On 2017年12月20日 01:21, Christopher Lameter wrote:
> On Tue, 19 Dec 2017, Michal Hocko wrote:
>
>>> Well the reason for s8 was to keep the data structures small so that they
>>> fit in the higher level cpu caches. The large these structures become the
>>> more cachelines are used by the counters
On 2017年12月20日 01:21, Christopher Lameter wrote:
> On Tue, 19 Dec 2017, Michal Hocko wrote:
>
>>> Well the reason for s8 was to keep the data structures small so that they
>>> fit in the higher level cpu caches. The large these structures become the
>>> more cachelines are used by the counters
On 2017年12月19日 20:38, Michal Hocko wrote:
> On Tue 19-12-17 14:39:23, Kemi Wang wrote:
>> The type s8 used for vm_diff_nodestat[] as local cpu counters has the
>> limitation of global counters update frequency, especially for those
>> monotone increasing type of counters like NUMA counters with
On 2017年12月19日 20:38, Michal Hocko wrote:
> On Tue 19-12-17 14:39:23, Kemi Wang wrote:
>> The type s8 used for vm_diff_nodestat[] as local cpu counters has the
>> limitation of global counters update frequency, especially for those
>> monotone increasing type of counters like NUMA counters with
On Tue, 19 Dec 2017, Michal Hocko wrote:
> > Well the reason for s8 was to keep the data structures small so that they
> > fit in the higher level cpu caches. The large these structures become the
> > more cachelines are used by the counters and the larger the performance
> > influence on the
On Tue, 19 Dec 2017, Michal Hocko wrote:
> > Well the reason for s8 was to keep the data structures small so that they
> > fit in the higher level cpu caches. The large these structures become the
> > more cachelines are used by the counters and the larger the performance
> > influence on the
On Tue 19-12-17 10:05:48, Cristopher Lameter wrote:
> On Tue, 19 Dec 2017, Kemi Wang wrote:
>
> > The type s8 used for vm_diff_nodestat[] as local cpu counters has the
> > limitation of global counters update frequency, especially for those
> > monotone increasing type of counters like NUMA
On Tue 19-12-17 10:05:48, Cristopher Lameter wrote:
> On Tue, 19 Dec 2017, Kemi Wang wrote:
>
> > The type s8 used for vm_diff_nodestat[] as local cpu counters has the
> > limitation of global counters update frequency, especially for those
> > monotone increasing type of counters like NUMA
On Tue, 19 Dec 2017, Kemi Wang wrote:
> The type s8 used for vm_diff_nodestat[] as local cpu counters has the
> limitation of global counters update frequency, especially for those
> monotone increasing type of counters like NUMA counters with more and more
> cpus/nodes. This patch extends the
On Tue, 19 Dec 2017, Kemi Wang wrote:
> The type s8 used for vm_diff_nodestat[] as local cpu counters has the
> limitation of global counters update frequency, especially for those
> monotone increasing type of counters like NUMA counters with more and more
> cpus/nodes. This patch extends the
On Tue 19-12-17 14:39:23, Kemi Wang wrote:
> The type s8 used for vm_diff_nodestat[] as local cpu counters has the
> limitation of global counters update frequency, especially for those
> monotone increasing type of counters like NUMA counters with more and more
> cpus/nodes. This patch extends
On Tue 19-12-17 14:39:23, Kemi Wang wrote:
> The type s8 used for vm_diff_nodestat[] as local cpu counters has the
> limitation of global counters update frequency, especially for those
> monotone increasing type of counters like NUMA counters with more and more
> cpus/nodes. This patch extends
The type s8 used for vm_diff_nodestat[] as local cpu counters has the
limitation of global counters update frequency, especially for those
monotone increasing type of counters like NUMA counters with more and more
cpus/nodes. This patch extends the type of vm_diff_nodestat from s8 to s16
without
The type s8 used for vm_diff_nodestat[] as local cpu counters has the
limitation of global counters update frequency, especially for those
monotone increasing type of counters like NUMA counters with more and more
cpus/nodes. This patch extends the type of vm_diff_nodestat from s8 to s16
without
14 matches
Mail list logo