git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
To: git@vger.kernel.org
Cc: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
Subject: [PATCH 18/20] update-index: manually enable or disable untracked cache
Date: Wed,  7 May 2014 21:51:58 +0700	[thread overview]
Message-ID: <1399474320-6840-19-git-send-email-pclouds@gmail.com> (raw)
In-Reply-To: <1399474320-6840-1-git-send-email-pclouds@gmail.com>

Some numbers below. In short, the saving on wt_status_collect_untracked()
is about 80%. There are some overhead on read/write_cache, but it seems
lower than 50ms, while the .._untracked() saving is in the 500ms range
(except linux-2.6, about 150ms). "git status" time saving ranges from
33% to 42%.

On gentoo-x86.git (100k files, 23k dirs, quite balance
tree, 8.5MB index v4, cache-tree fully populated), before turning
untracked cache on (the most important line is wt_status_collect:625)

   184.650 gitmodules_config:201 if (read_cache() < 0) die("index
     0.004 cmd_status:1299 read_cache_preload(&s.pathspec)
   226.231 cmd_status:1300 refresh_index(&the_index, REFRESH_QUIET
     3.096 cmd_status:1304 update_index_if_able(&the_index, &index_lock)
     6.788  wt_status_collect:619 wt_status_collect_changes_worktree(s)
     6.780  wt_status_collect:624 wt_status_collect_changes_index(s)
   772.866  wt_status_collect:625 wt_status_collect_untracked(s)
   786.686 cmd_status:1308 wt_status_collect(&s)

real    0m1.211s
user    0m0.566s
sys     0m0.638s

and after (saving 42% total time):

   220.888 gitmodules_config:201 if (read_cache() < 0) die("index
    36.368 cmd_status:1299 read_cache_preload(&s.pathspec)
   223.936 cmd_status:1300 refresh_index(&the_index, REFRESH_QUIET
     2.935 cmd_status:1304 update_index_if_able(&the_index, &index_lock)
     7.031  wt_status_collect:619 wt_status_collect_changes_worktree(s)
     7.156  wt_status_collect:624 wt_status_collect_changes_index(s)
   148.022  wt_status_collect:625 wt_status_collect_untracked(s)
   162.443 cmd_status:1308 wt_status_collect(&s)
    36.943 cmd_status:1348 if (the_index.untracked) { struct

real    0m0.696s
user    0m0.406s
sys     0m0.288s

On webkit.git (182k files, 6k dirs, 14M index v4), before:

   283.182 gitmodules_config:201 if (read_cache() < 0) die("index
     0.004 cmd_status:1299 read_cache_preload(&s.pathspec)
   515.836 cmd_status:1300 refresh_index(&the_index, REFRESH_QUIET
     5.428 cmd_status:1304 update_index_if_able(&the_index, &index_lock)
    11.162  wt_status_collect:619 wt_status_collect_changes_worktree(s)
    11.068  wt_status_collect:624 wt_status_collect_changes_index(s)
   887.247  wt_status_collect:625 wt_status_collect_untracked(s)
   909.722 cmd_status:1308 wt_status_collect(&s)

real    0m1.729s
user    0m0.785s
sys     0m0.941s

and after (saving 38% total time):

   290.994 gitmodules_config:201 if (read_cache() < 0) die("index
    10.132 cmd_status:1299 read_cache_preload(&s.pathspec)
   516.656 cmd_status:1300 refresh_index(&the_index, REFRESH_QUIET
     5.159 cmd_status:1304 update_index_if_able(&the_index, &index_lock)
    12.605  wt_status_collect:619 wt_status_collect_changes_worktree(s)
    11.262  wt_status_collect:624 wt_status_collect_changes_index(s)
   186.032  wt_status_collect:625 wt_status_collect_untracked(s)
   210.134 cmd_status:1308 wt_status_collect(&s)
    12.332 cmd_status:1348 if (the_index.untracked) { struct index_state

real    0m1.058s
user    0m0.525s
sys     0m0.532s

And linux-2.6 (45k files, 3k dirs, 3.2MB index v4), before:

    68.668 gitmodules_config:201 if (read_cache() < 0) die("index
     0.004 cmd_status:1299 read_cache_preload(&s.pathspec)
   114.270 cmd_status:1300 refresh_index(&the_index, REFRESH_QUIET
     1.180 cmd_status:1304 update_index_if_able(&the_index, &index_lock)
     4.027  wt_status_collect:619 wt_status_collect_changes_worktree(s)
     4.265  wt_status_collect:624 wt_status_collect_changes_index(s)
   191.285  wt_status_collect:625 wt_status_collect_untracked(s)
   199.825 cmd_status:1308 wt_status_collect(&s)

real    0m0.392s
user    0m0.177s
sys     0m0.215s

and after (saving 33%):

    71.756 gitmodules_config:201 if (read_cache() < 0) die("index
     5.201 cmd_status:1299 read_cache_preload(&s.pathspec)
   111.064 cmd_status:1300 refresh_index(&the_index, REFRESH_QUIET
     1.171 cmd_status:1304 update_index_if_able(&the_index, &index_lock)
     3.054  wt_status_collect:619 wt_status_collect_changes_worktree(s)
     4.945  wt_status_collect:624 wt_status_collect_changes_index(s)
    27.203  wt_status_collect:625 wt_status_collect_untracked(s)
    35.475 cmd_status:1308 wt_status_collect(&s)
    25.759 cmd_status:1348 if (the_index.untracked) { struct index_state

real    0m0.259s
user    0m0.106s
sys     0m0.132s
---
 builtin/update-index.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/builtin/update-index.c b/builtin/update-index.c
index ba54e19..003e28e 100644
--- a/builtin/update-index.c
+++ b/builtin/update-index.c
@@ -734,6 +734,7 @@ static int reupdate_callback(struct parse_opt_ctx_t *ctx,
 int cmd_update_index(int argc, const char **argv, const char *prefix)
 {
 	int newfd, entries, has_errors = 0, line_termination = '\n';
+	int untracked_cache = -1;
 	int read_from_stdin = 0;
 	int prefix_length = prefix ? strlen(prefix) : 0;
 	int preferred_index_format = 0;
@@ -822,6 +823,8 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 			resolve_undo_clear_callback},
 		OPT_INTEGER(0, "index-version", &preferred_index_format,
 			N_("write index in this format")),
+		OPT_BOOL(0, "untracked-cache", &untracked_cache,
+			N_("enable/disable untracked cache")),
 		OPT_END()
 	};
 
@@ -915,6 +918,20 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 		strbuf_release(&buf);
 	}
 
+	if (untracked_cache > 0) {
+		struct untracked_cache *uc;
+
+		uc = xcalloc(1, sizeof(*uc));
+		uc->exclude_per_dir = ".gitignore";
+		/* should be the same flags used by git-status */
+		uc->dir_flags = DIR_SHOW_OTHER_DIRECTORIES | DIR_HIDE_EMPTY_DIRECTORIES;
+		the_index.untracked = uc;
+		active_cache_changed = 1;
+	} else if (!untracked_cache) {
+		the_index.untracked = NULL;
+		active_cache_changed = 1;
+	}
+
 	if (active_cache_changed) {
 		if (newfd < 0) {
 			if (refresh_args.flags & REFRESH_QUIET)
-- 
1.9.1.346.ga2b5940

  parent reply	other threads:[~2014-05-07 14:53 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-07 14:51 [PATCH 00/20] Untracked cache to speed up "git status" Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 01/20] dir.c: coding style fix Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 02/20] dir.h: move struct exclude declaration to top level Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 03/20] prep_exclude: remove the artificial PATH_MAX limit Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 04/20] dir.c: optionally compute sha-1 of a .gitignore file Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 05/20] untracked cache: record .gitignore information and dir hierarchy Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 06/20] untracked cache: initial untracked cache validation Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 07/20] untracked cache: invalidate dirs recursively if .gitignore changes Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 08/20] untracked cache: record/validate dir mtime and reuse cached output Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 09/20] untracked cache: mark what dirs should be recursed/saved Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 10/20] untracked cache: don't open non-existent .gitignore Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 11/20] untracked cache: save to an index extension Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 12/20] untracked cache: load from UNTR " Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 13/20] untracked cache: invalidate at index addition or removal Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 14/20] untracked cache: print untracked statistics with $GIT_TRACE_UNTRACKED Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 15/20] read-cache.c: split racy stat test to a separate function Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 16/20] untracked cache: avoid racy timestamps Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` [PATCH 17/20] status: support untracked cache Nguyễn Thái Ngọc Duy
2014-05-07 14:51 ` Nguyễn Thái Ngọc Duy [this message]
2014-05-07 14:51 ` [PATCH 19/20] update-index: test the system before enabling " Nguyễn Thái Ngọc Duy
2014-05-07 14:52 ` [PATCH 20/20] t7063: tests for " Nguyễn Thái Ngọc Duy

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1399474320-6840-19-git-send-email-pclouds@gmail.com \
    --to=pclouds@gmail.com \
    --cc=git@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).