Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932560AbaGQMl6 (ORCPT ); Thu, 17 Jul 2014 08:41:58 -0400 Received: from userp1040.oracle.com ([156.151.31.81]:33794 "EHLO userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756043AbaGQMl4 (ORCPT ); Thu, 17 Jul 2014 08:41:56 -0400 To: "hch\@infradead.org" Cc: "Martin K. Petersen" , "Elliott\, Robert \(Server Storage\)" , James Bottomley , "linux-kernel\@vger.kernel.org" , "devel\@linuxdriverproject.org" , "apw\@canonical.com" , "kys\@microsoft.com" , "stable\@vger.kernel.org" , "linux-scsi\@vger.kernel.org" , "ohering\@suse.com" , "jasowang\@redhat.com" Subject: Re: [PATCH 4/8] Drivers: scsi: storvsc: Filter WRITE_SAME_16 From: "Martin K. Petersen" Organization: Oracle Corporation References: <20140711063216.GA20660@infradead.org> <328b7a6174ef4dd8a54a7db5ac959834@BY2PR03MB299.namprd03.prod.outlook.com> <20140716110111.GA7382@infradead.org> <20140716173827.GB20528@infradead.org> <1405533734.3165.12.camel@dabdike.int.hansenpartnership.com> <94D0CD8314A33A4D9D801C0FE68B402958BA721F@G9W0745.americas.hpqcorp.net> <20140717074234.GA7604@infradead.org> Date: Thu, 17 Jul 2014 08:41:09 -0400 In-Reply-To: <20140717074234.GA7604@infradead.org> (hch@infradead.org's message of "Thu, 17 Jul 2014 00:42:34 -0700") Message-ID: User-Agent: Gnus/5.130012 (Ma Gnus v0.12) Emacs/24.2 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain X-Source-IP: acsinet22.oracle.com [141.146.126.238] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org >>>>> "Christoph" == hch@infradead org writes: Christoph> That's mostly because we don't support larger than 512 byte Christoph> TRIM payloads yet.. I did add support for that a few years back but all hell broke loose and we had to revert it. There were several drives that failed with more than 512 bytes of payload despite advertising support for 4K. It's the same problem that we have now with queued TRIM. There are several vendors that have implemented it but until we added support in Linux they had no way of testing it. And as a result their implementations are buggy. Even with a Linux implementation readily available it's hard to get them to test since Linux is not a tier 1 platform in the consumer segment. For enterprise drives it's an entirely different matter, of course... -- Martin K. Petersen Oracle Linux Engineering -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/