Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

[I am sorry I didn't get to this earlier because I was at an internal conference last week] On Mon 21-09-15 01:06:58, Greg Thelen wrote: [...] > >From f5c39c2e8471c10fe0464ca7b6e6f743ce6920a6 Mon Sep 17 00:00:00 2001 > From: Greg Thelen > Date: Sat, 19 Sep 2015 16:21:18 -0700 > Subject: [PATCH]

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

[I am sorry I didn't get to this earlier because I was at an internal conference last week] On Mon 21-09-15 01:06:58, Greg Thelen wrote: [...] > >From f5c39c2e8471c10fe0464ca7b6e6f743ce6920a6 Mon Sep 17 00:00:00 2001 > From: Greg Thelen > Date: Sat, 19 Sep 2015 16:21:18 -0700

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

Dave Hansen wrote: > On 09/17/2015 11:09 PM, Greg Thelen wrote: >> I'm not denying the issue, bug the WARNING splat isn't necessarily >> catching a problem. The corresponding code comes from your debug patch: >> + >>

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

Dave Hansen wrote: > On 09/17/2015 11:09 PM, Greg Thelen wrote: >> I'm not denying the issue, bug the WARNING splat isn't necessarily >> catching a problem. The corresponding code comes from your debug patch: >> + >>

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

On 09/17/2015 11:09 PM, Greg Thelen wrote: > I'm not denying the issue, bug the WARNING splat isn't necessarily > catching a problem. The corresponding code comes from your debug patch: > + > WARN_ONCE(__this_cpu_read(memcg->stat->count[MEM_CGROUP_STAT_DIRTY]) > > (1UL<<30),

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

Greg Thelen wrote: > Dave Hansen wrote: > >> I've been seeing some strange behavior with 4.3-rc1 kernels on my Ubuntu >> 14.04.3 system. The system will run fine for a few hours, but suddenly >> start becoming horribly I/O bound. A compile of perf for instance takes >> 20-30 minutes and the

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

Dave Hansen wrote: > I've been seeing some strange behavior with 4.3-rc1 kernels on my Ubuntu > 14.04.3 system. The system will run fine for a few hours, but suddenly > start becoming horribly I/O bound. A compile of perf for instance takes > 20-30 minutes and the compile seems entirely I/O

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

Dave Hansen wrote: > I've been seeing some strange behavior with 4.3-rc1 kernels on my Ubuntu > 14.04.3 system. The system will run fine for a few hours, but suddenly > start becoming horribly I/O bound. A compile of perf for instance takes > 20-30 minutes and the compile seems entirely I/O

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

Greg Thelen wrote: > Dave Hansen wrote: > >> I've been seeing some strange behavior with 4.3-rc1 kernels on my Ubuntu >> 14.04.3 system. The system will run fine for a few hours, but suddenly >> start becoming horribly I/O bound. A compile of perf for instance takes >> 20-30 minutes and the

Re: 4.3-rc1 dirty page count underflow (cgroup-related?)

On 09/17/2015 11:09 PM, Greg Thelen wrote: > I'm not denying the issue, bug the WARNING splat isn't necessarily > catching a problem. The corresponding code comes from your debug patch: > + > WARN_ONCE(__this_cpu_read(memcg->stat->count[MEM_CGROUP_STAT_DIRTY]) > > (1UL<<30),

4.3-rc1 dirty page count underflow (cgroup-related?)

I've been seeing some strange behavior with 4.3-rc1 kernels on my Ubuntu 14.04.3 system. The system will run fine for a few hours, but suddenly start becoming horribly I/O bound. A compile of perf for instance takes 20-30 minutes and the compile seems entirely I/O bound. But, the SSD is only

4.3-rc1 dirty page count underflow (cgroup-related?)

I've been seeing some strange behavior with 4.3-rc1 kernels on my Ubuntu 14.04.3 system. The system will run fine for a few hours, but suddenly start becoming horribly I/O bound. A compile of perf for instance takes 20-30 minutes and the compile seems entirely I/O bound. But, the SSD is only