From 68142e117c080b7a563d681dc34c7df2ab945df5 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 17 May 2021 12:24:49 +0000 Subject: [PATCH 1/4] hashfile: use write_in_full() The flush() logic in csum-file.c was introduced originally by c38138c (git-pack-objects: write the pack files with a SHA1 csum, 2005-06-26) and a portion of the logic performs similar utility to write_in_full() in wrapper.c. The history of write_in_full() is full of moves and renames, but was originally introduced by 7230e6d (Add write_or_die(), a helper function, 2006-08-21). The point of these sections of code are to flush a write buffer using xwrite() and report errors in the case of disk space issues or other generic input/output errors. The logic in flush() can interpret the output of write_in_full() to provide the correct error messages to users. The logic in the hashfile API has an additional set of logic to augment the progress indicator between calls to xwrite(). This was introduced by 2a128d6 (add throughput display to git-push, 2007-10-30). It seems that since the hashfile's buffer is only 8KB, these additional progress indicators might not be incredibly necessary. Instead, update the progress only when write_in_full() complete. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- csum-file.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/csum-file.c b/csum-file.c index 7510950fa3..3c26389d49 100644 --- a/csum-file.c +++ b/csum-file.c @@ -25,21 +25,14 @@ static void flush(struct hashfile *f, const void *buf, unsigned int count) die("sha1 file '%s' validation error", f->name); } - for (;;) { - int ret = xwrite(f->fd, buf, count); - if (ret > 0) { - f->total += ret; - display_throughput(f->tp, f->total); - buf = (char *) buf + ret; - count -= ret; - if (count) - continue; - return; - } - if (!ret) + if (write_in_full(f->fd, buf, count) < 0) { + if (errno == ENOSPC) die("sha1 file '%s' write error. Out of diskspace", f->name); die_errno("sha1 file '%s' write error", f->name); } + + f->total += count; + display_throughput(f->tp, f->total); } void hashflush(struct hashfile *f) From 2ca245f8be56e3269d02076b658e825b91236e5d Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 18 May 2021 18:32:46 +0000 Subject: [PATCH 2/4] csum-file.h: increase hashfile buffer size The hashfile API uses a hard-coded buffer size of 8KB and has ever since it was introduced in c38138c (git-pack-objects: write the pack files with a SHA1 csum, 2005-06-26). It performs a similar function to the hashing buffers in read-cache.c, but that code was updated from 8KB to 128KB in f279894 (read-cache: make the index write buffer size 128K, 2021-02-18). The justification there was that do_write_index() improves from 1.02s to 0.72s. Since our end goal is to have the index writing code use the hashfile API, we need to unify this buffer size to avoid a performance regression. There is a buffer, 'check_buffer', that is used to verify the check_fd file descriptor. When this buffer increases to 128K to fit the data being flushed, it causes the stack to overflow the limits placed in the test suite. To avoid issues with stack size, move both 'buffer' and 'check_buffer' to be heap pointers within 'struct hashfile'. The 'check_buffer' member is left as NULL unless check_fd is set in hashfd_check(). Both buffers are cleared as part of finalize_hashfile() which also frees the full structure. Since these buffers are now on the heap, we can adjust their size based on the needs of the consumer. In particular, callers to hashfd_throughput() are expecting to report progress indicators as the buffer flushes. These callers would prefer the smaller 8k buffer to avoid large delays between updates, especially for users with slower networks. When the progress indicator is not used, the larger buffer is preferrable. By adding a new trace2 region in the chunk-format API, we can see that the writing portion of 'git multi-pack-index write' lowers from ~1.49s to ~1.47s on a Linux machine. These effects may be more pronounced or diminished on other filesystems. The end-to-end timing is too noisy to have a definitive change either way. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- chunk-format.c | 12 +++++--- csum-file.c | 77 +++++++++++++++++++++++++++++++++++++------------- csum-file.h | 4 ++- 3 files changed, 68 insertions(+), 25 deletions(-) diff --git a/chunk-format.c b/chunk-format.c index da191e59a2..1c3dca62e2 100644 --- a/chunk-format.c +++ b/chunk-format.c @@ -58,9 +58,11 @@ void add_chunk(struct chunkfile *cf, int write_chunkfile(struct chunkfile *cf, void *data) { - int i; + int i, result = 0; uint64_t cur_offset = hashfile_total(cf->f); + trace2_region_enter("chunkfile", "write", the_repository); + /* Add the table of contents to the current offset */ cur_offset += (cf->chunks_nr + 1) * CHUNK_TOC_ENTRY_SIZE; @@ -77,10 +79,10 @@ int write_chunkfile(struct chunkfile *cf, void *data) for (i = 0; i < cf->chunks_nr; i++) { off_t start_offset = hashfile_total(cf->f); - int result = cf->chunks[i].write_fn(cf->f, data); + result = cf->chunks[i].write_fn(cf->f, data); if (result) - return result; + goto cleanup; if (hashfile_total(cf->f) - start_offset != cf->chunks[i].size) BUG("expected to write %"PRId64" bytes to chunk %"PRIx32", but wrote %"PRId64" instead", @@ -88,7 +90,9 @@ int write_chunkfile(struct chunkfile *cf, void *data) hashfile_total(cf->f) - start_offset); } - return 0; +cleanup: + trace2_region_leave("chunkfile", "write", the_repository); + return result; } int read_table_of_contents(struct chunkfile *cf, diff --git a/csum-file.c b/csum-file.c index 3c26389d49..3487d28ed7 100644 --- a/csum-file.c +++ b/csum-file.c @@ -11,19 +11,24 @@ #include "progress.h" #include "csum-file.h" +static void verify_buffer_or_die(struct hashfile *f, + const void *buf, + unsigned int count) +{ + ssize_t ret = read_in_full(f->check_fd, f->check_buffer, count); + + if (ret < 0) + die_errno("%s: sha1 file read error", f->name); + if (ret != count) + die("%s: sha1 file truncated", f->name); + if (memcmp(buf, f->check_buffer, count)) + die("sha1 file '%s' validation error", f->name); +} + static void flush(struct hashfile *f, const void *buf, unsigned int count) { - if (0 <= f->check_fd && count) { - unsigned char check_buffer[8192]; - ssize_t ret = read_in_full(f->check_fd, check_buffer, count); - - if (ret < 0) - die_errno("%s: sha1 file read error", f->name); - if (ret != count) - die("%s: sha1 file truncated", f->name); - if (memcmp(buf, check_buffer, count)) - die("sha1 file '%s' validation error", f->name); - } + if (0 <= f->check_fd && count) + verify_buffer_or_die(f, buf, count); if (write_in_full(f->fd, buf, count) < 0) { if (errno == ENOSPC) @@ -46,6 +51,13 @@ void hashflush(struct hashfile *f) } } +static void free_hashfile(struct hashfile *f) +{ + free(f->buffer); + free(f->check_buffer); + free(f); +} + int finalize_hashfile(struct hashfile *f, unsigned char *result, unsigned int flags) { int fd; @@ -75,20 +87,20 @@ int finalize_hashfile(struct hashfile *f, unsigned char *result, unsigned int fl if (close(f->check_fd)) die_errno("%s: sha1 file error on close", f->name); } - free(f); + free_hashfile(f); return fd; } void hashwrite(struct hashfile *f, const void *buf, unsigned int count) { while (count) { - unsigned left = sizeof(f->buffer) - f->offset; + unsigned left = f->buffer_len - f->offset; unsigned nr = count > left ? left : count; if (f->do_crc) f->crc32 = crc32(f->crc32, buf, nr); - if (nr == sizeof(f->buffer)) { + if (nr == f->buffer_len) { /* * Flush a full batch worth of data directly * from the input, skipping the memcpy() to @@ -114,11 +126,6 @@ void hashwrite(struct hashfile *f, const void *buf, unsigned int count) } } -struct hashfile *hashfd(int fd, const char *name) -{ - return hashfd_throughput(fd, name, NULL); -} - struct hashfile *hashfd_check(const char *name) { int sink, check; @@ -132,10 +139,14 @@ struct hashfile *hashfd_check(const char *name) die_errno("unable to open '%s'", name); f = hashfd(sink, name); f->check_fd = check; + f->check_buffer = xmalloc(f->buffer_len); + return f; } -struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp) +static struct hashfile *hashfd_internal(int fd, const char *name, + struct progress *tp, + size_t buffer_len) { struct hashfile *f = xmalloc(sizeof(*f)); f->fd = fd; @@ -146,9 +157,35 @@ struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp f->name = name; f->do_crc = 0; the_hash_algo->init_fn(&f->ctx); + + f->buffer_len = buffer_len; + f->buffer = xmalloc(buffer_len); + f->check_buffer = NULL; + return f; } +struct hashfile *hashfd(int fd, const char *name) +{ + /* + * Since we are not going to use a progress meter to + * measure the rate of data passing through this hashfile, + * use a larger buffer size to reduce fsync() calls. + */ + return hashfd_internal(fd, name, NULL, 128 * 1024); +} + +struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp) +{ + /* + * Since we are expecting to report progress of the + * write into this hashfile, use a smaller buffer + * size so the progress indicators arrive at a more + * frequent rate. + */ + return hashfd_internal(fd, name, tp, 8 * 1024); +} + void hashfile_checkpoint(struct hashfile *f, struct hashfile_checkpoint *checkpoint) { hashflush(f); diff --git a/csum-file.h b/csum-file.h index e54d53d1d0..3044bd19ab 100644 --- a/csum-file.h +++ b/csum-file.h @@ -16,7 +16,9 @@ struct hashfile { const char *name; int do_crc; uint32_t crc32; - unsigned char buffer[8192]; + size_t buffer_len; + unsigned char *buffer; + unsigned char *check_buffer; }; /* Checkpoint */ From 410334ed5212979a3ff6c8ca119ca14290ee7790 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 18 May 2021 18:32:47 +0000 Subject: [PATCH 3/4] read-cache: use hashfile instead of git_hash_ctx The do_write_index() method in read-cache.c has its own hashing logic and buffering mechanism. Specifically, the ce_write() method was introduced by 4990aadc (Speed up index file writing by chunking it nicely, 2005-04-20) and similar mechanisms were introduced a few months later in c38138cd (git-pack-objects: write the pack files with a SHA1 csum, 2005-06-26). Based on the timing, in the early days of the Git codebase, I figured that these roughly equivalent code paths were never unified only because it got lost in the shuffle. The hashfile API has since been used extensively in other file formats, such as pack-indexes, multi-pack-indexes, and commit-graphs. Therefore, it seems prudent to unify the index writing code to use the same mechanism. I discovered this disparity while trying to create a new index format that uses the chunk-format API. That API uses a hashfile as its base, so it is incompatible with the custom code in read-cache.c. This rewrite is rather straightforward. It replaces all writes to the temporary file with writes to the hashfile struct. This takes care of many of the direct interactions with the_hash_algo. There are still some git_hash_ctx uses remaining: the extension headers are hashed for use in the End of Index Entries (EOIE) extension. This use of the git_hash_ctx is left as-is. There are multiple reasons to not use a hashfile here, including the fact that the data is not actually writing to a file, just a hash computation. These hashes do not block our adoption of the chunk-format API in a future change to the index, so leave it as-is. The internals of the algorithms are mostly identical. Previously, the hashfile API used a smaller 8KB buffer instead of the 128KB buffer from read-cache.c. The previous change already unified these sizes. There is one subtle point: we do not pass the CSUM_FSYNC to the finalize_hashfile() method, which differs from most consumers of the hashfile API. The extra fsync() call indicated by this flag causes a significant peformance degradation that is noticeable for quick commands that write the index, such as "git add". Other consumers can absorb this cost with their more complicated data structure organization, and further writing structures such as pack-files and commit-graphs is rarely in the critical path for common user interactions. Some static methods become orphaned in this diff, so I marked them as MAYBE_UNUSED. The diff is much harder to read if they are deleted during this change. Instead, they will be deleted in the following change. In addition to the test suite passing, I computed indexes using the previous binaries and the binaries compiled after this change, and found the index data to be exactly equal. Finally, I did extensive performance testing of "git update-index --force-write" on repos of various sizes, including one with over 2 million paths at HEAD. These tests demonstrated less than 1% difference in behavior. As expected, the performance should be considered unchanged. The previous changes to increase the hashfile buffer size from 8K to 128K ensured this change would not create a peformance regression. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- read-cache.c | 137 +++++++++++++++++++++++++-------------------------- 1 file changed, 66 insertions(+), 71 deletions(-) diff --git a/read-cache.c b/read-cache.c index 1b3c2eb408..e3c9ab8033 100644 --- a/read-cache.c +++ b/read-cache.c @@ -26,6 +26,7 @@ #include "thread-utils.h" #include "progress.h" #include "sparse-index.h" +#include "csum-file.h" /* Mask for the name length in ce_flags in the on-disk index */ @@ -2525,6 +2526,7 @@ int repo_index_has_changes(struct repository *repo, static unsigned char write_buffer[WRITE_BUFFER_SIZE]; static unsigned long write_buffer_len; +MAYBE_UNUSED static int ce_write_flush(git_hash_ctx *context, int fd) { unsigned int buffered = write_buffer_len; @@ -2537,6 +2539,7 @@ static int ce_write_flush(git_hash_ctx *context, int fd) return 0; } +MAYBE_UNUSED static int ce_write(git_hash_ctx *context, int fd, void *data, unsigned int len) { while (len) { @@ -2559,19 +2562,24 @@ static int ce_write(git_hash_ctx *context, int fd, void *data, unsigned int len) return 0; } -static int write_index_ext_header(git_hash_ctx *context, git_hash_ctx *eoie_context, - int fd, unsigned int ext, unsigned int sz) +static int write_index_ext_header(struct hashfile *f, + git_hash_ctx *eoie_f, + unsigned int ext, + unsigned int sz) { - ext = htonl(ext); - sz = htonl(sz); - if (eoie_context) { - the_hash_algo->update_fn(eoie_context, &ext, 4); - the_hash_algo->update_fn(eoie_context, &sz, 4); + hashwrite_be32(f, ext); + hashwrite_be32(f, sz); + + if (eoie_f) { + ext = htonl(ext); + sz = htonl(sz); + the_hash_algo->update_fn(eoie_f, &ext, sizeof(ext)); + the_hash_algo->update_fn(eoie_f, &sz, sizeof(sz)); } - return ((ce_write(context, fd, &ext, 4) < 0) || - (ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0; + return 0; } +MAYBE_UNUSED static int ce_flush(git_hash_ctx *context, int fd, unsigned char *hash) { unsigned int left = write_buffer_len; @@ -2673,11 +2681,10 @@ static void copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, } } -static int ce_write_entry(git_hash_ctx *c, int fd, struct cache_entry *ce, +static int ce_write_entry(struct hashfile *f, struct cache_entry *ce, struct strbuf *previous_name, struct ondisk_cache_entry *ondisk) { int size; - int result; unsigned int saved_namelen; int stripped_name = 0; static unsigned char padding[8] = { 0x00 }; @@ -2693,11 +2700,9 @@ static int ce_write_entry(git_hash_ctx *c, int fd, struct cache_entry *ce, if (!previous_name) { int len = ce_namelen(ce); copy_cache_entry_to_ondisk(ondisk, ce); - result = ce_write(c, fd, ondisk, size); - if (!result) - result = ce_write(c, fd, ce->name, len); - if (!result) - result = ce_write(c, fd, padding, align_padding_size(size, len)); + hashwrite(f, ondisk, size); + hashwrite(f, ce->name, len); + hashwrite(f, padding, align_padding_size(size, len)); } else { int common, to_remove, prefix_size; unsigned char to_remove_vi[16]; @@ -2711,13 +2716,10 @@ static int ce_write_entry(git_hash_ctx *c, int fd, struct cache_entry *ce, prefix_size = encode_varint(to_remove, to_remove_vi); copy_cache_entry_to_ondisk(ondisk, ce); - result = ce_write(c, fd, ondisk, size); - if (!result) - result = ce_write(c, fd, to_remove_vi, prefix_size); - if (!result) - result = ce_write(c, fd, ce->name + common, ce_namelen(ce) - common); - if (!result) - result = ce_write(c, fd, padding, 1); + hashwrite(f, ondisk, size); + hashwrite(f, to_remove_vi, prefix_size); + hashwrite(f, ce->name + common, ce_namelen(ce) - common); + hashwrite(f, padding, 1); strbuf_splice(previous_name, common, to_remove, ce->name + common, ce_namelen(ce) - common); @@ -2727,7 +2729,7 @@ static int ce_write_entry(git_hash_ctx *c, int fd, struct cache_entry *ce, ce->ce_flags &= ~CE_STRIP_NAME; } - return result; + return 0; } /* @@ -2839,8 +2841,8 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, int strip_extensions) { uint64_t start = getnanotime(); - int newfd = tempfile->fd; - git_hash_ctx c, eoie_c; + struct hashfile *f; + git_hash_ctx *eoie_c = NULL; struct cache_header hdr; int i, err = 0, removed, extended, hdr_version; struct cache_entry **cache = istate->cache; @@ -2854,6 +2856,8 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, struct index_entry_offset_table *ieot = NULL; int nr, nr_threads; + f = hashfd(tempfile->fd, tempfile->filename.buf); + for (i = removed = extended = 0; i < entries; i++) { if (cache[i]->ce_flags & CE_REMOVE) removed++; @@ -2882,9 +2886,7 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, hdr.hdr_version = htonl(hdr_version); hdr.hdr_entries = htonl(entries - removed); - the_hash_algo->init_fn(&c); - if (ce_write(&c, newfd, &hdr, sizeof(hdr)) < 0) - return -1; + hashwrite(f, &hdr, sizeof(hdr)); if (!HAVE_THREADS || git_config_get_index_threads(&nr_threads)) nr_threads = 1; @@ -2919,12 +2921,8 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, } } - offset = lseek(newfd, 0, SEEK_CUR); - if (offset < 0) { - free(ieot); - return -1; - } - offset += write_buffer_len; + offset = hashfile_total(f); + nr = 0; previous_name = (hdr_version == 4) ? &previous_name_buf : NULL; @@ -2959,14 +2957,10 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, if (previous_name) previous_name->buf[0] = 0; nr = 0; - offset = lseek(newfd, 0, SEEK_CUR); - if (offset < 0) { - free(ieot); - return -1; - } - offset += write_buffer_len; + + offset = hashfile_total(f); } - if (ce_write_entry(&c, newfd, ce, previous_name, (struct ondisk_cache_entry *)&ondisk) < 0) + if (ce_write_entry(f, ce, previous_name, (struct ondisk_cache_entry *)&ondisk) < 0) err = -1; if (err) @@ -2985,14 +2979,16 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, return err; } - /* Write extension data here */ - offset = lseek(newfd, 0, SEEK_CUR); - if (offset < 0) { - free(ieot); - return -1; + offset = hashfile_total(f); + + /* + * The extension headers must be hashed on their own for the + * EOIE extension. Create a hashfile here to compute that hash. + */ + if (offset && record_eoie()) { + CALLOC_ARRAY(eoie_c, 1); + the_hash_algo->init_fn(eoie_c); } - offset += write_buffer_len; - the_hash_algo->init_fn(&eoie_c); /* * Lets write out CACHE_EXT_INDEXENTRYOFFSETTABLE first so that we @@ -3005,8 +3001,8 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, struct strbuf sb = STRBUF_INIT; write_ieot_extension(&sb, ieot); - err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_INDEXENTRYOFFSETTABLE, sb.len) < 0 - || ce_write(&c, newfd, sb.buf, sb.len) < 0; + err = write_index_ext_header(f, eoie_c, CACHE_EXT_INDEXENTRYOFFSETTABLE, sb.len) < 0; + hashwrite(f, sb.buf, sb.len); strbuf_release(&sb); free(ieot); if (err) @@ -3018,9 +3014,9 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, struct strbuf sb = STRBUF_INIT; err = write_link_extension(&sb, istate) < 0 || - write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_LINK, - sb.len) < 0 || - ce_write(&c, newfd, sb.buf, sb.len) < 0; + write_index_ext_header(f, eoie_c, CACHE_EXT_LINK, + sb.len) < 0; + hashwrite(f, sb.buf, sb.len); strbuf_release(&sb); if (err) return -1; @@ -3029,8 +3025,8 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, struct strbuf sb = STRBUF_INIT; cache_tree_write(&sb, istate->cache_tree); - err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_TREE, sb.len) < 0 - || ce_write(&c, newfd, sb.buf, sb.len) < 0; + err = write_index_ext_header(f, eoie_c, CACHE_EXT_TREE, sb.len) < 0; + hashwrite(f, sb.buf, sb.len); strbuf_release(&sb); if (err) return -1; @@ -3039,9 +3035,9 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, struct strbuf sb = STRBUF_INIT; resolve_undo_write(&sb, istate->resolve_undo); - err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_RESOLVE_UNDO, - sb.len) < 0 - || ce_write(&c, newfd, sb.buf, sb.len) < 0; + err = write_index_ext_header(f, eoie_c, CACHE_EXT_RESOLVE_UNDO, + sb.len) < 0; + hashwrite(f, sb.buf, sb.len); strbuf_release(&sb); if (err) return -1; @@ -3050,9 +3046,9 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, struct strbuf sb = STRBUF_INIT; write_untracked_extension(&sb, istate->untracked); - err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_UNTRACKED, - sb.len) < 0 || - ce_write(&c, newfd, sb.buf, sb.len) < 0; + err = write_index_ext_header(f, eoie_c, CACHE_EXT_UNTRACKED, + sb.len) < 0; + hashwrite(f, sb.buf, sb.len); strbuf_release(&sb); if (err) return -1; @@ -3061,14 +3057,14 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, struct strbuf sb = STRBUF_INIT; write_fsmonitor_extension(&sb, istate); - err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_FSMONITOR, sb.len) < 0 - || ce_write(&c, newfd, sb.buf, sb.len) < 0; + err = write_index_ext_header(f, eoie_c, CACHE_EXT_FSMONITOR, sb.len) < 0; + hashwrite(f, sb.buf, sb.len); strbuf_release(&sb); if (err) return -1; } if (istate->sparse_index) { - if (write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_SPARSE_DIRECTORIES, 0) < 0) + if (write_index_ext_header(f, eoie_c, CACHE_EXT_SPARSE_DIRECTORIES, 0) < 0) return -1; } @@ -3078,19 +3074,18 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, * read. Write it out regardless of the strip_extensions parameter as we need it * when loading the shared index. */ - if (offset && record_eoie()) { + if (eoie_c) { struct strbuf sb = STRBUF_INIT; - write_eoie_extension(&sb, &eoie_c, offset); - err = write_index_ext_header(&c, NULL, newfd, CACHE_EXT_ENDOFINDEXENTRIES, sb.len) < 0 - || ce_write(&c, newfd, sb.buf, sb.len) < 0; + write_eoie_extension(&sb, eoie_c, offset); + err = write_index_ext_header(f, NULL, CACHE_EXT_ENDOFINDEXENTRIES, sb.len) < 0; + hashwrite(f, sb.buf, sb.len); strbuf_release(&sb); if (err) return -1; } - if (ce_flush(&c, newfd, istate->oid.hash)) - return -1; + finalize_hashfile(f, istate->oid.hash, CSUM_HASH_IN_STREAM); if (close_tempfile_gently(tempfile)) { error(_("could not close '%s'"), get_tempfile_path(tempfile)); return -1; From f6e2cd0625c8f15505a1bc11828b21490dff59e6 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 18 May 2021 18:32:48 +0000 Subject: [PATCH 4/4] read-cache: delete unused hashing methods These methods were marked as MAYBE_UNUSED in the previous change to avoid a complicated diff. Delete them entirely, since we now use the hashfile API instead of this custom hashing code. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- read-cache.c | 64 ---------------------------------------------------- 1 file changed, 64 deletions(-) diff --git a/read-cache.c b/read-cache.c index e3c9ab8033..77961a3885 100644 --- a/read-cache.c +++ b/read-cache.c @@ -2522,46 +2522,6 @@ int repo_index_has_changes(struct repository *repo, } } -#define WRITE_BUFFER_SIZE (128 * 1024) -static unsigned char write_buffer[WRITE_BUFFER_SIZE]; -static unsigned long write_buffer_len; - -MAYBE_UNUSED -static int ce_write_flush(git_hash_ctx *context, int fd) -{ - unsigned int buffered = write_buffer_len; - if (buffered) { - the_hash_algo->update_fn(context, write_buffer, buffered); - if (write_in_full(fd, write_buffer, buffered) < 0) - return -1; - write_buffer_len = 0; - } - return 0; -} - -MAYBE_UNUSED -static int ce_write(git_hash_ctx *context, int fd, void *data, unsigned int len) -{ - while (len) { - unsigned int buffered = write_buffer_len; - unsigned int partial = WRITE_BUFFER_SIZE - buffered; - if (partial > len) - partial = len; - memcpy(write_buffer + buffered, data, partial); - buffered += partial; - if (buffered == WRITE_BUFFER_SIZE) { - write_buffer_len = buffered; - if (ce_write_flush(context, fd)) - return -1; - buffered = 0; - } - write_buffer_len = buffered; - len -= partial; - data = (char *) data + partial; - } - return 0; -} - static int write_index_ext_header(struct hashfile *f, git_hash_ctx *eoie_f, unsigned int ext, @@ -2579,30 +2539,6 @@ static int write_index_ext_header(struct hashfile *f, return 0; } -MAYBE_UNUSED -static int ce_flush(git_hash_ctx *context, int fd, unsigned char *hash) -{ - unsigned int left = write_buffer_len; - - if (left) { - write_buffer_len = 0; - the_hash_algo->update_fn(context, write_buffer, left); - } - - /* Flush first if not enough space for hash signature */ - if (left + the_hash_algo->rawsz > WRITE_BUFFER_SIZE) { - if (write_in_full(fd, write_buffer, left) < 0) - return -1; - left = 0; - } - - /* Append the hash signature at the end */ - the_hash_algo->final_fn(write_buffer + left, context); - hashcpy(hash, write_buffer + left); - left += the_hash_algo->rawsz; - return (write_in_full(fd, write_buffer, left) < 0) ? -1 : 0; -} - static void ce_smudge_racily_clean_entry(struct index_state *istate, struct cache_entry *ce) {