On 02/11/2016 11:51 PM, Andrew Morton wrote:
> On Wed, 10 Feb 2016 16:24:16 -0800 Tim Chen
> wrote:
>
>> On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
>>
>>>
>>> If a process is unmapping 4MB then it's pretty crazy for us to be
>>> hitting the percpu_counter 32 separate times for that
On 02/11/2016 11:51 PM, Andrew Morton wrote:
> On Wed, 10 Feb 2016 16:24:16 -0800 Tim Chen
> wrote:
>
>> On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
>>
>>>
>>> If a process is unmapping 4MB then it's pretty crazy for us to be
>>> hitting the
On Thu, 2016-02-11 at 12:51 -0800, Andrew Morton wrote:
> On Wed, 10 Feb 2016 16:24:16 -0800 Tim Chen
> wrote:
>
> > On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
> >
> > >
> > > If a process is unmapping 4MB then it's pretty crazy for us to be
> > > hitting the percpu_counter 32
On Wed, 10 Feb 2016 16:24:16 -0800 Tim Chen wrote:
> On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
>
> >
> > If a process is unmapping 4MB then it's pretty crazy for us to be
> > hitting the percpu_counter 32 separate times for that single operation.
> >
> > Is there some way in
On 02/11/2016 10:20 AM, Tim Chen wrote:
> The brk1 test is also somewhat pathologic. It
> does nothing but brk which is unlikely for real workload.
> So we have to be careful when we are tuning our system
> behavior for brk1 throughput. We'll need to make sure
> whatever changes we made don't
On Thu, 2016-02-11 at 16:54 +0300, Andrey Ryabinin wrote:
>
> On 02/11/2016 03:24 AM, Tim Chen wrote:
> > On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
> >
> >>
> >> If a process is unmapping 4MB then it's pretty crazy for us to be
> >> hitting the percpu_counter 32 separate times for
On Thu, 2016-02-11 at 16:36 +0300, Andrey Ryabinin wrote:
> On 02/10/2016 08:46 PM, Konstantin Khlebnikov wrote:
> > On Wed, Feb 10, 2016 at 5:52 PM, Andrey Ryabinin
> > wrote:
> >> Currently we use percpu_counter for accounting committed memory. Change
> >> of committed memory on more than
On 02/11/2016 03:24 AM, Tim Chen wrote:
> On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
>
>>
>> If a process is unmapping 4MB then it's pretty crazy for us to be
>> hitting the percpu_counter 32 separate times for that single operation.
>>
>> Is there some way in which we can batch up
On 02/10/2016 08:46 PM, Konstantin Khlebnikov wrote:
> On Wed, Feb 10, 2016 at 5:52 PM, Andrey Ryabinin
> wrote:
>> Currently we use percpu_counter for accounting committed memory. Change
>> of committed memory on more than vm_committed_as_batch pages leads to
>> grab of counter's spinlock. The
On 02/11/2016 10:20 AM, Tim Chen wrote:
> The brk1 test is also somewhat pathologic. It
> does nothing but brk which is unlikely for real workload.
> So we have to be careful when we are tuning our system
> behavior for brk1 throughput. We'll need to make sure
> whatever changes we made don't
On 02/11/2016 03:24 AM, Tim Chen wrote:
> On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
>
>>
>> If a process is unmapping 4MB then it's pretty crazy for us to be
>> hitting the percpu_counter 32 separate times for that single operation.
>>
>> Is there some way in which we can batch up
On 02/10/2016 08:46 PM, Konstantin Khlebnikov wrote:
> On Wed, Feb 10, 2016 at 5:52 PM, Andrey Ryabinin
> wrote:
>> Currently we use percpu_counter for accounting committed memory. Change
>> of committed memory on more than vm_committed_as_batch pages leads to
>> grab of
On Wed, 10 Feb 2016 16:24:16 -0800 Tim Chen wrote:
> On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
>
> >
> > If a process is unmapping 4MB then it's pretty crazy for us to be
> > hitting the percpu_counter 32 separate times for that single operation.
> >
On Thu, 2016-02-11 at 12:51 -0800, Andrew Morton wrote:
> On Wed, 10 Feb 2016 16:24:16 -0800 Tim Chen
> wrote:
>
> > On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
> >
> > >
> > > If a process is unmapping 4MB then it's pretty crazy for us to be
> > >
On Thu, 2016-02-11 at 16:36 +0300, Andrey Ryabinin wrote:
> On 02/10/2016 08:46 PM, Konstantin Khlebnikov wrote:
> > On Wed, Feb 10, 2016 at 5:52 PM, Andrey Ryabinin
> > wrote:
> >> Currently we use percpu_counter for accounting committed memory. Change
> >> of committed
On Thu, 2016-02-11 at 16:54 +0300, Andrey Ryabinin wrote:
>
> On 02/11/2016 03:24 AM, Tim Chen wrote:
> > On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
> >
> >>
> >> If a process is unmapping 4MB then it's pretty crazy for us to be
> >> hitting the percpu_counter 32 separate times for
On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
>
> If a process is unmapping 4MB then it's pretty crazy for us to be
> hitting the percpu_counter 32 separate times for that single operation.
>
> Is there some way in which we can batch up the modifications within the
> caller and update
On Wed, 10 Feb 2016 10:00:53 -0800 Tim Chen wrote:
> On Wed, 2016-02-10 at 17:52 +0300, Andrey Ryabinin wrote:
> > Currently we use percpu_counter for accounting committed memory. Change
> > of committed memory on more than vm_committed_as_batch pages leads to
> > grab of counter's spinlock. The
On Wed, 2016-02-10 at 17:52 +0300, Andrey Ryabinin wrote:
> Currently we use percpu_counter for accounting committed memory. Change
> of committed memory on more than vm_committed_as_batch pages leads to
> grab of counter's spinlock. The batch size is quite small - from 32 pages
> up to 0.4% of
On Wed, Feb 10, 2016 at 5:52 PM, Andrey Ryabinin
wrote:
> Currently we use percpu_counter for accounting committed memory. Change
> of committed memory on more than vm_committed_as_batch pages leads to
> grab of counter's spinlock. The batch size is quite small - from 32 pages
> up to 0.4% of the
Currently we use percpu_counter for accounting committed memory. Change
of committed memory on more than vm_committed_as_batch pages leads to
grab of counter's spinlock. The batch size is quite small - from 32 pages
up to 0.4% of the memory/cpu (usually several MBs even on large machines).
So
Currently we use percpu_counter for accounting committed memory. Change
of committed memory on more than vm_committed_as_batch pages leads to
grab of counter's spinlock. The batch size is quite small - from 32 pages
up to 0.4% of the memory/cpu (usually several MBs even on large machines).
So
On Wed, Feb 10, 2016 at 5:52 PM, Andrey Ryabinin
wrote:
> Currently we use percpu_counter for accounting committed memory. Change
> of committed memory on more than vm_committed_as_batch pages leads to
> grab of counter's spinlock. The batch size is quite small - from 32
On Wed, 2016-02-10 at 17:52 +0300, Andrey Ryabinin wrote:
> Currently we use percpu_counter for accounting committed memory. Change
> of committed memory on more than vm_committed_as_batch pages leads to
> grab of counter's spinlock. The batch size is quite small - from 32 pages
> up to 0.4% of
On Wed, 10 Feb 2016 10:00:53 -0800 Tim Chen wrote:
> On Wed, 2016-02-10 at 17:52 +0300, Andrey Ryabinin wrote:
> > Currently we use percpu_counter for accounting committed memory. Change
> > of committed memory on more than vm_committed_as_batch pages leads to
> >
On Wed, 2016-02-10 at 13:28 -0800, Andrew Morton wrote:
>
> If a process is unmapping 4MB then it's pretty crazy for us to be
> hitting the percpu_counter 32 separate times for that single operation.
>
> Is there some way in which we can batch up the modifications within the
> caller and update
26 matches
Mail list logo