git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: Josh Steadmon <steadmon@google.com>
To: git@vger.kernel.org, peff@peff.net, jonathantanmy@google.com,
	jrnieder@gmail.com
Subject: [PATCH v3] rev-list: exclude promisor objects at walk time
Date: Mon,  8 Apr 2019 14:06:04 -0700	[thread overview]
Message-ID: <9856e7fc74f51b60ae162cbed3f5c0cf8c603222.1554757275.git.steadmon@google.com> (raw)
In-Reply-To: <6de682d5e48186970644569586fc6613763d5caa.1554312374.git.steadmon@google.com>

For large repositories, enumerating the list of all promisor objects (in
order to exclude them from a rev-list walk) can take a significant
amount of time).

When --exclude-promisor-objects is passed to rev-list, don't enumerate
the promisor objects. Instead, filter them (and any children objects)
during the actual graph walk.

Remove the mark_uninteresting() function as it's not used anywhere else.

When testing against a large repo [1], this patch reduces the
connectivity check runtime from 3 minutes to ~7 seconds.

[1]: https://android.googlesource.com/platform/frameworks/base/

Helped-By: Jonathan Tan <jonathantanmy@google.com>
Helped-By: Jeff King <peff@peff.net>
Helped-By: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Josh Steadmon <steadmon@google.com>

Signed-off-by: Josh Steadmon <steadmon@google.com>
---
Changes since V2:
* Pulled the "OK to skip?" logic into a separate function.

Changes since V1:
* Switched to alternate approach, we now do the regular rev-list walk
  but skip promisor objects at walk time, rather than pre-excluding
  them.

Range-diff against v2:
1:  9f327d6d8d ! 1:  9856e7fc74 rev-list: exclude promisor objects at walk time
    @@ -10,9 +10,15 @@
         the promisor objects. Instead, filter them (and any children objects)
         during the actual graph walk.
     
    +    When testing against a large repo [1], this reduces the connectivity
    +    check runtime from 3 minutes to ~7 seconds.
    +
    +    [1]: https://android.googlesource.com/platform/frameworks/base/
    +
         Helped-By: Jonathan Tan <jonathantanmy@google.com>
         Helped-By: Jeff King <peff@peff.net>
         Helped-By: Jonathan Nieder <jrnieder@gmail.com>
    +    Signed-off-by: Josh Steadmon <steadmon@google.com>
     
     
    @@ -20,78 +26,55 @@
      --- a/list-objects.c
      +++ b/list-objects.c
     @@
    - 	struct object *obj = &blob->object;
    - 	size_t pathlen;
    - 	enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
    -+	struct object_info oi = OBJECT_INFO_INIT;
    + 	void *filter_data;
    + };
      
    - 	if (!ctx->revs->blob_objects)
    - 		return;
    ++static int should_skip_promisor_object(const struct rev_info *revs,
    ++				       const struct object_id *oid)
    ++{
    ++	struct object_info oi = OBJECT_INFO_INIT;
    ++	return (revs->exclude_promisor_objects &&
    ++		!oid_object_info_extended(the_repository, oid, &oi, 0) &&
    ++		oi.whence == OI_PACKED &&
    ++		oi.u.packed.pack->pack_promisor);
    ++}
    ++
    + static void process_blob(struct traversal_context *ctx,
    + 			 struct blob *blob,
    + 			 struct strbuf *path,
     @@
      		die("bad blob object");
      	if (obj->flags & (UNINTERESTING | SEEN))
      		return;
    -+	if (ctx->revs->exclude_promisor_objects &&
    -+	    !oid_object_info_extended(the_repository, &obj->oid, &oi, 0) &&
    -+	    oi.whence == OI_PACKED &&
    -+	    oi.u.packed.pack->pack_promisor)
    ++	if (should_skip_promisor_object(ctx->revs, &obj->oid))
     +		return;
      
      	/*
      	 * Pre-filter known-missing objects when explicitly requested.
    -@@
    - 	int baselen = base->len;
    - 	enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
    - 	int failed_parse;
    -+	struct object_info oi = OBJECT_INFO_INIT;
    - 
    - 	if (!revs->tree_objects)
    - 		return;
     @@
      		die("bad tree object");
      	if (obj->flags & (UNINTERESTING | SEEN))
      		return;
    -+	if (ctx->revs->exclude_promisor_objects &&
    -+	    !oid_object_info_extended(the_repository, &obj->oid, &oi, 0) &&
    -+	    oi.whence == OI_PACKED &&
    -+	    oi.u.packed.pack->pack_promisor)
    ++	if (should_skip_promisor_object(ctx->revs, &obj->oid))
     +		return;
      
      	failed_parse = parse_tree_gently(tree, 1);
      	if (failed_parse) {
    -@@
    - 				     struct strbuf *base)
    - {
    - 	int i;
    -+	struct object_info oi = OBJECT_INFO_INIT;
    - 
    - 	assert(base->len == 0);
    - 
     @@
      		struct object *obj = pending->item;
      		const char *name = pending->name;
      		const char *path = pending->path;
    -+		if (ctx->revs->exclude_promisor_objects &&
    -+		    !oid_object_info_extended(the_repository, &obj->oid, &oi, 0) &&
    -+		    oi.whence == OI_PACKED &&
    -+		    oi.u.packed.pack->pack_promisor)
    ++		if (should_skip_promisor_object(ctx->revs, &obj->oid))
     +			continue;
     +
      		if (obj->flags & (UNINTERESTING | SEEN))
      			continue;
      		if (obj->type == OBJ_TAG) {
     @@
    - {
    - 	struct commit *commit;
    - 	struct strbuf csp; /* callee's scratch pad */
    -+	struct object_info oi = OBJECT_INFO_INIT;
      	strbuf_init(&csp, PATH_MAX);
      
      	while ((commit = get_revision(ctx->revs)) != NULL) {
    -+		if (ctx->revs->exclude_promisor_objects &&
    -+		    !oid_object_info_extended(the_repository, &commit->object.oid, &oi, 0) &&
    -+		    oi.whence == OI_PACKED &&
    -+		    oi.u.packed.pack->pack_promisor)
    ++		if (should_skip_promisor_object(ctx->revs, &commit->object.oid))
     +			continue;
     +
      		/*

 list-objects.c | 20 ++++++++++++++++++++
 revision.c     | 16 ----------------
 2 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/list-objects.c b/list-objects.c
index dc77361e11..c153ee5dfb 100644
--- a/list-objects.c
+++ b/list-objects.c
@@ -22,6 +22,16 @@ struct traversal_context {
 	void *filter_data;
 };
 
+static int should_skip_promisor_object(const struct rev_info *revs,
+				       const struct object_id *oid)
+{
+	struct object_info oi = OBJECT_INFO_INIT;
+	return (revs->exclude_promisor_objects &&
+		!oid_object_info_extended(the_repository, oid, &oi, 0) &&
+		oi.whence == OI_PACKED &&
+		oi.u.packed.pack->pack_promisor);
+}
+
 static void process_blob(struct traversal_context *ctx,
 			 struct blob *blob,
 			 struct strbuf *path,
@@ -37,6 +47,8 @@ static void process_blob(struct traversal_context *ctx,
 		die("bad blob object");
 	if (obj->flags & (UNINTERESTING | SEEN))
 		return;
+	if (should_skip_promisor_object(ctx->revs, &obj->oid))
+		return;
 
 	/*
 	 * Pre-filter known-missing objects when explicitly requested.
@@ -156,6 +168,8 @@ static void process_tree(struct traversal_context *ctx,
 		die("bad tree object");
 	if (obj->flags & (UNINTERESTING | SEEN))
 		return;
+	if (should_skip_promisor_object(ctx->revs, &obj->oid))
+		return;
 
 	failed_parse = parse_tree_gently(tree, 1);
 	if (failed_parse) {
@@ -326,6 +340,9 @@ static void traverse_trees_and_blobs(struct traversal_context *ctx,
 		struct object *obj = pending->item;
 		const char *name = pending->name;
 		const char *path = pending->path;
+		if (should_skip_promisor_object(ctx->revs, &obj->oid))
+			continue;
+
 		if (obj->flags & (UNINTERESTING | SEEN))
 			continue;
 		if (obj->type == OBJ_TAG) {
@@ -356,6 +373,9 @@ static void do_traverse(struct traversal_context *ctx)
 	strbuf_init(&csp, PATH_MAX);
 
 	while ((commit = get_revision(ctx->revs)) != NULL) {
+		if (should_skip_promisor_object(ctx->revs, &commit->object.oid))
+			continue;
+
 		/*
 		 * an uninteresting boundary commit may not have its tree
 		 * parsed yet, but we are not going to show them anyway
diff --git a/revision.c b/revision.c
index eb8e51bc63..85974e941d 100644
--- a/revision.c
+++ b/revision.c
@@ -3067,17 +3067,6 @@ void reset_revision_walk(void)
 	clear_object_flags(SEEN | ADDED | SHOWN);
 }
 
-static int mark_uninteresting(const struct object_id *oid,
-			      struct packed_git *pack,
-			      uint32_t pos,
-			      void *cb)
-{
-	struct rev_info *revs = cb;
-	struct object *o = parse_object(revs->repo, oid);
-	o->flags |= UNINTERESTING | SEEN;
-	return 0;
-}
-
 define_commit_slab(indegree_slab, int);
 define_commit_slab(author_date_slab, timestamp_t);
 
@@ -3316,11 +3305,6 @@ int prepare_revision_walk(struct rev_info *revs)
 	    (revs->limited && limiting_can_increase_treesame(revs)))
 		revs->treesame.name = "treesame";
 
-	if (revs->exclude_promisor_objects) {
-		for_each_packed_object(mark_uninteresting, revs,
-				       FOR_EACH_OBJECT_PROMISOR_ONLY);
-	}
-
 	if (revs->no_walk != REVISION_WALK_NO_WALK_UNSORTED)
 		commit_list_sort_by_date(&revs->commits);
 	if (revs->no_walk)
-- 
2.21.0.392.gf8f6787159e-goog


  parent reply	other threads:[~2019-04-08 21:06 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-03 17:27 [PATCH] clone: do faster object check for partial clones Josh Steadmon
2019-04-03 18:58 ` Jonathan Tan
2019-04-03 19:41 ` Jeff King
2019-04-03 20:57   ` Jonathan Tan
2019-04-04  0:21     ` Josh Steadmon
2019-04-04  1:33     ` Jeff King
2019-04-04 22:53 ` [PATCH v2] rev-list: exclude promisor objects at walk time Josh Steadmon
2019-04-04 23:08   ` Jeff King
2019-04-04 23:47     ` Josh Steadmon
2019-04-05  0:00       ` Jeff King
2019-04-05  0:09         ` Josh Steadmon
2019-04-08 20:59           ` Josh Steadmon
2019-04-08 21:06 ` Josh Steadmon [this message]
2019-04-08 22:23   ` [PATCH v3] " Christian Couder
2019-04-08 23:12     ` Josh Steadmon
2019-04-09 15:14   ` Junio C Hamano
2019-04-09 15:15     ` Jeff King
2019-04-09 15:43       ` Junio C Hamano
2019-04-09 16:35         ` Josh Steadmon
2019-04-09 18:04   ` SZEDER Gábor
2019-04-09 23:42     ` Josh Steadmon
2019-04-11  4:06       ` Jeff King
2019-04-12 22:38         ` Josh Steadmon
2019-04-13  5:34           ` Jeff King
2019-04-19 20:26             ` Josh Steadmon
2019-04-19 21:00 ` [PATCH v4] clone: do faster object check for partial clones Josh Steadmon
2019-04-22 21:31   ` Jeff King

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=9856e7fc74f51b60ae162cbed3f5c0cf8c603222.1554757275.git.steadmon@google.com \
    --to=steadmon@google.com \
    --cc=git@vger.kernel.org \
    --cc=jonathantanmy@google.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).