From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Subject: Re: Missing log entries and other questions References: <036a01d19f62$717af530$5470df90$@cox.net> <20160427203823.GB25397@kernel.dk> <572A02B9.1040902@kernel.dk> <572A24AC.5090106@kernel.dk> <572A60D1.3050700@kernel.dk> <572A69F7.4010102@kernel.dk> <572CD03F.6060507@kernel.dk> From: Jens Axboe Message-ID: <572CD1EF.9000005@kernel.dk> Date: Fri, 6 May 2016 11:18:39 -0600 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit To: Mark Nelson , Paul Alcorn Cc: 'Mihkal Dunfjeld' , fio@vger.kernel.org, birger.lunstoeng@stud.ntnu.no List-ID: On 05/06/2016 11:16 AM, Mark Nelson wrote: > On 05/06/2016 12:11 PM, Jens Axboe wrote: >> On 05/05/2016 01:33 PM, Mark Nelson wrote: >>>>>>> Can you try the below patch? >>>>>> >>>>>> I'll also try to take a look at this as we've seen a fair amount of >>>>>> skew >>>>>> in the logs doing fio librbd upstream ceph testing. >>>>> >>>>> That'd be great. More complete version below, fwiw. >>> >>> Ok, I'll try this one. It might be a bit before I can test it since I'm >>> bisecting ceph right now looking for a regression that only hits 128k >>> sequential rbd reads. Go figure. :) >> >> When you get to it, here's an updated version. I'm tempted to shove this >> into a new branch, instead of flinging diffs around... Let me know what >> you prefer. > > new branch would be wonderful! Done, it's now in the 'logging' branch: http://git.kernel.dk/cgit/fio/commit/?h=logging&id=a47591e4923fb8faef18e1cd5125a50429282089 -- Jens Axboe