> -Original Message-
> From: linux-scsi-ow...@vger.kernel.org [mailto:linux-scsi-
> ow...@vger.kernel.org] On Behalf Of Keith Busch
> Sent: Tuesday, March 27, 2018 10:39 AM
> To: Linux NVMe ; Linux Block bl...@vger.kernel.org>
> Cc: Christoph Hellwig ; Sagi Grimberg ;
> Jianchao Wang ; Min
On 3/27/18 9:39 AM, Keith Busch wrote:
> The PCI interrupt vectors intended to be associated with a queue may
> not start at 0; a driver may allocate pre_vectors for special use. This
> patch adds an offset parameter so blk-mq may find the intended affinity
> mask and updates all drivers using this
On Tue, Mar 27, 2018 at 09:39:06AM -0600, Keith Busch wrote:
> The PCI interrupt vectors intended to be associated with a queue may
> not start at 0; a driver may allocate pre_vectors for special use. This
> patch adds an offset parameter so blk-mq may find the intended affinity
> mask and updates
On Fri, Mar 23, 2018 at 04:19:21PM -0600, Keith Busch wrote:
> The PCI interrupt vectors intended to be associated with a queue may
> not start at 0. This patch adds an offset parameter so blk-mq may find
> the intended affinity mask. The default value is 0 so existing drivers
> that don't care abo
On Mon, Mar 26, 2018 at 09:50:38AM +0800, Ming Lei wrote:
>
> Given no many callers of blk_mq_pci_map_queues(), I suggest to add the
> parameter of 'offset' to this API directly, then people may keep the
> '.pre_vectors' stuff in mind, and avoid to misuse it.
Yeah, I think I have to agree. I was
On Sat, Mar 24, 2018 at 09:55:49PM +0800, jianchao.wang wrote:
> Maybe we could provide a callback parameter for __blk_mq_pci_map_queues which
> give the mapping from hctx queue num to device-relative interrupt vector
> index.
If a driver's mapping is so complicated as to require a special per-hc
On Fri, Mar 23, 2018 at 04:19:21PM -0600, Keith Busch wrote:
> The PCI interrupt vectors intended to be associated with a queue may
> not start at 0. This patch adds an offset parameter so blk-mq may find
> the intended affinity mask. The default value is 0 so existing drivers
> that don't care abo
Hi Keith
Thanks for your time and patch for this.
On 03/24/2018 06:19 AM, Keith Busch wrote:
> The PCI interrupt vectors intended to be associated with a queue may
> not start at 0. This patch adds an offset parameter so blk-mq may find
> the intended affinity mask. The default value is 0 so exis
