Re: cgroups-related hard lockup in 4.14?

2017-12-20 Thread Dan Aloni
On Wed, Dec 20, 2017 at 03:24:09PM -0800, Tejun Heo wrote: > On Thu, Dec 21, 2017 at 12:59:23AM +0200, Dan Aloni wrote: > > Hi, > > > > Using netconsole, I was able to capture a hard lockup that seems to be > > related to cgroups, on a Fedora kernel based on v4.14.4. > > > > By my analysis, from

Re: cgroups-related hard lockup in 4.14?

2017-12-20 Thread Dan Aloni
On Wed, Dec 20, 2017 at 03:24:09PM -0800, Tejun Heo wrote: > On Thu, Dec 21, 2017 at 12:59:23AM +0200, Dan Aloni wrote: > > Hi, > > > > Using netconsole, I was able to capture a hard lockup that seems to be > > related to cgroups, on a Fedora kernel based on v4.14.4. > > > > By my analysis, from

Re: cgroups-related hard lockup in 4.14?

2017-12-20 Thread Tejun Heo
On Thu, Dec 21, 2017 at 12:59:23AM +0200, Dan Aloni wrote: > Hi, > > Using netconsole, I was able to capture a hard lockup that seems to be > related to cgroups, on a Fedora kernel based on v4.14.4. > > By my analysis, from the 16 CPUs below, 14 are on css_set_lock, one is > inside

Re: cgroups-related hard lockup in 4.14?

2017-12-20 Thread Tejun Heo
On Thu, Dec 21, 2017 at 12:59:23AM +0200, Dan Aloni wrote: > Hi, > > Using netconsole, I was able to capture a hard lockup that seems to be > related to cgroups, on a Fedora kernel based on v4.14.4. > > By my analysis, from the 16 CPUs below, 14 are on css_set_lock, one is > inside

cgroups-related hard lockup in 4.14?

2017-12-20 Thread Dan Aloni
Hi, Using netconsole, I was able to capture a hard lockup that seems to be related to cgroups, on a Fedora kernel based on v4.14.4. By my analysis, from the 16 CPUs below, 14 are on css_set_lock, one is inside css_task_iter_advance, and the last one stuck trying to send an IPI, I guess because

cgroups-related hard lockup in 4.14?

2017-12-20 Thread Dan Aloni
Hi, Using netconsole, I was able to capture a hard lockup that seems to be related to cgroups, on a Fedora kernel based on v4.14.4. By my analysis, from the 16 CPUs below, 14 are on css_set_lock, one is inside css_task_iter_advance, and the last one stuck trying to send an IPI, I guess because