netdev - Re: [PATCH net-next] mlx4: do not fire tasklet unless necessary

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 for Android: free password hash cracker in your pocket

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

Date:   Wed, 15 Feb 2017 06:34:14 -0800
From:   Eric Dumazet <eric.dumazet@...il.com>
To:     Saeed Mahameed <saeedm@....mellanox.co.il>
Cc:     David Miller <davem@...emloft.net>,
        netdev <netdev@...r.kernel.org>,
        Tariq Toukan <tariqt@...lanox.com>,
        Saeed Mahameed <saeedm@...lanox.com>,
        Matan Barak <matanb@...lanox.com>, jackm@...lanox.com
Subject: Re: [PATCH net-next] mlx4: do not fire tasklet unless necessary

On Wed, 2017-02-15 at 15:59 +0200, Saeed Mahameed wrote:

> can the tasklet run on a different core ?

No. tasklets are scheduled on local cpu, like softirqs in general.

They are not migrated, unless cpu is removed (hotplug)


> 
> the point is that if the EQ is full of CQEs from different CQs you would
> do the "  kick = list_empty(&tasklet_ctx->list);" test per empty CQ
> list rather than once at the end.
> 
> in mlx4_en case, you have only two CQs on each EQ but in RoCE/IB you
> can have as many CQs as you want.

list_empty() before one list_add_tail() is a single instruction.

By doing this right before manipulating the list, it comes with a zero
cache line penalty.

While if you do it at the wrong place, it incurs one extra cache line
miss.

This extra tasklet invocations can cost 3 % of cpu cycles.