From: Harris, James R <james.r.harris at intel.com>
To: spdk@lists.01.org
Subject: Re: [SPDK] Does SPDK have specific requirement for NVMe SSDs(device controller) to get it working in the best way?
Date: Tue, 26 Mar 2019 18:24:36 +0000 [thread overview]
Message-ID: <E92935C9-2FC2-4863-B16A-12866F97FDAC@intel.com> (raw)
In-Reply-To: MW2PR2101MB111398F1E2EAE64DA3C43982D55F0@MW2PR2101MB1113.namprd21.prod.outlook.com
[-- Attachment #1: Type: text/plain, Size: 2414 bytes --]
On 3/26/19, 9:45 AM, "SPDK on behalf of Liang Yang" <spdk-bounces(a)lists.01.org on behalf of liangy(a)microsoft.com> wrote:
> I understand for SPDK every I/O queue pairs operate in poll mode. But since you said "SPDK does not use interrupts", do you mean even the admin queue pair works in polling mode too with interrupt disabled?
Hi Liang,
Yes - that is correct.
-Jim
-----Original Message-----
From: SPDK <spdk-bounces(a)lists.01.org> On Behalf Of Walker, Benjamin
Sent: Monday, March 25, 2019 1:08 PM
To: spdk(a)lists.01.org
Subject: Re: [SPDK] Does SPDK have specific requirement for NVMe SSDs(device controller) to get it working in the best way?
On Mon, 2019-03-25 at 18:07 +0000, Liang Yang wrote:
> For example, how many I/O queue pairs, MSI-X messages, MDTS etc.
Most NVMe devices only need 1 I/O queue pair to get their full performance, but that's ultimately up to the device. SPDK places no new requirements above what the device requires.
SPDK does not use interrupts, so MSI-X is all disabled and doesn't matter.
SPDK will just automatically do the right thing for MDTS and optimal write size and striping and all of that. You don't have to worry about it.
Thanks,
Ben
>
> Liang
>
> _______________________________________________
> SPDK mailing list
> SPDK(a)lists.01.org
> https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Flist
> s.01.org%2Fmailman%2Flistinfo%2Fspdk&data=02%7C01%7Cliangy%40micro
> soft.com%7Cc6782acbee8e451260f808d6b15da6d5%7C72f988bf86f141af91ab2d7c
> d011db47%7C1%7C1%7C636891413137262799&sdata=4Mu998%2Buia5WsYkageTS
> 0QEPwkz%2B4C%2F8nSbYTpOfJ3c%3D&reserved=0
_______________________________________________
SPDK mailing list
SPDK(a)lists.01.org
https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.01.org%2Fmailman%2Flistinfo%2Fspdk&data=02%7C01%7Cliangy%40microsoft.com%7Cc6782acbee8e451260f808d6b15da6d5%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636891413137262799&sdata=4Mu998%2Buia5WsYkageTS0QEPwkz%2B4C%2F8nSbYTpOfJ3c%3D&reserved=0
_______________________________________________
SPDK mailing list
SPDK(a)lists.01.org
https://lists.01.org/mailman/listinfo/spdk
next reply other threads:[~2019-03-26 18:24 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-26 18:24 Harris, James R [this message]
-- strict thread matches above, loose matches on Subject: below --
2019-03-26 16:45 [SPDK] Does SPDK have specific requirement for NVMe SSDs(device controller) to get it working in the best way? Liang Yang
2019-03-25 20:08 Walker, Benjamin
2019-03-25 18:07 Liang Yang
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=E92935C9-2FC2-4863-B16A-12866F97FDAC@intel.com \
--to=spdk@lists.01.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox