From: Jens Axboe <axboe@kernel.dk>
To: Keith Busch <keith.busch@intel.com>
Cc: linux-block@vger.kernel.org, linux-scsi@vger.kernel.org,
linux-kernel@vger.kernel.org,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 11/14] irq: add support for allocating (and affinitizing) sets of IRQs
Date: Tue, 30 Oct 2018 10:42:07 -0600 [thread overview]
Message-ID: <27c1017a-9560-80cb-038d-f64727a162c3@kernel.dk> (raw)
In-Reply-To: <20181030160242.GD18906@localhost.localdomain>
On 10/30/18 10:02 AM, Keith Busch wrote:
> On Tue, Oct 30, 2018 at 09:18:05AM -0600, Jens Axboe wrote:
>> On 10/30/18 9:08 AM, Keith Busch wrote:
>>> On Tue, Oct 30, 2018 at 08:53:37AM -0600, Jens Axboe wrote:
>>>> The sum of the set can't exceed the nvecs passed in, the nvecs passed in
>>>> should be the less than or equal to nvecs. Granted this isn't enforced,
>>>> and perhaps that should be the case.
>>>
>>> That should at least initially be true for a proper functioning
>>> driver. It's not enforced as you mentioned, but that's only related to
>>> the issue I'm referring to.
>>>
>>> The problem is pci_alloc_irq_vectors_affinity() takes a range, min_vecs
>>> and max_vecs, but a range of allowable vector allocations doesn't make
>>> sense when using sets.
>>
>> I feel like we're going in circles here, not sure what you feel the
>> issue is now? The range is fine, whoever uses sets will need to adjust
>> their sets based on what pci_alloc_irq_vectors_affinity() returns,
>> if it didn't return the passed in desired max.
>
> Sorry, let me to try again.
>
> pci_alloc_irq_vectors_affinity() starts at the provided max_vecs. If
> that doesn't work, it will iterate down to min_vecs without returning to
> the caller. The caller doesn't have a chance to adjust its sets between
> iterations when you provide a range.
>
> The 'masks' overrun problem happens if the caller provides min_vecs
> as a smaller value than the sum of the set (plus any reserved).
>
> If it's up to the caller to ensure that doesn't happen, then min and
> max must both be the same value, and that value must also be the same as
> the set sum + reserved vectors. The range just becomes redundant since
> it is already bounded by the set.
>
> Using the nvme example, it would need something like this to prevent the
> 'masks' overrun:
OK, now I hear what you are saying. And you are right, the callers needs
to provide minvec == maxvec for sets, and then have a loop around that
to adjust as needed.
I'll make that change in nvme.
--
Jens Axboe
next prev parent reply other threads:[~2018-10-30 16:42 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-29 16:37 [PATCHSET v2 0/14] blk-mq: Add support for multiple queue maps Jens Axboe
2018-10-29 16:37 ` [PATCH 01/14] blk-mq: kill q->mq_map Jens Axboe
2018-10-29 16:46 ` Bart Van Assche
2018-10-29 16:51 ` Jens Axboe
2018-10-29 16:37 ` [PATCH 02/14] blk-mq: abstract out queue map Jens Axboe
2018-10-29 18:33 ` Bart Van Assche
2018-10-29 16:37 ` [PATCH 03/14] blk-mq: provide dummy blk_mq_map_queue_type() helper Jens Axboe
2018-10-29 17:22 ` Bart Van Assche
2018-10-29 17:27 ` Jens Axboe
2018-10-29 16:37 ` [PATCH 04/14] blk-mq: pass in request/bio flags to queue mapping Jens Axboe
2018-10-29 17:30 ` Bart Van Assche
2018-10-29 17:33 ` Jens Axboe
2018-10-29 16:37 ` [PATCH 05/14] blk-mq: allow software queue to map to multiple hardware queues Jens Axboe
2018-10-29 17:34 ` Bart Van Assche
2018-10-29 17:35 ` Jens Axboe
2018-10-29 16:37 ` [PATCH 06/14] blk-mq: add 'type' attribute to the sysfs hctx directory Jens Axboe
2018-10-29 17:40 ` Bart Van Assche
2018-10-29 16:37 ` [PATCH 07/14] blk-mq: support multiple hctx maps Jens Axboe
2018-10-29 18:15 ` Bart Van Assche
2018-10-29 19:24 ` Jens Axboe
2018-10-29 16:37 ` [PATCH 08/14] blk-mq: separate number of hardware queues from nr_cpu_ids Jens Axboe
2018-10-29 18:31 ` Bart Van Assche
2018-10-29 16:37 ` [PATCH 09/14] blk-mq: ensure that plug lists don't straddle hardware queues Jens Axboe
2018-10-29 19:27 ` Bart Van Assche
2018-10-29 19:30 ` Jens Axboe
2018-10-29 19:49 ` Jens Axboe
2018-10-30 8:08 ` Ming Lei
2018-10-30 17:22 ` Jens Axboe
2018-10-29 16:37 ` [PATCH 10/14] blk-mq: initial support for multiple queue maps Jens Axboe
2018-10-29 19:40 ` Bart Van Assche
2018-10-29 19:53 ` Jens Axboe
2018-10-29 20:00 ` Bart Van Assche
2018-10-29 20:09 ` Jens Axboe
2018-10-29 20:25 ` Bart Van Assche
2018-10-29 20:29 ` Jens Axboe
2018-10-29 16:37 ` [PATCH 11/14] irq: add support for allocating (and affinitizing) sets of IRQs Jens Axboe
2018-10-29 17:08 ` Thomas Gleixner
2018-10-29 17:09 ` Jens Axboe
2018-10-30 9:25 ` Ming Lei
2018-10-30 14:26 ` Keith Busch
2018-10-30 14:36 ` Jens Axboe
2018-10-30 14:45 ` Keith Busch
2018-10-30 14:53 ` Jens Axboe
2018-10-30 15:08 ` Keith Busch
2018-10-30 15:18 ` Jens Axboe
2018-10-30 16:02 ` Keith Busch
2018-10-30 16:42 ` Jens Axboe [this message]
2018-10-30 17:09 ` Jens Axboe
2018-10-30 17:22 ` Keith Busch
2018-10-30 17:33 ` Jens Axboe
2018-10-30 17:35 ` Keith Busch
2018-10-30 17:25 ` Thomas Gleixner
2018-10-30 17:34 ` Jens Axboe
2018-10-30 17:43 ` Jens Axboe
2018-10-30 17:46 ` Thomas Gleixner
2018-10-30 17:47 ` Jens Axboe
2018-10-29 16:37 ` [PATCH 12/14] nvme: utilize two queue maps, one for reads and one for writes Jens Axboe
2018-10-29 16:37 ` [PATCH 13/14] block: add REQ_HIPRI and inherit it from IOCB_HIPRI Jens Axboe
2018-10-29 16:37 ` [PATCH 14/14] nvme: add separate poll queue map Jens Axboe
[not found] <20181025211626.12692-1-axboe@kernel.dk>
2018-10-25 21:16 ` [PATCH 11/14] irq: add support for allocating (and affinitizing) sets of IRQs Jens Axboe
2018-10-25 21:52 ` Keith Busch
2018-10-25 23:07 ` Jens Axboe
2018-10-29 7:43 ` Hannes Reinecke
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=27c1017a-9560-80cb-038d-f64727a162c3@kernel.dk \
--to=axboe@kernel.dk \
--cc=keith.busch@intel.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=tglx@linutronix.de \
/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;
as well as URLs for NNTP newsgroup(s).