netdev - Re: UDP regression with packets rates

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:	Thu, 10 Sep 2009 17:39:17 -0400 (EDT)
From:	Christoph Lameter <cl@...ux-foundation.org>
To:	Eric Dumazet <eric.dumazet@...il.com>
cc:	netdev@...r.kernel.org
Subject: Re: UDP regression with packets rates < 10k per sec

On Thu, 10 Sep 2009, Eric Dumazet wrote:

> 22:28:11.223581 IP 55.225.18.7.9002 > 55.225.18.5.9002: UDP, length 32
> 22:28:11.223678 IP 55.225.18.5.9002 > 55.225.18.7.9002: UDP, length 32
>
> See how the answer is *very* slow ? Something like > 100 us ?

If you run tcpdump then you create some overhead I guess. 100 usec should
show up as latencies > 50usec in the report.

The latency request includes the timestamp from the source. So the
destination can take another timestamp at receive time. The sending back
of the reply to the timestamp request is not critical at all. The receiver
will just register the time differential established by the sender.

--
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