From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hans Westgaard Ry Subject: Re: [PATCH v2] net:Add sysctl_tcp_sg_max_skb_frags Date: Mon, 1 Feb 2016 14:12:36 +0100 Message-ID: <56AF59C4.1000807@oracle.com> References: <568F87AC.60405@oracle.com> <1453900829-3384-1-git-send-email-hans.westgaard.ry@oracle.com> <1453907702.20722.6.camel@edumazet-glaptop2.roam.corp.google.com> <56A9087C.20305@stressinduktion.org> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: "David S. Miller" , Alexey Kuznetsov , James Morris , Hideaki YOSHIFUJI , Patrick McHardy , "open list:NETWORKING [GENERAL]" , open list , Haakon Bugge To: Hannes Frederic Sowa , Eric Dumazet Return-path: In-Reply-To: <56A9087C.20305@stressinduktion.org> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On 01/27/2016 07:12 PM, Hannes Frederic Sowa wrote: > On 27.01.2016 16:15, Eric Dumazet wrote: >> >> If it is a common one, it should be /proc/sys/net/core/... instead >> of /proc/sys/net/ipv4/tcp_.... > > >> Other providers include : >> >> 1) GRO stack >> 2) callers of sock_alloc_send_pskb(), alloc_skb_with_frags(), >> sock_alloc_send_skb() .. > > I agree, this knob should get a generic name and live in a generic > net/ directory to control this globally, so things don't break during > forwarding etc. > > It does not solve the problem completely, e.g. when VMs send gso > packets through a vhost-net onto IPoIB, no? > > Thanks, > Hannes > I have understood more of the problem Hannes raises and I realize that we need a slowpath in IPoIB to handle the problem in question. I will make a new version of this patch with a more correct position/name of the sysctl-variable. I'll also make a separate patch adding the slowpath i IPoIB. Hans