@matheusbsbs / matheus-bagliano / commits / f62312e028

packfile: introduce 'find_kept_pack_entry()'

Future callers will want a function to fill a 'struct pack_entry' for a given object id but _only_ from its position in any kept pack(s). In particular, an new 'git repack' mode which ensures the resulting packs form a geometric progress by object count will mark packs that it does not want to repack as "kept in-core", and it will want to halt a reachability traversal as soon as it visits an object in any of the kept packs. But, it does not want to halt the traversal at non-kept, or .keep packs. The obvious alternative is 'find_pack_entry()', but this doesn't quite suffice since it only returns the first pack it finds, which may or may not be kept (and the mru cache makes it unpredictable which one you'll get if there are options). Short of that, you could walk over all packs looking for the object in each one, but it scales with the number of packs, which may be prohibitive. Introduce 'find_kept_pack_entry()', a function which is like 'find_pack_entry()', but only fills in objects in the kept packs. Handle packs which have .keep files, as well as in-core kept packs separately, since certain callers will want to distinguish one from the other. (Though on-disk and in-core kept packs share the adjective "kept", it is best to think of the two sets as independent.) There is a gotcha when looking up objects that are duplicated in kept and non-kept packs, particularly when the MIDX stores the non-kept version and the caller asked for kept objects only. This could be resolved by teaching the MIDX to resolve duplicates by always favoring the kept pack (if one exists), but this breaks an assumption in existing MIDXs, and so it would require a format change. The benefit to changing the MIDX in this way is marginal, so we instead have a more thorough check here which is explained with a comment. Callers will be added in subsequent patches. Co-authored-by: Jeff King <peff@peff.net> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Taylor Blau <me@ttaylorr.com> Reviewed-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Taylor Blau committed Feb 22, 2021 at 21:25 UTC f62312e02837d91e3b47ea876654bf3ac97b2905

2 files changed +64 -5

packfile.c

+59 -5

@@ -2042,7 +2042,10 @@ static int fill_pack_entry(const struct object_id *oid,

2042 return 1;

2043 }

2044

2045 -int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e)

2045 +static int find_one_pack_entry(struct repository *r,

2046 + const struct object_id *oid,

2047 + struct pack_entry *e,

2048 + int kept_only)

2049 {

2050 struct list_head *pos;

2051 struct multi_pack_index *m;

@@ -2052,26 +2055,77 @@ int find_pack_entry(struct repository *r, const struct object_id *oid, struct pa

2055 return 0;

2056

2057 for (m = r->objects->multi_pack_index; m; m = m->next) {

2055 - if (fill_midx_entry(r, oid, e, m))

2058 + if (!fill_midx_entry(r, oid, e, m))

2059 + continue;

2060 +

2061 + if (!kept_only)

2062 + return 1;

2063 +

2064 + if (((kept_only & ON_DISK_KEEP_PACKS) && e->p->pack_keep) ||

2065 + ((kept_only & IN_CORE_KEEP_PACKS) && e->p->pack_keep_in_core))

2066 return 1;

2067 }

2068

2069 list_for_each(pos, &r->objects->packed_git_mru) {

2070 struct packed_git *p = list_entry(pos, struct packed_git, mru);

2061 - if (!p->multi_pack_index && fill_pack_entry(oid, e, p)) {

2062 - list_move(&p->mru, &r->objects->packed_git_mru);

2063 - return 1;

2071 + if (p->multi_pack_index && !kept_only) {

2072 + /*

2073 + * If this pack is covered by the MIDX, we'd have found

2074 + * the object already in the loop above if it was here,

2075 + * so don't bother looking.

2076 + *

2077 + * The exception is if we are looking only at kept

2078 + * packs. An object can be present in two packs covered

2079 + * by the MIDX, one kept and one not-kept. And as the

2080 + * MIDX points to only one copy of each object, it might

2081 + * have returned only the non-kept version above. We

2082 + * have to check again to be thorough.

2083 + */

2084 + continue;

2085 + }

2086 + if (!kept_only ||

2087 + (((kept_only & ON_DISK_KEEP_PACKS) && p->pack_keep) ||

2088 + ((kept_only & IN_CORE_KEEP_PACKS) && p->pack_keep_in_core))) {

2089 + if (fill_pack_entry(oid, e, p)) {

2090 + list_move(&p->mru, &r->objects->packed_git_mru);

2091 + return 1;

2092 + }

2093 }

2094 }

2095 return 0;

2096 }

2097

2098 +int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e)

2099 +{

2100 + return find_one_pack_entry(r, oid, e, 0);

2101 +}

2102 +

2103 +int find_kept_pack_entry(struct repository *r,

2104 + const struct object_id *oid,

2105 + unsigned flags,

2106 + struct pack_entry *e)

2107 +{

2108 + /*

2109 + * Load all packs, including midx packs, since our "kept" strategy

2110 + * relies on that. We're relying on the side effect of it setting up

2111 + * r->objects->packed_git, which is a little ugly.

2112 + */

2113 + get_all_packs(r);

2114 + return find_one_pack_entry(r, oid, e, flags);

2115 +}

2116 +

2117 int has_object_pack(const struct object_id *oid)

2118 {

2119 struct pack_entry e;

2120 return find_pack_entry(the_repository, oid, &e);

2121 }

2122

2123 +int has_object_kept_pack(const struct object_id *oid, unsigned flags)

2124 +{

2125 + struct pack_entry e;

2126 + return find_kept_pack_entry(the_repository, oid, flags, &e);

2127 +}

2128 +

2129 int has_pack_index(const unsigned char *sha1)

2130 {

2131 struct stat st;

packfile.h

@@ -162,13 +162,18 @@ int packed_object_info(struct repository *r,

162 void mark_bad_packed_object(struct packed_git *p, const unsigned char *sha1);

163 const struct packed_git *has_packed_and_bad(struct repository *r, const unsigned char *sha1);

164

165 +#define ON_DISK_KEEP_PACKS 1

166 +#define IN_CORE_KEEP_PACKS 2

167 +

168 /*

169 * Iff a pack file in the given repository contains the object named by sha1,

170 * return true and store its location to e.

171 */

172 int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e);

173 +int find_kept_pack_entry(struct repository *r, const struct object_id *oid, unsigned flags, struct pack_entry *e);

174

175 int has_object_pack(const struct object_id *oid);

176 +int has_object_kept_pack(const struct object_id *oid, unsigned flags);

177

178 int has_pack_index(const unsigned char *sha1);

179