From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH] NET_DMA: free skbs periodically Date: Thu, 18 Mar 2010 20:36:44 -0700 (PDT) Message-ID: <20100318.203644.102533317.davem@davemloft.net> References: <1268752964-4397-1-git-send-email-steve@digidescorp.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, kuznet@ms2.inr.ac.ru, pekkas@netcore.fi, jmorris@namei.org, yoshfuji@linux-ipv6.org, kaber@trash.net, linux-kernel@vger.kernel.org To: steve@digidescorp.com Return-path: In-Reply-To: <1268752964-4397-1-git-send-email-steve@digidescorp.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org From: "Steven J. Magnani" Date: Tue, 16 Mar 2010 10:22:44 -0500 > Under NET_DMA, data transfer can grind to a halt when userland issues a > large read on a socket with a high RCVLOWAT (i.e., 512 KB for both). > This appears to be because the NET_DMA design queues up lots of memcpy > operations, but doesn't issue or wait for them (and thus free the > associated skbs) until it is time for tcp_recvmesg() to return. > The socket hangs when its TCP window goes to zero before enough data is > available to satisfy the read. > > Periodically issue asynchronous memcpy operations, and free skbs for ones > that have completed, to prevent sockets from going into zero-window mode. > > Signed-off-by: Steven J. Magnani Can one of the NET DMA folks review this. It's a pretty fundamental problem with how this stuff works it seems.