netdev - Re: [RFC 1/3] tcp: randomize tcp timestamp offsets for each connection

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: <1472141147.14381.136.camel@edumazet-glaptop3.roam.corp.google.com>
Date:   Thu, 25 Aug 2016 09:05:47 -0700
From:   Eric Dumazet <eric.dumazet@...il.com>
To:     Florian Westphal <fw@...len.de>
Cc:     netdev@...r.kernel.org
Subject: Re: [RFC 1/3] tcp: randomize tcp timestamp offsets for each
 connection

On Thu, 2016-08-25 at 16:49 +0200, Florian Westphal wrote:
> Eric Dumazet <eric.dumazet@...il.com> wrote:
> > Here at Google we have been using usec resolution in TCP timestamps for
> > a while for all our DC traffic, and we have to upstream this at some
> > point.
> > 
> > It would be nice if the randomization was optional, because having usec
> > timestamps with a common base (ie no per flow random base) helps a lot
> > to understand the host delays at transmit time, and receive time.
> 
> Would it help to make it per-host instead of per-flow?

Not really.

By looking at tcpdump, and TS val of xmit packets of multiple flows, we
can deduct the relative qdisc delays (think of fq pacing).
This should work even if we have one flow per remote peer.

> 
> > I will review your patch more in depth today, thanks.
> 
> Great, thanks a lot!