diff options
Diffstat (limited to 'read-cache.c')
| -rw-r--r-- | read-cache.c | 300 |
1 files changed, 151 insertions, 149 deletions
diff --git a/read-cache.c b/read-cache.c index 5a907af2fb..0c3ac3cefc 100644 --- a/read-cache.c +++ b/read-cache.c @@ -25,6 +25,8 @@ #include "fsmonitor.h" #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 */ @@ -47,6 +49,7 @@ #define CACHE_EXT_FSMONITOR 0x46534D4E /* "FSMN" */ #define CACHE_EXT_ENDOFINDEXENTRIES 0x454F4945 /* "EOIE" */ #define CACHE_EXT_INDEXENTRYOFFSETTABLE 0x49454F54 /* "IEOT" */ +#define CACHE_EXT_SPARSE_DIRECTORIES 0x73646972 /* "sdir" */ /* changes that can be kept in $GIT_DIR/index (basically all extensions) */ #define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \ @@ -101,6 +104,9 @@ static const char *alternate_index_output; static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce) { + if (S_ISSPARSEDIR(ce->ce_mode)) + istate->sparse_index = 1; + istate->cache[nr] = ce; add_name_hash(istate, ce); } @@ -544,7 +550,7 @@ int cache_name_stage_compare(const char *name1, int len1, int stage1, const char return 0; } -static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage) +static int index_name_stage_pos(struct index_state *istate, const char *name, int namelen, int stage) { int first, last; @@ -562,10 +568,31 @@ static int index_name_stage_pos(const struct index_state *istate, const char *na } first = next+1; } + + if (istate->sparse_index && + first > 0) { + /* Note: first <= istate->cache_nr */ + struct cache_entry *ce = istate->cache[first - 1]; + + /* + * If we are in a sparse-index _and_ the entry before the + * insertion position is a sparse-directory entry that is + * an ancestor of 'name', then we need to expand the index + * and search again. This will only trigger once, because + * thereafter the index is fully expanded. + */ + if (S_ISSPARSEDIR(ce->ce_mode) && + ce_namelen(ce) < namelen && + !strncmp(name, ce->name, ce_namelen(ce))) { + ensure_full_index(istate); + return index_name_stage_pos(istate, name, namelen, stage); + } + } + return -first-1; } -int index_name_pos(const struct index_state *istate, const char *name, int namelen) +int index_name_pos(struct index_state *istate, const char *name, int namelen) { return index_name_stage_pos(istate, name, namelen, 0); } @@ -813,8 +840,11 @@ struct cache_entry *make_empty_cache_entry(struct index_state *istate, size_t le return mem_pool__ce_calloc(find_mem_pool(istate), len); } -struct cache_entry *make_empty_transient_cache_entry(size_t len) +struct cache_entry *make_empty_transient_cache_entry(size_t len, + struct mem_pool *ce_mem_pool) { + if (ce_mem_pool) + return mem_pool__ce_calloc(ce_mem_pool, len); return xcalloc(1, cache_entry_size(len)); } @@ -848,8 +878,11 @@ struct cache_entry *make_cache_entry(struct index_state *istate, return ret; } -struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct object_id *oid, - const char *path, int stage) +struct cache_entry *make_transient_cache_entry(unsigned int mode, + const struct object_id *oid, + const char *path, + int stage, + struct mem_pool *ce_mem_pool) { struct cache_entry *ce; int len; @@ -860,7 +893,7 @@ struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct o } len = strlen(path); - ce = make_empty_transient_cache_entry(len); + ce = make_empty_transient_cache_entry(len, ce_mem_pool); oidcpy(&ce->oid, oid); memcpy(ce->name, path, len); @@ -985,7 +1018,7 @@ inside: } } if (protect_ntfs) { -#ifdef GIT_WINDOWS_NATIVE +#if defined GIT_WINDOWS_NATIVE || defined __CYGWIN__ if (c == '\\') return 0; #endif @@ -999,8 +1032,14 @@ inside: c = *path++; if ((c == '.' && !verify_dotfile(path, mode)) || - is_dir_sep(c) || c == '\0') + is_dir_sep(c)) return 0; + /* + * allow terminating directory separators for + * sparse directory entries. + */ + if (c == '\0') + return S_ISDIR(mode); } else if (c == '\\' && protect_ntfs) { if (is_ntfs_dotgit(path)) return 0; @@ -1514,6 +1553,7 @@ int refresh_index(struct index_state *istate, unsigned int flags, int quiet = (flags & REFRESH_QUIET) != 0; int not_new = (flags & REFRESH_IGNORE_MISSING) != 0; int ignore_submodules = (flags & REFRESH_IGNORE_SUBMODULES) != 0; + int ignore_skip_worktree = (flags & REFRESH_IGNORE_SKIP_WORKTREE) != 0; int first = 1; int in_porcelain = (flags & REFRESH_IN_PORCELAIN); unsigned int options = (CE_MATCH_REFRESH | @@ -1545,6 +1585,8 @@ int refresh_index(struct index_state *istate, unsigned int flags, */ preload_index(istate, pathspec, 0); trace2_region_enter("index", "refresh", NULL); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; i < istate->cache_nr; i++) { struct cache_entry *ce, *new_entry; int cache_errno = 0; @@ -1556,6 +1598,8 @@ int refresh_index(struct index_state *istate, unsigned int flags, ce = istate->cache[i]; if (ignore_submodules && S_ISGITLINK(ce->ce_mode)) continue; + if (ignore_skip_worktree && ce_skip_worktree(ce)) + continue; if (pathspec && !ce_path_match(istate, ce, pathspec, seen)) filtered = 1; @@ -1584,8 +1628,7 @@ int refresh_index(struct index_state *istate, unsigned int flags, t2_sum_scan += t2_did_scan; if (new_entry == ce) continue; - if (progress) - display_progress(progress, i); + display_progress(progress, i); if (!new_entry) { const char *fmt; @@ -1620,10 +1663,8 @@ int refresh_index(struct index_state *istate, unsigned int flags, trace2_data_intmax("index", NULL, "refresh/sum_lstat", t2_sum_lstat); trace2_data_intmax("index", NULL, "refresh/sum_scan", t2_sum_scan); trace2_region_leave("index", "refresh", NULL); - if (progress) { - display_progress(progress, istate->cache_nr); - stop_progress(&progress); - } + display_progress(progress, istate->cache_nr); + stop_progress(&progress); trace_performance_leave("refresh index"); return has_errors; } @@ -1760,6 +1801,10 @@ static int read_index_extension(struct index_state *istate, case CACHE_EXT_INDEXENTRYOFFSETTABLE: /* already handled in do_read_index() */ break; + case CACHE_EXT_SPARSE_DIRECTORIES: + /* no content, only an indicator */ + istate->sparse_index = 1; + break; default: if (*ext < 'A' || 'Z' < *ext) return error(_("index uses %.4s extension, which we do not understand"), @@ -1845,7 +1890,7 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool, ce->ce_flags = flags & ~CE_NAMEMASK; ce->ce_namelen = len; ce->index = 0; - hashcpy(ce->oid.hash, ondisk->data); + oidread(&ce->oid, ondisk->data); memcpy(ce->name, name, len); ce->name[len] = '\0'; @@ -2195,7 +2240,7 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist) if (verify_hdr(hdr, mmap_size) < 0) goto unmap; - hashcpy(istate->oid.hash, (const unsigned char *)hdr + mmap_size - the_hash_algo->rawsz); + oidread(&istate->oid, (const unsigned char *)hdr + mmap_size - the_hash_algo->rawsz); istate->version = ntohl(hdr->hdr_version); istate->cache_nr = ntohl(hdr->hdr_entries); istate->cache_alloc = alloc_nr(istate->cache_nr); @@ -2273,6 +2318,12 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist) trace2_data_intmax("index", the_repository, "read/cache_nr", istate->cache_nr); + if (!istate->repo) + istate->repo = the_repository; + prepare_repo_settings(istate->repo); + if (istate->repo->settings.command_requires_full_index) + ensure_full_index(istate); + return istate->cache_nr; unmap: @@ -2457,6 +2508,8 @@ int repo_index_has_changes(struct repository *repo, diff_flush(&opt); return opt.flags.has_changes != 0; } else { + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; sb && i < istate->cache_nr; i++) { if (i) strbuf_addch(sb, ' '); @@ -2466,80 +2519,23 @@ 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; - -static int ce_write_flush(git_hash_ctx *context, int fd) +static int write_index_ext_header(struct hashfile *f, + git_hash_ctx *eoie_f, + unsigned int ext, + unsigned int sz) { - 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; -} + hashwrite_be32(f, ext); + hashwrite_be32(f, sz); -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; + 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 0; } -static int write_index_ext_header(git_hash_ctx *context, git_hash_ctx *eoie_context, - int fd, 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); - } - return ((ce_write(context, fd, &ext, 4) < 0) || - (ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0; -} - -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) { @@ -2618,11 +2614,10 @@ 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 }; @@ -2638,11 +2633,9 @@ 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]; @@ -2656,13 +2649,10 @@ 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); @@ -2672,7 +2662,7 @@ 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; } /* @@ -2784,8 +2774,8 @@ 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; @@ -2799,6 +2789,8 @@ 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++; @@ -2827,9 +2819,7 @@ 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; @@ -2864,12 +2854,8 @@ 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; @@ -2904,14 +2890,10 @@ 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) @@ -2930,14 +2912,16 @@ 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 @@ -2950,8 +2934,8 @@ 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) @@ -2963,9 +2947,9 @@ 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; @@ -2974,8 +2958,8 @@ 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; @@ -2984,9 +2968,9 @@ 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; @@ -2995,9 +2979,9 @@ 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; @@ -3006,12 +2990,16 @@ 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(f, eoie_c, CACHE_EXT_SPARSE_DIRECTORIES, 0) < 0) + return -1; + } /* * CACHE_EXT_ENDOFINDEXENTRIES must be written as the last entry before the SHA1 @@ -3019,19 +3007,18 @@ 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; @@ -3071,6 +3058,14 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l unsigned flags) { int ret; + int was_full = !istate->sparse_index; + + ret = convert_to_sparse(istate); + + if (ret) { + warning(_("failed to convert to a sparse-index")); + return ret; + } /* * TODO trace2: replace "the_repository" with the actual repo instance @@ -3082,6 +3077,9 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l trace2_region_leave_printf("index", "do_write_index", the_repository, "%s", get_lock_file_path(lock)); + if (was_full) + ensure_full_index(istate); + if (ret) return ret; if (flags & COMMIT_LOCK) @@ -3172,9 +3170,10 @@ static int write_shared_index(struct index_state *istate, struct tempfile **temp) { struct split_index *si = istate->split_index; - int ret; + int ret, was_full = !istate->sparse_index; move_cache_to_base_index(istate); + convert_to_sparse(istate); trace2_region_enter_printf("index", "shared/do_write_index", the_repository, "%s", get_tempfile_path(*temp)); @@ -3182,6 +3181,9 @@ static int write_shared_index(struct index_state *istate, trace2_region_leave_printf("index", "shared/do_write_index", the_repository, "%s", get_tempfile_path(*temp)); + if (was_full) + ensure_full_index(istate); + if (ret) return ret; ret = adjust_shared_perm(get_tempfile_path(*temp)); @@ -3350,8 +3352,8 @@ int repo_read_index_unmerged(struct repository *repo) * We helpfully remove a trailing "/" from directories so that * the output of read_directory can be used as-is. */ -int index_name_is_other(const struct index_state *istate, const char *name, - int namelen) +int index_name_is_other(struct index_state *istate, const char *name, + int namelen) { int pos; if (namelen && name[namelen - 1] == '/') @@ -3369,7 +3371,7 @@ int index_name_is_other(const struct index_state *istate, const char *name, return 1; } -void *read_blob_data_from_index(const struct index_state *istate, +void *read_blob_data_from_index(struct index_state *istate, const char *path, unsigned long *size) { int pos, len; |