From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bart Van Assche Subject: Re: LIO: FILEIO vs IBLOCK read performance Date: Wed, 1 Feb 2017 19:55:21 +0000 Message-ID: <1485978900.2560.9.camel@sandisk.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Return-path: Received: from mail-sn1nam01on0057.outbound.protection.outlook.com ([104.47.32.57]:44384 "EHLO NAM01-SN1-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751548AbdBATzb (ORCPT ); Wed, 1 Feb 2017 14:55:31 -0500 In-Reply-To: Content-Language: en-US Content-ID: <5D836F2684033E49A96EAD154D6C8DB3@sandisk.com> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: "linux-scsi@vger.kernel.org" , "nefelim4ag@gmail.com" On Wed, 2017-02-01 at 11:18 +0300, Timofey Titovets wrote: > so, short results (random read on /dev/sdb on client): > block + /dev/sdb ~ 500 iops (emulate_write_cache=3D0) > fileio + /dev/sdb ~ 90 iops (emulate_write_cache=3D0) > fileio + /dev/sdb ~ 90 iops (emulate_write_cache=3D1) > fileio + /storage/LUN/1 ~90 iops (emulate_write_cache=3D0) > fileio + /storage/LUN/1 ~90 iops (emulate_write_cache=3D1) > block + /dev/loop0 ~ 90 iops loop directio=3D0 > block + /dev/loop0 ~ 500 iops loop directio=3D0 The address of the LIO mailing list is target-devel@vger.kernel.org instead of linux-scsi@vger.kernel.org. Anyway, have you tried to disable readahead on /dev/sdb (blockdev --setra / --setfra)? Readahead can have a significant negative impact on random I/O. There is a heuristic in the kernel for automatically disabling readahead for random I/O but maybe that algorithm did not recognize your workload properly. Bart.=