From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Ahern Subject: Re: [patch iproute2] tc: add -bs option for batch mode Date: Wed, 20 Dec 2017 17:13:45 -0700 Message-ID: <106c1e7d-14fc-f375-ae0b-6b5eed63cd6d@gmail.com> References: <20171219063346.19300-1-chrism@mellanox.com> <20171219072231.055bcc9d@xeon-e3> <20171220071744.25f9dd41@xeon-e3> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Cc: "netdev@vger.kernel.org" , "gerlitz.or@gmail.com" To: Stephen Hemminger , Chris Mi Return-path: Received: from mail-pl0-f65.google.com ([209.85.160.65]:42232 "EHLO mail-pl0-f65.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756529AbdLUANs (ORCPT ); Wed, 20 Dec 2017 19:13:48 -0500 Received: by mail-pl0-f65.google.com with SMTP id bd8so9969275plb.9 for ; Wed, 20 Dec 2017 16:13:48 -0800 (PST) In-Reply-To: <20171220071744.25f9dd41@xeon-e3> Content-Language: en-US Sender: netdev-owner@vger.kernel.org List-ID: On 12/20/17 8:17 AM, Stephen Hemminger wrote: > On Wed, 20 Dec 2017 09:23:34 +0000 > Chris Mi wrote: > >>> Your real performance win is just not asking for ACK for every rule. >> No. Even if batch_size > 1, we ack every rule. The real performance win is >> to send multiple rules in one system call. If we are not asking for ACK for every rule, >> the performance will be improved further. > > Try the no ACK method. > > When we were optimizing routing daemons like Quagga, it was discovered > that an ACK for every route insert was the main bottleneck. Doing asynchronous > error handling got a bigger win than your batching. > > Please try that, doing multiple messages using iov is not necessary. > FWIW, I plan to look at batching routes in a similar fashion.