An IPI is sent to flush remote TLBs when a page is unmapped that was
potentially accesssed by other CPUs. There are many circumstances where
this happens but the obvious one is kswapd reclaiming pages belonging to
a running process as kswapd and the task are likely running on separate CPUs.
On
An IPI is sent to flush remote TLBs when a page is unmapped that was
potentially accesssed by other CPUs. There are many circumstances where
this happens but the obvious one is kswapd reclaiming pages belonging to
a running process as kswapd and the task are likely running on separate CPUs.
On
On Thu, Jun 11, 2015 at 05:02:51PM +0200, Ingo Molnar wrote:
>
> * Mel Gorman wrote:
>
> > > In the full-flushing case (v6 without patch 4) the batching limit is
> > > 'infinite', we'll batch as long as possible, right?
> >
> > No because we must flush before pages are freed so the maximum
* Mel Gorman wrote:
> > In the full-flushing case (v6 without patch 4) the batching limit is
> > 'infinite', we'll batch as long as possible, right?
>
> No because we must flush before pages are freed so the maximum batching is
> related to SWAP_CLUSTER_MAX. If we free a page before the
* Mel Gorman mgor...@suse.de wrote:
In the full-flushing case (v6 without patch 4) the batching limit is
'infinite', we'll batch as long as possible, right?
No because we must flush before pages are freed so the maximum batching is
related to SWAP_CLUSTER_MAX. If we free a page before
On Thu, Jun 11, 2015 at 05:02:51PM +0200, Ingo Molnar wrote:
* Mel Gorman mgor...@suse.de wrote:
In the full-flushing case (v6 without patch 4) the batching limit is
'infinite', we'll batch as long as possible, right?
No because we must flush before pages are freed so the maximum
On Wed, Jun 10, 2015 at 10:26:40AM +0200, Ingo Molnar wrote:
>
> * Mel Gorman wrote:
>
> > On a 4-socket machine the results were
> >
> > 4.1.0-rc6 4.1.0-rc6
> > batchdirty-v6 batchunmap-v6
> > Ops
On Wed, Jun 10, 2015 at 10:33:32AM +0200, Ingo Molnar wrote:
>
> * Mel Gorman wrote:
>
> > Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs
> >
> > 4.1.0-rc6 4.1.0-rc6
> > vanilla
On Wed, Jun 10, 2015 at 10:21:07AM +0200, Ingo Molnar wrote:
>
> * Mel Gorman wrote:
>
> > On Wed, Jun 10, 2015 at 09:47:04AM +0200, Ingo Molnar wrote:
> > >
> > > * Mel Gorman wrote:
> > >
> > > > --- a/include/linux/sched.h
> > > > +++ b/include/linux/sched.h
> > > > @@ -1289,6 +1289,18 @@
* Mel Gorman wrote:
> Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs
>
> 4.1.0-rc6 4.1.0-rc6
> vanilla flushfull-v6
> Ops lru-file-mmap-read-elapsed 162.88 ( 0.00%) 120.81 (
* Mel Gorman wrote:
> On a 4-socket machine the results were
>
> 4.1.0-rc6 4.1.0-rc6
> batchdirty-v6 batchunmap-v6
> Ops lru-file-mmap-read-elapsed 121.27 ( 0.00%) 118.79 ( 2.05%)
>
>
* Mel Gorman wrote:
> On Wed, Jun 10, 2015 at 09:47:04AM +0200, Ingo Molnar wrote:
> >
> > * Mel Gorman wrote:
> >
> > > --- a/include/linux/sched.h
> > > +++ b/include/linux/sched.h
> > > @@ -1289,6 +1289,18 @@ enum perf_event_task_context {
> > > perf_nr_task_contexts,
> > > };
> > >
On Wed, Jun 10, 2015 at 09:47:04AM +0200, Ingo Molnar wrote:
>
> * Mel Gorman wrote:
>
> > --- a/include/linux/sched.h
> > +++ b/include/linux/sched.h
> > @@ -1289,6 +1289,18 @@ enum perf_event_task_context {
> > perf_nr_task_contexts,
> > };
> >
> > +/* Track pages that require TLB
* Mel Gorman wrote:
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1289,6 +1289,18 @@ enum perf_event_task_context {
> perf_nr_task_contexts,
> };
>
> +/* Track pages that require TLB flushes */
> +struct tlbflush_unmap_batch {
> + /*
> + * Each bit set is a
On Wed, Jun 10, 2015 at 09:47:04AM +0200, Ingo Molnar wrote:
* Mel Gorman mgor...@suse.de wrote:
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1289,6 +1289,18 @@ enum perf_event_task_context {
perf_nr_task_contexts,
};
+/* Track pages that require TLB
* Mel Gorman mgor...@suse.de wrote:
On Wed, Jun 10, 2015 at 09:47:04AM +0200, Ingo Molnar wrote:
* Mel Gorman mgor...@suse.de wrote:
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1289,6 +1289,18 @@ enum perf_event_task_context {
perf_nr_task_contexts,
};
* Mel Gorman mgor...@suse.de wrote:
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1289,6 +1289,18 @@ enum perf_event_task_context {
perf_nr_task_contexts,
};
+/* Track pages that require TLB flushes */
+struct tlbflush_unmap_batch {
+ /*
+ * Each bit set
On Wed, Jun 10, 2015 at 10:21:07AM +0200, Ingo Molnar wrote:
* Mel Gorman mgor...@suse.de wrote:
On Wed, Jun 10, 2015 at 09:47:04AM +0200, Ingo Molnar wrote:
* Mel Gorman mgor...@suse.de wrote:
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1289,6
On Wed, Jun 10, 2015 at 10:33:32AM +0200, Ingo Molnar wrote:
* Mel Gorman mgor...@suse.de wrote:
Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs
4.1.0-rc6 4.1.0-rc6
vanilla
* Mel Gorman mgor...@suse.de wrote:
On a 4-socket machine the results were
4.1.0-rc6 4.1.0-rc6
batchdirty-v6 batchunmap-v6
Ops lru-file-mmap-read-elapsed 121.27 ( 0.00%) 118.79 ( 2.05%)
* Mel Gorman mgor...@suse.de wrote:
Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs
4.1.0-rc6 4.1.0-rc6
vanilla flushfull-v6
Ops lru-file-mmap-read-elapsed 162.88 ( 0.00%)
On Wed, Jun 10, 2015 at 10:26:40AM +0200, Ingo Molnar wrote:
* Mel Gorman mgor...@suse.de wrote:
On a 4-socket machine the results were
4.1.0-rc6 4.1.0-rc6
batchdirty-v6 batchunmap-v6
Ops
On 06/09/2015 01:31 PM, Mel Gorman wrote:
> An IPI is sent to flush remote TLBs when a page is unmapped that was
> potentially accesssed by other CPUs. There are many circumstances where
> this happens but the obvious one is kswapd reclaiming pages belonging to
> a running process as kswapd and
An IPI is sent to flush remote TLBs when a page is unmapped that was
potentially accesssed by other CPUs. There are many circumstances where
this happens but the obvious one is kswapd reclaiming pages belonging to
a running process as kswapd and the task are likely running on separate CPUs.
On
An IPI is sent to flush remote TLBs when a page is unmapped that was
potentially accesssed by other CPUs. There are many circumstances where
this happens but the obvious one is kswapd reclaiming pages belonging to
a running process as kswapd and the task are likely running on separate CPUs.
On
On 06/09/2015 01:31 PM, Mel Gorman wrote:
An IPI is sent to flush remote TLBs when a page is unmapped that was
potentially accesssed by other CPUs. There are many circumstances where
this happens but the obvious one is kswapd reclaiming pages belonging to
a running process as kswapd and the
26 matches
Mail list logo