On Mon, 4 May 2015 10:48:44 +1000
Dave Chinner wrote:
> > I'm not sure why it does the ndelay() and not just a cpu_relax(), but
>
> Because the code was writtenlong before cpu_relax() existed, just
> like it was written long before the generic percpu counter code was
> added...
Ah, legacy
On Mon, 4 May 2015 10:48:44 +1000
Dave Chinner da...@fromorbit.com wrote:
I'm not sure why it does the ndelay() and not just a cpu_relax(), but
Because the code was writtenlong before cpu_relax() existed, just
like it was written long before the generic percpu counter code was
added...
On Thu, Apr 30, 2015 at 12:33:03PM -0400, Steven Rostedt wrote:
> Running a test on a large CPU count box with xfs, I hit a live lock
> with the following backtraces on several CPUs:
>
> Call Trace:
> [] __const_udelay+0x28/0x30
> [] xfs_icsb_lock_cntr+0x2a/0x40 [xfs]
> []
On Thu, Apr 30, 2015 at 12:33:03PM -0400, Steven Rostedt wrote:
Running a test on a large CPU count box with xfs, I hit a live lock
with the following backtraces on several CPUs:
Call Trace:
[812c34f8] __const_udelay+0x28/0x30
[a033ab9a]
On Thu, 30 Apr 2015 11:40:07 -0700
Austin Schuh wrote:
> On Thu, Apr 30, 2015 at 11:32 AM, Steven Rostedt wrote:
> > On Thu, 30 Apr 2015 20:07:21 +0200
> > Peter Zijlstra wrote:
> >> The irony, this is distinctly non deterministic code you're putting
> >> under a RT specific preempt_disable
On Thu, Apr 30, 2015 at 11:32 AM, Steven Rostedt wrote:
> On Thu, 30 Apr 2015 20:07:21 +0200
> Peter Zijlstra wrote:
>> The irony, this is distinctly non deterministic code you're putting
>> under a RT specific preempt_disable ;-)
>
> I know :-(
>
> Unfortunately, a RT behaving fix would be much
On Thu, 30 Apr 2015 11:33:27 -0700
Christoph Hellwig wrote:
> FYI, this code is gone in 4.1-rc.
:-)
Well, when we port -rt to 4.1 that will be the answer!
But for now, we need to band-aid the older versions of the kernel that
we do support.
-- Steve
--
To unsubscribe from this list: send the
FYI, this code is gone in 4.1-rc.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
On Thu, 30 Apr 2015 20:07:21 +0200
Peter Zijlstra wrote:
> On Thu, Apr 30, 2015 at 12:33:03PM -0400, Steven Rostedt wrote:
> > diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
> > index 51435dbce9c4..dbaa1ce3f308 100644
> > --- a/fs/xfs/xfs_mount.c
> > +++ b/fs/xfs/xfs_mount.c
> > @@ -1660,6
On Thu, Apr 30, 2015 at 12:33:03PM -0400, Steven Rostedt wrote:
> diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
> index 51435dbce9c4..dbaa1ce3f308 100644
> --- a/fs/xfs/xfs_mount.c
> +++ b/fs/xfs/xfs_mount.c
> @@ -1660,6 +1660,12 @@ xfs_icsb_lock_all_counters(
> xfs_icsb_cnts_t *cntp;
Running a test on a large CPU count box with xfs, I hit a live lock
with the following backtraces on several CPUs:
Call Trace:
[] __const_udelay+0x28/0x30
[] xfs_icsb_lock_cntr+0x2a/0x40 [xfs]
[] xfs_icsb_modify_counters+0x71/0x280 [xfs]
[] xfs_trans_reserve+0x171/0x210
FYI, this code is gone in 4.1-rc.
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
On Thu, Apr 30, 2015 at 11:32 AM, Steven Rostedt rost...@goodmis.org wrote:
On Thu, 30 Apr 2015 20:07:21 +0200
Peter Zijlstra pet...@infradead.org wrote:
The irony, this is distinctly non deterministic code you're putting
under a RT specific preempt_disable ;-)
I know :-(
Unfortunately, a
On Thu, 30 Apr 2015 11:33:27 -0700
Christoph Hellwig h...@infradead.org wrote:
FYI, this code is gone in 4.1-rc.
:-)
Well, when we port -rt to 4.1 that will be the answer!
But for now, we need to band-aid the older versions of the kernel that
we do support.
-- Steve
--
To unsubscribe from
Running a test on a large CPU count box with xfs, I hit a live lock
with the following backtraces on several CPUs:
Call Trace:
[812c34f8] __const_udelay+0x28/0x30
[a033ab9a] xfs_icsb_lock_cntr+0x2a/0x40 [xfs]
[a033c871]
On Thu, Apr 30, 2015 at 12:33:03PM -0400, Steven Rostedt wrote:
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 51435dbce9c4..dbaa1ce3f308 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1660,6 +1660,12 @@ xfs_icsb_lock_all_counters(
xfs_icsb_cnts_t *cntp;
On Thu, 30 Apr 2015 20:07:21 +0200
Peter Zijlstra pet...@infradead.org wrote:
On Thu, Apr 30, 2015 at 12:33:03PM -0400, Steven Rostedt wrote:
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 51435dbce9c4..dbaa1ce3f308 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
On Thu, 30 Apr 2015 11:40:07 -0700
Austin Schuh aus...@peloton-tech.com wrote:
On Thu, Apr 30, 2015 at 11:32 AM, Steven Rostedt rost...@goodmis.org wrote:
On Thu, 30 Apr 2015 20:07:21 +0200
Peter Zijlstra pet...@infradead.org wrote:
The irony, this is distinctly non deterministic code
18 matches
Mail list logo