On Fri, Sep 21, 2007 at 16:58:15 +0100,
Hugh Dickins <[EMAIL PROTECTED]> wrote:
>
> But once I look harder at it, I wonder what would have kept
> 2.6.18 to 2.6.23 safe from the same issue: per-cpu deltas from
> the global vm stats too low to get synched back to global, yet
> adding up to somethi
On Fri, 2007-09-21 at 03:33 -0700, Andrew Morton wrote:
> On Fri, 21 Sep 2007 11:25:41 +0100 richard kennedy <[EMAIL PROTECTED]> wrote:
>
> > > That's all a bit crappy if the wrong races happen and some other task is
> > > somehow exceeding the dirty limits each time this task polls them. Seems
>
On Fri, 21 Sep 2007 16:58:15 +0100 (BST) Hugh Dickins
<[EMAIL PROTECTED]> wrote:
> But once I look harder at it, I wonder what would have kept
> 2.6.18 to 2.6.23 safe from the same issue: per-cpu deltas from
> the global vm stats too low to get synched back to global, yet
> adding up to something
On 09/21/2007 11:58 AM, Hugh Dickins wrote:
> Looking at the 2.6.18-2.6.23 code, I'm uncertain what to try instead.
> There is a refresh_vm_stats function which we could call (then retest
> the break condition) just before resorting to congestion_wait. But
> the big NUMA people might get very upse
On Fri, 21 Sep 2007, Andy Whitcroft wrote:
> This sounds an awful lot like the same problem I reported with fsck
> hanging. I believe that Hugh had a candidate patch for that, which was
> related to dirty tracking limits. It seems that that patch tested, and
> acked by Peter. All on lkml under:
On 09/21/2007 05:39 AM, Andy Whitcroft wrote:
> This sounds an awful lot like the same problem I reported with fsck
> hanging. I believe that Hugh had a candidate patch for that, which was
> related to dirty tracking limits. It seems that that patch tested, and
> acked by Peter. All on lkml unde
On Fri, 2007-09-21 at 03:33 -0700, Andrew Morton wrote:
> On Fri, 21 Sep 2007 11:25:41 +0100 richard kennedy <[EMAIL PROTECTED]> wrote:
>
> > > That's all a bit crappy if the wrong races happen and some other task is
> > > somehow exceeding the dirty limits each time this task polls them. Seems
>
On Fri, 21 Sep 2007 11:25:41 +0100 richard kennedy <[EMAIL PROTECTED]> wrote:
> > That's all a bit crappy if the wrong races happen and some other task is
> > somehow exceeding the dirty limits each time this task polls them. Seems
> > unlikely that such a condition would persist forever.
> >
>
On Thu, 2007-09-20 at 15:36 -0700, Andrew Morton wrote:
> On Thu, 20 Sep 2007 18:04:38 -0400
> Chuck Ebbert <[EMAIL PROTECTED]> wrote:
>
> > >
> > >> Can we get some kind of band-aid, like making the endless 'for' loop in
> > >> balance_dirty_pages() terminate after some number of iterations? Cle
This sounds an awful lot like the same problem I reported with fsck
hanging. I believe that Hugh had a candidate patch for that, which was
related to dirty tracking limits. It seems that that patch tested, and
acked by Peter. All on lkml under:
2.6.23-rc6-mm1 -- mkfs stuck in 'D'
-apw
On Fri, 21 Sep 2007 10:08:08 +0200 Matthias Hensler <[EMAIL PROTECTED]> wrote:
> On Thu, Sep 20, 2007 at 03:36:54PM -0700, Andrew Morton wrote:
> > That's all a bit crappy if the wrong races happen and some other task
> > is somehow exceeding the dirty limits each time this task polls them.
> > Se
On Thu, Sep 20, 2007 at 03:36:54PM -0700, Andrew Morton wrote:
> That's all a bit crappy if the wrong races happen and some other task
> is somehow exceeding the dirty limits each time this task polls them.
> Seems unlikely that such a condition would persist forever.
How exactly do you define for
On 09/20/2007 06:36 PM, Andrew Morton wrote:
>
> So the question is, why do we have large amounts of dirty pages for one
> disk which appear to be sitting there not getting written?
>
> Do we know if there's any writeout at all happening when the system is in
> this state?
>
> I guess it's possi
On Thu, 20 Sep 2007 18:04:38 -0400
Chuck Ebbert <[EMAIL PROTECTED]> wrote:
> >
> >> Can we get some kind of band-aid, like making the endless 'for' loop in
> >> balance_dirty_pages() terminate after some number of iterations? Clearly
> >> if we haven't written "write_chunk" pages after a few trie
On 09/20/2007 05:29 PM, Andrew Morton wrote:
> On Thu, 20 Sep 2007 17:07:15 -0400
> Chuck Ebbert <[EMAIL PROTECTED]> wrote:
>
>> On 08/09/2007 12:55 PM, Andrew Morton wrote:
>>> On Thu, 9 Aug 2007 11:59:43 +0200 Matthias Hensler <[EMAIL PROTECTED]>
>>> wrote:
>>>
On Sat, Aug 04, 2007 at 10:4
On Thu, 20 Sep 2007 17:07:15 -0400
Chuck Ebbert <[EMAIL PROTECTED]> wrote:
> On 08/09/2007 12:55 PM, Andrew Morton wrote:
> > On Thu, 9 Aug 2007 11:59:43 +0200 Matthias Hensler <[EMAIL PROTECTED]>
> > wrote:
> >
> >> On Sat, Aug 04, 2007 at 10:44:26AM +0200, Matthias Hensler wrote:
> >>> On Fri,
On 08/09/2007 12:55 PM, Andrew Morton wrote:
> On Thu, 9 Aug 2007 11:59:43 +0200 Matthias Hensler <[EMAIL PROTECTED]> wrote:
>
>> On Sat, Aug 04, 2007 at 10:44:26AM +0200, Matthias Hensler wrote:
>>> On Fri, Aug 03, 2007 at 11:34:07AM -0700, Andrew Morton wrote:
>>> [...]
>>> I am also willing to
On Thu, Aug 09, 2007 at 09:55:34AM -0700, Andrew Morton wrote:
> On Thu, 9 Aug 2007 11:59:43 +0200 Matthias Hensler <[EMAIL PROTECTED]> wrote:
> > On Sat, Aug 04, 2007 at 10:44:26AM +0200, Matthias Hensler wrote:
> > > On Fri, Aug 03, 2007 at 11:34:07AM -0700, Andrew Morton wrote:
> > > [...]
> > >
On Thu, 9 Aug 2007 11:59:43 +0200 Matthias Hensler <[EMAIL PROTECTED]> wrote:
> On Sat, Aug 04, 2007 at 10:44:26AM +0200, Matthias Hensler wrote:
> > On Fri, Aug 03, 2007 at 11:34:07AM -0700, Andrew Morton wrote:
> > [...]
> > I am also willing to try the patch posted by Richard.
>
> I want to gi
On Sat, Aug 04, 2007 at 10:44:26AM +0200, Matthias Hensler wrote:
> On Fri, Aug 03, 2007 at 11:34:07AM -0700, Andrew Morton wrote:
> [...]
> I am also willing to try the patch posted by Richard.
I want to give some update here:
1. We finally hit the problem on a third system, with a total differe
On Fri, Aug 03, 2007 at 11:34:07AM -0700, Andrew Morton wrote:
> (attempting to cc Matthias. If I have the wrong one, please fix it up)
You got the correct one.
> > Looks like the same problem with spinlock unfairness we've seen
> > elsewhere: it seems to be looping here? Or is everyone stuck
>
Chuck Ebbert wrote:
>
> Looks like the same problem with spinlock unfairness we've seen
> elsewhere: it seems to be looping here? Or is everyone stuck
> just waiting for writeout?
>
> lock_timer_base():
> for (;;) {
> tvec_base_t *prelock_base = timer->base;
>
(attempting to cc Matthias. If I have the wrong one, please fix it up)
(please generally cc reporters when forwarding their bug reports)
On Wed, 01 Aug 2007 18:39:51 -0400
Chuck Ebbert <[EMAIL PROTECTED]> wrote:
> Looks like the same problem with spinlock unfairness we've seen
> elsewhere: it
On Wed, 01 Aug 2007 18:39:51 -0400, Chuck Ebbert wrote:
> Looks like the same problem with spinlock unfairness we've seen
> elsewhere: it seems to be looping here? Or is everyone stuck just
> waiting for writeout?
>
> lock_timer_base():
> for (;;) {
> tvec_base_t *prelock_
Looks like the same problem with spinlock unfairness we've seen
elsewhere: it seems to be looping here? Or is everyone stuck
just waiting for writeout?
lock_timer_base():
for (;;) {
tvec_base_t *prelock_base = timer->base;
base = tbase_get_base(prelock_base)
25 matches
Mail list logo