From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Ahern Subject: Re: [patch net-next v4 0/4] return offloaded stats as default and expose original sw stats Date: Fri, 17 Jun 2016 09:35:53 -0600 Message-ID: <9f8e85ac-3e96-257e-cf7f-e7e793d41cf4@cumulusnetworks.com> References: <1466066237-7719-1-git-send-email-jiri@resnulli.us> <20160616.172632.1759391103978744570.davem@davemloft.net> <20160617082411.GA1981@nanopsycho.orion> <20160617140512.GB1981@nanopsycho.orion> <57640F2A.7090003@mojatatu.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Cc: David Miller , netdev@vger.kernel.org, nogahf@mellanox.com, idosch@mellanox.com, eladr@mellanox.com, yotamg@mellanox.com, ogerlitz@mellanox.com, roopa@cumulusnetworks.com, nikolay@cumulusnetworks.com, linville@tuxdriver.com, tgraf@suug.ch, gospo@cumulusnetworks.com, sfeldma@gmail.com, sd@queasysnail.net, eranbe@mellanox.com, ast@plumgrid.com, edumazet@google.com, hannes@stressinduktion.org, f.fainelli@gmail.com To: Jamal Hadi Salim , Jiri Pirko Return-path: Received: from mail-pa0-f45.google.com ([209.85.220.45]:33344 "EHLO mail-pa0-f45.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753305AbcFQPgD (ORCPT ); Fri, 17 Jun 2016 11:36:03 -0400 Received: by mail-pa0-f45.google.com with SMTP id b13so29557609pat.0 for ; Fri, 17 Jun 2016 08:36:02 -0700 (PDT) In-Reply-To: <57640F2A.7090003@mojatatu.com> Sender: netdev-owner@vger.kernel.org List-ID: On 6/17/16 8:54 AM, Jamal Hadi Salim wrote: > On 16-06-17 10:05 AM, Jiri Pirko wrote: >> Fri, Jun 17, 2016 at 03:48:35PM CEST, dsa@cumulusnetworks.com wrote: >>> On 6/17/16 2:24 AM, Jiri Pirko wrote: >>>> > >> >> That is problematic. Existing apps depend on rtnetlink stats. But if we >> don't count offloaded forwarded packets, the apps don't see anything. >> Therefore I believe that this patchset approach is better. The existing >> apps continue to work and future apps can use newly introduces sw_stats >> to query slowpath traffic. Makes sense to me. >> > > I agree with Jiri. It is a bad idea to depend on ethtool for any of > this stuff. Is there a way we can tag netlink stats instead > to indicate they are hardware or software? Right, old API but the key here is that low level h/w stats are returned by a different API. By default ip, ifconfig, snmpd, etc all continue to get traditional S/W stats - counters as seen by the CPU.