git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: sbeller@google.com, peff@peff.net, jrnieder@gmail.com,
	avarab@gmail.com, Junio C Hamano <gitster@pobox.com>,
	Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH v2 5/7] multi-pack-index: implement 'expire' verb
Date: Fri, 21 Dec 2018 08:28:41 -0800 (PST)	[thread overview]
Message-ID: <1c4af93f5e9833d74a7cf7fc6d38df7fd93c1acc.1545409716.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.92.v2.git.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

The 'git multi-pack-index expire' command 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 command. 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                      | 82 +++++++++++++++++++++++++++++++++++--
 t/t5319-multi-pack-index.sh | 15 +++++++
 2 files changed, 93 insertions(+), 4 deletions(-)

diff --git a/midx.c b/midx.c
index 3bd7183a53..043cd1fd97 100644
--- a/midx.c
+++ b/midx.c
@@ -751,7 +751,8 @@ 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;
@@ -765,6 +766,7 @@ int write_midx_file(const char *object_dir)
 	uint32_t nr_entries, num_large_offsets = 0;
 	struct pack_midx_entry *entries = NULL;
 	int large_offsets_needed = 0;
+	int result = 0;
 
 	midx_name = get_midx_filename(object_dir);
 	if (safe_create_leading_directories(midx_name)) {
@@ -773,7 +775,10 @@ 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_list = packs.m ? packs.m->num_packs : 16;
@@ -787,7 +792,25 @@ int write_midx_file(const char *object_dir)
 	ALLOC_ARRAY(packs.perm, packs.alloc_perm);
 
 	if (packs.m) {
+		int drop_index = 0, missing_drops = 0;
 		for (i = 0; i < packs.m->num_packs; i++) {
+			if (packs_to_drop && drop_index < packs_to_drop->nr) {
+				int cmp = strcmp(packs.m->pack_names[i],
+						 packs_to_drop->items[drop_index].string);
+
+				if (!cmp) {
+					drop_index++;
+					continue;
+				} else if (cmp > 0) {
+					error(_("did not see pack-file %s to drop"),
+					      packs_to_drop->items[drop_index].string);
+					drop_index++;
+					i--;
+					missing_drops++;
+					continue;
+				}
+			}
+
 			ALLOC_GROW(packs.list, packs.nr + 1, packs.alloc_list);
 			ALLOC_GROW(packs.names, packs.nr + 1, packs.alloc_names);
 			ALLOC_GROW(packs.perm, packs.nr + 1, packs.alloc_perm);
@@ -798,6 +821,12 @@ int write_midx_file(const char *object_dir)
 			packs.pack_name_concat_len += strlen(packs.names[packs.nr]) + 1;
 			packs.nr++;
 		}
+
+		if (packs_to_drop && (drop_index < packs_to_drop->nr || missing_drops)) {
+			error(_("did not see all pack-files to drop"));
+			result = 1;
+			goto cleanup;
+		}
 	}
 
 	for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &packs);
@@ -932,7 +961,12 @@ int write_midx_file(const char *object_dir)
 	free(packs.perm);
 	free(entries);
 	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)
@@ -1034,5 +1068,45 @@ 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 948effc1ee..210279a3cf 100755
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -395,4 +395,19 @@ 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
+	)
+'
+
 test_done
-- 
gitgitgadget


  parent reply	other threads:[~2018-12-21 16:28 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   ` Derrick Stolee via GitGitGadget [this message]
2018-12-21 16:28   ` [PATCH v2 7/7] midx: implement midx_repack() Derrick Stolee via GitGitGadget
2018-12-21 16:28   ` [PATCH v2 6/7] multi-pack-index: prepare 'repack' subcommand 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 4/9] midx: simplify computation of pack name lengths 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 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 04/10] midx: simplify computation of pack name lengths 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 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         ` [PATCH v5 06/11] multi-pack-index: implement 'expire' subcommand Derrick Stolee
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=1c4af93f5e9833d74a7cf7fc6d38df7fd93c1acc.1545409716.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@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 \
    --cc=sbeller@google.com \
    /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).