lkml.org 
[lkml]   [2015]   [Mar]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: kswapd hogging in lowmem_shrink
On 03/16/2015 03:45 AM, Vaibhav Shinde wrote:
>
>
> On Fri, Mar 13, 2015 at 7:52 AM, Rik van Riel <riel@redhat.com
> <mailto:riel@redhat.com>> wrote:
>>
>> On 03/13/2015 10:25 AM, Vaibhav Shinde wrote:
>> >
>> > On low memory situation, I see various shrinkers being invoked, but in
>> > lowmem_shrink() case, kswapd is found to be hogging for around 150msecs.
>> >
>> > Due to this my application suffer latency issue, as the cpu was not
>> > released by kswapd0.
>> >
>> > I took below traces with vmscan events, that show lowmem_shrink taking
>> > such long time for execution.
>>
>> This is the Android low memory killer, which kills the
>> task with the lowest priority in the system.
>>
>> The low memory killer will iterate over all the tasks
>> in the system to identify the task to kill.
>>
>> This is not a problem in Android systems, and other
>> small systems where this piece of code is used.
>>
>> What kind of system are you trying to use the low
>> memory killer on?
>>
>> How many tasks are you running?
>>
> yes, lowmemorykiller kills the task depending on its oom_score, I am
> using a embedded device with 2GB memory, there are task running that
> cause lowmemory situation - no issue about it.
>
> But my concern is kswapd takes too long to iterate through all the
> processes(lowmem_shrink() => for_each_process()), the time taken is
> around 150msec, due to which my high priority application suffer system
> latency that cause malfunctioning.

If it is an issue for you, you will have to fix that.

--
All rights reversed


\
 
 \ /
  Last update: 2015-03-16 13:01    [W:0.066 / U:5.572 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site