linux-kernel - Re: [PATCH] net/sock: move memory_allocated over to percpu

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]

Message-ID: <CAOesGMgRrb4D2S_qWwgo00iNxbCL9EEGfhD5Ji-2HMWuZeq0Yw@mail.gmail.com>
Date:   Thu, 6 Sep 2018 23:20:15 -0700
From:   Olof Johansson <olof@...om.net>
To:     Herbert Xu <herbert@...dor.apana.org.au>
Cc:     Eric Dumazet <edumazet@...gle.com>,
        David Miller <davem@...emloft.net>,
        Neil Horman <nhorman@...driver.com>,
        Marcelo Ricardo Leitner <marcelo.leitner@...il.com>,
        Vladislav Yasevich <vyasevich@...il.com>,
        Alexey Kuznetsov <kuznet@....inr.ac.ru>,
        Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>,
        linux-crypto@...r.kernel.org, LKML <linux-kernel@...r.kernel.org>,
        linux-sctp@...r.kernel.org, netdev <netdev@...r.kernel.org>,
        linux-decnet-user@...ts.sourceforge.net,
        kernel-team <kernel-team@...com>
Subject: Re: [PATCH] net/sock: move memory_allocated over to percpu_counter variables

Hi,

On Thu, Sep 6, 2018 at 8:32 PM, Herbert Xu <herbert@...dor.apana.org.au> wrote:
> On Thu, Sep 06, 2018 at 12:33:58PM -0700, Eric Dumazet wrote:
>> On Thu, Sep 6, 2018 at 12:21 PM Olof Johansson <olof@...om.net> wrote:
>> >
>> > Today these are all global shared variables per protocol, and in
>> > particular tcp_memory_allocated can get hot on a system with
>> > large number of CPUs and a substantial number of connections.
>> >
>> > Moving it over to a per-cpu variable makes it significantly cheaper,
>> > and the added overhead when summing up the percpu copies is still smaller
>> > than the cost of having a hot cacheline bouncing around.
>>
>> I am curious. We never noticed contention on this variable, at least for TCP.
>
> Yes these variables are heavily amortised so I'm surprised that
> they would cause much contention.
>
>> Please share some numbers with us.
>
> Indeed.

Certainly, just had to collect them again.

This is on a dual xeon box, with ~150-200k TCP connections. I see
about .7% CPU spent in __sk_mem_{reduce,raise}_allocated in the
inlined atomic ops, most of those in reduce.

Call path for reduce is practically all from tcp_write_timer on softirq:

                __sk_mem_reduce_allocated
                tcp_write_timer
                call_timer_fn
                run_timer_softirq
                __do_softirq
                irq_exit
                smp_apic_timer_interrupt
                apic_timer_interrupt
                cpuidle_enter_state

With this patch, I see about .18+.11+.07 = .36% in percpu-related
functions called from the same __sk_mem functions.

Now, that's a halving of cycles samples on that specific setup. The
real difference though, is on another platform where atomics are more
expensive. There, this makes a significant difference. Unfortunately,
I can't share specifics but I think this change stands on its own on
the dual xeon setup as well, maybe with slightly less strong wording
on just how hot the variable/line happens to be.


-Olof