linux-kernel - Re: [PATCH] mm: Make count list_lru_one::nr

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:   Fri, 29 Sep 2017 11:15:04 +0300
From:   Kirill Tkhai <ktkhai@...tuozzo.com>
To:     Andrew Morton <akpm@...ux-foundation.org>
Cc:     vdavydov.dev@...il.com, apolyakov@...et.ru,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        aryabinin@...tuozzo.com
Subject: Re: [PATCH] mm: Make count list_lru_one::nr_items lockless

On 29.09.2017 00:02, Andrew Morton wrote:
> On Thu, 28 Sep 2017 10:48:55 +0300 Kirill Tkhai <ktkhai@...tuozzo.com> 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.

Kirill