[PATCH v3 09/16] diff: skip batch object download when possible

From: Garima Singh via GitGitGadget <gitgitgadget@gmail.com>
Date: Mar 30, 2020, 00:31 UTC
Message-ID: <55824cda89c1dca7756c8c2d831d6e115f4a9ddb.1585528298.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.497.v3.git.1585528298.gitgitgadget@gmail.com>

From: Garima Singh <garima.singh@microsoft.com>

When computing changed-path Bloom filters or performing a name-only diff, we do not need the blob contents before completing the diff values. Thus, we do not need to download a pack containing the blobs we do not have on-disk before completing our diff calculation.

This prevents downloading every blob in a partial clone when computing changed path Bloom filters. It also prevents over-aggressive downloads during "git log --raw" commands.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Garima Singh <garima.singh@microsoft.com>
---
 bloom.c | 1 +
 diff.c  | 8 +++++++-
 diff.h  | 1 +
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/bloom.c b/bloom.c
index a16eee92331..dbcf594baec 100644
--- a/bloom.c
+++ b/bloom.c
@@ -142,6 +142,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 
 	repo_diff_setup(r, &diffopt);
 	diffopt.flags.recursive = 1;
+	diffopt.detect_rename = 0;
 	diffopt.max_changes = max_changes;
 	diff_setup_done(&diffopt);
 
diff --git a/diff.c b/diff.c
index 1010d806f50..63376adb011 100644
--- a/diff.c
+++ b/diff.c
@@ -4633,6 +4633,10 @@ void diff_setup_done(struct diff_options *options)
 	if (!options->use_color || external_diff())
 		options->color_moved = 0;
 
+	if (!(options->output_format & ~(DIFF_FORMAT_NAME | DIFF_FORMAT_RAW)) &&
+	    !options->detect_rename)
+			options->skip_batch_download_objects = 1;
+
 	FREE_AND_NULL(options->parseopts);
 }
 
@@ -6507,7 +6511,9 @@ static void add_if_missing(struct repository *r,
 
 void diffcore_std(struct diff_options *options)
 {
-	if (options->repo == the_repository && has_promisor_remote()) {
+	if (!options->skip_batch_download_objects &&
+	    options->repo == the_repository &&
+		has_promisor_remote()) {
 		/*
 		 * Prefetch the diff pairs that are about to be flushed.
 		 */
diff --git a/diff.h b/diff.h
index 9443dc1b003..e9f104309c4 100644
--- a/diff.h
+++ b/diff.h
@@ -281,6 +281,7 @@ struct diff_options {
 	int show_rename_progress;
 	int dirstat_permille;
 	int setup;
+	int skip_batch_download_objects;
 
 	/* Number of hexdigits to abbreviate raw format output to. */
 	int abbrev;

-- 
gitgitgadget