git/list[1] front-page[2] threads[3] people[4] search[5] about
 

Re: [PATCH/RFC v3 7/9] write_entry(): use fstat() instead of lstat() when file is open

From
Johannes Schindelin <johannes.schindelin@gmx.de>
Date
Feb 5, 2009, 11:03 UTC
Message-ID
<alpine.DEB.1.00.0902051202440.7491@intel-tinevez-2-302>
In-Reply-To
<498A9FD3.2020601@viscovery.net>
Hi,
On Thu, 5 Feb 2009, Johannes Sixt wrote:
Show 13 quoted lines
> Kjetil Barvik schrieb:
> >   And, yes, since each lstat() call cost approximately 44 microseconds
> >   compared to 12-16 for each lstat() on my Linux box, there was a little
>                                ^^^^^^^ fstat()?
> >   performance gain from this patch.
> 
> This does look like a good gain. But do you have hard numbers that back
> the claim?
> 
> If you can squeeze out a 10% improvement on Linux with this patch, we
> should take it, and if it turns out that it doesn't work on Windows, we
> could trivially throw in an #ifdef MINGW (or even #ifdef WIN32 if Cygwin
> is affected, too) that skips the fstat() optimization.

Of course, what we _really_ would do is to provide a flag, say, FSTAT_UNRELIABLE and test for _that_ (after defining it in the Makefile for the appropriate platforms).

Ciao, Dscho

Previous: Johannes SixtNext: Junio C Hamano
Message 17 of 23 in “git checkout: more cleanups, optimisation, less lstat() calls”
  1. 0/9 git checkout: more cleanups, optimisation, less lstat() callsKjetil Barvik, Feb 4, 2009
  2. 1/9 lstat_cache(): small cleanup and optimisationKjetil Barvik, Feb 4, 2009
  3. 2/9 lstat_cache(): generalise longest_match_lstat_cache()Kjetil Barvik, Feb 4, 2009
  4. 3/9 lstat_cache(): swap func(length, string) into func(string, length)Kjetil Barvik, Feb 4, 2009
  5. 4/9 unlink_entry(): introduce schedule_dir_for_removal()Kjetil Barvik, Feb 4, 2009
  6. Junio C HamanoFeb 4, 2009
  7. Junio C HamanoFeb 4, 2009
  8. Kjetil BarvikFeb 4, 2009
  9. 5/9 create_directories(): remove some memcpy() and strchr() callsKjetil Barvik, Feb 4, 2009
  10. 6/9 write_entry(): cleanup of some duplicated codeKjetil Barvik, Feb 4, 2009
  11. 7/9 write_entry(): use fstat() instead of lstat() when file is openKjetil Barvik, Feb 4, 2009
  12. Johannes SixtFeb 4, 2009
  13. Junio C HamanoFeb 4, 2009
  14. Kjetil BarvikFeb 4, 2009
  15. Junio C HamanoFeb 4, 2009
  16. Johannes SixtFeb 5, 2009
  17. Johannes SchindelinFeb 5, 2009
  18. Junio C HamanoFeb 5, 2009
  19. Kjetil BarvikFeb 6, 2009
  20. Johannes SchindelinFeb 6, 2009
  21. Kjetil BarvikFeb 14, 2009
  22. 8/9 show_patch_diff(): remove a call to fstat()Kjetil Barvik, Feb 4, 2009
  23. 9/9 lstat_cache(): print a warning if doing ping-pong between cache typesKjetil Barvik, Feb 4, 2009

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.