netdev - Re: [PATCH] tcp: SO_TIMESTAMP implementation for TCP

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, 30 Apr 2010 22:40:38 -0700
From:	Tom Herbert <therbert@...gle.com>
To:	Bill Fink <billfink@...dspring.com>
Cc:	David Miller <davem@...emloft.net>, netdev@...r.kernel.org
Subject: Re: [PATCH] tcp: SO_TIMESTAMP implementation for TCP

> Not being a kernel hacker, I will naively ask if the kernel tracing
> facility could somehow be used to provide the desired info (or could
> be modified to provide it).
>

We did consider kernel tracing (more in the context of implementing
RFC 4898).  In the case of trying get per packet timestamps,
correlating a ktrace event with an application message is probably too
high to make it practical.  If it weren't for the cost of
timestamp'ing every single skb being received, we'd probably have
SO_TIMESTAMP turned on permanently for many connections.  For now
we're settling for a percentage of messages for sampling.

Tom
--
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