git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / mirror / code / Atom feed
From: Taylor Blau <me@ttaylorr.com>
To: git@vger.kernel.org
Cc: peff@peff.net, jonathantanmy@google.com, dstolee@microsoft.com,
	gitster@pobox.com
Subject: [PATCH v4 22/24] pack-bitmap-write: use existing bitmaps
Date: Tue, 8 Dec 2020 17:05:21 -0500	[thread overview]
Message-ID: <e0d989b98f2f3fde4c9a24a333f980b9ad624449.1607464775.git.me@ttaylorr.com> (raw)
In-Reply-To: <cover.1607464775.git.me@ttaylorr.com>

From: Derrick Stolee <dstolee@microsoft.com>

When constructing new bitmaps, we perform a commit and tree walk in
fill_bitmap_commit() and fill_bitmap_tree(). This walk would benefit
from using existing bitmaps when available. We must track the existing
bitmaps and translate them into the new object order, but this is
generally faster than parsing trees.

In fill_bitmap_commit(), we must reorder thing somewhat. The priority
queue walks commits from newest-to-oldest, which means we correctly stop
walking when reaching a commit with a bitmap. However, if we walk trees
interleaved with the commits, then we might be parsing trees that are
actually part of a re-used bitmap. To avoid over-walking trees, add them
to a LIFO queue and walk them after exploring commits completely.

On git.git, this reduces a second immediate bitmap computation from 2.0s
to 1.0s. On linux.git, we go from 32s to 22s. On chromium's fork
network, we go from 227s to 198s.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 pack-bitmap-write.c | 40 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 36 insertions(+), 4 deletions(-)

diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c
index 333058854d..76c8236f94 100644
--- a/pack-bitmap-write.c
+++ b/pack-bitmap-write.c
@@ -340,20 +340,37 @@ static void fill_bitmap_tree(struct bitmap *bitmap,
 
 static void fill_bitmap_commit(struct bb_commit *ent,
 			       struct commit *commit,
-			       struct prio_queue *queue)
+			       struct prio_queue *queue,
+			       struct prio_queue *tree_queue,
+			       struct bitmap_index *old_bitmap,
+			       const uint32_t *mapping)
 {
 	if (!ent->bitmap)
 		ent->bitmap = bitmap_new();
 
-	bitmap_set(ent->bitmap, find_object_pos(&commit->object.oid));
 	prio_queue_put(queue, commit);
 
 	while (queue->nr) {
 		struct commit_list *p;
 		struct commit *c = prio_queue_get(queue);
 
+		if (old_bitmap && mapping) {
+			struct ewah_bitmap *old = bitmap_for_commit(old_bitmap, c);
+			/*
+			 * If this commit has an old bitmap, then translate that
+			 * bitmap and add its bits to this one. No need to walk
+			 * parents or the tree for this commit.
+			 */
+			if (old && !rebuild_bitmap(mapping, old, ent->bitmap))
+				continue;
+		}
+
+		/*
+		 * Mark ourselves and queue our tree. The commit
+		 * walk ensures we cover all parents.
+		 */
 		bitmap_set(ent->bitmap, find_object_pos(&c->object.oid));
-		fill_bitmap_tree(ent->bitmap, get_commit_tree(c));
+		prio_queue_put(tree_queue, get_commit_tree(c));
 
 		for (p = c->parents; p; p = p->next) {
 			int pos = find_object_pos(&p->item->object.oid);
@@ -363,6 +380,9 @@ static void fill_bitmap_commit(struct bb_commit *ent,
 			}
 		}
 	}
+
+	while (tree_queue->nr)
+		fill_bitmap_tree(ent->bitmap, prio_queue_get(tree_queue));
 }
 
 static void store_selected(struct bb_commit *ent, struct commit *commit)
@@ -386,6 +406,9 @@ void bitmap_writer_build(struct packing_data *to_pack)
 	size_t i;
 	int nr_stored = 0; /* for progress */
 	struct prio_queue queue = { compare_commits_by_gen_then_commit_date };
+	struct prio_queue tree_queue = { NULL };
+	struct bitmap_index *old_bitmap;
+	uint32_t *mapping;
 
 	writer.bitmaps = kh_init_oid_map();
 	writer.to_pack = to_pack;
@@ -395,6 +418,12 @@ void bitmap_writer_build(struct packing_data *to_pack)
 	trace2_region_enter("pack-bitmap-write", "building_bitmaps_total",
 			    the_repository);
 
+	old_bitmap = prepare_bitmap_git(to_pack->repo);
+	if (old_bitmap)
+		mapping = create_bitmap_mapping(old_bitmap, to_pack);
+	else
+		mapping = NULL;
+
 	bitmap_builder_init(&bb, &writer);
 	for (i = bb.commits_nr; i > 0; i--) {
 		struct commit *commit = bb.commits[i-1];
@@ -402,7 +431,8 @@ void bitmap_writer_build(struct packing_data *to_pack)
 		struct commit *child;
 		int reused = 0;
 
-		fill_bitmap_commit(ent, commit, &queue);
+		fill_bitmap_commit(ent, commit, &queue, &tree_queue,
+				   old_bitmap, mapping);
 
 		if (ent->selected) {
 			store_selected(ent, commit);
@@ -428,7 +458,9 @@ void bitmap_writer_build(struct packing_data *to_pack)
 		ent->bitmap = NULL;
 	}
 	clear_prio_queue(&queue);
+	clear_prio_queue(&tree_queue);
 	bitmap_builder_clear(&bb);
+	free(mapping);
 
 	trace2_region_leave("pack-bitmap-write", "building_bitmaps_total",
 			    the_repository);
-- 
2.29.2.533.g07db1f5344


  parent reply	other threads:[~2020-12-08 22:09 UTC|newest]

Thread overview: 173+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-11 19:41 [PATCH 00/23] pack-bitmap: bitmap generation improvements Taylor Blau
2020-11-11 19:41 ` [PATCH 01/23] ewah/ewah_bitmap.c: grow buffer past 1 Taylor Blau
2020-11-22 19:36   ` Junio C Hamano
2020-11-23 16:22     ` Taylor Blau
2020-11-24  2:48       ` Jeff King
2020-11-24  2:51         ` Jeff King
2020-12-01 22:56           ` Taylor Blau
2020-11-11 19:41 ` [PATCH 02/23] pack-bitmap: fix header size check Taylor Blau
2020-11-12 17:39   ` Martin Ågren
2020-11-11 19:42 ` [PATCH 03/23] pack-bitmap: bounds-check size of cache extension Taylor Blau
2020-11-12 17:47   ` Martin Ågren
2020-11-13  4:57     ` Jeff King
2020-11-13  5:26       ` Martin Ågren
2020-11-13 21:29       ` Taylor Blau
2020-11-13 21:39         ` Jeff King
2020-11-13 21:49           ` Taylor Blau
2020-11-13 22:11             ` Jeff King
2020-11-11 19:42 ` [PATCH 04/23] t5310: drop size of truncated ewah bitmap Taylor Blau
2020-11-11 19:42 ` [PATCH 05/23] rev-list: die when --test-bitmap detects a mismatch Taylor Blau
2020-11-11 19:42 ` [PATCH 06/23] ewah: factor out bitmap growth Taylor Blau
2020-11-11 19:42 ` [PATCH 07/23] ewah: make bitmap growth less aggressive Taylor Blau
2020-11-22 20:32   ` Junio C Hamano
2020-11-23 16:49     ` Taylor Blau
2020-11-24  3:00       ` Jeff King
2020-11-24 20:11         ` Junio C Hamano
2020-11-11 19:43 ` [PATCH 08/23] ewah: implement bitmap_or() Taylor Blau
2020-11-22 20:34   ` Junio C Hamano
2020-11-23 16:52     ` Taylor Blau
2020-11-11 19:43 ` [PATCH 09/23] ewah: add bitmap_dup() function Taylor Blau
2020-11-11 19:43 ` [PATCH 10/23] pack-bitmap-write: reimplement bitmap writing Taylor Blau
2020-11-11 19:43 ` [PATCH 11/23] pack-bitmap-write: pass ownership of intermediate bitmaps Taylor Blau
2020-11-11 19:43 ` [PATCH 12/23] pack-bitmap-write: fill bitmap with commit history Taylor Blau
2020-11-11 19:43 ` [PATCH 13/23] bitmap: add bitmap_diff_nonzero() Taylor Blau
2020-11-11 19:43 ` [PATCH 14/23] commit: implement commit_list_contains() Taylor Blau
2020-11-11 19:43 ` [PATCH 15/23] t5310: add branch-based checks Taylor Blau
2020-11-11 20:58   ` Derrick Stolee
2020-11-11 21:04     ` Junio C Hamano
2020-11-15 23:26       ` Johannes Schindelin
2020-11-11 19:43 ` [PATCH 16/23] pack-bitmap-write: rename children to reverse_edges Taylor Blau
2020-11-11 19:43 ` [PATCH 17/23] pack-bitmap-write: build fewer intermediate bitmaps Taylor Blau
2020-11-13 22:23   ` SZEDER Gábor
2020-11-13 23:03     ` Jeff King
2020-11-14  6:23       ` Jeff King
2020-11-11 19:43 ` [PATCH 18/23] pack-bitmap-write: ignore BITMAP_FLAG_REUSE Taylor Blau
2020-11-11 19:44 ` [PATCH 19/23] pack-bitmap: factor out 'bitmap_for_commit()' Taylor Blau
2020-11-11 19:44 ` [PATCH 20/23] pack-bitmap: factor out 'add_commit_to_bitmap()' Taylor Blau
2020-11-11 19:44 ` [PATCH 21/23] pack-bitmap-write: use existing bitmaps Taylor Blau
2020-11-11 19:44 ` [PATCH 22/23] pack-bitmap-write: relax unique rewalk condition Taylor Blau
2020-11-11 19:44 ` [PATCH 23/23] pack-bitmap-write: better reuse bitmaps Taylor Blau
2020-11-17 21:46 ` [PATCH v2 00/24] pack-bitmap: bitmap generation improvements Taylor Blau
2020-11-17 21:46   ` [PATCH v2 01/24] ewah/ewah_bitmap.c: grow buffer past 1 Taylor Blau
2020-11-17 21:46   ` [PATCH v2 02/24] pack-bitmap: fix header size check Taylor Blau
2020-11-17 21:46   ` [PATCH v2 03/24] pack-bitmap: bounds-check size of cache extension Taylor Blau
2020-11-17 21:46   ` [PATCH v2 04/24] t5310: drop size of truncated ewah bitmap Taylor Blau
2020-11-17 21:46   ` [PATCH v2 05/24] rev-list: die when --test-bitmap detects a mismatch Taylor Blau
2020-11-17 21:46   ` [PATCH v2 06/24] ewah: factor out bitmap growth Taylor Blau
2020-11-17 21:47   ` [PATCH v2 07/24] ewah: make bitmap growth less aggressive Taylor Blau
2020-11-17 21:47   ` [PATCH v2 08/24] ewah: implement bitmap_or() Taylor Blau
2020-11-17 21:47   ` [PATCH v2 09/24] ewah: add bitmap_dup() function Taylor Blau
2020-11-17 21:47   ` [PATCH v2 10/24] pack-bitmap-write: reimplement bitmap writing Taylor Blau
2020-11-25  0:53     ` Jonathan Tan
2020-11-28 17:27       ` Taylor Blau
2020-11-17 21:47   ` [PATCH v2 11/24] pack-bitmap-write: pass ownership of intermediate bitmaps Taylor Blau
2020-11-25  1:00     ` Jonathan Tan
2020-11-17 21:47   ` [PATCH v2 12/24] pack-bitmap-write: fill bitmap with commit history Taylor Blau
2020-11-22 21:50     ` Junio C Hamano
2020-11-23 14:54       ` Derrick Stolee
2020-11-25  1:14     ` Jonathan Tan
2020-11-28 17:21       ` Taylor Blau
2020-11-30 18:33         ` Jonathan Tan
2020-11-17 21:47   ` [PATCH v2 13/24] bitmap: add bitmap_diff_nonzero() Taylor Blau
2020-11-22 22:01     ` Junio C Hamano
2020-11-23 20:19       ` Taylor Blau
2020-11-17 21:47   ` [PATCH v2 14/24] commit: implement commit_list_contains() Taylor Blau
2020-11-17 21:47   ` [PATCH v2 15/24] t5310: add branch-based checks Taylor Blau
2020-11-25  1:17     ` Jonathan Tan
2020-11-28 17:30       ` Taylor Blau
2020-11-17 21:47   ` [PATCH v2 16/24] pack-bitmap-write: rename children to reverse_edges Taylor Blau
2020-11-17 21:47   ` [PATCH v2 17/24] pack-bitmap.c: check reads more aggressively when loading Taylor Blau
2020-11-17 21:48   ` [PATCH v2 18/24] pack-bitmap-write: build fewer intermediate bitmaps Taylor Blau
2020-11-24  6:07     ` Jonathan Tan
2020-11-25  1:46     ` Jonathan Tan
2020-11-30 18:41       ` Derrick Stolee
2020-11-17 21:48   ` [PATCH v2 19/24] pack-bitmap-write: ignore BITMAP_FLAG_REUSE Taylor Blau
2020-12-02  7:13     ` Jonathan Tan
2020-11-17 21:48   ` [PATCH v2 20/24] pack-bitmap: factor out 'bitmap_for_commit()' Taylor Blau
2020-12-02  7:17     ` Jonathan Tan
2020-11-17 21:48   ` [PATCH v2 21/24] pack-bitmap: factor out 'add_commit_to_bitmap()' Taylor Blau
2020-12-02  7:20     ` Jonathan Tan
2020-11-17 21:48   ` [PATCH v2 22/24] pack-bitmap-write: use existing bitmaps Taylor Blau
2020-12-02  7:28     ` Jonathan Tan
2020-12-02 16:21       ` Taylor Blau
2020-11-17 21:48   ` [PATCH v2 23/24] pack-bitmap-write: relax unique rewalk condition Taylor Blau
2020-12-02  7:44     ` Jonathan Tan
2020-12-02 16:30       ` Taylor Blau
2020-12-07 18:19         ` Jonathan Tan
2020-12-07 18:43           ` Derrick Stolee
2020-12-07 18:45             ` Derrick Stolee
2020-12-07 18:48           ` Jeff King
2020-11-17 21:48   ` [PATCH v2 24/24] pack-bitmap-write: better reuse bitmaps Taylor Blau
2020-12-02  8:08     ` Jonathan Tan
2020-12-02 16:35       ` Taylor Blau
2020-12-02 18:22         ` Derrick Stolee
2020-12-02 18:25           ` Taylor Blau
2020-12-07 18:26             ` Jonathan Tan
2020-12-07 18:24           ` Jonathan Tan
2020-12-07 19:20             ` Derrick Stolee
2020-11-18 18:32   ` [PATCH v2 00/24] pack-bitmap: bitmap generation improvements SZEDER Gábor
2020-11-18 19:51     ` Taylor Blau
2020-11-22  2:17       ` Taylor Blau
2020-11-22  2:28         ` Taylor Blau
2020-11-20  6:34   ` Martin Ågren
2020-11-21 19:37     ` Junio C Hamano
2020-11-21 20:11       ` Martin Ågren
2020-11-22  2:31         ` Taylor Blau
2020-11-24  2:43           ` Jeff King
2020-12-01 23:04             ` Taylor Blau
2020-12-01 23:37               ` Jonathan Tan
2020-12-01 23:43                 ` Taylor Blau
2020-12-02  8:11                   ` Jonathan Tan
2020-12-08  0:04 ` [PATCH v3 " Taylor Blau
2020-12-08  0:04   ` [PATCH v3 01/24] ewah/ewah_bitmap.c: avoid open-coding ALLOC_GROW() Taylor Blau
2020-12-08  0:04   ` [PATCH v3 02/24] pack-bitmap: fix header size check Taylor Blau
2020-12-08  0:04   ` [PATCH v3 03/24] pack-bitmap: bounds-check size of cache extension Taylor Blau
2020-12-08  0:04   ` [PATCH v3 04/24] t5310: drop size of truncated ewah bitmap Taylor Blau
2020-12-08  0:04   ` [PATCH v3 05/24] rev-list: die when --test-bitmap detects a mismatch Taylor Blau
2020-12-08  0:04   ` [PATCH v3 06/24] ewah: factor out bitmap growth Taylor Blau
2020-12-08  0:04   ` [PATCH v3 07/24] ewah: make bitmap growth less aggressive Taylor Blau
2020-12-08  0:04   ` [PATCH v3 08/24] ewah: implement bitmap_or() Taylor Blau
2020-12-08  0:04   ` [PATCH v3 09/24] ewah: add bitmap_dup() function Taylor Blau
2020-12-08  0:04   ` [PATCH v3 10/24] pack-bitmap-write: reimplement bitmap writing Taylor Blau
2020-12-08  0:05   ` [PATCH v3 11/24] pack-bitmap-write: pass ownership of intermediate bitmaps Taylor Blau
2020-12-08  0:05   ` [PATCH v3 12/24] pack-bitmap-write: fill bitmap with commit history Taylor Blau
2020-12-08  0:05   ` [PATCH v3 13/24] bitmap: implement bitmap_is_subset() Taylor Blau
2020-12-08  0:05   ` [PATCH v3 14/24] commit: implement commit_list_contains() Taylor Blau
2020-12-08  0:05   ` [PATCH v3 15/24] t5310: add branch-based checks Taylor Blau
2020-12-08  0:05   ` [PATCH v3 16/24] pack-bitmap-write: rename children to reverse_edges Taylor Blau
2020-12-08  0:05   ` [PATCH v3 17/24] pack-bitmap.c: check reads more aggressively when loading Taylor Blau
2020-12-08  0:05   ` [PATCH v3 18/24] pack-bitmap-write: build fewer intermediate bitmaps Taylor Blau
2020-12-08  0:05   ` [PATCH v3 19/24] pack-bitmap-write: ignore BITMAP_FLAG_REUSE Taylor Blau
2020-12-08  0:05   ` [PATCH v3 20/24] pack-bitmap: factor out 'bitmap_for_commit()' Taylor Blau
2020-12-08  0:05   ` [PATCH v3 21/24] pack-bitmap: factor out 'add_commit_to_bitmap()' Taylor Blau
2020-12-08  0:05   ` [PATCH v3 22/24] pack-bitmap-write: use existing bitmaps Taylor Blau
2020-12-08  0:05   ` [PATCH v3 23/24] pack-bitmap-write: relax unique rewalk condition Taylor Blau
2020-12-08  0:05   ` [PATCH v3 24/24] pack-bitmap-write: better reuse bitmaps Taylor Blau
2020-12-08 20:56   ` [PATCH v3 00/24] pack-bitmap: bitmap generation improvements Junio C Hamano
2020-12-08 21:03     ` Taylor Blau
2020-12-08 22:03       ` Junio C Hamano
2020-12-08 22:03 ` [PATCH v4 " Taylor Blau
2020-12-08 22:03   ` [PATCH v4 01/24] ewah/ewah_bitmap.c: avoid open-coding ALLOC_GROW() Taylor Blau
2020-12-08 22:03   ` [PATCH v4 02/24] pack-bitmap: fix header size check Taylor Blau
2020-12-08 22:03   ` [PATCH v4 03/24] pack-bitmap: bounds-check size of cache extension Taylor Blau
2020-12-08 22:03   ` [PATCH v4 04/24] t5310: drop size of truncated ewah bitmap Taylor Blau
2020-12-08 22:03   ` [PATCH v4 05/24] rev-list: die when --test-bitmap detects a mismatch Taylor Blau
2020-12-08 22:03   ` [PATCH v4 06/24] ewah: factor out bitmap growth Taylor Blau
2020-12-08 22:03   ` [PATCH v4 07/24] ewah: make bitmap growth less aggressive Taylor Blau
2020-12-08 22:03   ` [PATCH v4 08/24] ewah: implement bitmap_or() Taylor Blau
2020-12-08 22:03   ` [PATCH v4 09/24] ewah: add bitmap_dup() function Taylor Blau
2020-12-08 22:03   ` [PATCH v4 10/24] pack-bitmap-write: reimplement bitmap writing Taylor Blau
2020-12-08 22:03   ` [PATCH v4 11/24] pack-bitmap-write: pass ownership of intermediate bitmaps Taylor Blau
2020-12-08 22:04   ` [PATCH v4 12/24] pack-bitmap-write: fill bitmap with commit history Taylor Blau
2020-12-08 22:04   ` [PATCH v4 13/24] bitmap: implement bitmap_is_subset() Taylor Blau
2020-12-08 22:04   ` [PATCH v4 14/24] commit: implement commit_list_contains() Taylor Blau
2020-12-08 22:04   ` [PATCH v4 15/24] t5310: add branch-based checks Taylor Blau
2020-12-08 22:04   ` [PATCH v4 16/24] pack-bitmap-write: rename children to reverse_edges Taylor Blau
2020-12-08 22:04   ` [PATCH v4 17/24] pack-bitmap.c: check reads more aggressively when loading Taylor Blau
2020-12-08 22:04   ` [PATCH v4 18/24] pack-bitmap-write: build fewer intermediate bitmaps Taylor Blau
2020-12-08 22:04   ` [PATCH v4 19/24] pack-bitmap-write: ignore BITMAP_FLAG_REUSE Taylor Blau
2020-12-08 22:04   ` [PATCH v4 20/24] pack-bitmap: factor out 'bitmap_for_commit()' Taylor Blau
2020-12-08 22:05   ` [PATCH v4 21/24] pack-bitmap: factor out 'add_commit_to_bitmap()' Taylor Blau
2020-12-08 22:05   ` Taylor Blau [this message]
2020-12-08 22:05   ` [PATCH v4 23/24] pack-bitmap-write: relax unique revwalk condition Taylor Blau
2020-12-08 22:05   ` [PATCH v4 24/24] pack-bitmap-write: better reuse bitmaps Taylor Blau

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=e0d989b98f2f3fde4c9a24a333f980b9ad624449.1607464775.git.me@ttaylorr.com \
    --to=me@ttaylorr.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=jonathantanmy@google.com \
    --cc=peff@peff.net \
    --subject='Re: [PATCH v4 22/24] pack-bitmap-write: use existing bitmaps' \
    /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

git@vger.kernel.org list mirror (unofficial, one of many)

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V1 git git/ https://public-inbox.org/git \
		git@vger.kernel.org
	public-inbox-index git

Example config snippet for mirrors.
Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://7fh6tueqddpjyxjmgtdiueylzoqt6pt7hec3pukyptlmohoowvhde4yd.onion/inbox.comp.version-control.git
	nntp://ie5yzdi7fg72h7s4sdcztq5evakq23rdt33mfyfcddc5u3ndnw24ogqd.onion/inbox.comp.version-control.git
	nntp://4uok3hntl7oi7b4uf4rtfwefqeexfzil2w6kgk2jn5z2f764irre7byd.onion/inbox.comp.version-control.git
	nntp://news.gmane.io/gmane.comp.version-control.git
 note: .onion URLs require Tor: https://www.torproject.org/

code repositories for project(s) associated with this inbox:

	https://80x24.org/mirrors/git.git

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git