Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-30 Thread Ben Hutchings
[Dropped John Stultz from the cc list as this doesn't seem to relate to his changes.] On Fri, 2012-04-27 at 15:30 +0200, Sven Hoexter wrote: On Fri, Apr 27, 2012 at 04:19:21AM +0100, Ben Hutchings wrote: Hi, So it looks like in this case at least you're seeing a bug in USB error

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-27 Thread Sven Hoexter
On Fri, Apr 27, 2012 at 04:19:21AM +0100, Ben Hutchings wrote: Hi, So it looks like in this case at least you're seeing a bug in USB error recovery and not anything to do with timing using the TSC vs HPET. Ok, a few minutes ago I got aware of another system with the given symptoms with a

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-26 Thread Sven Hoexter
On Thu, Apr 26, 2012 at 04:49:56AM +0100, Ben Hutchings wrote: On Wed, 2012-04-25 at 10:36 +0200, Sven Hoexter wrote: Hi, Searching through munin graphs we could narrow down the starting point of this issue to the point when the hpet interrupts for one CPU core multiplied. Sometimes

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-26 Thread Sven Hoexter
On Wed, Apr 25, 2012 at 09:33:44PM -0700, John Stultz wrote: Hi, When you can connect to the system that is having problems, do you see any problems with the time? ie: does date show the correct time, and does it increment normally? I don't see any jumps in time here: while true; do

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-26 Thread Ben Hutchings
On Thu, 2012-04-26 at 10:02 +0200, Sven Hoexter wrote: On Thu, Apr 26, 2012 at 04:49:56AM +0100, Ben Hutchings wrote: On Wed, 2012-04-25 at 10:36 +0200, Sven Hoexter wrote: Hi, Searching through munin graphs we could narrow down the starting point of this issue to the point when

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-26 Thread Sven Hoexter
On Thu, Apr 26, 2012 at 01:45:30PM +0100, Ben Hutchings wrote: Hi, You can use 'echo w /proc/sysrq-trigger' to get a traceback for all the tasks in D state, which might provide some clues. ok, see the attached file. Regards, Sven Apr 26 16:08:34 vdf1 kernel: [6726714.281854] SysRq : Show

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-26 Thread Ben Hutchings
On Thu, 2012-04-26 at 16:17 +0200, Sven Hoexter wrote: On Thu, Apr 26, 2012 at 01:45:30PM +0100, Ben Hutchings wrote: Hi, You can use 'echo w /proc/sysrq-trigger' to get a traceback for all the tasks in D state, which might provide some clues. ok, see the attached file. Apr 26

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-25 Thread Sven Hoexter
Package: linux-image-2.6.32-5-amd64 Version: 2.6.32-41squeeze2 Severity: important Hi, since about December 2011 we've seen systems were SSH sessions suddenly hang and further logins on the physical TTY or via SSH are no longer possible. In some cases ssh logins still work and you see motd and

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-25 Thread Ben Hutchings
On Wed, 2012-04-25 at 10:36 +0200, Sven Hoexter wrote: Package: linux-image-2.6.32-5-amd64 Version: 2.6.32-41squeeze2 Severity: important Hi, since about December 2011 we've seen systems were SSH sessions suddenly hang and further logins on the physical TTY or via SSH are no longer

Bug#670398: linux-image-2.6.32-5-amd64: SSH logins hang while hpet interrupts multiply on Intel Nehalem CPUs

2012-04-25 Thread John Stultz
On 04/25/2012 08:49 PM, Ben Hutchings wrote: On Wed, 2012-04-25 at 10:36 +0200, Sven Hoexter wrote: Package: linux-image-2.6.32-5-amd64 Version: 2.6.32-41squeeze2 Severity: important Hi, since about December 2011 we've seen systems were SSH sessions suddenly hang and further logins on the