fsync error on '%s'", msg); } From 011b7b392ba761b8f70fca3647ae1f3f2df39842 Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:43 +0000 Subject: [PATCH 05/11] core.fsyncobjectfiles: add windows support for batch mode This commit adds a win32 implementation for fsync_no_flush that is called git_fsync. The 'NtFlushBuffersFileEx' function being called is available since Windows 8. If the function is not available, we return -1 and Git falls back to doing a full fsync. The operating system is told to flush data only without a hardware flush primitive. A later full fsync will cause the metadata log to be flushed and then the disk cache to be flushed on NTFS and ReFS. Other filesystems will treat this as a full flush operation. I added a new file here for this system call so as not to conflict with downstream changes in the git-for-windows repository related to fscache. Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- compat/mingw.h | 3 +++ compat/win32/flush.c | 28 ++++++++++++++++++++++++++++ config.mak.uname | 2 ++ contrib/buildsystems/CMakeLists.txt | 3 ++- wrapper.c | 4 ++++ 5 files changed, 39 insertions(+), 1 deletion(-) create mode 100644 compat/win32/flush.c diff --git a/compat/mingw.h b/compat/mingw.h index c9a52ad64a681f..6074a3d3cedb56 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -329,6 +329,9 @@ int mingw_getpagesize(void); #define getpagesize mingw_getpagesize #endif +int win32_fsync_no_flush(int fd); +#define fsync_no_flush win32_fsync_no_flush + struct rlimit { unsigned int rlim_cur; }; diff --git a/compat/win32/flush.c b/compat/win32/flush.c new file mode 100644 index 00000000000000..75324c24ee7cef --- /dev/null +++ b/compat/win32/flush.c @@ -0,0 +1,28 @@ +#include "../../git-compat-util.h" +#include +#include "lazyload.h" + +int win32_fsync_no_flush(int fd) +{ + IO_STATUS_BLOCK io_status; + +#define FLUSH_FLAGS_FILE_DATA_ONLY 1 + + DECLARE_PROC_ADDR(ntdll.dll, NTSTATUS, NtFlushBuffersFileEx, + HANDLE FileHandle, ULONG Flags, PVOID Parameters, ULONG ParameterSize, + PIO_STATUS_BLOCK IoStatusBlock); + + if (!INIT_PROC_ADDR(NtFlushBuffersFileEx)) { + errno = ENOSYS; + return -1; + } + + memset(&io_status, 0, sizeof(io_status)); + if (NtFlushBuffersFileEx((HANDLE)_get_osfhandle(fd), FLUSH_FLAGS_FILE_DATA_ONLY, + NULL, 0, &io_status)) { + errno = EINVAL; + return -1; + } + + return 0; +} diff --git a/config.mak.uname b/config.mak.uname index 7ba731a646f255..a46116e1d06eda 100644 --- a/config.mak.uname +++ b/config.mak.uname @@ -449,6 +449,7 @@ endif CFLAGS = BASIC_CFLAGS = -nologo -I. -Icompat/vcbuild/include -DWIN32 -D_CONSOLE -DHAVE_STRING_H -D_CRT_SECURE_NO_WARNINGS -D_CRT_NONSTDC_NO_DEPRECATE COMPAT_OBJS = compat/msvc.o compat/winansi.o \ + compat/win32/flush.o \ compat/win32/path-utils.o \ compat/win32/pthread.o compat/win32/syslog.o \ compat/win32/trace2_win32_process_info.o \ @@ -623,6 +624,7 @@ ifneq (,$(findstring MINGW,$(uname_S))) COMPAT_CFLAGS += -DSTRIP_EXTENSION=\".exe\" COMPAT_OBJS += compat/mingw.o compat/winansi.o \ compat/win32/trace2_win32_process_info.o \ + compat/win32/flush.o \ compat/win32/path-utils.o \ compat/win32/pthread.o compat/win32/syslog.o \ compat/win32/dirent.o diff --git a/contrib/buildsystems/CMakeLists.txt b/contrib/buildsystems/CMakeLists.txt index 171b4124afef58..b573a5ee122e33 100644 --- a/contrib/buildsystems/CMakeLists.txt +++ b/contrib/buildsystems/CMakeLists.txt @@ -261,7 +261,8 @@ if(CMAKE_SYSTEM_NAME STREQUAL "Windows") NOGDI OBJECT_CREATION_MODE=1 __USE_MINGW_ANSI_STDIO=0 USE_NED_ALLOCATOR OVERRIDE_STRDUP MMAP_PREVENTS_DELETE USE_WIN32_MMAP UNICODE _UNICODE HAVE_WPGMPTR ENSURE_MSYSTEM_IS_SET) - list(APPEND compat_SOURCES compat/mingw.c compat/winansi.c compat/win32/path-utils.c + list(APPEND compat_SOURCES compat/mingw.c compat/winansi.c + compat/win32/flush.c compat/win32/path-utils.c compat/win32/pthread.c compat/win32mmap.c compat/win32/syslog.c compat/win32/trace2_win32_process_info.c compat/win32/dirent.c compat/nedmalloc/nedmalloc.c compat/strdup.c) diff --git a/wrapper.c b/wrapper.c index bb4f9f043cedad..1a1e2fba9c942d 100644 --- a/wrapper.c +++ b/wrapper.c @@ -567,6 +567,10 @@ int git_fsync(int fd, enum fsync_action action) SYNC_FILE_RANGE_WAIT_AFTER); #endif +#ifdef fsync_no_flush + return fsync_no_flush(fd); +#endif + errno = ENOSYS; return -1; From 02434e6fe9afdee49a8a6182a3ea1045c645dfb3 Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:44 +0000 Subject: [PATCH 06/11] update-index: use the bulk-checkin infrastructure The update-index functionality is used internally by 'git stash push' to setup the internal stashed commit. This change enables bulk-checkin for update-index infrastructure to speed up adding new objects to the object database by leveraging the pack functionality and the new bulk-fsync functionality. There is some risk with this change, since under batch fsync, the object files will not be available until the update-index is entirely complete. This usage is unlikely, since any tool invoking update-index and expecting to see objects would have to synchronize with the update-index process after passing it a file path. Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- builtin/update-index.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/builtin/update-index.c b/builtin/update-index.c index 187203e8bb53cb..dc7368bb1ee2e5 100644 --- a/builtin/update-index.c +++ b/builtin/update-index.c @@ -5,6 +5,7 @@ */ #define USE_THE_INDEX_COMPATIBILITY_MACROS #include "cache.h" +#include "bulk-checkin.h" #include "config.h" #include "lockfile.h" #include "quote.h" @@ -1088,6 +1089,9 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) the_index.updated_skipworktree = 1; + /* we might be adding many objects to the object database */ + plug_bulk_checkin(); + /* * Custom copy of parse_options() because we want to handle * filename arguments as they come. @@ -1168,6 +1172,8 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) strbuf_release(&buf); } + /* by now we must have added all of the new objects */ + unplug_bulk_checkin(); if (split_index > 0) { if (git_config_get_split_index() == 0) warning(_("core.splitIndex is set to false; " From cfc560e4e73a5af8d5b5b7fe5fafc2f3bd104955 Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:45 +0000 Subject: [PATCH 07/11] unpack-objects: use the bulk-checkin infrastructure The unpack-objects functionality is used by fetch, push, and fast-import to turn the transfered data into object database entries when there are fewer objects than the 'unpacklimit' setting. By enabling bulk-checkin when unpacking objects, we can take advantage of batched fsyncs. Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- builtin/unpack-objects.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c index 4a9466295ba10d..51eb4f7b531aab 100644 --- a/builtin/unpack-objects.c +++ b/builtin/unpack-objects.c @@ -1,5 +1,6 @@ #include "builtin.h" #include "cache.h" +#include "bulk-checkin.h" #include "config.h" #include "object-store.h" #include "object.h" @@ -503,10 +504,12 @@ static void unpack_all(void) if (!quiet) progress = start_progress(_("Unpacking objects"), nr_objects); CALLOC_ARRAY(obj_list, nr_objects); + plug_bulk_checkin(); for (i = 0; i < nr_objects; i++) { unpack_one(i); display_progress(progress, i + 1); } + unplug_bulk_checkin(); stop_progress(&progress); if (delta_list) From 589d0fd711f0ed57a8345c99175fd7f7d034511d Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:46 +0000 Subject: [PATCH 08/11] core.fsyncobjectfiles: tests for batch mode Add test cases to exercise batch mode for: * 'git add' * 'git stash' * 'git update-index' * 'git unpack-objects' These tests ensure that the added data winds up in the object database. In this change we introduce a new test helper lib-unique-files.sh. The goal of this library is to create a tree of files that have different oids from any other files that may have been created in the current test repo. This helps us avoid missing validation of an object being added due to it already being in the repo. Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- t/lib-unique-files.sh | 36 ++++++++++++++++++++++++++++++++++++ t/t3700-add.sh | 20 ++++++++++++++++++++ t/t3903-stash.sh | 14 ++++++++++++++ t/t5300-pack-object.sh | 30 +++++++++++++++++++----------- 4 files changed, 89 insertions(+), 11 deletions(-) create mode 100644 t/lib-unique-files.sh diff --git a/t/lib-unique-files.sh b/t/lib-unique-files.sh new file mode 100644 index 00000000000000..a7de4ca8512ac5 --- /dev/null +++ b/t/lib-unique-files.sh @@ -0,0 +1,36 @@ +# Helper to create files with unique contents + + +# Create multiple files with unique contents. Takes the number of +# directories, the number of files in each directory, and the base +# directory. +# +# test_create_unique_files 2 3 my_dir -- Creates 2 directories with 3 files +# each in my_dir, all with unique +# contents. + +test_create_unique_files() { + test "$#" -ne 3 && BUG "3 param" + + local dirs=$1 + local files=$2 + local basedir=$3 + local counter=0 + test_tick + local basedata=$test_tick + + + rm -rf $basedir + + for i in $(test_seq $dirs) + do + local dir=$basedir/dir$i + + mkdir -p "$dir" + for j in $(test_seq $files) + do + counter=$((counter + 1)) + echo "$basedata.$counter" >"$dir/file$j.txt" + done + done +} diff --git a/t/t3700-add.sh b/t/t3700-add.sh index 4086e1ebbc97f1..36049a53ff7f0a 100755 --- a/t/t3700-add.sh +++ b/t/t3700-add.sh @@ -7,6 +7,8 @@ test_description='Test of git add, including the -- option.' . ./test-lib.sh +. $TEST_DIRECTORY/lib-unique-files.sh + # Test the file mode "$1" of the file "$2" in the index. test_mode_in_index () { case "$(git ls-files -s "$2")" in @@ -33,6 +35,24 @@ test_expect_success \ 'Test that "git add -- -q" works' \ 'touch -- -q && git add -- -q' +test_expect_success 'git add: core.fsyncobjectfiles=batch' " + test_create_unique_files 2 4 fsync-files && + git -c core.fsyncobjectfiles=batch add -- ./fsync-files/ && + rm -f fsynced_files && + git ls-files --stage fsync-files/ > fsynced_files && + test_line_count = 8 fsynced_files && + awk -- '{print \$2}' fsynced_files | xargs -n1 git cat-file -e +" + +test_expect_success 'git update-index: core.fsyncobjectfiles=batch' " + test_create_unique_files 2 4 fsync-files2 && + find fsync-files2 ! -type d -print | xargs git -c core.fsyncobjectfiles=batch update-index --add -- && + rm -f fsynced_files2 && + git ls-files --stage fsync-files2/ > fsynced_files2 && + test_line_count = 8 fsynced_files2 && + awk -- '{print \$2}' fsynced_files2 | xargs -n1 git cat-file -e +" + test_expect_success \ 'git add: Test that executable bit is not used if core.filemode=0' \ 'git config core.filemode 0 && diff --git a/t/t3903-stash.sh b/t/t3903-stash.sh index f0a82be9de7654..6324b52c874bef 100755 --- a/t/t3903-stash.sh +++ b/t/t3903-stash.sh @@ -9,6 +9,7 @@ GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME . ./test-lib.sh +. $TEST_DIRECTORY/lib-unique-files.sh diff_cmp () { for i in "$1" "$2" @@ -1293,6 +1294,19 @@ test_expect_success 'stash handles skip-worktree entries nicely' ' git rev-parse --verify refs/stash:A.t ' +test_expect_success 'stash with core.fsyncobjectfiles=batch' " + test_create_unique_files 2 4 fsync-files && + git -c core.fsyncobjectfiles=batch stash push -u -- ./fsync-files/ && + rm -f fsynced_files && + + # The files were untracked, so use the third parent, + # which contains the untracked files + git ls-tree -r stash^3 -- ./fsync-files/ > fsynced_files && + test_line_count = 8 fsynced_files && + awk -- '{print \$3}' fsynced_files | xargs -n1 git cat-file -e +" + + test_expect_success 'stash -c stash.useBuiltin=false warning ' ' expected="stash.useBuiltin support has been removed" && diff --git a/t/t5300-pack-object.sh b/t/t5300-pack-object.sh index e13a884207589d..38663dc1393654 100755 --- a/t/t5300-pack-object.sh +++ b/t/t5300-pack-object.sh @@ -162,23 +162,23 @@ test_expect_success 'pack-objects with bogus arguments' ' check_unpack () { test_when_finished "rm -rf git2" && - git init --bare git2 && - git -C git2 unpack-objects -n <"$1".pack && - git -C git2 unpack-objects <"$1".pack && - (cd .git && find objects -type f -print) | - while read path - do - cmp git2/$path .git/$path || { - echo $path differs. - return 1 - } - done + git $2 init --bare git2 && + ( + git $2 -C git2 unpack-objects -n <"$1".pack && + git $2 -C git2 unpack-objects <"$1".pack && + git $2 -C git2 cat-file --batch-check="%(objectname)" + ) current && + cmp obj-list current } test_expect_success 'unpack without delta' ' check_unpack test-1-${packname_1} ' +test_expect_success 'unpack without delta (core.fsyncobjectfiles=batch)' ' + check_unpack test-1-${packname_1} "-c core.fsyncobjectfiles=batch" +' + test_expect_success 'pack with REF_DELTA' ' packname_2=$(git pack-objects --progress test-2 stderr) && check_deltas stderr -gt 0 @@ -188,6 +188,10 @@ test_expect_success 'unpack with REF_DELTA' ' check_unpack test-2-${packname_2} ' +test_expect_success 'unpack with REF_DELTA (core.fsyncobjectfiles=batch)' ' + check_unpack test-2-${packname_2} "-c core.fsyncobjectfiles=batch" +' + test_expect_success 'pack with OFS_DELTA' ' packname_3=$(git pack-objects --progress --delta-base-offset test-3 \ stderr) && @@ -198,6 +202,10 @@ test_expect_success 'unpack with OFS_DELTA' ' check_unpack test-3-${packname_3} ' +test_expect_success 'unpack with OFS_DELTA (core.fsyncobjectfiles=batch)' ' + check_unpack test-3-${packname_3} "-c core.fsyncobjectfiles=batch" +' + test_expect_success 'compare delta flavors' ' perl -e '\'' defined($_ = -s $_) or die for @ARGV; From 3d1dbaf3cfef23003d1c67fb889ce809519cf9bf Mon Sep 17 00:00:00 2001 From: Neeraj Singh Date: Mon, 4 Oct 2021 16:57:47 +0000 Subject: [PATCH 09/11] core.fsyncobjectfiles: performance tests for add and stash Add a basic performance test for "git add" and "git stash" of a lot of new objects with various fsync settings. Signed-off-by: Neeraj Singh Signed-off-by: Junio C Hamano --- t/perf/p3700-add.sh | 43 ++++++++++++++++++++++++++++++++++++++++ t/perf/p3900-stash.sh | 46 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 89 insertions(+) create mode 100755 t/perf/p3700-add.sh create mode 100755 t/perf/p3900-stash.sh diff --git a/t/perf/p3700-add.sh b/t/perf/p3700-add.sh new file mode 100755 index 00000000000000..e93c08a2e70a8f --- /dev/null +++ b/t/perf/p3700-add.sh @@ -0,0 +1,43 @@ +#!/bin/sh +# +# This test measures the performance of adding new files to the object database +# and index. The test was originally added to measure the effect of the +# core.fsyncObjectFiles=batch mode, which is why we are testing different values +# of that setting explicitly and creating a lot of unique objects. + +test_description="Tests performance of add" + +. ./perf-lib.sh + +. $TEST_DIRECTORY/lib-unique-files.sh + +test_perf_default_repo +test_checkout_worktree + +dir_count=10 +files_per_dir=50 +total_files=$((dir_count * files_per_dir)) + +# We need to create the files each time we run the perf test, but +# we do not want to measure the cost of creating the files, so run +# the tet once. +if test "${GIT_PERF_REPEAT_COUNT-1}" -ne 1 +then + echo "warning: Setting GIT_PERF_REPEAT_COUNT=1" >&2 + GIT_PERF_REPEAT_COUNT=1 +fi + +for m in false true batch +do + test_expect_success "create the files for core.fsyncObjectFiles=$m" ' + git reset --hard && + # create files across directories + test_create_unique_files $dir_count $files_per_dir files + ' + + test_perf "add $total_files files (core.fsyncObjectFiles=$m)" " + git -c core.fsyncobjectfiles=$m add files + " +done + +test_done diff --git a/t/perf/p3900-stash.sh b/t/perf/p3900-stash.sh new file mode 100755 index 00000000000000..c9fcd0c03eb9b7 --- /dev/null +++ b/t/perf/p3900-stash.sh @@ -0,0 +1,46 @@ +#!/bin/sh +# +# This test measures the performance of adding new files to the object database +# and index. The test was originally added to measure the effect of the +# core.fsyncObjectFiles=batch mode, which is why we are testing different values +# of that setting explicitly and creating a lot of unique objects. + +test_description="Tests performance of stash" + +. ./perf-lib.sh + +. $TEST_DIRECTORY/lib-unique-files.sh + +test_perf_default_repo +test_checkout_worktree + +dir_count=10 +files_per_dir=50 +total_files=$((dir_count * files_per_dir)) + +# We need to create the files each time we run the perf test, but +# we do not want to measure the cost of creating the files, so run +# the tet once. +if test "${GIT_PERF_REPEAT_COUNT-1}" -ne 1 +then + echo "warning: Setting GIT_PERF_REPEAT_COUNT=1" >&2 + GIT_PERF_REPEAT_COUNT=1 +fi + +for m in false true batch +do + test_expect_success "create the files for core.fsyncObjectFiles=$m" ' + git reset --hard && + # create files across directories + test_create_unique_files $dir_count $files_per_dir files + ' + + # We only stash files in the 'files' subdirectory since + # the perf test infrastructure creates files in the + # current working directory that need to be preserved + test_perf "stash 500 files (core.fsyncObjectFiles=$m)" " + git -c core.fsyncobjectfiles=$m stash push -u -- files + " +done + +test_done From 976559d234bb7968192002e37f30e263f9cfcf23 Mon Sep 17 00:00:00 2001 From: "Neeraj K. Singh" Date: Wed, 27 Oct 2021 14:22:42 -0700 Subject: [PATCH 10/11] mingw: do not call xutftowcs_path in mingw_mktemp The `xutftowcs_path` function canonicalizes absolute paths using GetFullPathNameW. This canonicalization may change the length of the string (e.g. getting rid of \.\), which breaks callers that pass the template string in a strbuf and expect the length of the string to remain the same. In my particular case, the tmp-objdir code is passing a strbuf to mkdtemp and is breaking since the strbuf.len is no longer synchronized with strlen(strbuf.buf). Signed-off-by: Neeraj K. Singh Signed-off-by: Johannes Schindelin --- compat/mingw.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/compat/mingw.c b/compat/mingw.c index a56fb6cb35aa8f..a96fbc6f34f781 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -1239,8 +1239,11 @@ char *mingw_mktemp(char *template) int offset = 0; /* we need to return the path, thus no long paths here! */ - if (xutftowcs_path(wtemplate, template) < 0) + if (xutftowcsn(wtemplate, template, MAX_PATH, -1) < 0) { + if (errno == ERANGE) + errno = ENAMETOOLONG; return NULL; + } if (is_dir_sep(template[0]) && !is_dir_sep(template[1]) && iswalpha(wtemplate[0]) && wtemplate[1] == L':') { From ac845e12bad4790c28bdc8fbcd07f9efbcc7e929 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Thu, 28 Oct 2021 17:59:53 +0200 Subject: [PATCH 11/11] mingw: make core.fsyncObjectFiles default explicit Now that we have a `batch` mode, let's be explicit. This is a follow-up to ce4786fc77ce (mingw: change core.fsyncObjectFiles = 1 by default, 2017-09-04) and will most likely have to be squashed into it before upstreaming that patch (after the `batch` fsync mode was upstreamed). Signed-off-by: Johannes Schindelin --- compat/mingw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/compat/mingw.c b/compat/mingw.c index a96fbc6f34f781..5185289ff5a5d3 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -3757,7 +3757,7 @@ int wmain(int argc, const wchar_t **wargv) maybe_redirect_std_handles(); adjust_symlink_flags(); - fsync_object_files = 1; + fsync_object_files = FSYNC_OBJECT_FILES_ON; /* determine size of argv and environ conversion buffer */ maxlen = wcslen(wargv[0]);