builtin/maintenance: make the geometric factor configurable

The geometric repacking task uses a factor of two for its geometric
sequence, meaning that each next pack must contain at least twice as
many objects as the next-smaller one. In some cases it may be helpful to
configure this factor though to reduce the number of packfile merges
even further, e.g. in very big repositories. But while git-repack(1)
itself supports doing this, the maintenance task does not give us a way
to tune it.

Introduce a new "maintenance.geometric-repack.splitFactor" configuration
to plug this gap.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Acked-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/config/maintenance.adoc b/Documentation/config/maintenance.adoc
index 26dc5de..45fdafc 100644 (file)
--- a/Documentation/config/maintenance.adoc
+++ b/Documentation/config/maintenance.adoc
@@ -86,6 +86,11 @@ maintenance.geometric-repack.auto::
        objects that would be written into a new packfile. The default value is
        100.
 
+maintenance.geometric-repack.splitFactor::
+       This integer config option controls the factor used for the geometric
+       sequence. See the `--geometric=` option in linkgit:git-repack[1] for
+       more details. Defaults to `2`.
+
 maintenance.reflog-expire.auto::
        This integer config option controls how often the `reflog-expire` task
        should be run as part of `git maintenance run --auto`. If zero, then

diff --git a/builtin/gc.c b/builtin/gc.c
index 2c9ecd4..fb1a82e 100644 (file)
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -1582,6 +1582,9 @@ static int maintenance_task_geometric_repack(struct maintenance_run_opts *opts,
        struct child_process child = CHILD_PROCESS_INIT;
        int ret;
 
+       repo_config_get_int(the_repository, "maintenance.geometric-repack.splitFactor",
+                           &geometry.split_factor);
+
        existing_packs.repo = the_repository;
        existing_packs_collect(&existing_packs, &kept_packs);
        pack_geometry_init(&geometry, &existing_packs, &po_args);
@@ -1591,7 +1594,8 @@ static int maintenance_task_geometric_repack(struct maintenance_run_opts *opts,
 
        strvec_pushl(&child.args, "repack", "-d", "-l", NULL);
        if (geometry.split < geometry.pack_nr)
-               strvec_push(&child.args, "--geometric=2");
+               strvec_pushf(&child.args, "--geometric=%d",
+                            geometry.split_factor);
        else
                add_repack_all_option(cfg, NULL, &child.args);
        if (opts->quiet)
@@ -1632,6 +1636,9 @@ static int geometric_repack_auto_condition(struct gc_config *cfg UNUSED)
        if (auto_value < 0)
                return 1;
 
+       repo_config_get_int(the_repository, "maintenance.geometric-repack.splitFactor",
+                           &geometry.split_factor);
+
        existing_packs.repo = the_repository;
        existing_packs_collect(&existing_packs, &kept_packs);
        pack_geometry_init(&geometry, &existing_packs, &po_args);

diff --git a/t/t7900-maintenance.sh b/t/t7900-maintenance.sh
index ace0ba8..e0352fd 100755 (executable)
--- a/t/t7900-maintenance.sh
+++ b/t/t7900-maintenance.sh
@@ -603,6 +603,38 @@ test_expect_success 'geometric repacking with --auto' '
        )
 '
 
+test_expect_success 'geometric repacking honors configured split factor' '
+       test_when_finished "rm -rf repo" &&
+       git init repo &&
+       (
+               cd repo &&
+               git config set maintenance.auto false &&
+
+               # Create three different packs with 9, 2 and 1 object, respectively.
+               # This is done so that only a subset of packs would be merged
+               # together so that we can verify that `git repack` receives the
+               # correct geometric factor.
+               for i in $(test_seq 9)
+               do
+                       echo first-$i | git hash-object -w --stdin -t blob || return 1
+               done &&
+               git repack --geometric=2 -d &&
+
+               for i in $(test_seq 2)
+               do
+                       echo second-$i | git hash-object -w --stdin -t blob || return 1
+               done &&
+               git repack --geometric=2 -d &&
+
+               echo third | git hash-object -w --stdin -t blob &&
+               git repack --geometric=2 -d &&
+
+               test_geometric_repack_needed false splitFactor=2 &&
+               test_geometric_repack_needed true splitFactor=3 &&
+               test_subcommand git repack -d -l --geometric=3 --quiet --write-midx <trace2.txt
+       )
+'
+
 test_expect_success 'pack-refs task' '
        for n in $(test_seq 1 5)
        do