From: willy@linux.intel.com (Matthew Wilcox)
Subject: if the NVMe driver has been validated on dual-cpu platform
Date: Mon, 24 Mar 2014 02:09:01 -0400 [thread overview]
Message-ID: <20140324060901.GA5777@linux.intel.com> (raw)
In-Reply-To: <45840288.abae.144f2312ef0.Coremail.liaohengquan1986@163.com>
On Mon, Mar 24, 2014@11:45:13AM +0800, liaohengquan1986 wrote:
> I want to ask that if the NVMe driver has been validated on dual-cpu platform?
I've run it on a dual socket platform. Performance is better if the
application is running on the socket that the card is attached to :-)
WARNING: multiple messages have this Message-ID (diff)
From: Matthew Wilcox <willy@linux.intel.com>
To: liaohengquan1986 <liaohengquan1986@163.com>
Cc: "Keith Busch" <keith.busch@intel.com>,
"Alexander Gordeev" <agordeev@redhat.com>,
linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org
Subject: Re: if the NVMe driver has been validated on dual-cpu platform
Date: Mon, 24 Mar 2014 02:09:01 -0400 [thread overview]
Message-ID: <20140324060901.GA5777@linux.intel.com> (raw)
In-Reply-To: <45840288.abae.144f2312ef0.Coremail.liaohengquan1986@163.com>
On Mon, Mar 24, 2014 at 11:45:13AM +0800, liaohengquan1986 wrote:
> I want to ask that if the NVMe driver has been validated on dual-cpu platform?
I've run it on a dual socket platform. Performance is better if the
application is running on the socket that the card is attached to :-)
next prev parent reply other threads:[~2014-03-24 6:09 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-28 8:38 [PATCH 00/14] NVMe: Cleanup device initialization Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 01/14] NVMe: Fix setup of affinity hint for unallocated queues Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 02/14] NVMe: Cleanup nvme_alloc_queue() and nvme_free_queue() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 03/14] NVMe: Cleanup nvme_create_queue() and nvme_disable_queue() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 04/14] NVMe: Cleanup adapter_alloc_cq/sg() and adapter_delete_cq/sg() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 05/14] NVMe: Get rid of superfluous qid parameter to nvme_init_queue() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 06/14] NVMe: Get rid of superfluous dev parameter to queue_request_irq() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 07/14] NVMe: Make returning value consistent across all functions Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 08/14] NVMe: nvme_dev_map() is a bad place to set admin queue IRQ number Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 09/14] NVMe: Access interrupt vectors using nvme_queue::cq_vector only Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 10/14] NVMe: Factor out nvme_set_queue_count() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 11/14] NVMe: Factor out nvme_init_bar() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 12/14] NVMe: Factor out nvme_init_interrupts() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:38 ` [PATCH 13/14] NVMe: Factor out nvme_setup_interrupts() Alexander Gordeev
2014-01-28 8:38 ` Alexander Gordeev
2014-01-28 8:39 ` [PATCH 14/14] NVMe: Rework "NVMe: Disable admin queue on init failure" commit Alexander Gordeev
2014-01-28 8:39 ` Alexander Gordeev
2014-02-18 16:53 ` [PATCH 00/14] NVMe: Cleanup device initialization Alexander Gordeev
2014-02-18 16:53 ` Alexander Gordeev
2014-03-11 15:08 ` Alexander Gordeev
2014-03-11 15:08 ` Alexander Gordeev
[not found] ` <196070e8.d690.144bb7e553f.Coremail.liaohengquan1986@163.com>
2014-03-13 19:20 ` problem in the development of nvme disk Matthew Wilcox
2014-03-13 19:20 ` Matthew Wilcox
[not found] ` <785daaf7.5696.144e2af49b0.Coremail.liaohengquan1986@163.com>
2014-03-21 20:11 ` A question about NVMe's nvme-irq Matthew Wilcox
2014-03-21 20:11 ` Matthew Wilcox
[not found] ` <45840288.abae.144f2312ef0.Coremail.liaohengquan1986@163.com>
2014-03-24 6:09 ` Matthew Wilcox [this message]
2014-03-24 6:09 ` if the NVMe driver has been validated on dual-cpu platform Matthew Wilcox
[not found] ` <42744e02.6f7d.144f1b148b3.Coremail.liaohengquan1986@163.com>
2014-03-24 6:09 ` A question about NVMe's nvme-irq Matthew Wilcox
2014-03-24 6:09 ` Matthew Wilcox
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20140324060901.GA5777@linux.intel.com \
--to=willy@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.