Not to compound upon this again. However if BFQ isn't suitable to
replace CFQ for high I/O workloads (I've yet to see 20k IOPS on any
reasonably sized SAN (SC4020 / v5000, etc)), can't we at-least default
BFQ to become the default I/O scheduler for people otherwise
requesting CFQ? Paolo has had a
Remove annoying white space damage in pci.c.
Signed-off-by: Stephen Bates
---
drivers/nvme/host/pci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index a7c6e9d..e2b3243 100644
---
This patch checks to see if an ATA device supports NCQ command priorities.
If so and the user has specified an iocontext that indicates
IO_PRIO_CLASS_RT then we build a tf with a high priority command.
This is done to improve the tail latency of commands that are high
priority by passing priority
Patch adds an association between iocontext ioprio and the ioprio of a
request. This is done to enable request based drivers the ability to
act on priority information stored in the request. An example being
ATA devices that support command priorities. If the ATA driver discovers
that the device
Hi Don,
did you also have a chance to test the patch and verify that the
queues are properly set up with a smartpqi controller?
--
To unsubscribe from this list: send the line "unsubscribe linux-block" in
the body of a message to majord...@vger.kernel.org
More majordomo info at
> -Original Message-
> From: Johannes Thumshirn [mailto:jthumsh...@suse.de]
> Sent: Monday, October 17, 2016 2:34 AM
> To: Christoph Hellwig
> Cc: martin.peter...@oracle.com; Don Brace; ax...@kernel.dk; linux-
> s...@vger.kernel.org; linux-block@vger.kernel.org
> Subject: Re: [PATCH 3/3]
On Mon, Oct 17, 2016 at 09:27:03AM +0200, Johannes Thumshirn wrote:
> Shouldn't this hunk go into the previous patch?
Yes, it should, thanks.
--
To unsubscribe from this list: send the line "unsubscribe linux-block" in
the body of a message to majord...@vger.kernel.org
More majordomo info at
On Sat, Oct 15, 2016 at 10:47:19AM +0200, Christoph Hellwig wrote:
> This will allow SCSI to have a single blk_mq_ops structure that either
> lets the LLDD map the queues to PCIe MSIx vectors or use the default.
>
> Signed-off-by: Christoph Hellwig
> ---
> block/blk-mq.h |