mirror of
https://github.com/git-for-windows/git.git
synced 2026-02-04 03:33:01 -06:00
repack: add --path-walk option
Since 'git pack-objects' supports a --path-walk option, allow passing it through in 'git repack'. This presents interesting testing opportunities for comparing the different repacking strategies against each other. Add the --path-walk option to the performance tests in p5313. For the microsoft/fluentui repo [1] checked out at a specific commit [2], the results are very interesting: Test this tree ------------------------------------------------------------------ 5313.2: thin pack 0.40(0.47+0.04) 5313.3: thin pack size 1.2M 5313.4: thin pack with --full-name-hash 0.09(0.10+0.04) 5313.5: thin pack size with --full-name-hash 22.8K 5313.6: thin pack with --path-walk 0.08(0.06+0.02) 5313.7: thin pack size with --path-walk 20.8K 5313.8: big pack 2.16(8.43+0.23) 5313.9: big pack size 17.7M 5313.10: big pack with --full-name-hash 1.42(3.06+0.21) 5313.11: big pack size with --full-name-hash 18.0M 5313.12: big pack with --path-walk 2.21(8.39+0.24) 5313.13: big pack size with --path-walk 17.8M 5313.14: repack 98.05(662.37+2.64) 5313.15: repack size 449.1K 5313.16: repack with --full-name-hash 33.95(129.44+2.63) 5313.17: repack size with --full-name-hash 182.9K 5313.18: repack with --path-walk 106.21(121.58+0.82) 5313.19: repack size with --path-walk 159.6K [1] https://github.com/microsoft/fluentui [2] e70848ebac1cd720875bccaa3026f4a9ed700e08 This repo suffers from having a lot of paths that collide in the name hash, so examining them in groups by path leads to better deltas. Also, in this case, the single-threaded implementation is competitive with the full repack. This is saving time diffing files that have significant differences from each other. A similar, but private, repo has even more extremes in the thin packs: Test this tree -------------------------------------------------------------- 5313.2: thin pack 2.39(2.91+0.10) 5313.3: thin pack size 4.5M 5313.4: thin pack with --full-name-hash 0.29(0.47+0.12) 5313.5: thin pack size with --full-name-hash 15.5K 5313.6: thin pack with --path-walk 0.35(0.31+0.04) 5313.7: thin pack size with --path-walk 14.2K Notice, however, that while the --full-name-hash version is working quite well in these cases for the thin pack, it does poorly for some other standard cases, such as this test on the Linux kernel repository: Test this tree -------------------------------------------------------------- 5313.2: thin pack 0.01(0.00+0.00) 5313.3: thin pack size 310 5313.4: thin pack with --full-name-hash 0.00(0.00+0.00) 5313.5: thin pack size with --full-name-hash 1.4K 5313.6: thin pack with --path-walk 0.00(0.00+0.00) 5313.7: thin pack size with --path-walk 310 Here, the --full-name-hash option does much worse than the default name hash, but the path-walk option does exactly as well. Signed-off-by: Derrick Stolee <stolee@gmail.com>
This commit is contained in:
Derrick Stolee
Johannes Schindelin
parent
26fe7cd37a
commit
d4de6513cd
@ -11,7 +11,7 @@ SYNOPSIS
|
||||
[verse]
|
||||
'git repack' [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [-m]
|
||||
[--window=<n>] [--depth=<n>] [--threads=<n>] [--keep-pack=<pack-name>]
|
||||
[--write-midx] [--name-hash-version=<n>]
|
||||
[--write-midx] [--name-hash-version=<n>] [--path-walk]
|
||||
|
||||
DESCRIPTION
|
||||
-----------
|
||||
@ -255,6 +255,18 @@ linkgit:git-multi-pack-index[1]).
|
||||
Provide this argument to the underlying `git pack-objects` process.
|
||||
See linkgit:git-pack-objects[1] for full details.
|
||||
|
||||
--path-walk::
|
||||
This option passes the `--path-walk` option to the underlying
|
||||
`git pack-options` process (see linkgit:git-pack-objects[1]).
|
||||
By default, `git pack-objects` walks objects in an order that
|
||||
presents trees and blobs in an order unrelated to the path they
|
||||
appear relative to a commit's root tree. The `--path-walk` option
|
||||
enables a different walking algorithm that organizes trees and
|
||||
blobs by path. This has the potential to improve delta compression
|
||||
especially in the presence of filenames that cause collisions in
|
||||
Git's default name-hash algorithm. Due to changing how the objects
|
||||
are walked, this option is not compatible with `--delta-islands`
|
||||
or `--filter`.
|
||||
|
||||
CONFIGURATION
|
||||
-------------
|
||||
|
||||
@ -43,7 +43,7 @@ static char *packdir, *packtmp_name, *packtmp;
|
||||
static const char *const git_repack_usage[] = {
|
||||
N_("git repack [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [-m]\n"
|
||||
"[--window=<n>] [--depth=<n>] [--threads=<n>] [--keep-pack=<pack-name>]\n"
|
||||
"[--write-midx] [--name-hash-version=<n>]"),
|
||||
"[--write-midx] [--name-hash-version=<n>] [--path-walk]"),
|
||||
NULL
|
||||
};
|
||||
|
||||
@ -63,6 +63,7 @@ struct pack_objects_args {
|
||||
int quiet;
|
||||
int local;
|
||||
int name_hash_version;
|
||||
int path_walk;
|
||||
struct list_objects_filter_options filter_options;
|
||||
};
|
||||
|
||||
@ -313,6 +314,8 @@ static void prepare_pack_objects(struct child_process *cmd,
|
||||
strvec_pushf(&cmd->args, "--no-reuse-object");
|
||||
if (args->name_hash_version)
|
||||
strvec_pushf(&cmd->args, "--name-hash-version=%d", args->name_hash_version);
|
||||
if (args->path_walk)
|
||||
strvec_pushf(&cmd->args, "--path-walk");
|
||||
if (args->local)
|
||||
strvec_push(&cmd->args, "--local");
|
||||
if (args->quiet)
|
||||
@ -1212,6 +1215,8 @@ int cmd_repack(int argc,
|
||||
N_("pass --no-reuse-object to git-pack-objects")),
|
||||
OPT_INTEGER(0, "name-hash-version", &po_args.name_hash_version,
|
||||
N_("specify the name hash version to use for grouping similar objects by path")),
|
||||
OPT_BOOL(0, "path-walk", &po_args.path_walk,
|
||||
N_("(EXPERIMENTAL!) pass --path-walk to git-pack-objects")),
|
||||
OPT_NEGBIT('n', NULL, &run_update_server_info,
|
||||
N_("do not run git-update-server-info"), 1),
|
||||
OPT__QUIET(&po_args.quiet, N_("be quiet")),
|
||||
|
||||
@ -67,4 +67,28 @@ do
|
||||
'
|
||||
done
|
||||
|
||||
test_perf 'thin pack with --path-walk' '
|
||||
git pack-objects --thin --stdout --revs --sparse --path-walk <in-thin >out
|
||||
'
|
||||
|
||||
test_size 'thin pack size with --path-walk' '
|
||||
wc -c <out
|
||||
'
|
||||
|
||||
test_perf 'big pack with --path-walk' '
|
||||
git pack-objects --stdout --revs --sparse --path-walk <in-big >out
|
||||
'
|
||||
|
||||
test_size 'big pack size with --path-walk' '
|
||||
wc -c <out
|
||||
'
|
||||
|
||||
test_perf 'repack with --path-walk' '
|
||||
git repack -adf --path-walk
|
||||
'
|
||||
|
||||
test_size 'repack size with --path-walk' '
|
||||
wc -c <.git/objects/pack/pack-*.pack
|
||||
'
|
||||
|
||||
test_done
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user