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 v3 24/24] pack-bitmap-write: better reuse bitmaps
Date: Mon, 7 Dec 2020 19:05:57 -0500	[thread overview]
Message-ID: <6b9950771e57bd89dadcddaee7f27269e6ded535.1607385833.git.me@ttaylorr.com> (raw)
In-Reply-To: <cover.1607385833.git.me@ttaylorr.com>

From: Derrick Stolee <dstolee@microsoft.com>

If the old bitmap file contains a bitmap for a given commit, then that
commit does not need help from intermediate commits in its history to
compute its final bitmap. Eject that commit from the walk and insert it
into a separate list of reusable commits that are eventually stored in
the list of commits for computing bitmaps.

This helps the repeat bitmap computation task, even if the selected
commits shift drastically. This helps when a previously-bitmapped commit
exists in the first-parent history of a newly-selected commit. Since we
stop the walk at these commits and we use a first-parent walk, it is
harder to walk "around" these bitmapped commits. It's not impossible,
but we can greatly reduce the computation time for many selected
commits.

             |   runtime (sec)    |   peak heap (GB)   |
             |                    |                    |
             |   from  |   with   |   from  |   with   |
             | scratch | existing | scratch | existing |
  -----------+---------+----------+---------+-----------
  last patch |  88.478 |   53.218 |   2.157 |    2.224 |
  this patch |  86.681 |   16.164 |   2.157 |    2.222 |

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 pack-bitmap-write.c | 40 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c
index d2af4a974f..cc5ead9990 100644
--- a/pack-bitmap-write.c
+++ b/pack-bitmap-write.c
@@ -195,10 +195,13 @@ struct bitmap_builder {
 };
 
 static void bitmap_builder_init(struct bitmap_builder *bb,
-				struct bitmap_writer *writer)
+				struct bitmap_writer *writer,
+				struct bitmap_index *old_bitmap)
 {
 	struct rev_info revs;
 	struct commit *commit;
+	struct commit_list *reusable = NULL;
+	struct commit_list *r;
 	unsigned int i, num_maximal = 0;
 
 	memset(bb, 0, sizeof(*bb));
@@ -234,6 +237,31 @@ static void bitmap_builder_init(struct bitmap_builder *bb,
 
 		c_ent = bb_data_at(&bb->data, commit);
 
+		/*
+		 * If there is no commit_mask, there is no reason to iterate
+		 * over this commit; it is not selected (if it were, it would
+		 * not have a blank commit mask) and all its children have
+		 * existing bitmaps (see the comment starting with "This commit
+		 * has an existing bitmap" below), so it does not contribute
+		 * anything to the final bitmap file or its descendants.
+		 */
+		if (!c_ent->commit_mask)
+			continue;
+
+		if (old_bitmap && bitmap_for_commit(old_bitmap, commit)) {
+			/*
+			 * This commit has an existing bitmap, so we can
+			 * get its bits immediately without an object
+			 * walk. That is, it is reusable as-is and there is no
+			 * need to continue walking beyond it.
+			 *
+			 * Mark it as such and add it to bb->commits separately
+			 * to avoid allocating a position in the commit mask.
+			 */
+			commit_list_insert(commit, &reusable);
+			goto next;
+		}
+
 		if (c_ent->maximal) {
 			num_maximal++;
 			ALLOC_GROW(bb->commits, bb->commits_nr + 1, bb->commits_alloc);
@@ -278,14 +306,22 @@ static void bitmap_builder_init(struct bitmap_builder *bb,
 			}
 		}
 
+next:
 		bitmap_free(c_ent->commit_mask);
 		c_ent->commit_mask = NULL;
 	}
 
+	for (r = reusable; r; r = r->next) {
+		ALLOC_GROW(bb->commits, bb->commits_nr + 1, bb->commits_alloc);
+		bb->commits[bb->commits_nr++] = r->item;
+	}
+
 	trace2_data_intmax("pack-bitmap-write", the_repository,
 			   "num_selected_commits", writer->selected_nr);
 	trace2_data_intmax("pack-bitmap-write", the_repository,
 			   "num_maximal_commits", num_maximal);
+
+	free_commit_list(reusable);
 }
 
 static void bitmap_builder_clear(struct bitmap_builder *bb)
@@ -420,7 +456,7 @@ void bitmap_writer_build(struct packing_data *to_pack)
 	else
 		mapping = NULL;
 
-	bitmap_builder_init(&bb, &writer);
+	bitmap_builder_init(&bb, &writer, old_bitmap);
 	for (i = bb.commits_nr; i > 0; i--) {
 		struct commit *commit = bb.commits[i-1];
 		struct bb_commit *ent = bb_data_at(&bb.data, commit);
-- 
2.29.2.533.g07db1f5344

  parent reply	other threads:[~2020-12-08  0:07 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   ` Taylor Blau [this message]
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   ` [PATCH v4 22/24] pack-bitmap-write: use existing bitmaps Taylor Blau
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=6b9950771e57bd89dadcddaee7f27269e6ded535.1607385833.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 v3 24/24] pack-bitmap-write: better reuse 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