On Wed, 2017-01-25 at 16:06 +0100, Sebastian Andrzej Siewior wrote:
> According to the to description of radix_tree_preload() the return code
> of 0 means that the following addition of a single element does not
> fail. But in RT's case this requirement is not fulfilled. There is more
> than just
On Wed, 2017-01-25 at 16:06 +0100, Sebastian Andrzej Siewior wrote:
> According to the to description of radix_tree_preload() the return code
> of 0 means that the following addition of a single element does not
> fail. But in RT's case this requirement is not fulfilled. There is more
> than just
On 2017-01-06 09:13:23 [+0100], Mike Galbraith wrote:
> radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
>
> Having no preload, which turns accounting off for non-rt kernels, trying to
> allocate coming from shmem_fault() when memcg is full sends us scurrying off
> to
On 2017-01-06 09:13:23 [+0100], Mike Galbraith wrote:
> radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
>
> Having no preload, which turns accounting off for non-rt kernels, trying to
> allocate coming from shmem_fault() when memcg is full sends us scurrying off
> to
Trace of the bad thing about to happen.
madvise06-4719 [003] ... 1187.428766: handle_mm_fault
<-__do_page_fault
madvise06-4719 [003] ... 1187.428766: __rcu_read_lock
<-handle_mm_fault
madvise06-4719 [003] ... 1187.428766: mem_cgroup_from_task
Trace of the bad thing about to happen.
madvise06-4719 [003] ... 1187.428766: handle_mm_fault
<-__do_page_fault
madvise06-4719 [003] ... 1187.428766: __rcu_read_lock
<-handle_mm_fault
madvise06-4719 [003] ... 1187.428766: mem_cgroup_from_task
On Fri, 2017-01-06 at 13:20 +0100, Mike Galbraith wrote:
> > > madvise06 isn't as deadly to the twiddled PREEMPT kernel as
> it is to PREEMPT_RT_FULL, but a very few runs attracted the oom beast.
The very next run paniced the box... deadly enough for gvt. work :)
On Fri, 2017-01-06 at 13:20 +0100, Mike Galbraith wrote:
> > > madvise06 isn't as deadly to the twiddled PREEMPT kernel as
> it is to PREEMPT_RT_FULL, but a very few runs attracted the oom beast.
The very next run paniced the box... deadly enough for gvt. work :)
On Fri, 2017-01-06 at 11:52 +0100, Mike Galbraith wrote:
> On Fri, 2017-01-06 at 09:55 +0100, Michal Hocko wrote:
> > On Fri 06-01-17 09:13:23, Mike Galbraith wrote:
> > > radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
> > >
> > > Having no preload, which turns
On Fri, 2017-01-06 at 11:52 +0100, Mike Galbraith wrote:
> On Fri, 2017-01-06 at 09:55 +0100, Michal Hocko wrote:
> > On Fri 06-01-17 09:13:23, Mike Galbraith wrote:
> > > radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
> > >
> > > Having no preload, which turns
On Fri, 2017-01-06 at 09:55 +0100, Michal Hocko wrote:
> On Fri 06-01-17 09:13:23, Mike Galbraith wrote:
> > radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
> >
> > Having no preload, which turns accounting off for non-rt kernels, trying to
> > allocate coming from
On Fri, 2017-01-06 at 09:55 +0100, Michal Hocko wrote:
> On Fri 06-01-17 09:13:23, Mike Galbraith wrote:
> > radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
> >
> > Having no preload, which turns accounting off for non-rt kernels, trying to
> > allocate coming from
On Fri 06-01-17 09:13:23, Mike Galbraith wrote:
> radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
>
> Having no preload, which turns accounting off for non-rt kernels, trying to
> allocate coming from shmem_fault() when memcg is full sends us scurrying off
> to
On Fri 06-01-17 09:13:23, Mike Galbraith wrote:
> radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
>
> Having no preload, which turns accounting off for non-rt kernels, trying to
> allocate coming from shmem_fault() when memcg is full sends us scurrying off
> to
radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
Having no preload, which turns accounting off for non-rt kernels, trying to
allocate coming from shmem_fault() when memcg is full sends us scurrying off
to pagefault_out_of_memory(), with dramatic (usually terminal)
radix-tree: Partially disable memcg accounting in radix_tree_node_alloc()
Having no preload, which turns accounting off for non-rt kernels, trying to
allocate coming from shmem_fault() when memcg is full sends us scurrying off
to pagefault_out_of_memory(), with dramatic (usually terminal)
16 matches
Mail list logo