summaryrefslogtreecommitdiff
path: root/pack-revindex.c
diff options
context:
space:
mode:
authorJunio C Hamano <gitster@pobox.com>2021-04-08 20:23:25 (GMT)
committerJunio C Hamano <gitster@pobox.com>2021-04-08 20:23:25 (GMT)
commite6b971fcf5d85db821636f2d887cfaf204b32bda (patch)
tree8d94e5501218bd7614729a363637e3746568a814 /pack-revindex.c
parenta0dda6023ed82b927fa205c474654699a5b07a82 (diff)
parent30077524611cae8f25111e2c8b8d42136aa58787 (diff)
downloadgit-e6b971fcf5d85db821636f2d887cfaf204b32bda.zip
git-e6b971fcf5d85db821636f2d887cfaf204b32bda.tar.gz
git-e6b971fcf5d85db821636f2d887cfaf204b32bda.tar.bz2
Merge branch 'tb/reverse-midx'
An on-disk reverse-index to map the in-pack location of an object back to its object name across multiple packfiles is introduced. * tb/reverse-midx: midx.c: improve cache locality in midx_pack_order_cmp() pack-revindex: write multi-pack reverse indexes pack-write.c: extract 'write_rev_file_order' pack-revindex: read multi-pack reverse indexes Documentation/technical: describe multi-pack reverse indexes midx: make some functions non-static midx: keep track of the checksum midx: don't free midx_name early midx: allow marking a pack as preferred t/helper/test-read-midx.c: add '--show-objects' builtin/multi-pack-index.c: display usage on unrecognized command builtin/multi-pack-index.c: don't enter bogus cmd_mode builtin/multi-pack-index.c: split sub-commands builtin/multi-pack-index.c: define common usage with a macro builtin/multi-pack-index.c: don't handle 'progress' separately builtin/multi-pack-index.c: inline 'flags' with options
Diffstat (limited to 'pack-revindex.c')
-rw-r--r--pack-revindex.c126
1 files changed, 126 insertions, 0 deletions
diff --git a/pack-revindex.c b/pack-revindex.c
index 4262530..0e4a31d 100644
--- a/pack-revindex.c
+++ b/pack-revindex.c
@@ -3,6 +3,7 @@
#include "object-store.h"
#include "packfile.h"
#include "config.h"
+#include "midx.h"
struct revindex_entry {
off_t offset;
@@ -293,6 +294,43 @@ int load_pack_revindex(struct packed_git *p)
return -1;
}
+int load_midx_revindex(struct multi_pack_index *m)
+{
+ char *revindex_name;
+ int ret;
+ if (m->revindex_data)
+ return 0;
+
+ revindex_name = get_midx_rev_filename(m);
+
+ ret = load_revindex_from_disk(revindex_name,
+ m->num_objects,
+ &m->revindex_map,
+ &m->revindex_len);
+ if (ret)
+ goto cleanup;
+
+ m->revindex_data = (const uint32_t *)((const char *)m->revindex_map + RIDX_HEADER_SIZE);
+
+cleanup:
+ free(revindex_name);
+ return ret;
+}
+
+int close_midx_revindex(struct multi_pack_index *m)
+{
+ if (!m || !m->revindex_map)
+ return 0;
+
+ munmap((void*)m->revindex_map, m->revindex_len);
+
+ m->revindex_map = NULL;
+ m->revindex_data = NULL;
+ m->revindex_len = 0;
+
+ return 0;
+}
+
int offset_to_pack_pos(struct packed_git *p, off_t ofs, uint32_t *pos)
{
unsigned lo, hi;
@@ -347,3 +385,91 @@ off_t pack_pos_to_offset(struct packed_git *p, uint32_t pos)
else
return nth_packed_object_offset(p, pack_pos_to_index(p, pos));
}
+
+uint32_t pack_pos_to_midx(struct multi_pack_index *m, uint32_t pos)
+{
+ if (!m->revindex_data)
+ BUG("pack_pos_to_midx: reverse index not yet loaded");
+ if (m->num_objects <= pos)
+ BUG("pack_pos_to_midx: out-of-bounds object at %"PRIu32, pos);
+ return get_be32(m->revindex_data + pos);
+}
+
+struct midx_pack_key {
+ uint32_t pack;
+ off_t offset;
+
+ uint32_t preferred_pack;
+ struct multi_pack_index *midx;
+};
+
+static int midx_pack_order_cmp(const void *va, const void *vb)
+{
+ const struct midx_pack_key *key = va;
+ struct multi_pack_index *midx = key->midx;
+
+ uint32_t versus = pack_pos_to_midx(midx, (uint32_t*)vb - (const uint32_t *)midx->revindex_data);
+ uint32_t versus_pack = nth_midxed_pack_int_id(midx, versus);
+ off_t versus_offset;
+
+ uint32_t key_preferred = key->pack == key->preferred_pack;
+ uint32_t versus_preferred = versus_pack == key->preferred_pack;
+
+ /*
+ * First, compare the preferred-ness, noting that the preferred pack
+ * comes first.
+ */
+ if (key_preferred && !versus_preferred)
+ return -1;
+ else if (!key_preferred && versus_preferred)
+ return 1;
+
+ /* Then, break ties first by comparing the pack IDs. */
+ if (key->pack < versus_pack)
+ return -1;
+ else if (key->pack > versus_pack)
+ return 1;
+
+ /* Finally, break ties by comparing offsets within a pack. */
+ versus_offset = nth_midxed_offset(midx, versus);
+ if (key->offset < versus_offset)
+ return -1;
+ else if (key->offset > versus_offset)
+ return 1;
+
+ return 0;
+}
+
+int midx_to_pack_pos(struct multi_pack_index *m, uint32_t at, uint32_t *pos)
+{
+ struct midx_pack_key key;
+ uint32_t *found;
+
+ if (!m->revindex_data)
+ BUG("midx_to_pack_pos: reverse index not yet loaded");
+ if (m->num_objects <= at)
+ BUG("midx_to_pack_pos: out-of-bounds object at %"PRIu32, at);
+
+ key.pack = nth_midxed_pack_int_id(m, at);
+ key.offset = nth_midxed_offset(m, at);
+ key.midx = m;
+ /*
+ * The preferred pack sorts first, so determine its identifier by
+ * looking at the first object in pseudo-pack order.
+ *
+ * Note that if no --preferred-pack is explicitly given when writing a
+ * multi-pack index, then whichever pack has the lowest identifier
+ * implicitly is preferred (and includes all its objects, since ties are
+ * broken first by pack identifier).
+ */
+ key.preferred_pack = nth_midxed_pack_int_id(m, pack_pos_to_midx(m, 0));
+
+ found = bsearch(&key, m->revindex_data, m->num_objects,
+ sizeof(*m->revindex_data), midx_pack_order_cmp);
+
+ if (!found)
+ return error("bad offset for revindex");
+
+ *pos = found - m->revindex_data;
+ return 0;
+}