Messages in this thread | | | Date | Sun, 11 Jun 2006 04:31:41 -0700 | From | "Robin H. Johnson" <> | Subject | Re: [PATCH] tmpfs time granularity fix for [acm]time moving backwards. |
| |
On Sun, Jun 11, 2006 at 12:12:41PM +0200, Jan Engelhardt wrote: > >Test output from a filesystem supporting sub-second timestamps (jfs,xfs,ramfs): > >creat: m=1149891452.928796249 c=1149891452.928796249 a=1149891452.928796249 > >futimes: m=1149891452.928796249 c=1149891452.928796249 a=1149891452.928796249 > > > >Test output from the tmpfs filesystem with the patch below: > >creat: m=1149892086.382150894 c=1149892086.382150894 a=1149892075.473249075 > >futimes: m=1149892086.383150885 c=1149892086.383150885 a=1149892086.383150885 > > > Is it normal that creat and futimes match for jfs/xfs? My testcase just seemed to run nice and fast there, if I do some work in the middle or sleep, the numbers will be different more, but otherwise I think it implies that both operations are taking place during the same time instance (I have HZ=1000 as you may be able to deduce by the 1ms differences in some of the pairs).
I ran it a few more times on ramfs for good measure. creat: m=1150025153.933532153 c=1150025153.933532153 a=1150025151.29558289 futimes: m=1150025153.933532153 c=1150025153.933532153 a=1150025153.933532153 ... creat: m=1150025156.860505810 c=1150025156.860505810 a=1150025153.933532153 futimes: m=1150025156.861505801 c=1150025156.861505801 a=1150025156.861505801 ... creat: m=1150025247.906686387 c=1150025247.906686387 a=1150025247.459690410 futimes: m=1150025247.907686378 c=1150025247.907686378 a=1150025247.907686378
> >Signed-off-by: Robin H. Johnson <robbat2@gentoo.org> > Hint: Cc it to the shmem.c maintainer, or it may get missed :) Will do, thanks.
-- Robin Hugh Johnson E-Mail : robbat2@gentoo.org GnuPG FP : 11AC BA4F 4778 E3F6 E4ED F38E B27B 944E 3488 4E85 [unhandled content-type:application/pgp-signature] | |