netdev - Re: [net] 4890b686f4: netperf.Throughput

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, 27 Jun 2022 09:48:01 -0700
From:   Shakeel Butt <shakeelb@...gle.com>
To:     Eric Dumazet <edumazet@...gle.com>
Cc:     Feng Tang <feng.tang@...el.com>, Linux MM <linux-mm@...ck.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Roman Gushchin <roman.gushchin@...ux.dev>,
        Michal Hocko <mhocko@...nel.org>,
        Johannes Weiner <hannes@...xchg.org>,
        Muchun Song <songmuchun@...edance.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Xin Long <lucien.xin@...il.com>,
        Marcelo Ricardo Leitner <marcelo.leitner@...il.com>,
        kernel test robot <oliver.sang@...el.com>,
        Soheil Hassas Yeganeh <soheil@...gle.com>,
        LKML <linux-kernel@...r.kernel.org>,
        network dev <netdev@...r.kernel.org>,
        linux-s390@...r.kernel.org, MPTCP Upstream <mptcp@...ts.linux.dev>,
        "linux-sctp @ vger . kernel . org" <linux-sctp@...r.kernel.org>,
        lkp@...ts.01.org, kbuild test robot <lkp@...el.com>,
        Huang Ying <ying.huang@...el.com>,
        Xing Zhengjun <zhengjun.xing@...ux.intel.com>,
        Yin Fengwei <fengwei.yin@...el.com>, Ying Xu <yinxu@...hat.com>
Subject: Re: [net] 4890b686f4: netperf.Throughput_Mbps -69.4% regression

On Mon, Jun 27, 2022 at 9:26 AM Eric Dumazet <edumazet@...gle.com> wrote:
>
[...]
> >
>
> I simply did the following and got much better results.
>
> But I am not sure if updates to ->usage are really needed that often...

I suspect we need to improve the per-cpu memcg stock usage here. Were
the updates mostly from uncharge path or charge path or that's
irrelevant?

I think doing full drain (i.e. drain_stock()) within __refill_stock()
when the local cache is larger than MEMCG_CHARGE_BATCH is not best.
Rather we should always keep at least MEMCG_CHARGE_BATCH for such
scenarios.

>
>
> diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
> index 679591301994d316062f92b275efa2459a8349c9..e267be4ba849760117d9fd041e22c2a44658ab36
> 100644
> --- a/include/linux/page_counter.h
> +++ b/include/linux/page_counter.h
> @@ -3,12 +3,15 @@
>  #define _LINUX_PAGE_COUNTER_H
>
>  #include <linux/atomic.h>
> +#include <linux/cache.h>
>  #include <linux/kernel.h>
>  #include <asm/page.h>
>
>  struct page_counter {
> -       atomic_long_t usage;
> -       unsigned long min;
> +       /* contended cache line. */
> +       atomic_long_t usage ____cacheline_aligned_in_smp;
> +
> +       unsigned long min ____cacheline_aligned_in_smp;

Do we need to align 'min' too?

>         unsigned long low;
>         unsigned long high;
>         unsigned long max;
> @@ -27,12 +30,6 @@ struct page_counter {
>         unsigned long watermark;
>         unsigned long failcnt;
>
> -       /*
> -        * 'parent' is placed here to be far from 'usage' to reduce
> -        * cache false sharing, as 'usage' is written mostly while
> -        * parent is frequently read for cgroup's hierarchical
> -        * counting nature.
> -        */
>         struct page_counter *parent;
>  };
>
>
>