From mboxrd@z Thu Jan 1 00:00:00 1970 From: Malahal Naineni Subject: Re: [PATCH] block: QUEUE_FLAG_CLUSTER and no_cluster are NOT in sync Date: Sun, 29 Aug 2010 13:31:50 -0700 Message-ID: <20100829203149.GC24466@us.ibm.com> References: <5e7598cf7714083ffd84.1283104752@malahal> Reply-To: device-mapper development Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: <5e7598cf7714083ffd84.1283104752@malahal> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com To: jaxboe@fusionio.com, dm-devel@redhat.com List-Id: dm-devel.ids Here is the missing header: no_cluster is used by device mapper (may be others) resulting in multipath devices setting QUEUE_FLAG_CLUSTER flag even though the underlying devices (e.g. open iscsi virtual adapter) don't support it. Signed-off-by: Malahal Naineni (malahal@us.ibm.com) Malahal Naineni [malahal@us.ibm.com] wrote: > diff -r 8305d08f6ecf -r 5e7598cf7714 drivers/scsi/scsi_lib.c > --- a/drivers/scsi/scsi_lib.c Wed Aug 25 13:44:33 2010 -0700 > +++ b/drivers/scsi/scsi_lib.c Wed Aug 25 13:44:33 2010 -0700 > @@ -1633,8 +1633,10 @@ struct request_queue *__scsi_alloc_queue > blk_queue_max_segment_size(q, dma_get_max_seg_size(dev)); > > /* New queue, no concurrency on queue_flags */ > - if (!shost->use_clustering) > + if (!shost->use_clustering) { > queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q); > + q->limits.no_cluster = 1; > + } > > /* > * set a reasonable default alignment on word boundaries: the > > -- > dm-devel mailing list > dm-devel@redhat.com > https://www.redhat.com/mailman/listinfo/dm-devel