netdev - Re: [PATCH] net: reduce number of reference taken on sk

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: <20090509.133454.111098477.davem@davemloft.net>
Date:	Sat, 09 May 2009 13:34:54 -0700 (PDT)
From:	David Miller <davem@...emloft.net>
To:	dada1@...mosbay.com
Cc:	khc@...waw.pl, netdev@...r.kernel.org
Subject: Re: [PATCH] net: reduce number of reference taken on sk_refcnt

From: Eric Dumazet <dada1@...mosbay.com>
Date: Sat, 09 May 2009 14:13:59 +0200

> BTW, oprofile for this kind of workload gives a surprising result.
> (timer stuff being *very* expensive)
> CPU doing the NAPI stuff has this profile :
> 
> 88688    88688          9.7805   9.7805    lock_timer_base
> 72692    161380         8.0165  17.7970    bnx2_poll_work
> 66958    228338         7.3842  25.1812    mod_timer
> 47980    276318         5.2913  30.4724    __wake_up
> 43312    319630         4.7765  35.2489    task_rq_lock

To me this seems to indicate that timers keep getting scheduled on
different cpus.

Probably it would be helped by google's packet-processing-locality
patches, or some variant thereof.

Consider the case where we always send some message on CPU A and
then process the ACK on CPU B.  We'll always be cancelling the
timer on a foreign cpu.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html