From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH net-next v2] unix: add read side socket memory accounting for dgram sockets Date: Wed, 19 Feb 2014 14:49:27 -0500 (EST) Message-ID: <20140219.144927.1558282069067885839.davem@davemloft.net> References: <20140217035826.GG8634@order.stressinduktion.org> <20140217130353.GA22833@order.stressinduktion.org> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, yannick@koehler.name, eric.dumazet@gmail.com, xiyou.wangcong@gmail.com, dan@mindstab.net To: hannes@stressinduktion.org Return-path: Received: from shards.monkeyblade.net ([149.20.54.216]:46388 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754034AbaBST6L (ORCPT ); Wed, 19 Feb 2014 14:58:11 -0500 In-Reply-To: <20140217130353.GA22833@order.stressinduktion.org> Sender: netdev-owner@vger.kernel.org List-ID: From: Hannes Frederic Sowa Date: Mon, 17 Feb 2014 14:03:53 +0100 > We still allocate dgram packets with sock_alloc_send_pskb, which now > does normally not block if the socket has too many packets in flight. It seems like it does to me, it does sock_wait_for_wmem(), right? Or are you trying to say that usually this is not the point at which we block, but rather it's when we check the peer's receive queue?