From: Derrick Stolee <stolee@gmail.com>
To: git@vger.kernel.org
Cc: peff@peff.net, jrnieder@gmail.com, avarab@gmail.com,
gitster@pobox.com, Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH v5 06/11] multi-pack-index: implement 'expire' subcommand
Date: Wed, 24 Apr 2019 11:14:23 -0400 [thread overview]
Message-ID: <20190424151428.170316-7-dstolee@microsoft.com> (raw)
In-Reply-To: <20190424151428.170316-1-dstolee@microsoft.com>
The 'git multi-pack-index expire' subcommand looks at the existing
mult-pack-index, counts the number of objects referenced in each
pack-file, deletes the pack-fils with no referenced objects, and
rewrites the multi-pack-index to no longer reference those packs.
Refactor the write_midx_file() method to call write_midx_internal()
which now takes an existing 'struct multi_pack_index' and a list
of pack-files to drop (as specified by the names of their pack-
indexes). As we write the new multi-pack-index, we drop those
file names from the list of known pack-files.
The expire_midx_packs() method removes the unreferenced pack-files
after carefully closing the packs to avoid open handles.
Test that a new pack-file that covers the contents of two other
pack-files leads to those pack-files being deleted during the
expire subcommand. Be sure to read the multi-pack-index to ensure
it no longer references those packs.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
midx.c | 120 +++++++++++++++++++++++++++++++++---
t/t5319-multi-pack-index.sh | 20 ++++++
2 files changed, 130 insertions(+), 10 deletions(-)
diff --git a/midx.c b/midx.c
index 95c39106b2..299e9b2e8f 100644
--- a/midx.c
+++ b/midx.c
@@ -33,6 +33,8 @@
#define MIDX_CHUNK_LARGE_OFFSET_WIDTH (sizeof(uint64_t))
#define MIDX_LARGE_OFFSET_NEEDED 0x80000000
+#define PACK_EXPIRED UINT_MAX
+
static char *get_midx_filename(const char *object_dir)
{
return xstrfmt("%s/pack/multi-pack-index", object_dir);
@@ -381,6 +383,7 @@ struct pack_info {
uint32_t orig_pack_int_id;
char *pack_name;
struct packed_git *p;
+ unsigned expired : 1;
};
static int pack_info_compare(const void *_a, const void *_b)
@@ -428,6 +431,7 @@ static void add_pack_to_midx(const char *full_path, size_t full_path_len,
packs->info[packs->nr].pack_name = xstrdup(file_name);
packs->info[packs->nr].orig_pack_int_id = packs->nr;
+ packs->info[packs->nr].expired = 0;
packs->nr++;
}
}
@@ -587,13 +591,17 @@ static size_t write_midx_pack_names(struct hashfile *f,
size_t written = 0;
for (i = 0; i < num_packs; i++) {
- size_t writelen = strlen(info[i].pack_name) + 1;
+ size_t writelen;
+
+ if (info[i].expired)
+ continue;
if (i && strcmp(info[i].pack_name, info[i - 1].pack_name) <= 0)
BUG("incorrect pack-file order: %s before %s",
info[i - 1].pack_name,
info[i].pack_name);
+ writelen = strlen(info[i].pack_name) + 1;
hashwrite(f, info[i].pack_name, writelen);
written += writelen;
}
@@ -675,6 +683,11 @@ static size_t write_midx_object_offsets(struct hashfile *f, int large_offset_nee
for (i = 0; i < nr_objects; i++) {
struct pack_midx_entry *obj = list++;
+ if (perm[obj->pack_int_id] == PACK_EXPIRED)
+ BUG("object %s is in an expired pack with int-id %d",
+ oid_to_hex(&obj->oid),
+ obj->pack_int_id);
+
hashwrite_be32(f, perm[obj->pack_int_id]);
if (large_offset_needed && obj->offset >> 31)
@@ -721,7 +734,8 @@ static size_t write_midx_large_offsets(struct hashfile *f, uint32_t nr_large_off
return written;
}
-int write_midx_file(const char *object_dir)
+static int write_midx_internal(const char *object_dir, struct multi_pack_index *m,
+ struct string_list *packs_to_drop)
{
unsigned char cur_chunk, num_chunks = 0;
char *midx_name;
@@ -737,6 +751,8 @@ int write_midx_file(const char *object_dir)
struct pack_midx_entry *entries = NULL;
int large_offsets_needed = 0;
int pack_name_concat_len = 0;
+ int dropped_packs = 0;
+ int result = 0;
midx_name = get_midx_filename(object_dir);
if (safe_create_leading_directories(midx_name)) {
@@ -745,7 +761,10 @@ int write_midx_file(const char *object_dir)
midx_name);
}
- packs.m = load_multi_pack_index(object_dir, 1);
+ if (m)
+ packs.m = m;
+ else
+ packs.m = load_multi_pack_index(object_dir, 1);
packs.nr = 0;
packs.alloc = packs.m ? packs.m->num_packs : 16;
@@ -759,13 +778,14 @@ int write_midx_file(const char *object_dir)
packs.info[packs.nr].orig_pack_int_id = i;
packs.info[packs.nr].pack_name = xstrdup(packs.m->pack_names[i]);
packs.info[packs.nr].p = NULL;
+ packs.info[packs.nr].expired = 0;
packs.nr++;
}
}
for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &packs);
- if (packs.m && packs.nr == packs.m->num_packs)
+ if (packs.m && packs.nr == packs.m->num_packs && !packs_to_drop)
goto cleanup;
entries = get_sorted_entries(packs.m, packs.info, packs.nr, &nr_entries);
@@ -779,6 +799,34 @@ int write_midx_file(const char *object_dir)
QSORT(packs.info, packs.nr, pack_info_compare);
+ if (packs_to_drop && packs_to_drop->nr) {
+ int drop_index = 0;
+ int missing_drops = 0;
+
+ for (i = 0; i < packs.nr && drop_index < packs_to_drop->nr; i++) {
+ int cmp = strcmp(packs.info[i].pack_name,
+ packs_to_drop->items[drop_index].string);
+
+ if (!cmp) {
+ drop_index++;
+ packs.info[i].expired = 1;
+ } else if (cmp > 0) {
+ error(_("did not see pack-file %s to drop"),
+ packs_to_drop->items[drop_index].string);
+ drop_index++;
+ missing_drops++;
+ i--;
+ } else {
+ packs.info[i].expired = 0;
+ }
+ }
+
+ if (missing_drops) {
+ result = 1;
+ goto cleanup;
+ }
+ }
+
/*
* pack_perm stores a permutation between pack-int-ids from the
* previous multi-pack-index to the new one we are writing:
@@ -787,11 +835,18 @@ int write_midx_file(const char *object_dir)
*/
ALLOC_ARRAY(pack_perm, packs.nr);
for (i = 0; i < packs.nr; i++) {
- pack_perm[packs.info[i].orig_pack_int_id] = i;
+ if (packs.info[i].expired) {
+ dropped_packs++;
+ pack_perm[packs.info[i].orig_pack_int_id] = PACK_EXPIRED;
+ } else {
+ pack_perm[packs.info[i].orig_pack_int_id] = i - dropped_packs;
+ }
}
- for (i = 0; i < packs.nr; i++)
- pack_name_concat_len += strlen(packs.info[i].pack_name) + 1;
+ for (i = 0; i < packs.nr; i++) {
+ if (!packs.info[i].expired)
+ pack_name_concat_len += strlen(packs.info[i].pack_name) + 1;
+ }
if (pack_name_concat_len % MIDX_CHUNK_ALIGNMENT)
pack_name_concat_len += MIDX_CHUNK_ALIGNMENT -
@@ -807,7 +862,7 @@ int write_midx_file(const char *object_dir)
cur_chunk = 0;
num_chunks = large_offsets_needed ? 5 : 4;
- written = write_midx_header(f, num_chunks, packs.nr);
+ written = write_midx_header(f, num_chunks, packs.nr - dropped_packs);
chunk_ids[cur_chunk] = MIDX_CHUNKID_PACKNAMES;
chunk_offsets[cur_chunk] = written + (num_chunks + 1) * MIDX_CHUNKLOOKUP_WIDTH;
@@ -908,7 +963,12 @@ int write_midx_file(const char *object_dir)
free(entries);
free(pack_perm);
free(midx_name);
- return 0;
+ return result;
+}
+
+int write_midx_file(const char *object_dir)
+{
+ return write_midx_internal(object_dir, NULL, NULL);
}
void clear_midx_file(struct repository *r)
@@ -1010,5 +1070,45 @@ int verify_midx_file(const char *object_dir)
int expire_midx_packs(const char *object_dir)
{
- return 0;
+ uint32_t i, *count, result = 0;
+ struct string_list packs_to_drop = STRING_LIST_INIT_DUP;
+ struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+
+ if (!m)
+ return 0;
+
+ count = xcalloc(m->num_packs, sizeof(uint32_t));
+ for (i = 0; i < m->num_objects; i++) {
+ int pack_int_id = nth_midxed_pack_int_id(m, i);
+ count[pack_int_id]++;
+ }
+
+ for (i = 0; i < m->num_packs; i++) {
+ char *pack_name;
+
+ if (count[i])
+ continue;
+
+ if (prepare_midx_pack(m, i))
+ continue;
+
+ if (m->packs[i]->pack_keep)
+ continue;
+
+ pack_name = xstrdup(m->packs[i]->pack_name);
+ close_pack(m->packs[i]);
+ FREE_AND_NULL(m->packs[i]);
+
+ string_list_insert(&packs_to_drop, m->pack_names[i]);
+ unlink_pack_path(pack_name, 0);
+ free(pack_name);
+ }
+
+ free(count);
+
+ if (packs_to_drop.nr)
+ result = write_midx_internal(object_dir, m, &packs_to_drop);
+
+ string_list_clear(&packs_to_drop, 0);
+ return result;
}
diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index a8528f7da0..65e85debec 100755
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -397,4 +397,24 @@ test_expect_success 'expire does not remove any packs' '
)
'
+test_expect_success 'expire removes unreferenced packs' '
+ (
+ cd dup &&
+ git pack-objects --revs .git/objects/pack/pack-combined <<-EOF &&
+ refs/heads/A
+ ^refs/heads/C
+ EOF
+ git multi-pack-index write &&
+ ls .git/objects/pack | grep -v -e pack-[AB] >expect &&
+ git multi-pack-index expire &&
+ ls .git/objects/pack >actual &&
+ test_cmp expect actual &&
+ ls .git/objects/pack/ | grep idx >expect-idx &&
+ test-tool read-midx .git/objects | grep idx >actual-midx &&
+ test_cmp expect-idx actual-midx &&
+ git multi-pack-index verify &&
+ git fsck
+ )
+'
+
test_done
--
2.21.0.1096.g1c91fdc207
next prev parent reply other threads:[~2019-04-24 15:15 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-10 18:06 [PATCH 0/5] Create 'expire' and 'repack' verbs for git-multi-pack-index Derrick Stolee via GitGitGadget
2018-12-10 18:06 ` [PATCH 1/5] multi-pack-index: prepare for 'expire' verb Derrick Stolee via GitGitGadget
2018-12-11 1:35 ` Stefan Beller
2018-12-11 1:59 ` SZEDER Gábor
2018-12-11 12:32 ` Derrick Stolee
2018-12-10 18:06 ` [PATCH 2/5] midx: refactor permutation logic Derrick Stolee via GitGitGadget
2018-12-10 18:06 ` [PATCH 3/5] multi-pack-index: implement 'expire' verb Derrick Stolee via GitGitGadget
2018-12-10 18:06 ` [PATCH 4/5] multi-pack-index: prepare 'repack' verb Derrick Stolee via GitGitGadget
2018-12-11 1:54 ` Stefan Beller
2018-12-11 12:45 ` Derrick Stolee
2018-12-10 18:06 ` [PATCH 5/5] midx: implement midx_repack() Derrick Stolee via GitGitGadget
2018-12-11 2:32 ` Stefan Beller
2018-12-11 13:00 ` Derrick Stolee
2018-12-12 7:40 ` Junio C Hamano
2018-12-13 4:23 ` Junio C Hamano
2018-12-21 16:28 ` [PATCH v2 0/7] Create 'expire' and 'repack' verbs for git-multi-pack-index Derrick Stolee via GitGitGadget
2018-12-21 16:28 ` [PATCH v2 1/7] repack: refactor pack deletion for future use Derrick Stolee via GitGitGadget
2018-12-21 16:28 ` [PATCH v2 2/7] Docs: rearrange subcommands for multi-pack-index Derrick Stolee via GitGitGadget
2018-12-21 16:28 ` [PATCH v2 3/7] multi-pack-index: prepare for 'expire' subcommand Derrick Stolee via GitGitGadget
2018-12-21 16:28 ` [PATCH v2 4/7] midx: refactor permutation logic Derrick Stolee via GitGitGadget
2018-12-21 16:28 ` [PATCH v2 5/7] multi-pack-index: implement 'expire' verb Derrick Stolee via GitGitGadget
2018-12-21 16:28 ` [PATCH v2 6/7] multi-pack-index: prepare 'repack' subcommand Derrick Stolee via GitGitGadget
2018-12-21 16:28 ` [PATCH v2 7/7] midx: implement midx_repack() Derrick Stolee via GitGitGadget
2019-01-09 15:21 ` [PATCH v3 0/9] Create 'expire' and 'repack' verbs for git-multi-pack-index Derrick Stolee via GitGitGadget
2019-01-09 15:21 ` [PATCH v3 1/9] repack: refactor pack deletion for future use Derrick Stolee via GitGitGadget
2019-01-09 15:21 ` [PATCH v3 2/9] Docs: rearrange subcommands for multi-pack-index Derrick Stolee via GitGitGadget
2019-01-09 15:21 ` [PATCH v3 3/9] multi-pack-index: prepare for 'expire' subcommand Derrick Stolee via GitGitGadget
2019-01-09 15:21 ` [PATCH v3 4/9] midx: simplify computation of pack name lengths Derrick Stolee via GitGitGadget
2019-01-09 15:21 ` [PATCH v3 5/9] midx: refactor permutation logic and pack sorting Derrick Stolee via GitGitGadget
2019-01-23 21:00 ` Jonathan Tan
2019-01-24 17:34 ` Derrick Stolee
2019-01-24 19:17 ` Derrick Stolee
2019-01-09 15:21 ` [PATCH v3 6/9] multi-pack-index: implement 'expire' verb Derrick Stolee via GitGitGadget
2019-01-09 15:54 ` SZEDER Gábor
2019-01-10 18:05 ` Junio C Hamano
2019-01-23 22:13 ` Jonathan Tan
2019-01-24 17:36 ` Derrick Stolee
2019-01-09 15:21 ` [PATCH v3 7/9] multi-pack-index: prepare 'repack' subcommand Derrick Stolee via GitGitGadget
2019-01-09 15:56 ` SZEDER Gábor
2019-01-23 22:38 ` Jonathan Tan
2019-01-24 19:36 ` Derrick Stolee
2019-01-24 21:38 ` Jonathan Tan
2019-01-09 15:21 ` [PATCH v3 8/9] midx: implement midx_repack() Derrick Stolee via GitGitGadget
2019-01-23 22:33 ` Jonathan Tan
2019-01-09 15:21 ` [PATCH v3 9/9] multi-pack-index: test expire while adding packs Derrick Stolee via GitGitGadget
2019-01-17 15:27 ` [PATCH v3 0/9] Create 'expire' and 'repack' verbs for git-multi-pack-index Derrick Stolee
2019-01-23 22:44 ` Jonathan Tan
2019-01-24 21:51 ` [PATCH v4 00/10] " Derrick Stolee via GitGitGadget
2019-01-24 21:51 ` [PATCH v4 01/10] repack: refactor pack deletion for future use Derrick Stolee via GitGitGadget
2019-01-24 21:51 ` [PATCH v4 02/10] Docs: rearrange subcommands for multi-pack-index Derrick Stolee via GitGitGadget
2019-01-24 21:51 ` [PATCH v4 03/10] multi-pack-index: prepare for 'expire' subcommand Derrick Stolee via GitGitGadget
2019-01-24 21:51 ` [PATCH v4 05/10] midx: refactor permutation logic and pack sorting Derrick Stolee via GitGitGadget
2019-01-24 21:51 ` [PATCH v4 04/10] midx: simplify computation of pack name lengths Derrick Stolee via GitGitGadget
2019-01-24 21:51 ` [PATCH v4 07/10] multi-pack-index: prepare 'repack' subcommand Derrick Stolee via GitGitGadget
2019-01-25 23:24 ` Josh Steadmon
2019-01-24 21:51 ` [PATCH v4 06/10] multi-pack-index: implement 'expire' subcommand Derrick Stolee via GitGitGadget
2019-01-24 21:52 ` [PATCH v4 08/10] midx: implement midx_repack() Derrick Stolee via GitGitGadget
2019-01-26 17:10 ` Derrick Stolee
2019-01-27 22:50 ` Junio C Hamano
2019-01-24 21:52 ` [PATCH v4 09/10] multi-pack-index: test expire while adding packs Derrick Stolee via GitGitGadget
2019-01-24 21:52 ` [PATCH v4 10/10] midx: add test that 'expire' respects .keep files Derrick Stolee via GitGitGadget
2019-01-24 22:14 ` [PATCH v4 00/10] Create 'expire' and 'repack' verbs for git-multi-pack-index Jonathan Tan
2019-01-25 23:49 ` Josh Steadmon
2019-04-24 15:14 ` [PATCH v5 00/11] " Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 01/11] repack: refactor pack deletion for future use Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 02/11] Docs: rearrange subcommands for multi-pack-index Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 03/11] multi-pack-index: prepare for 'expire' subcommand Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 04/11] midx: simplify computation of pack name lengths Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 05/11] midx: refactor permutation logic and pack sorting Derrick Stolee
2019-04-24 15:14 ` Derrick Stolee [this message]
2019-04-24 15:14 ` [PATCH v5 07/11] multi-pack-index: prepare 'repack' subcommand Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 08/11] midx: implement midx_repack() Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 09/11] multi-pack-index: test expire while adding packs Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 10/11] midx: add test that 'expire' respects .keep files Derrick Stolee
2019-04-24 15:14 ` [PATCH v5 11/11] t5319-multi-pack-index.sh: test batch size zero Derrick Stolee
2019-04-25 5:38 ` [PATCH v5 00/11] Create 'expire' and 'repack' verbs for git-multi-pack-index Junio C Hamano
2019-04-25 11:06 ` Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 " Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 01/11] repack: refactor pack deletion for future use Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 02/11] Docs: rearrange subcommands for multi-pack-index Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 03/11] multi-pack-index: prepare for 'expire' subcommand Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 04/11] midx: simplify computation of pack name lengths Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 05/11] midx: refactor permutation logic and pack sorting Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 06/11] multi-pack-index: implement 'expire' subcommand Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 07/11] multi-pack-index: prepare 'repack' subcommand Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 08/11] midx: implement midx_repack() Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 09/11] multi-pack-index: test expire while adding packs Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 10/11] midx: add test that 'expire' respects .keep files Derrick Stolee
2019-05-14 18:47 ` [PATCH v6 11/11] t5319-multi-pack-index.sh: test batch size zero Derrick Stolee
2019-06-10 14:15 ` [PATCH v6 00/11] Create 'expire' and 'repack' verbs for git-multi-pack-index Derrick Stolee
2019-06-10 17:31 ` Junio C Hamano
2019-06-10 17:57 ` Derrick Stolee
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190424151428.170316-7-dstolee@microsoft.com \
--to=stolee@gmail.com \
--cc=avarab@gmail.com \
--cc=dstolee@microsoft.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=jrnieder@gmail.com \
--cc=peff@peff.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).