netdev - Re: r8169: jumbo frames

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] [day] [month] [year] [list]

Message-ID: <20070903205756.GA4444@electric-eye.fr.zoreil.com>
Date:	Mon, 3 Sep 2007 22:57:56 +0200
From:	Francois Romieu <romieu@...zoreil.com>
To:	Shane <shane@....ca>
Cc:	netdev@...r.kernel.org
Subject: Re: r8169: jumbo frames

Shane <shane@....ca> :
[...]
> Just wanted to report that when setting a mtu of 4074, I'm
> getting slow Samba performance with an r8169 based NIC even
> with the fix for this posted here applied.  all dmesg shows
> is:
> NETDEV WATCHDOG: eth0: transmit timed out

It is a bit terse:
- which kernel ?
- which fix exactly (Message-Id or URL) ? The one I sent the
  29 of 08/2007 or something else ?
- which chipset (lspci -vvx) ?

Fwiw, I have rediffed the patchkit against 2.6.23-rc5. See:
http://www.fr.zoreil.com/people/francois/misc/20070903-2.6.23-rc5-r8169-test.patch
or:
http://www.fr.zoreil.com/linux/kernel/2.6.x/2.6.23-rc5/r8169-20070903/

If you have not done so already, I would appreciate that you try
to reproduce the problem with a 1500 bytes MTU with/without the
aforementioned patch.

> The mtu value is due to Windows workstations which support
> this value and 9k MTU but the r8169 doesn't appear to like
> 9k although that's where I'd like it to be on this network.

The 8169 will not fly above 7200, be it on Linux or Windows. :o/

-- 
Ueimor
-
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