[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: update: sys_ftruncate call lasting 17 hours on ext3 filesystem from mutt



Thanks - sorry I didn't find redhat's bugzilla sooner.
I found
   https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=71157
which seems even more closely related.  So I added comments to it
as well as to 77669.

-Neal

On Fri, Nov 15, 2002 at 05:12:20PM +0000, Stephen C. Tweedie wrote:
> On Mon, Nov 11, 2002 at 12:35:02PM -0700, Neal McBurnett wrote:
> > In August I reported a problem with the sys_ftruncate call that caused
> > me to reboot my machine.  I didn't see any responses to it then on the
> > ext3 list, and the problem is now recurring, so I thought I'd try
> > again.  I don't think I've rebooted since the last problem.
> >  
> > In the last few days it hasn't taken as long as 17 hours, but it has
> > sometimes taken unusual and uncomfortable amounts of time (many
> > minutes at least). 
> 
> Please have a look at 
> 
>   https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=77669
> 
> as this sounds like the same problem.  The user in that case reports
> that it happens with ext2 too.  Seems that the core VM truncate code
> in that kernel is livelocking under some situations.
> 
> --Stephen





[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]