linux-kernel - Re: [PATCH] mm/oom_kill: count global and memory cgroup oom kills

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 22 May 2017 12:11:19 +0300
From:   Konstantin Khlebnikov <khlebnikov@...dex-team.ru>
To:     Roman Guschin <guroan@...il.com>
Cc:     linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
        Tejun Heo <tj@...nel.org>, cgroups@...r.kernel.org,
        linux-kernel@...r.kernel.org, Vlastimil Babka <vbabka@...e.cz>,
        Michal Hocko <mhocko@...nel.org>, hannes@...xchg.org
Subject: Re: [PATCH] mm/oom_kill: count global and memory cgroup oom kills



On 19.05.2017 19:34, Roman Guschin wrote:
> 2017-05-19 15:22 GMT+01:00 Konstantin Khlebnikov <khlebnikov@...dex-team.ru>:
>> Show count of global oom killer invocations in /proc/vmstat and
>> count of oom kills inside memory cgroup in knob "memory.events"
>> (in memory.oom_control for v1 cgroup).
>>
>> Also describe difference between "oom" and "oom_kill" in memory
>> cgroup documentation. Currently oom in memory cgroup kills tasks
>> iff shortage has happened inside page fault.
>>
>> These counters helps in monitoring oom kills - for now
>> the only way is grepping for magic words in kernel log.
>>
>> Signed-off-by: Konstantin Khlebnikov <khlebnikov@...dex-team.ru>
>> ---
>>   Documentation/cgroup-v2.txt   |   12 +++++++++++-
>>   include/linux/memcontrol.h    |    1 +
>>   include/linux/vm_event_item.h |    1 +
>>   mm/memcontrol.c               |    2 ++
>>   mm/oom_kill.c                 |    6 ++++++
>>   mm/vmstat.c                   |    1 +
>>   6 files changed, 22 insertions(+), 1 deletion(-)
>>
>> diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
>> index dc5e2dcdbef4..a742008d76aa 100644
>> --- a/Documentation/cgroup-v2.txt
>> +++ b/Documentation/cgroup-v2.txt
>> @@ -830,9 +830,19 @@ PAGE_SIZE multiple when read back.
>>
>>            oom
>>
>> +               The number of time the cgroup's memory usage was
>> +               reached the limit and allocation was about to fail.
>> +               Result could be oom kill, -ENOMEM from any syscall or
>> +               completely ignored in cases like disk readahead.
>> +               For now oom in memory cgroup kills tasks iff shortage
>> +               has happened inside page fault.
> 
>  From a user's point of view the difference between "oom" and "max"
> becomes really vague here,
> assuming that "max" is described almost in the same words:
> 
> "The number of times the cgroup's memory usage was
> about to go over the max boundary.  If direct reclaim
> fails to bring it down, the OOM killer is invoked."
> 
> I wonder, if it's better to fix the existing "oom" value  to show what
> it has to show, according to docs,
> rather than to introduce a new one?
> 

Nope, they are different. I think we should rephase documentation somehow

low - count of reclaims below low level
high - count of post-allocation reclaims above high level
max - count of direct reclaims
oom - count of failed direct reclaims
oom_kill - count of oom killer invocations and killed processes

>> +
>> +         oom_kill
>> +
>>                  The number of times the OOM killer has been invoked in
>>                  the cgroup.  This may not exactly match the number of
>> -               processes killed but should generally be close.
>> +               processes killed but should generally be close: each
>> +               invocation could kill several processes at once.
>>
>>     memory.stat
>>