From 1c573cdd7219db5600fb2b5249f7c8835c8d416d Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 20 May 2022 19:17:38 -0400 Subject: pack-write: pass 'struct packing_data' to 'stage_tmp_packfiles' This structure will be used to communicate the per-object mtimes when writing a cruft pack. Here, we need the full packing_data structure because the mtime information is stored in an array there, not on the individual object_entry's themselves (to avoid paying the overhead in structure width for operations which do not generate a cruft pack). We haven't passed this information down before because one of the two callers (in bulk-checkin.c) does not have a packing_data structure at all. In that case (where no cruft pack will be generated), NULL is passed instead. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- pack-write.c | 1 + 1 file changed, 1 insertion(+) (limited to 'pack-write.c') diff --git a/pack-write.c b/pack-write.c index 51812cb129..a2adc565f4 100644 --- a/pack-write.c +++ b/pack-write.c @@ -484,6 +484,7 @@ void stage_tmp_packfiles(struct strbuf *name_buffer, const char *pack_tmp_name, struct pack_idx_entry **written_list, uint32_t nr_written, + struct packing_data *to_pack, struct pack_idx_option *pack_idx_opts, unsigned char hash[], char **idx_tmp_name) -- cgit v1.3 From d9fef9d90d27b6794350ec3bc622042b79397088 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 20 May 2022 19:17:41 -0400 Subject: chunk-format.h: extract oid_version() There are three definitions of an identical function which converts `the_hash_algo` into either 1 (for SHA-1) or 2 (for SHA-256). There is a copy of this function for writing both the commit-graph and multi-pack-index file, and another inline definition used to write the .rev header. Consolidate these into a single definition in chunk-format.h. It's not clear that this is the best header to define this function in, but it should do for now. (Worth noting, the .rev caller expects a 4-byte unsigned, but the other two callers work with a single unsigned byte. The consolidated version uses the latter type, and lets the compiler widen it when required). Another caller will be added in a subsequent patch. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- chunk-format.c | 12 ++++++++++++ chunk-format.h | 3 +++ commit-graph.c | 18 +++--------------- midx.c | 18 +++--------------- pack-write.c | 15 ++------------- 5 files changed, 23 insertions(+), 43 deletions(-) (limited to 'pack-write.c') diff --git a/chunk-format.c b/chunk-format.c index 1c3dca62e2..0275b74a89 100644 --- a/chunk-format.c +++ b/chunk-format.c @@ -181,3 +181,15 @@ int read_chunk(struct chunkfile *cf, return CHUNK_NOT_FOUND; } + +uint8_t oid_version(const struct git_hash_algo *algop) +{ + switch (hash_algo_by_ptr(algop)) { + case GIT_HASH_SHA1: + return 1; + case GIT_HASH_SHA256: + return 2; + default: + die(_("invalid hash version")); + } +} diff --git a/chunk-format.h b/chunk-format.h index 9ccbe00377..7885aa0848 100644 --- a/chunk-format.h +++ b/chunk-format.h @@ -2,6 +2,7 @@ #define CHUNK_FORMAT_H #include "git-compat-util.h" +#include "hash.h" struct hashfile; struct chunkfile; @@ -65,4 +66,6 @@ int read_chunk(struct chunkfile *cf, chunk_read_fn fn, void *data); +uint8_t oid_version(const struct git_hash_algo *algop); + #endif diff --git a/commit-graph.c b/commit-graph.c index 441b36016b..f430d5058b 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -193,18 +193,6 @@ char *get_commit_graph_chain_filename(struct object_directory *odb) return xstrfmt("%s/info/commit-graphs/commit-graph-chain", odb->path); } -static uint8_t oid_version(void) -{ - switch (hash_algo_by_ptr(the_hash_algo)) { - case GIT_HASH_SHA1: - return 1; - case GIT_HASH_SHA256: - return 2; - default: - die(_("invalid hash version")); - } -} - static struct commit_graph *alloc_commit_graph(void) { struct commit_graph *g = xcalloc(1, sizeof(*g)); @@ -365,9 +353,9 @@ struct commit_graph *parse_commit_graph(struct repository *r, } hash_version = *(unsigned char*)(data + 5); - if (hash_version != oid_version()) { + if (hash_version != oid_version(the_hash_algo)) { error(_("commit-graph hash version %X does not match version %X"), - hash_version, oid_version()); + hash_version, oid_version(the_hash_algo)); return NULL; } @@ -1921,7 +1909,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) hashwrite_be32(f, GRAPH_SIGNATURE); hashwrite_u8(f, GRAPH_VERSION); - hashwrite_u8(f, oid_version()); + hashwrite_u8(f, oid_version(the_hash_algo)); hashwrite_u8(f, get_num_chunks(cf)); hashwrite_u8(f, ctx->num_commit_graphs_after - 1); diff --git a/midx.c b/midx.c index 107365d211..d7459fd616 100644 --- a/midx.c +++ b/midx.c @@ -41,18 +41,6 @@ #define PACK_EXPIRED UINT_MAX -static uint8_t oid_version(void) -{ - switch (hash_algo_by_ptr(the_hash_algo)) { - case GIT_HASH_SHA1: - return 1; - case GIT_HASH_SHA256: - return 2; - default: - die(_("invalid hash version")); - } -} - const unsigned char *get_midx_checksum(struct multi_pack_index *m) { return m->data + m->data_len - the_hash_algo->rawsz; @@ -134,9 +122,9 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local m->version); hash_version = m->data[MIDX_BYTE_HASH_VERSION]; - if (hash_version != oid_version()) { + if (hash_version != oid_version(the_hash_algo)) { error(_("multi-pack-index hash version %u does not match version %u"), - hash_version, oid_version()); + hash_version, oid_version(the_hash_algo)); goto cleanup_fail; } m->hash_len = the_hash_algo->rawsz; @@ -420,7 +408,7 @@ static size_t write_midx_header(struct hashfile *f, { hashwrite_be32(f, MIDX_SIGNATURE); hashwrite_u8(f, MIDX_VERSION); - hashwrite_u8(f, oid_version()); + hashwrite_u8(f, oid_version(the_hash_algo)); hashwrite_u8(f, num_chunks); hashwrite_u8(f, 0); /* unused */ hashwrite_be32(f, num_packs); diff --git a/pack-write.c b/pack-write.c index a2adc565f4..27b171e440 100644 --- a/pack-write.c +++ b/pack-write.c @@ -2,6 +2,7 @@ #include "pack.h" #include "csum-file.h" #include "remote.h" +#include "chunk-format.h" void reset_pack_idx_option(struct pack_idx_option *opts) { @@ -181,21 +182,9 @@ static int pack_order_cmp(const void *va, const void *vb, void *ctx) static void write_rev_header(struct hashfile *f) { - uint32_t oid_version; - switch (hash_algo_by_ptr(the_hash_algo)) { - case GIT_HASH_SHA1: - oid_version = 1; - break; - case GIT_HASH_SHA256: - oid_version = 2; - break; - default: - die("write_rev_header: unknown hash version"); - } - hashwrite_be32(f, RIDX_SIGNATURE); hashwrite_be32(f, RIDX_VERSION); - hashwrite_be32(f, oid_version); + hashwrite_be32(f, oid_version(the_hash_algo)); } static void write_rev_index_positions(struct hashfile *f, -- cgit v1.3 From 5dfaf49a5a651d3e8c3552bc2e833312a3671a4f Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 20 May 2022 19:17:43 -0400 Subject: pack-mtimes: support writing pack .mtimes files Now that the `.mtimes` format is defined, supplement the pack-write API to be able to conditionally write an `.mtimes` file along with a pack by setting an additional flag and passing an oidmap that contains the timestamps corresponding to each object in the pack. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- pack-objects.c | 6 +++++ pack-objects.h | 25 +++++++++++++++++++ pack-write.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ pack.h | 1 + 4 files changed, 109 insertions(+) (limited to 'pack-write.c') diff --git a/pack-objects.c b/pack-objects.c index fe2a4eace9..272e8d4517 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -170,6 +170,9 @@ struct object_entry *packlist_alloc(struct packing_data *pdata, if (pdata->layer) REALLOC_ARRAY(pdata->layer, pdata->nr_alloc); + + if (pdata->cruft_mtime) + REALLOC_ARRAY(pdata->cruft_mtime, pdata->nr_alloc); } new_entry = pdata->objects + pdata->nr_objects++; @@ -198,6 +201,9 @@ struct object_entry *packlist_alloc(struct packing_data *pdata, if (pdata->layer) pdata->layer[pdata->nr_objects - 1] = 0; + if (pdata->cruft_mtime) + pdata->cruft_mtime[pdata->nr_objects - 1] = 0; + return new_entry; } diff --git a/pack-objects.h b/pack-objects.h index dca2351ef9..393b9db546 100644 --- a/pack-objects.h +++ b/pack-objects.h @@ -168,6 +168,14 @@ struct packing_data { /* delta islands */ unsigned int *tree_depth; unsigned char *layer; + + /* + * Used when writing cruft packs. + * + * Object mtimes are stored in pack order when writing, but + * written out in lexicographic (index) order. + */ + uint32_t *cruft_mtime; }; void prepare_packing_data(struct repository *r, struct packing_data *pdata); @@ -289,4 +297,21 @@ static inline void oe_set_layer(struct packing_data *pack, pack->layer[e - pack->objects] = layer; } +static inline uint32_t oe_cruft_mtime(struct packing_data *pack, + struct object_entry *e) +{ + if (!pack->cruft_mtime) + return 0; + return pack->cruft_mtime[e - pack->objects]; +} + +static inline void oe_set_cruft_mtime(struct packing_data *pack, + struct object_entry *e, + uint32_t mtime) +{ + if (!pack->cruft_mtime) + CALLOC_ARRAY(pack->cruft_mtime, pack->nr_alloc); + pack->cruft_mtime[e - pack->objects] = mtime; +} + #endif diff --git a/pack-write.c b/pack-write.c index 27b171e440..23c0342018 100644 --- a/pack-write.c +++ b/pack-write.c @@ -3,6 +3,10 @@ #include "csum-file.h" #include "remote.h" #include "chunk-format.h" +#include "pack-mtimes.h" +#include "oidmap.h" +#include "chunk-format.h" +#include "pack-objects.h" void reset_pack_idx_option(struct pack_idx_option *opts) { @@ -277,6 +281,70 @@ const char *write_rev_file_order(const char *rev_name, return rev_name; } +static void write_mtimes_header(struct hashfile *f) +{ + hashwrite_be32(f, MTIMES_SIGNATURE); + hashwrite_be32(f, MTIMES_VERSION); + hashwrite_be32(f, oid_version(the_hash_algo)); +} + +/* + * Writes the object mtimes of "objects" for use in a .mtimes file. + * Note that objects must be in lexicographic (index) order, which is + * the expected ordering of these values in the .mtimes file. + */ +static void write_mtimes_objects(struct hashfile *f, + struct packing_data *to_pack, + struct pack_idx_entry **objects, + uint32_t nr_objects) +{ + uint32_t i; + for (i = 0; i < nr_objects; i++) { + struct object_entry *e = (struct object_entry*)objects[i]; + hashwrite_be32(f, oe_cruft_mtime(to_pack, e)); + } +} + +static void write_mtimes_trailer(struct hashfile *f, const unsigned char *hash) +{ + hashwrite(f, hash, the_hash_algo->rawsz); +} + +static const char *write_mtimes_file(const char *mtimes_name, + struct packing_data *to_pack, + struct pack_idx_entry **objects, + uint32_t nr_objects, + const unsigned char *hash) +{ + struct hashfile *f; + int fd; + + if (!to_pack) + BUG("cannot call write_mtimes_file with NULL packing_data"); + + if (!mtimes_name) { + struct strbuf tmp_file = STRBUF_INIT; + fd = odb_mkstemp(&tmp_file, "pack/tmp_mtimes_XXXXXX"); + mtimes_name = strbuf_detach(&tmp_file, NULL); + } else { + unlink(mtimes_name); + fd = xopen(mtimes_name, O_CREAT|O_EXCL|O_WRONLY, 0600); + } + f = hashfd(fd, mtimes_name); + + write_mtimes_header(f); + write_mtimes_objects(f, to_pack, objects, nr_objects); + write_mtimes_trailer(f, hash); + + if (adjust_shared_perm(mtimes_name) < 0) + die(_("failed to make %s readable"), mtimes_name); + + finalize_hashfile(f, NULL, FSYNC_COMPONENT_PACK_METADATA, + CSUM_HASH_IN_STREAM | CSUM_CLOSE | CSUM_FSYNC); + + return mtimes_name; +} + off_t write_pack_header(struct hashfile *f, uint32_t nr_entries) { struct pack_header hdr; @@ -479,6 +547,7 @@ void stage_tmp_packfiles(struct strbuf *name_buffer, char **idx_tmp_name) { const char *rev_tmp_name = NULL; + const char *mtimes_tmp_name = NULL; if (adjust_shared_perm(pack_tmp_name)) die_errno("unable to make temporary pack file readable"); @@ -491,9 +560,17 @@ void stage_tmp_packfiles(struct strbuf *name_buffer, rev_tmp_name = write_rev_file(NULL, written_list, nr_written, hash, pack_idx_opts->flags); + if (pack_idx_opts->flags & WRITE_MTIMES) { + mtimes_tmp_name = write_mtimes_file(NULL, to_pack, written_list, + nr_written, + hash); + } + rename_tmp_packfile(name_buffer, pack_tmp_name, "pack"); if (rev_tmp_name) rename_tmp_packfile(name_buffer, rev_tmp_name, "rev"); + if (mtimes_tmp_name) + rename_tmp_packfile(name_buffer, mtimes_tmp_name, "mtimes"); } void write_promisor_file(const char *promisor_name, struct ref **sought, int nr_sought) diff --git a/pack.h b/pack.h index fd27cfdfd7..01d385903a 100644 --- a/pack.h +++ b/pack.h @@ -44,6 +44,7 @@ struct pack_idx_option { #define WRITE_IDX_STRICT 02 #define WRITE_REV 04 #define WRITE_REV_VERIFY 010 +#define WRITE_MTIMES 020 uint32_t version; uint32_t off32_limit; -- cgit v1.3