[PATCH 4/4] features: feature.manyFiles implies fast index writes

From: Derrick Stolee via GitGitGadget <gitgitgadget@gmail.com>
Date: Dec 7, 2022, 17:25 UTC
Message-ID: <77bf5d5ff27729a39ac00d52af3c09610d733b14.1670433958.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.1439.git.1670433958.gitgitgadget@gmail.com>

From: Derrick Stolee <derrickstolee@github.com>

The recent addition of the index.skipHash config option allows index writes to speed up by skipping the hash computation for the trailing checksum. This is particularly critical for repositories with many files at HEAD, so add this config option to two cases where users in that scenario may opt-in to such behavior:

 1. The feature.manyFiles config option enables some options that are
    helpful for repositories with many files at HEAD.

 2. 'scalar register' and 'scalar reconfigure' set config options that
    optimize for large repositories.

In both of these cases, set index.skipHash=true to gain this speedup. Add tests that demonstrate the proper way that index.skipHash=true can override feature.manyFiles=true.

Signed-off-by: Derrick Stolee <derrickstolee@github.com>
---
 Documentation/config/feature.txt |  3 +++
 read-cache.c                     |  7 ++++---
 repo-settings.c                  |  2 ++
 repository.h                     |  1 +
 scalar.c                         |  1 +
 t/t1600-index.sh                 | 13 ++++++++++++-
 6 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/Documentation/config/feature.txt b/Documentation/config/feature.txt
index 95975e50912..f0e1d4cb2be 100644
--- a/Documentation/config/feature.txt
+++ b/Documentation/config/feature.txt
@@ -23,6 +23,9 @@ feature.manyFiles::
 	working directory. With many files, commands such as `git status` and
 	`git checkout` may be slow and these new defaults improve performance:
 +
+* `index.skipHash=true` speeds up index writes by not computing a trailing
+  checksum.
++
 * `index.version=4` enables path-prefix compression in the index.
 +
 * `core.untrackedCache=true` enables the untracked cache. This setting assumes
diff --git a/read-cache.c b/read-cache.c
index fb4d6fb6387..1844953fba7 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -2923,12 +2923,13 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
 	int ieot_entries = 1;
 	struct index_entry_offset_table *ieot = NULL;
 	int nr, nr_threads;
-	int skip_hash;
 
 	f = hashfd(tempfile->fd, tempfile->filename.buf);
 
-	if (!git_config_get_maybe_bool("index.skiphash", &skip_hash))
-		f->skip_hash = skip_hash;
+	if (istate->repo) {
+		prepare_repo_settings(istate->repo);
+		f->skip_hash = istate->repo->settings.index_skip_hash;
+	}
 
 	for (i = removed = extended = 0; i < entries; i++) {
 		if (cache[i]->ce_flags & CE_REMOVE)
diff --git a/repo-settings.c b/repo-settings.c
index 3021921c53d..3dbd3f0e2ec 100644
--- a/repo-settings.c
+++ b/repo-settings.c
@@ -47,6 +47,7 @@ void prepare_repo_settings(struct repository *r)
 	}
 	if (manyfiles) {
 		r->settings.index_version = 4;
+		r->settings.index_skip_hash = 1;
 		r->settings.core_untracked_cache = UNTRACKED_CACHE_WRITE;
 	}
 
@@ -61,6 +62,7 @@ void prepare_repo_settings(struct repository *r)
 	repo_cfg_bool(r, "pack.usesparse", &r->settings.pack_use_sparse, 1);
 	repo_cfg_bool(r, "core.multipackindex", &r->settings.core_multi_pack_index, 1);
 	repo_cfg_bool(r, "index.sparse", &r->settings.sparse_index, 0);
+	repo_cfg_bool(r, "index.skiphash", &r->settings.index_skip_hash, r->settings.index_skip_hash);
 
 	/*
 	 * The GIT_TEST_MULTI_PACK_INDEX variable is special in that
diff --git a/repository.h b/repository.h
index 6c461c5b9de..e8c67ffe165 100644
--- a/repository.h
+++ b/repository.h
@@ -42,6 +42,7 @@ struct repo_settings {
 	struct fsmonitor_settings *fsmonitor; /* lazily loaded */
 
 	int index_version;
+	int index_skip_hash;
 	enum untracked_cache_setting core_untracked_cache;
 
 	int pack_use_sparse;
diff --git a/scalar.c b/scalar.c
index 6c52243cdf1..b49bb8c24ec 100644
--- a/scalar.c
+++ b/scalar.c
@@ -143,6 +143,7 @@ static int set_recommended_config(int reconfigure)
 		{ "credential.validate", "false", 1 }, /* GCM4W-only */
 		{ "gc.auto", "0", 1 },
 		{ "gui.GCWarning", "false", 1 },
+		{ "index.skipHash", "false", 1 },
 		{ "index.threads", "true", 1 },
 		{ "index.version", "4", 1 },
 		{ "merge.stat", "false", 1 },
diff --git a/t/t1600-index.sh b/t/t1600-index.sh
index 55816756607..be0a0a8a008 100755
--- a/t/t1600-index.sh
+++ b/t/t1600-index.sh
@@ -72,7 +72,18 @@ test_expect_success 'index.skipHash config option' '
 		test_trailing_hash .git/index >hash &&
 		echo $(test_oid zero) >expect &&
 		test_cmp expect hash &&
-		git fsck
+		git fsck &&
+
+		rm -f .git/index &&
+		git -c feature.manyFiles=true add a &&
+		test_trailing_hash .git/index >hash &&
+		test_cmp expect hash &&
+
+		rm -f .git/index &&
+		git -c feature.manyFiles=true \
+		    -c index.skipHash=false add a &&
+		test_trailing_hash .git/index >hash &&
+		! test_cmp expect hash
 	)
 '

-- 
gitgitgadget