From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: Re: Possible explanation for SCSI benchmark problems in 2.5 Date: Mon, 30 Sep 2002 09:47:02 +0200 Sender: linux-scsi-owner@vger.kernel.org Message-ID: <20020930074702.GD27420@suse.de> References: <200209292048.g8TKmN424799@localhost.localdomain> <3D976864.65C82D7B@digeo.com> <20020930073033.GA27420@suse.de> <3D980142.971B70AD@digeo.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <3D980142.971B70AD@digeo.com> List-Id: linux-scsi@vger.kernel.org To: Andrew Morton Cc: James Bottomley , linux-scsi@vger.kernel.org On Mon, Sep 30 2002, Andrew Morton wrote: > Jens Axboe wrote: > > > > On Sun, Sep 29 2002, Andrew Morton wrote: > > > But high-IO is bust for IDE as well at present, so at least > > > we're being fair ;) > > > > Nah that's fixed, it worries me that you say otherwise. Doesn't it work > > for you in stock 2.5.39? > > > > Ah you're right, it went away. I was assuming that it was still > a problem because my fixit patch wasn't throwing rejects... I _think_ we should have that patch in addition (it seems noone calls pci_set_dma_mask on the ide pci dev). At least it cannot hurt, so feel free to pass it along. -- Jens Axboe