git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: Johannes.Schindelin@gmx.de, sandals@crustytoothpaste.net,
	steadmon@google.com, jrnieder@gmail.com, peff@peff.net,
	congdanhqx@gmail.com, phillip.wood123@gmail.com,
	Derrick Stolee <derrickstolee@github.com>,
	Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH 18/21] maintenance: add auto condition for commit-graph task
Date: Tue, 07 Jul 2020 14:21:32 +0000	[thread overview]
Message-ID: <37fa3f6157ab7799f29331e8cf11f55e7f123e49.1594131695.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.671.git.1594131695.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

Instead of writing a new commit-graph in every 'git maintenance run
--auto' process (when maintenance.commit-graph.enalbed is configured to
be true), only write when there are "enough" commits not in a
commit-graph file.

This count is controlled by the maintenance.commit-graph.auto config
option.

To compute the count, use a depth-first search starting at each ref, and
leaving markers using the PARENT1 flag. If this count reaches the limit,
then terminate early and start the task. Otherwise, this operation will
peel every ref and parse the commit it points to. If these are all in
the commit-graph, then this is typically a very fast operation. Users
with many refs might feel a slow-down, and hence could consider updating
their limit to be very small. A negative value will force the step to
run every time.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 Documentation/config/maintenance.txt | 10 ++++
 builtin/gc.c                         | 76 ++++++++++++++++++++++++++++
 object.h                             |  1 +
 3 files changed, 87 insertions(+)

diff --git a/Documentation/config/maintenance.txt b/Documentation/config/maintenance.txt
index 370cbfb42f..9bd69b9df3 100644
--- a/Documentation/config/maintenance.txt
+++ b/Documentation/config/maintenance.txt
@@ -2,3 +2,13 @@ maintenance.<task>.enabled::
 	This boolean config option controls whether the maintenance task
 	with name `<task>` is run when no `--task` option is specified.
 	By default, only `maintenance.gc.enabled` is true.
+
+maintenance.commit-graph.auto::
+	This integer config option controls how often the `commit-graph` task
+	should be run as part of `git maintenance run --auto`. If zero, then
+	the `commit-graph` task will not run with the `--auto` option. A
+	negative value will force the task to run every time. Otherwise, a
+	positive value implies the command should run when the number of
+	reachable commits that are not in the commit-graph file is at least
+	the value of `maintenance.commit-graph.auto`. The default value is
+	100.
diff --git a/builtin/gc.c b/builtin/gc.c
index dd24026b41..81b076b012 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -30,6 +30,7 @@
 #include "promisor-remote.h"
 #include "remote.h"
 #include "midx.h"
+#include "refs.h"
 
 #define FAILED_RUN "failed to run %s"
 
@@ -720,6 +721,80 @@ struct maintenance_opts {
 	int tasks_selected;
 } opts;
 
+/* Remember to update object flag allocation in object.h */
+#define PARENT1		(1u<<16)
+
+static int num_commits_not_in_graph = 0;
+static int limit_commits_not_in_graph = 100;
+
+static int dfs_on_ref(const char *refname,
+		      const struct object_id *oid, int flags,
+		      void *cb_data)
+{
+	int result = 0;
+	struct object_id peeled;
+	struct commit_list *stack = NULL;
+	struct commit *commit;
+
+	if (!peel_ref(refname, &peeled))
+		oid = &peeled;
+	if (oid_object_info(the_repository, oid, NULL) != OBJ_COMMIT)
+		return 0;
+
+	commit = lookup_commit(the_repository, oid);
+	if (!commit)
+		return 0;
+	if (parse_commit(commit))
+		return 0;
+
+	commit_list_append(commit, &stack);
+
+	while (!result && stack) {
+		struct commit_list *parent;
+
+		commit = pop_commit(&stack);
+
+		for (parent = commit->parents; parent; parent = parent->next) {
+			if (parse_commit(parent->item) ||
+			    commit_graph_position(parent->item) != COMMIT_NOT_FROM_GRAPH ||
+			    parent->item->object.flags & PARENT1)
+				continue;
+
+			parent->item->object.flags |= PARENT1;
+			num_commits_not_in_graph++;
+
+			if (num_commits_not_in_graph >= limit_commits_not_in_graph) {
+				result = 1;
+				break;
+			}
+
+			commit_list_append(parent->item, &stack);
+		}
+	}
+
+	free_commit_list(stack);
+	return result;
+}
+
+static int should_write_commit_graph(struct repository *r)
+{
+	int result;
+
+	repo_config_get_int(r, "maintenance.commit-graph.auto",
+			    &limit_commits_not_in_graph);
+
+	if (!limit_commits_not_in_graph)
+		return 0;
+	if (limit_commits_not_in_graph < 0)
+		return 1;
+
+	result = for_each_ref(dfs_on_ref, NULL);
+
+	clear_commit_marks_all(PARENT1);
+
+	return result;
+}
+
 static int run_write_commit_graph(struct repository *r)
 {
 	int result;
@@ -1250,6 +1325,7 @@ static void initialize_tasks(struct repository *r)
 
 	tasks[num_tasks]->name = "commit-graph";
 	tasks[num_tasks]->fn = maintenance_task_commit_graph;
+	tasks[num_tasks]->auto_condition = should_write_commit_graph;
 	num_tasks++;
 
 	hashmap_init(&task_map, task_entry_cmp, NULL, MAX_NUM_TASKS);
diff --git a/object.h b/object.h
index 38dc2d5a6c..4f886495d7 100644
--- a/object.h
+++ b/object.h
@@ -73,6 +73,7 @@ struct object_array {
  * list-objects-filter.c:                                      21
  * builtin/fsck.c:           0--3
  * builtin/index-pack.c:                                     2021
+ * builtin/maintenance.c:                           16
  * builtin/pack-objects.c:                                   20
  * builtin/reflog.c:                   10--12
  * builtin/show-branch.c:    0-------------------------------------------26
-- 
gitgitgadget


  parent reply	other threads:[~2020-07-07 14:22 UTC|newest]

Thread overview: 164+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-07 14:21 [PATCH 00/21] Maintenance builtin, allowing 'gc --auto' customization Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 01/21] gc: use the_repository less often Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 02/21] gc: use repository in too_many_loose_objects() Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 03/21] gc: use repo config Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 04/21] gc: drop the_repository in log location Derrick Stolee via GitGitGadget
2020-07-09  2:22   ` Jonathan Tan
2020-07-09 11:13     ` Derrick Stolee
2020-07-07 14:21 ` [PATCH 05/21] maintenance: create basic maintenance runner Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 06/21] maintenance: add --quiet option Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 07/21] maintenance: replace run_auto_gc() Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 08/21] maintenance: initialize task array and hashmap Derrick Stolee via GitGitGadget
2020-07-09  2:25   ` Jonathan Tan
2020-07-09 13:15     ` Derrick Stolee
2020-07-09 13:51       ` Junio C Hamano
2020-07-07 14:21 ` [PATCH 09/21] maintenance: add commit-graph task Derrick Stolee via GitGitGadget
2020-07-09  2:29   ` Jonathan Tan
2020-07-09 11:14     ` Derrick Stolee
2020-07-09 22:52       ` Jeff King
2020-07-09 23:41         ` Derrick Stolee
2020-07-07 14:21 ` [PATCH 10/21] maintenance: add --task option Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 11/21] maintenance: take a lock on the objects directory Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 12/21] maintenance: add fetch task Derrick Stolee via GitGitGadget
2020-07-09  2:35   ` Jonathan Tan
2020-07-07 14:21 ` [PATCH 13/21] maintenance: add loose-objects task Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 14/21] maintenance: add pack-files task Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 15/21] maintenance: auto-size pack-files batch Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 16/21] maintenance: create maintenance.<task>.enabled config Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 17/21] maintenance: use pointers to check --auto Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` Derrick Stolee via GitGitGadget [this message]
2020-07-07 14:21 ` [PATCH 19/21] maintenance: create auto condition for loose-objects Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 20/21] maintenance: add pack-files auto condition Derrick Stolee via GitGitGadget
2020-07-07 14:21 ` [PATCH 21/21] midx: use start_delayed_progress() Derrick Stolee via GitGitGadget
2020-07-08 23:57 ` [PATCH 00/21] Maintenance builtin, allowing 'gc --auto' customization Emily Shaffer
2020-07-09 11:21   ` Derrick Stolee
2020-07-09 12:43     ` Derrick Stolee
2020-07-09 23:16       ` Jeff King
2020-07-09 23:45         ` Derrick Stolee
2020-07-10 18:46           ` Emily Shaffer
2020-07-10 19:30             ` Son Luong Ngoc
2020-07-09 14:05     ` Junio C Hamano
2020-07-09 15:54       ` Derrick Stolee
2020-07-09 16:26         ` Junio C Hamano
2020-07-09 16:56           ` Derrick Stolee
2020-07-23 17:56 ` [PATCH v2 00/18] " Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 01/18] maintenance: create basic maintenance runner Derrick Stolee via GitGitGadget
2020-07-25  1:26     ` Taylor Blau
2020-07-25  1:47     ` Đoàn Trần Công Danh
2020-07-29 22:19     ` Jonathan Nieder
2020-07-30 13:12       ` Derrick Stolee
2020-07-31  0:30         ` Jonathan Nieder
2020-08-03 17:37           ` Derrick Stolee
2020-08-03 17:46             ` Jonathan Nieder
2020-08-03 22:46               ` Taylor Blau
2020-08-03 23:01                 ` Jonathan Nieder
2020-08-03 23:08                   ` Taylor Blau
2020-08-03 23:17                     ` Jonathan Nieder
2020-08-04  0:07                       ` Junio C Hamano
2020-08-04 13:32                       ` Derrick Stolee
2020-08-04 14:42                         ` Jonathan Nieder
2020-08-04 16:32                           ` Derrick Stolee
2020-08-04 17:02                             ` Jonathan Nieder
2020-08-04 17:51                               ` Derrick Stolee
2020-08-05 15:02               ` Derrick Stolee
2020-07-31 16:40         ` Jonathan Nieder
2020-08-03 23:52         ` Jonathan Nieder
2020-07-23 17:56   ` [PATCH v2 02/18] maintenance: add --quiet option Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 03/18] maintenance: replace run_auto_gc() Derrick Stolee via GitGitGadget
2020-07-23 20:21     ` Junio C Hamano
2020-07-25  1:33       ` Taylor Blau
2020-07-30 13:29       ` Derrick Stolee
2020-07-30 13:31         ` Derrick Stolee
2020-07-30 19:00           ` Eric Sunshine
2020-07-30 20:21             ` Derrick Stolee
2020-07-23 17:56   ` [PATCH v2 04/18] maintenance: initialize task array Derrick Stolee via GitGitGadget
2020-07-23 19:57     ` Junio C Hamano
2020-07-24 12:23       ` Derrick Stolee
2020-07-24 12:51         ` Derrick Stolee
2020-07-24 19:39           ` Junio C Hamano
2020-07-25  1:46           ` Taylor Blau
2020-07-29 22:19     ` Emily Shaffer
2020-07-23 17:56   ` [PATCH v2 05/18] maintenance: add commit-graph task Derrick Stolee via GitGitGadget
2020-07-23 20:22     ` Junio C Hamano
2020-07-24 13:09       ` Derrick Stolee
2020-07-24 19:47         ` Junio C Hamano
2020-07-25  1:52           ` Taylor Blau
2020-07-30 13:59             ` Derrick Stolee
2020-07-29  0:22     ` Jeff King
2020-07-23 17:56   ` [PATCH v2 06/18] maintenance: add --task option Derrick Stolee via GitGitGadget
2020-07-23 20:21     ` Junio C Hamano
2020-07-23 22:18       ` Junio C Hamano
2020-07-24 13:36       ` Derrick Stolee
2020-07-24 19:50         ` Junio C Hamano
2020-07-23 17:56   ` [PATCH v2 07/18] maintenance: take a lock on the objects directory Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 08/18] maintenance: add prefetch task Derrick Stolee via GitGitGadget
2020-07-23 20:53     ` Junio C Hamano
2020-07-24 14:25       ` Derrick Stolee
2020-07-24 20:47         ` Junio C Hamano
2020-07-25  1:37     ` Đoàn Trần Công Danh
2020-07-25  1:48       ` Junio C Hamano
2020-07-27 14:07         ` Derrick Stolee
2020-07-27 16:13           ` Junio C Hamano
2020-07-27 18:27             ` Derrick Stolee
2020-07-28 16:37               ` [PATCH v2] fetch: optionally allow disabling FETCH_HEAD update Junio C Hamano
2020-07-29  9:12                 ` Phillip Wood
2020-07-29  9:17                   ` Phillip Wood
2020-07-30 15:17                 ` Derrick Stolee
2020-07-23 17:56   ` [PATCH v2 09/18] maintenance: add loose-objects task Derrick Stolee via GitGitGadget
2020-07-23 20:59     ` Junio C Hamano
2020-07-24 14:50       ` Derrick Stolee
2020-07-24 19:57         ` Junio C Hamano
2020-07-29 22:21     ` Emily Shaffer
2020-07-30 15:38       ` Derrick Stolee
2020-07-23 17:56   ` [PATCH v2 10/18] maintenance: add incremental-repack task Derrick Stolee via GitGitGadget
2020-07-23 22:00     ` Junio C Hamano
2020-07-24 15:03       ` Derrick Stolee
2020-07-29 22:22     ` Emily Shaffer
2020-07-23 17:56   ` [PATCH v2 11/18] maintenance: auto-size incremental-repack batch Derrick Stolee via GitGitGadget
2020-07-23 22:15     ` Junio C Hamano
2020-07-23 23:09       ` Eric Sunshine
2020-07-23 23:24         ` Junio C Hamano
2020-07-24 16:09           ` Derrick Stolee
2020-07-24 19:51       ` Derrick Stolee
2020-07-24 20:17         ` Junio C Hamano
2020-07-29 22:23     ` Emily Shaffer
2020-07-30 16:57       ` Derrick Stolee
2020-07-30 19:02         ` Derrick Stolee
2020-07-30 19:24           ` Chris Torek
2020-08-05 12:37           ` Đoàn Trần Công Danh
2020-08-06 13:54             ` Derrick Stolee
2020-07-23 17:56   ` [PATCH v2 12/18] maintenance: create maintenance.<task>.enabled config Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 13/18] maintenance: use pointers to check --auto Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 14/18] maintenance: add auto condition for commit-graph task Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 15/18] maintenance: create auto condition for loose-objects Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 16/18] maintenance: add incremental-repack auto condition Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 17/18] midx: use start_delayed_progress() Derrick Stolee via GitGitGadget
2020-07-23 17:56   ` [PATCH v2 18/18] maintenance: add trace2 regions for task execution Derrick Stolee via GitGitGadget
2020-07-29 22:03   ` [PATCH v2 00/18] Maintenance builtin, allowing 'gc --auto' customization Emily Shaffer
2020-07-30 22:24   ` [PATCH v3 00/20] " Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 01/20] maintenance: create basic maintenance runner Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 02/20] maintenance: add --quiet option Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 03/20] maintenance: replace run_auto_gc() Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 04/20] maintenance: initialize task array Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 05/20] maintenance: add commit-graph task Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 06/20] maintenance: add --task option Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 07/20] maintenance: take a lock on the objects directory Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 08/20] fetch: optionally allow disabling FETCH_HEAD update Junio C Hamano via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 09/20] maintenance: add prefetch task Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 10/20] maintenance: add loose-objects task Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 11/20] midx: enable core.multiPackIndex by default Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 12/20] maintenance: add incremental-repack task Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 13/20] maintenance: auto-size incremental-repack batch Derrick Stolee via GitGitGadget
2020-07-30 23:36       ` Chris Torek
2020-08-03 17:43         ` Derrick Stolee
2020-07-30 22:24     ` [PATCH v3 14/20] maintenance: create maintenance.<task>.enabled config Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 15/20] maintenance: use pointers to check --auto Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 16/20] maintenance: add auto condition for commit-graph task Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 17/20] maintenance: create auto condition for loose-objects Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 18/20] maintenance: add incremental-repack auto condition Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 19/20] midx: use start_delayed_progress() Derrick Stolee via GitGitGadget
2020-07-30 22:24     ` [PATCH v3 20/20] maintenance: add trace2 regions for task execution Derrick Stolee via GitGitGadget
2020-07-30 23:06     ` [PATCH v3 00/20] Maintenance builtin, allowing 'gc --auto' customization Junio C Hamano
2020-07-30 23:31     ` Junio C Hamano
2020-07-31  2:58       ` Junio C Hamano
2020-08-06 17:58     ` 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

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=37fa3f6157ab7799f29331e8cf11f55e7f123e49.1594131695.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=Johannes.Schindelin@gmx.de \
    --cc=congdanhqx@gmail.com \
    --cc=derrickstolee@github.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=jrnieder@gmail.com \
    --cc=peff@peff.net \
    --cc=phillip.wood123@gmail.com \
    --cc=sandals@crustytoothpaste.net \
    --cc=steadmon@google.com \
    --subject='Re: [PATCH 18/21] maintenance: add auto condition for commit-graph task' \
    /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

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 NNTP newsgroup(s).