git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Chuck Lever <cel@citi.umich.edu>
To: Linus Torvalds <torvalds@osdl.org>
Cc: Ray Lehtiniemi <rayl@mail.com>, Alex Riesen <raa.lkml@gmail.com>,
	Radoslaw Szkodzinski <astralstorm@gorzow.mm.pl>,
	Keith Packard <keithp@keithp.com>,
	Junio C Hamano <junkio@cox.net>,
	cworth@cworth.org, Martin Langhoff <martin.langhoff@gmail.com>,
	Git Mailing List <git@vger.kernel.org>,
	Trond Myklebust <trond.myklebust@fys.uio.no>
Subject: Re: [Census] So who uses git?
Date: Mon, 06 Feb 2006 16:15:01 -0500	[thread overview]
Message-ID: <43E7BC55.8010908@citi.umich.edu> (raw)
In-Reply-To: <Pine.LNX.4.64.0601311747360.7301@g5.osdl.org>

[-- Attachment #1: Type: text/plain, Size: 1654 bytes --]

Linus Torvalds wrote:
>>for comparison, one of our sandboxes is sitting on an NTFS file system,
>>accessed via SMB:
>>
>>  smbfs$ time git update-index --refresh
>>  real    11m36.502s
>>  user    0m6.830s
>>  sys     0m5.086s
> 
> 
> Ouch, ouch, ouch.
> 
> Sounds like every single stat() will go out the wire. I forget what the 
> Linux NFS client does, but I _think_ it has a metadata timeout that avoids 
> this. But it might be as bad under NFS.
> 
> Has anybody used git over NFS? If it's this bad (or even close to), I 
> guess the "mark files as up-to-date in the index" approach is a really 
> good idea..
> 
> Of course, the whole point of git is that you should keep your repository 
> close, but sometimes NFS - or similar - is enforced upon you by other 
> issues, like the fact that the powers-that-be want anonymous workstations 
> and everybody should work with a home-directory automounted over NFS..

yes, i keep my Linux kernel repository in NFS (and my stgit and git 
repositories too).

there are some things that are slow precisely because my think time is 
longer than the NFS client's attribute timeout, which means that all of 
git's lstat()s turn into GETATTRs.

using the "noatime,nodiratime,actimeo=7200" mount options can have some 
benefit.  however, i found that keeping the repository packed provides 
the greatest positive impact.  that means that most of the objects are 
in a single file, and can be validated with just one GETATTR.

one thing we might conclude from this is that making "packing" an 
efficient operation (or even an incremental one) would go a long way to 
helping performance on network file systems.

[-- Attachment #2: cel.vcf --]
[-- Type: text/x-vcard, Size: 451 bytes --]

begin:vcard
fn:Chuck Lever
n:Lever;Charles
org:Network Appliance, Incorporated;Open Source NFS Client Development
adr:535 West William Street, Suite 3100;;Center for Information Technology Integration;Ann Arbor;MI;48103-4943;USA
email;internet:cel@citi.umich.edu
title:Member of Technical Staff
tel;work:+1 734 763 4415
tel;fax:+1 734 763 4434
tel;home:+1 734 668 1089
x-mozilla-html:FALSE
url:http://troy.citi.umich.edu/u/cel/
version:2.1
end:vcard


  parent reply	other threads:[~2006-02-06 21:15 UTC|newest]

Thread overview: 110+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-01-26  2:10 LCA06 Cogito/GIT workshop - (Re: git-whatchanged: exit out early on errors) Martin Langhoff
2006-01-28  4:47 ` Linus Torvalds
2006-01-28  5:33   ` Martin Langhoff
2006-01-28  5:53     ` Linus Torvalds
2006-01-28  6:32       ` Junio C Hamano
2006-01-29 10:12       ` Fredrik Kuivinen
2006-01-29 20:15         ` Junio C Hamano
2006-01-28 11:00     ` Keith Packard
2006-01-28 21:08       ` [Census] So who uses git? Junio C Hamano
2006-01-29  2:14         ` Morten Welinder
2006-01-29  3:53           ` Junio C Hamano
2006-01-29 14:19             ` Morten Welinder
2006-01-29 20:15               ` Junio C Hamano
2006-01-29 10:09         ` Keith Packard
2006-01-29 11:18           ` Radoslaw Szkodzinski
2006-01-29 18:12             ` Greg KH
2006-01-31 18:33               ` Radoslaw Szkodzinski
2006-01-31 19:50                 ` Radoslaw Szkodzinski
2006-01-31 20:43                   ` Junio C Hamano
2006-01-31 21:02                     ` Radoslaw Szkodzinski
2006-01-30 22:51             ` Alex Riesen
2006-01-31 21:25               ` Linus Torvalds
2006-01-31 21:52                 ` J. Bruce Fields
2006-01-31 22:01                 ` Alex Riesen
     [not found]                   ` <20060201013901.GA16832@mail.com>
2006-02-01  2:04                     ` Linus Torvalds
2006-02-01  2:09                       ` Linus Torvalds
2006-02-09  5:15                         ` [PATCH] "Assume unchanged" git Junio C Hamano
2006-02-09  5:49                           ` [PATCH] "Assume unchanged" git: do not set CE_VALID with --refresh Junio C Hamano
2006-02-09  5:50                           ` [PATCH] ls-files: debugging aid for CE_VALID changes Junio C Hamano
2006-02-01  2:31                       ` [Census] So who uses git? Junio C Hamano
2006-02-01  3:43                         ` Linus Torvalds
2006-02-01  7:03                           ` Junio C Hamano
     [not found]                         ` <20060201045337.GC25753@mail.com>
2006-02-01  5:04                           ` Linus Torvalds
2006-02-01  5:42                           ` Junio C Hamano
2006-02-01 16:15                       ` Jason Riedy
2006-02-01 19:20                       ` Julian Phillips
2006-02-01 19:29                         ` Linus Torvalds
2006-02-06 21:15                       ` Chuck Lever [this message]
2006-02-01  2:52                     ` Martin Langhoff
2006-02-01  3:48                       ` Linus Torvalds
2006-02-01 19:30                         ` H. Peter Anvin
2006-02-01 14:55                       ` Alex Riesen
2006-02-01 16:25                         ` Linus Torvalds
2006-02-02  9:12                           ` Alex Riesen
2006-01-29 18:37         ` Dave Jones
2006-01-29 20:17           ` Daniel Barkalow
2006-01-29 20:29             ` Martin Langhoff
2006-01-30 15:23             ` Mike McCormack
2006-01-30 18:58         ` Carl Baldwin
2006-01-31 10:27           ` Johannes Schindelin
2006-01-31 15:24             ` Carl Baldwin
2006-01-31 15:31               ` Johannes Schindelin
2006-01-31 17:30             ` Linus Torvalds
2006-01-31 18:12               ` J. Bruce Fields
2006-01-31 19:33                 ` Junio C Hamano
2006-01-31 19:44                   ` Jon Loeliger
2006-01-31 19:52                     ` Junio C Hamano
     [not found]                     ` <7vd5i8w2nc.fsf@assigned-by-dhcp.cox.net>
2006-01-31 20:56                       ` J. Bruce Fields
2006-01-31 20:06                   ` J. Bruce Fields
2006-01-31 19:01               ` Keith Packard
2006-01-31 19:21                 ` Linus Torvalds
2006-01-31 22:55                   ` Joel Becker
2006-02-01 14:43                     ` Johannes Schindelin
2006-01-31 20:56                 ` Sam Ravnborg
2006-01-31 22:21                   ` Junio C Hamano
2006-02-01 19:34               ` H. Peter Anvin
2006-01-31 23:16             ` Daniel Barkalow
2006-01-31 23:36               ` Petr Baudis
2006-01-31 23:47               ` Junio C Hamano
2006-02-01  0:38                 ` Linus Torvalds
2006-02-01  0:52                   ` Junio C Hamano
2006-02-01  2:19                   ` Daniel Barkalow
2006-02-01  6:42                   ` Junio C Hamano
2006-02-01  7:22                     ` Carl Worth
2006-02-01  8:26                       ` Junio C Hamano
2006-02-01  9:59                         ` Randal L. Schwartz
2006-02-01 20:48                           ` Junio C Hamano
2006-02-01 17:11                     ` Linus Torvalds
2006-02-01 17:18                     ` Nicolas Pitre
2006-02-01 20:27                       ` Junio C Hamano
2006-02-01 21:09                         ` Linus Torvalds
2006-02-01 21:34                           ` Nicolas Pitre
2006-02-01 21:59                           ` Junio C Hamano
2006-02-01 22:25                             ` Nicolas Pitre
2006-02-01 22:50                               ` Junio C Hamano
2006-02-02 14:59                                 ` Andreas Ericsson
2006-02-01 22:35                             ` Linus Torvalds
2006-02-01 23:33                               ` Two ideas for improving git's user interface Carl Worth
2006-02-02  0:38                                 ` Junio C Hamano
2006-02-02  1:16                                   ` Carl Worth
2006-02-02  2:25                                     ` Junio C Hamano
2006-02-03 23:57                                       ` Carl Worth
2006-02-02  1:23                                 ` Linus Torvalds
2006-02-02  1:44                                   ` Linus Torvalds
2006-02-04  8:03                                     ` Alan Chandler
2006-02-04  8:25                                       ` Junio C Hamano
2006-02-04  9:30                                         ` Alan Chandler
2006-02-04  0:20                                   ` Carl Worth
2006-02-04  2:08                                     ` Linus Torvalds
2006-02-06 23:42                                       ` Carl Worth
2006-02-02 12:31                                 ` Florian Weimer
2006-02-02 16:30                                 ` Carl Baldwin
2006-02-01 22:57                             ` [Census] So who uses git? Daniel Barkalow
2006-02-01 22:00                         ` Joel Becker
2006-02-01 19:32           ` H. Peter Anvin
  -- strict thread matches above, loose matches on Subject: below --
2006-02-01  7:08 linux
2006-02-01  8:51 ` Junio C Hamano
2006-02-01 16:04 ` Linus Torvalds
2006-02-01 16:10 ` Alex Riesen
2006-02-01 21:27   ` linux

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=43E7BC55.8010908@citi.umich.edu \
    --to=cel@citi.umich.edu \
    --cc=astralstorm@gorzow.mm.pl \
    --cc=cworth@cworth.org \
    --cc=git@vger.kernel.org \
    --cc=junkio@cox.net \
    --cc=keithp@keithp.com \
    --cc=martin.langhoff@gmail.com \
    --cc=raa.lkml@gmail.com \
    --cc=rayl@mail.com \
    --cc=torvalds@osdl.org \
    --cc=trond.myklebust@fys.uio.no \
    /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).