netdev - Re: TCPBacklogDrops during aggressive bursts of traffic

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, 18 May 2012 16:45:51 +0100
From:	Kieran Mansley <kmansley@...arflare.com>
To:	Eric Dumazet <eric.dumazet@...il.com>
CC:	Ben Hutchings <bhutchings@...arflare.com>, <netdev@...r.kernel.org>
Subject: Re: TCPBacklogDrops during aggressive bursts of traffic

On Thu, 2012-05-17 at 18:37 +0200, Eric Dumazet wrote:
> 
> Hmm, I was not suggesting running production servers with this
> setting, only do an experiment.

OK.  I've found a more reliable way to reproduce it (use MSG_WAITALL to
make the recv call wait till the socket buffer will be more full) and
tried with the tcp_adv_win_scale to -2.  It's hard to make any confident
assertions about the impact of it, but if it does change the behaviour
it is a small change.  There are certainly still plenty of drops with
that setting.

> With net-next and tcp coalescing, I no longer have TCPBacklogDrops /
> collapses, but I dont have sfc card/driver. 

I'll try that.

Kieran

--
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