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  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:   Wed, 29 Nov 2017 16:27:45 -0800
From:   Shakeel Butt <>
To:     Kirill Tkhai <>
Cc:     Andrew Morton <>,
        Vladimir Davydov <>,,
        LKML <>,
        Linux MM <>,
        Andrey Ryabinin <>
Subject: Re: [PATCH] mm: Make count list_lru_one::nr_items lockless

On Fri, Sep 29, 2017 at 1:15 AM, Kirill Tkhai <> wrote:
> On 29.09.2017 00:02, Andrew Morton wrote:
>> On Thu, 28 Sep 2017 10:48:55 +0300 Kirill Tkhai <> wrote:
>>>>> This patch aims to make super_cache_count() (and other functions,
>>>>> which count LRU nr_items) more effective.
>>>>> It allows list_lru_node::memcg_lrus to be RCU-accessed, and makes
>>>>> __list_lru_count_one() count nr_items lockless to minimize
>>>>> overhead introduced by locking operation, and to make parallel
>>>>> reclaims more scalable.
>>>> And...  what were the effects of the patch?  Did you not run the same
>>>> performance tests after applying it?
>>> I've just detected the such high usage of shrink slab on production node. It's rather
>>> difficult to make it use another kernel, than it uses, only kpatches are possible.
>>> So, I haven't estimated how it acts on node's performance.
>>> On test node I see, that the patch obviously removes raw_spin_lock from perf profile.
>>> So, it's a little bit untested in this way.
>> Well that's a problem.  The patch increases list_lru.o text size by a
>> lot (4800->5696) which will have a cost.  And we don't have proof that
>> any benefit is worth that cost.  It shouldn't be too hard to cook up a
>> synthetic test to trigger memcg slab reclaim and then run a
>> before-n-after benchmark?
> Ok, then, please, ignore this for a while, I'll try to do it a little bit later.

I rebased this patch on linus tree (replacing kfree_rcu with call_rcu
as there is no kvfree_rcu) and did some experiments. I think the patch
is worth to be included.

Setup: running a fork-bomb in a memcg of 200MiB on a 8GiB and 4 vcpu
VM and recording the trace with 'perf record -g -a'.

The trace without the patch:

+  34.19%  [kernel.kallsyms]  [k] queued_spin_lock_slowpath
+  30.77%  [kernel.kallsyms]  [k] _raw_spin_lock
+   3.53%  [kernel.kallsyms]  [k] list_lru_count_one
+   2.26%  [kernel.kallsyms]  [k] super_cache_count
+   1.68%  [kernel.kallsyms]  [k] shrink_slab
+   0.59%  [kernel.kallsyms]  [k] down_read_trylock
+   0.48%  [kernel.kallsyms]  [k] _raw_spin_unlock_irqrestore
+   0.38%  [kernel.kallsyms]  [k] shrink_node_memcg
+   0.32%  [kernel.kallsyms]  [k] queue_work_on
+   0.26%  [kernel.kallsyms]  [k] count_shadow_nodes

With the patch:

+   0.16%     swapper  [kernel.kallsyms]    [k] default_idle
+   0.13%     oom_reaper  [kernel.kallsyms]    [k] mutex_spin_on_owner
+   0.05%     perf  [kernel.kallsyms]    [k] copy_user_generic_string
+   0.05%     init.real  [kernel.kallsyms]    [k] wait_consider_task
+   0.05%     kworker/0:0  [kernel.kallsyms]    [k] finish_task_switch
+   0.04%     kworker/2:1  [kernel.kallsyms]    [k] finish_task_switch
+   0.04%     kworker/3:1  [kernel.kallsyms]    [k] finish_task_switch
+   0.04%     kworker/1:0  [kernel.kallsyms]    [k] finish_task_switch
+   0.03%     binary  [kernel.kallsyms]    [k] copy_page

Kirill, can you resend your patch with this info or do you want me
send the rebased patch?

Powered by blists - more mailing lists