From mboxrd@z Thu Jan 1 00:00:00 1970 From: Or Gerlitz Subject: Re: [PATCH net-next 2/2] net/mlx4: Revert "mlx4: set maximal number of default RSS queues" Date: Thu, 2 Jan 2014 11:35:23 +0200 Message-ID: <52C532DB.9000200@mellanox.com> References: <1388581537-4810-1-git-send-email-amirv@mellanox.com> <1388581537-4810-3-git-send-email-amirv@mellanox.com> <979A8436335E3744ADCD3A9F2A2B68A52AF21A1A@SJEXCHMB10.corp.ad.broadcom.com> <979A8436335E3744ADCD3A9F2A2B68A52AF21C13@SJEXCHMB10.corp.ad.broadcom.com> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1"; format=flowed Content-Transfer-Encoding: 7bit Cc: Amir Vadai , "David S. Miller" , "netdev@vger.kernel.org" , Eugenia Emantayev , Ido Shamay To: Yuval Mintz , Or Gerlitz Return-path: Received: from eu1sys200aog120.obsmtp.com ([207.126.144.149]:35468 "EHLO eu1sys200aog120.obsmtp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750707AbaABJlR (ORCPT ); Thu, 2 Jan 2014 04:41:17 -0500 In-Reply-To: <979A8436335E3744ADCD3A9F2A2B68A52AF21C13@SJEXCHMB10.corp.ad.broadcom.com> Sender: netdev-owner@vger.kernel.org List-ID: On 02/01/2014 08:04, Yuval Mintz wrote: >>> [...] If you believe this is a better default (or some relaxation will be, e.g., 16 >> instead of 8), why not set it as default for ALL multi-queue networking >> drivers? >> >> Going back to your original commit 16917b87a "net-next: Add >> netif_get_num_default_rss_queues" I am still not clear why we want >> >> 1. why we want a common default to all MQ devices? > Although networking benefits from multiple Interrupt vectors > (enabling more rings, better performance, etc.), bounding this > number only to the number of cpus is unreasonable as it strains > system resources; e.g., consider a 40-cpu server - we might wish > to have 40 vectors per device, but that means that connecting > several devices to the same server might cause other functions > to fail probe as they will no longer be able to acquire interrupt > vectors of their own. Modern servers which have tens of CPUs typically have thousands of MSI-X vectors which means you should be easily able to plug four cards into a server with 64 cores which will consume 256 out of the 1-4K vectors out there. Anyway, let me continue your approach - how about raising the default hard limit to 16 or having it as the number of cores @ the numa node where the card is plugged? Or. > > Since networking has an API allowing the user to manually set the > number of channels, the default is upper-bounded. > >> 2. why this default has to be hard coded and not derived e.g from the >> number of cores or alike attribute of the system? > This is not entirely correct; The default number is derived from > the number of online cpus - it's only upper bounded by some > hard-coded value. > > Cheers, > Yuval