From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-dm3nam03on0072.outbound.protection.outlook.com ([104.47.41.72]:40984 "EHLO NAM03-DM3-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752061AbdBOW2N (ORCPT ); Wed, 15 Feb 2017 17:28:13 -0500 From: Todd Lawall Subject: Has anyone run into write_bw_log and write_io_log recording segments of low numbers? Date: Wed, 15 Feb 2017 22:28:09 +0000 Message-ID: Content-Language: en-US Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Sender: fio-owner@vger.kernel.org List-Id: fio@vger.kernel.org To: "fio@vger.kernel.org" I've been running fio on an iSCSI volume where I can monitor things like th= e network traffic (to ensure that indeed it is flowing) as well as on the m= achine the volume is hosted on. I'm seeing a steady state of 300MB/s, but = when I stop the FIO process and writes the detailed bandwidth and iops logs= , there's segments where iops drop to 0, but bandwidth for the same time po= int is somewhere around the single digits or teens. =20 Has anyone else seen this behavior? Does anyone have an idea why I might b= e seeing this? Here is the job file I ran: [global] ioengine=3Dwindowsaio do_verify=3D0 offset=3D0 write_bw_log=3DC:\\haggis\\manualfio\\stats-running write_iops_log=3DC:\\haggis\\manualfio\\stats-running write_lat_log=3DC:\\haggis\\manualfio\\stats-running verify=3Dcrc32c-intel runtime=3D292000 thread [fio-0] filename=3D\\.\PhysicalDrive1 iodepth=3D1 blocksize=3D256k readwrite=3Dwrite [fio-1] = = =20 filename=3D\\.\PhysicalDrive2 = = =20 iodepth=3D1 = = =20 blocksize=3D256k = = =20 readwrite=3Dwrite =