[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <4F2B53F1.6080405@redhat.com>
Date: Fri, 03 Feb 2012 11:26:41 +0800
From: Jason Wang <jasowang@...hat.com>
To: Jason Wang <jasowang@...hat.com>
CC: netdev@...r.kernel.org, davem@...emloft.net,
linux-kernel@...r.kernel.org, glommer@...allels.com, mst@...hat.com
Subject: Re: [v3.3-rc2+ PATCH] tcp: properly initialize tcp memory limits
On 02/02/2012 06:07 PM, Jason Wang wrote:
> Commit 4acb4190 tries to fix the using uninitialized value
> introduced by commit 3dc43e3, but it would make the
> per-socket memory limits too small.
>
> This patch fixes this and also remove the redundant codes
> introduced in 4acb4190.
>
> Signed-off-by: Jason Wang<jasowang@...hat.com>
> ---
Just FYI, this fix the tcp performance regression, I test the virtio-net
tcp performance:
without this patch:
[root@...-6168-8-1 net-next]# netperf -H 192.168.100.4 -t TCP_MAERTS
TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.100.4
(192.168.100.4) port 0 AF_INET
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.00 5997.95
with this patch:
[root@...-6168-8-1 net-next]# netperf -H 192.168.100.4 -t TCP_MAERTS
TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.100.4
(192.168.100.4) port 0 AF_INET
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.00 9670.98
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists