lkml.org 
[lkml]   [1999]   [Jun]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: 2.3.4: deadlocks when writing many data
Hi!

> > `subj` is what I see.
> >
> > I can see a deadlock, and any write to filesystem will mean one more
> > locked process. I see
> >
> > kflushd: waiting on wait_on_super and
> > update+syslogd+random_processes: waiting on wakeup_bdflush
> >
> > Any ideas?
>
> Ok, I'm following up myself. This just happened again, this time at
> 2.3.5.
>
> kflushd: stuck at down_failed
> sync: stuck at wakeup_bdflush
> more processes got stuck, some at wait_on_super
>
> This is more reproducible than I'd like it too. Similar crash happened
> yesterday with nbd, these crashes are with loop in use.

Ok, lets see. Random process does lock_super and then writes too much
data (=> wakeup_bdflush). Ok, now superblock is locked and bdflush is
called. But due to loop, bdflush tries to write to sparse block, which
can require lock_super. (Am I right)? Is there bug in my thinking?
(I did not investigate code too closely.)

Pavel
--
I'm really pavel@ucw.cz. Look at http://195.113.31.123/~pavel. Pavel
Hi! I'm a .signature virus! Copy me into your ~/.signature, please!

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:52    [W:0.073 / U:0.792 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site