On Fri, Apr 06, 2018 at 04:52:15PM +0300, Andrey Ryabinin wrote:
> On 04/06/2018 05:13 AM, Shakeel Butt wrote:
> > Question: Should this 'flags' be per-node? Is it ok for a congested
> > memcg to call wait_iff_congested for all nodes?
>
> Indeed, congestion state should be pre-node. If memcg on
On Fri, Apr 06, 2018 at 04:52:15PM +0300, Andrey Ryabinin wrote:
> On 04/06/2018 05:13 AM, Shakeel Butt wrote:
> > Question: Should this 'flags' be per-node? Is it ok for a congested
> > memcg to call wait_iff_congested for all nodes?
>
> Indeed, congestion state should be pre-node. If memcg on
On Fri, Apr 6, 2018 at 8:09 AM, Andrey Ryabinin wrote:
>
>
> On 04/06/2018 05:37 PM, Shakeel Butt wrote:
>
>>>
>>> @@ -2482,7 +2494,7 @@ static inline bool should_continue_reclaim(struct
>>> pglist_data *pgdat,
>>> static bool pgdat_memcg_congested(pg_data_t *pgdat,
On Fri, Apr 6, 2018 at 8:09 AM, Andrey Ryabinin wrote:
>
>
> On 04/06/2018 05:37 PM, Shakeel Butt wrote:
>
>>>
>>> @@ -2482,7 +2494,7 @@ static inline bool should_continue_reclaim(struct
>>> pglist_data *pgdat,
>>> static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup
>>>
On 04/06/2018 05:37 PM, Shakeel Butt wrote:
>>
>> @@ -2482,7 +2494,7 @@ static inline bool should_continue_reclaim(struct
>> pglist_data *pgdat,
>> static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup
>> *memcg)
>> {
>> return test_bit(PGDAT_CONGESTED, >flags) ||
>>
On 04/06/2018 05:37 PM, Shakeel Butt wrote:
>>
>> @@ -2482,7 +2494,7 @@ static inline bool should_continue_reclaim(struct
>> pglist_data *pgdat,
>> static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup
>> *memcg)
>> {
>> return test_bit(PGDAT_CONGESTED, >flags) ||
>>
On Fri, Apr 6, 2018 at 6:52 AM, Andrey Ryabinin wrote:
> On 04/06/2018 05:13 AM, Shakeel Butt wrote:
>> Question: Should this 'flags' be per-node? Is it ok for a congested
>> memcg to call wait_iff_congested for all nodes?
>
> Indeed, congestion state should be pre-node.
On Fri, Apr 6, 2018 at 6:52 AM, Andrey Ryabinin wrote:
> On 04/06/2018 05:13 AM, Shakeel Butt wrote:
>> Question: Should this 'flags' be per-node? Is it ok for a congested
>> memcg to call wait_iff_congested for all nodes?
>
> Indeed, congestion state should be pre-node. If memcg on node A is
>
8 matches
Mail list logo