From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:36435 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752679AbcKPQX0 (ORCPT ); Wed, 16 Nov 2016 11:23:26 -0500 Received: from pps.filterd (m0098413.ppops.net [127.0.0.1]) by mx0b-001b2d01.pphosted.com (8.16.0.17/8.16.0.17) with SMTP id uAGGIgLZ084014 for ; Wed, 16 Nov 2016 11:23:25 -0500 Received: from e24smtp05.br.ibm.com (e24smtp05.br.ibm.com [32.104.18.26]) by mx0b-001b2d01.pphosted.com with ESMTP id 26rq3fw13h-1 (version=TLSv1.2 cipher=AES256-SHA bits=256 verify=NOT) for ; Wed, 16 Nov 2016 11:23:24 -0500 Received: from localhost by e24smtp05.br.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Wed, 16 Nov 2016 14:23:23 -0200 From: Gabriel Krisman Bertazi To: Bart Van Assche Cc: , , Brian King , Douglas Miller , Subject: Re: [PATCH 2/2] blk-mq: Avoid memory reclaim when remapping queues References: <1479151478-19725-1-git-send-email-krisman@linux.vnet.ibm.com> <1479151478-19725-2-git-send-email-krisman@linux.vnet.ibm.com> <39a42839-b877-21b7-aa85-314cf499e234@sandisk.com> Date: Wed, 16 Nov 2016 14:23:18 -0200 In-Reply-To: <39a42839-b877-21b7-aa85-314cf499e234@sandisk.com> (Bart Van Assche's message of "Tue, 15 Nov 2016 14:51:30 -0800") MIME-Version: 1.0 Content-Type: text/plain Message-Id: <8737irmm15.fsf@linux.vnet.ibm.com> Sender: linux-block-owner@vger.kernel.org List-Id: linux-block@vger.kernel.org Bart Van Assche writes: > I don't think that GFP_NOWAIT is acceptable in this context. Have you > tried GFP_NOIO instead of GFP_NOWAIT? At first I used GFP_NOIO, but after reviewing gfp.h I convinced myself GFP_NOWAIT was what I wanted because I was concerned about FS accesses that aren't restricted in GFP_NOIO. For some reason, I assumed this was an issue. I'm ok with the change and can submit a v2 shortly, after more tests. in fact, this will make the change more compliant with the rest of block layer critical allocations that use GFP_NOIO. Thanks, -- Gabriel Krisman Bertazi From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gabriel Krisman Bertazi Subject: Re: [PATCH 2/2] blk-mq: Avoid memory reclaim when remapping queues Date: Wed, 16 Nov 2016 14:23:18 -0200 Message-ID: <8737irmm15.fsf@linux.vnet.ibm.com> References: <1479151478-19725-1-git-send-email-krisman@linux.vnet.ibm.com> <1479151478-19725-2-git-send-email-krisman@linux.vnet.ibm.com> <39a42839-b877-21b7-aa85-314cf499e234@sandisk.com> Mime-Version: 1.0 Content-Type: text/plain Return-path: Received: from mx0a-001b2d01.pphosted.com ([148.163.156.1]:41729 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753033AbcKPQX0 (ORCPT ); Wed, 16 Nov 2016 11:23:26 -0500 Received: from pps.filterd (m0098404.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.16.0.17/8.16.0.17) with SMTP id uAGGIhVh006819 for ; Wed, 16 Nov 2016 11:23:25 -0500 Received: from e24smtp05.br.ibm.com (e24smtp05.br.ibm.com [32.104.18.26]) by mx0a-001b2d01.pphosted.com with ESMTP id 26rnseg8br-1 (version=TLSv1.2 cipher=AES256-SHA bits=256 verify=NOT) for ; Wed, 16 Nov 2016 11:23:25 -0500 Received: from localhost by e24smtp05.br.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Wed, 16 Nov 2016 14:23:23 -0200 In-Reply-To: <39a42839-b877-21b7-aa85-314cf499e234@sandisk.com> (Bart Van Assche's message of "Tue, 15 Nov 2016 14:51:30 -0800") Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Bart Van Assche Cc: axboe@fb.com, linux-block@vger.kernel.org, Brian King , Douglas Miller , linux-scsi@vger.kernel.org Bart Van Assche writes: > I don't think that GFP_NOWAIT is acceptable in this context. Have you > tried GFP_NOIO instead of GFP_NOWAIT? At first I used GFP_NOIO, but after reviewing gfp.h I convinced myself GFP_NOWAIT was what I wanted because I was concerned about FS accesses that aren't restricted in GFP_NOIO. For some reason, I assumed this was an issue. I'm ok with the change and can submit a v2 shortly, after more tests. in fact, this will make the change more compliant with the rest of block layer critical allocations that use GFP_NOIO. Thanks, -- Gabriel Krisman Bertazi