diff mbox series

[4/4] pack-bitmap: pass object filter to fill-in traversal

Message ID f1eb194b9fdf5e385610fa3c0ddee22b89cf4f0e.1588633810.git.me@ttaylorr.com (mailing list archive)
State New, archived
Headers show
Series pack-bitmap: use bitmaps for traversals with '--filter=tree:0' | expand

Commit Message

Taylor Blau May 4, 2020, 11:12 p.m. UTC 
From: Jeff King <peff@peff.net>

Sometimes a bitmap traversal still has to walk some commits manually,
because those commits aren't included in the bitmap packfile (e.g., due
to a push or commit since the last full repack). If we're given an
object filter, we don't pass it down to this traversal. It's not
necessary for correctness because the bitmap code has its own filters to
post-process the bitmap result (which it must, to filter out the objects
that _are_ mentioned in the bitmapped packfile).

And with blob filters, there was no performance reason to pass along
those filters, either. The fill-in traversal could omit them from the
result, but it wouldn't save us any time to do so, since we'd still have
to walk each tree entry to see if it's a blob or not.

But now that we support tree filters, there's opportunity for savings. A
tree:depth=0 filter means we can avoid accessing trees entirely, since
we know we won't them (or any of the subtrees or blobs they point to).
The new test in p5310 shows this off (the "partial bitmap" state is one
where HEAD~100 and its ancestors are all in a bitmapped pack, but
HEAD~100..HEAD are not). Here are the results (run against linux.git):

  Test                                                  HEAD^               HEAD
  -------------------------------------------------------------------------------------------------
  [...]
  5310.16: rev-list with tree filter (partial bitmap)   0.19(0.17+0.02)     0.03(0.02+0.01) -84.2%

The absolute number of savings isn't _huge_, but keep in mind that we
only omitted 100 first-parent links (in the version of linux.git here,
that's 894 actual commits). In a more pathological case, we might have a
much larger proportion of non-bitmapped commits. I didn't bother
creating such a case in the perf script because the setup is expensive,
and this is plenty to show the savings as a percentage.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 pack-bitmap.c                | 14 +++++++++-----
 t/perf/p5310-pack-bitmaps.sh |  5 +++++
 2 files changed, 14 insertions(+), 5 deletions(-)

Comments

Junio C Hamano May 5, 2020, 5:40 a.m. UTC | #1 
Taylor Blau <me@ttaylorr.com> writes:

> But now that we support tree filters, there's opportunity for savings. A
> tree:depth=0 filter means we can avoid accessing trees entirely, since
> we know we won't them (or any of the subtrees or blobs they point to).

"we know we won't _have_ them"?

> @@ -506,7 +506,8 @@ static int should_include(struct commit *commit, void *_data)
>  static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
>  				   struct rev_info *revs,
>  				   struct object_list *roots,
> -				   struct bitmap *seen)
> +				   struct bitmap *seen,
> +				   struct list_objects_filter_options *filter)
>  {
>  	struct bitmap *base = NULL;
>  	int needs_walk = 0;
> @@ -599,8 +600,9 @@ static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
>  		show_data.bitmap_git = bitmap_git;
>  		show_data.base = base;
>  
> -		traverse_commit_list(revs, show_commit, show_object,
> -				     &show_data);
> +		traverse_commit_list_filtered(filter, revs,
> +					      show_commit, show_object,
> +					      &show_data, NULL);

And then finally the change in step 1/4 pays off.

>  	}
>  
>  	return base;
> @@ -999,7 +1001,8 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
>  
>  	if (haves) {
>  		revs->ignore_missing_links = 1;
> -		haves_bitmap = find_objects(bitmap_git, revs, haves, NULL);
> +		haves_bitmap = find_objects(bitmap_git, revs, haves, NULL,
> +					    filter);
>  		reset_revision_walk();
>  		revs->ignore_missing_links = 0;
>  
> @@ -1007,7 +1010,8 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
>  			BUG("failed to perform bitmap walk");
>  	}
>  
> -	wants_bitmap = find_objects(bitmap_git, revs, wants, haves_bitmap);
> +	wants_bitmap = find_objects(bitmap_git, revs, wants, haves_bitmap,
> +				    filter);
>  
>  	if (!wants_bitmap)
>  		BUG("failed to perform bitmap walk");
> diff --git a/t/perf/p5310-pack-bitmaps.sh b/t/perf/p5310-pack-bitmaps.sh
> index 75ccf9f4e3..b3e725f031 100755
> --- a/t/perf/p5310-pack-bitmaps.sh
> +++ b/t/perf/p5310-pack-bitmaps.sh
> @@ -91,4 +91,9 @@ test_perf 'pack to file (partial bitmap)' '
>  	git pack-objects --use-bitmap-index --all pack2b </dev/null >/dev/null
>  '
>  
> +test_perf 'rev-list with tree filter (partial bitmap)' '
> +	git rev-list --use-bitmap-index --count --objects --all \
> +		--filter=tree:0 >/dev/null
> +'
> +
>  test_done
Taylor Blau May 5, 2020, 4 p.m. UTC | #2 
On Mon, May 04, 2020 at 10:40:43PM -0700, Junio C Hamano wrote:
> Taylor Blau <me@ttaylorr.com> writes:
>
> > But now that we support tree filters, there's opportunity for savings. A
> > tree:depth=0 filter means we can avoid accessing trees entirely, since
> > we know we won't them (or any of the subtrees or blobs they point to).
>
> "we know we won't _have_ them"?

Yep, fixed. Thanks for pointing it out.

> > @@ -506,7 +506,8 @@ static int should_include(struct commit *commit, void *_data)
> >  static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
> >  				   struct rev_info *revs,
> >  				   struct object_list *roots,
> > -				   struct bitmap *seen)
> > +				   struct bitmap *seen,
> > +				   struct list_objects_filter_options *filter)
> >  {
> >  	struct bitmap *base = NULL;
> >  	int needs_walk = 0;
> > @@ -599,8 +600,9 @@ static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
> >  		show_data.bitmap_git = bitmap_git;
> >  		show_data.base = base;
> >
> > -		traverse_commit_list(revs, show_commit, show_object,
> > -				     &show_data);
> > +		traverse_commit_list_filtered(filter, revs,
> > +					      show_commit, show_object,
> > +					      &show_data, NULL);
>
> And then finally the change in step 1/4 pays off.

Woohoo!

> >  	}
> >
> >  	return base;
> > @@ -999,7 +1001,8 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
> >
> >  	if (haves) {
> >  		revs->ignore_missing_links = 1;
> > -		haves_bitmap = find_objects(bitmap_git, revs, haves, NULL);
> > +		haves_bitmap = find_objects(bitmap_git, revs, haves, NULL,
> > +					    filter);
> >  		reset_revision_walk();
> >  		revs->ignore_missing_links = 0;
> >
> > @@ -1007,7 +1010,8 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
> >  			BUG("failed to perform bitmap walk");
> >  	}
> >
> > -	wants_bitmap = find_objects(bitmap_git, revs, wants, haves_bitmap);
> > +	wants_bitmap = find_objects(bitmap_git, revs, wants, haves_bitmap,
> > +				    filter);
> >
> >  	if (!wants_bitmap)
> >  		BUG("failed to perform bitmap walk");
> > diff --git a/t/perf/p5310-pack-bitmaps.sh b/t/perf/p5310-pack-bitmaps.sh
> > index 75ccf9f4e3..b3e725f031 100755
> > --- a/t/perf/p5310-pack-bitmaps.sh
> > +++ b/t/perf/p5310-pack-bitmaps.sh
> > @@ -91,4 +91,9 @@ test_perf 'pack to file (partial bitmap)' '
> >  	git pack-objects --use-bitmap-index --all pack2b </dev/null >/dev/null
> >  '
> >
> > +test_perf 'rev-list with tree filter (partial bitmap)' '
> > +	git rev-list --use-bitmap-index --count --objects --all \
> > +		--filter=tree:0 >/dev/null
> > +'
> > +
> >  test_done

Thanks,
Taylor
diff mbox series

Patch

diff --git a/pack-bitmap.c b/pack-bitmap.c
index 195ee8cad0..4077e731e8 100644
--- a/pack-bitmap.c
+++ b/pack-bitmap.c
@@ -506,7 +506,8 @@  static int should_include(struct commit *commit, void *_data)
 static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
 				   struct rev_info *revs,
 				   struct object_list *roots,
-				   struct bitmap *seen)
+				   struct bitmap *seen,
+				   struct list_objects_filter_options *filter)
 {
 	struct bitmap *base = NULL;
 	int needs_walk = 0;
@@ -599,8 +600,9 @@  static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
 		show_data.bitmap_git = bitmap_git;
 		show_data.base = base;
 
-		traverse_commit_list(revs, show_commit, show_object,
-				     &show_data);
+		traverse_commit_list_filtered(filter, revs,
+					      show_commit, show_object,
+					      &show_data, NULL);
 	}
 
 	return base;
@@ -999,7 +1001,8 @@  struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
 
 	if (haves) {
 		revs->ignore_missing_links = 1;
-		haves_bitmap = find_objects(bitmap_git, revs, haves, NULL);
+		haves_bitmap = find_objects(bitmap_git, revs, haves, NULL,
+					    filter);
 		reset_revision_walk();
 		revs->ignore_missing_links = 0;
 
@@ -1007,7 +1010,8 @@  struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
 			BUG("failed to perform bitmap walk");
 	}
 
-	wants_bitmap = find_objects(bitmap_git, revs, wants, haves_bitmap);
+	wants_bitmap = find_objects(bitmap_git, revs, wants, haves_bitmap,
+				    filter);
 
 	if (!wants_bitmap)
 		BUG("failed to perform bitmap walk");
diff --git a/t/perf/p5310-pack-bitmaps.sh b/t/perf/p5310-pack-bitmaps.sh
index 75ccf9f4e3..b3e725f031 100755
--- a/t/perf/p5310-pack-bitmaps.sh
+++ b/t/perf/p5310-pack-bitmaps.sh
@@ -91,4 +91,9 @@  test_perf 'pack to file (partial bitmap)' '
 	git pack-objects --use-bitmap-index --all pack2b </dev/null >/dev/null
 '
 
+test_perf 'rev-list with tree filter (partial bitmap)' '
+	git rev-list --use-bitmap-index --count --objects --all \
+		--filter=tree:0 >/dev/null
+'
+
 test_done