Message134252
| Author |
sdaoden |
| Recipients |
nadeem.vawda, neologix, pitrou, ronaldoussoren, santoso.wijaya, sdaoden, vstinner |
| Date |
2011年04月21日.20:27:08 |
| SpamBayes Score |
5.415243e-05 |
| Marked as misclassified |
No |
| Message-id |
<20110421202659.GA82546@sherwood.local> |
| In-reply-to |
<1303411987.24.0.672069847024.issue11877@psf.upfronthosting.co.za> |
| Content |
Charles-Francois Natali wrote:
> I'm -10 on sync_file_range on Linux:
> [...] last time I checked [...]
I just looked at
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=blob;f=fs/sync.c;h=c38ec163da6ccba00a0146c75606c1b548b31343;hb=HEAD
and it seems - as far as i understand what i read - that you're
still right; and, furthermore, that fsync() does everything
anyway. (But here an idiot is talking about *very* complicated
stuff.)
I've also "search"ed for the called filemap_write_and_wait_range()
and found the commit message for
2daea67e966dc0c42067ebea015ddac6834cef88 as part of that;
very interesting in respect to our issue here.
I will wait before i update the patch though, just in case some
experienced NetBSD or AIX user posts some message. For OpenBSD
i think i can confirm that fsync(2) alone is enough after taking
a (shallow, all shallow) look into kernel/vfs_syscalls.c and
ufs/ffs/{ffs_softdep.c,softdep.h}. |
|