backfill: add --batch-size=<n> option

Users may want to specify a minimum batch size for their needs. This is only a minimum: the path-walk API provides a list of OIDs that correspond to the same path, and thus it is optimal to allow delta compression across those objects in a single server request. We could consider limiting the request to have a maximum batch size in the future. Signed-off-by: Derrick Stolee <[email protected]>
git-for-windows · Jan 11, 2025 · 6bbc831 · 6bbc831
1 parent ebd1692
commit 6bbc831
Show file tree

Hide file tree

Showing 3 changed files with 30 additions and 2 deletions.
diff --git a/Documentation/git-backfill.txt b/Documentation/git-backfill.txt
@@ -9,7 +9,7 @@ git-backfill - Download missing objects in a partial clone
 SYNOPSIS
 --------
 [verse]
-'git backfill' [<options>]
+'git backfill' [--batch-size=<n>]
 
 DESCRIPTION
 -----------
@@ -38,6 +38,14 @@ delta compression in the packfile sent by the server.
 By default, `git backfill` downloads all blobs reachable from the `HEAD`
 commit. This set can be restricted or expanded using various options.
 
+OPTIONS
+-------
+
+--batch-size=<n>::
+	Specify a minimum size for a batch of missing objects to request
+	from the server. This size may be exceeded by the last set of
+	blobs seen at a given path. Default batch size is 16,000.
+
 SEE ALSO
 --------
 linkgit:git-clone[1].

diff --git a/builtin/backfill.c b/builtin/backfill.c
@@ -21,7 +21,7 @@
 #include "path-walk.h"
 
 static const char * const builtin_backfill_usage[] = {
-	N_("git backfill [<options>]"),
+	N_("git backfill [--batch-size=<n>]"),
 	NULL
 };
 
@@ -113,6 +113,8 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
 		.batch_size = 50000,
 	};
 	struct option options[] = {
+		OPT_INTEGER(0, "batch-size", &ctx.batch_size,
+			    N_("Minimun number of objects to request at a time")),
 		OPT_END(),
 	};
 

diff --git a/t/t5620-backfill.sh b/t/t5620-backfill.sh
@@ -59,6 +59,24 @@ test_expect_success 'do partial clone 1, backfill gets all objects' '
 	test_line_count = 0 revs2
 '
 
+test_expect_success 'do partial clone 2, backfill batch size' '
+	git clone --no-checkout --filter=blob:none	\
+		--single-branch --branch=main 		\
+		"file://$(pwd)/srv.bare" backfill2 &&
+
+	GIT_TRACE2_EVENT="$(pwd)/batch-trace" git \
+		-C backfill2 backfill --batch-size=20 &&
+
+	# Batches were used
+	test_trace2_data promisor fetch_count 20 <batch-trace >matches &&
+	test_line_count = 2 matches &&
+	test_trace2_data promisor fetch_count 8 <batch-trace &&
+
+	# No more missing objects!
+	git -C backfill2 rev-list --quiet --objects --missing=print HEAD >revs2 &&
+	test_line_count = 0 revs2
+'
+
 . "$TEST_DIRECTORY"/lib-httpd.sh
 start_httpd