From: John Garry <john.garry@huawei.com>
To: Hannes Reinecke <hare@suse.de>,
Anand Lodnoor <anand.lodnoor@broadcom.com>
Cc: <linux-scsi@vger.kernel.org>,
Kashyap Desai <kashyap.desai@broadcom.com>,
Sumit Saxena <sumit.saxena@broadcom.com>,
Kiran Kumar Kasturi <kiran-kumar.kasturi@broadcom.com>,
Sankar Patra <sankar.patra@broadcom.com>,
Sasikumar PC <sasikumar.pc@broadcom.com>,
Shivasharan Srikanteshwara
<shivasharan.srikanteshwara@broadcom.com>,
Chandrakanth Patil <chandrakanth.patil@broadcom.com>,
Ming Lei <ming.lei@redhat.com>,
"Bart Van Assche" <bvanassche@acm.org>,
"Martin K . Petersen" <martin.petersen@oracle.com>
Subject: Re: [PATCH v2 10/11] megaraid_sas: Use Block layer API to check SCSI device in-flight IO requests
Date: Mon, 2 Mar 2020 09:51:48 +0000 [thread overview]
Message-ID: <5ac6fd4f-eef8-700b-89d2-c8b3cd6e12ca@huawei.com> (raw)
In-Reply-To: <79fe7843-9d71-bdde-957c-32dde22437d9@suse.de>
>> static inline void
>> megasas_get_msix_index(struct megasas_instance *instance,
>> struct scsi_cmnd *scmd,
>> struct megasas_cmd_fusion *cmd,
>> u8 data_arms)
>> {
>> ...
>>
>> sdev_busy = atomic_read(&hctx->nr_active);
>>
>> if (instance->perf_mode == MR_BALANCED_PERF_MODE &&
>> sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH))
>> cmd->request_desc->SCSIIO.MSIxIndex =
>> mega_mod64(...),
>> else if (instance->msix_load_balance)
>> cmd->request_desc->SCSIIO.MSIxIndex =
>> (mega_mod64(...),
>> instance->msix_vectors));
>>
>> Will this make a difference? I am not sure. Maybe, on this basis,
>> magaraid sas is not a good candidate to change to expose multiple queues.
>>
>> Ignoring that for a moment, since we no longer keep a host busy count,
>> and I figure that we don't want to back to using
>> scsi_device.device_busy, is the judgement of hctx->nr_active ok to use
>> to decide whether to use these performance queues?
>>
> Personally, I wonder if the current implementation of high-IOPs queues
> makes sense with multiqueue. > Thing is, the current high-IOPs queue mechanism of shifting I/O to
> another internal queue doesn't align nicely with the blk-mq architecture.
Right, we should not be hiding HW queues from blk-mq like this. This
breaks the symmetry. Maybe we can move this functionality to blk-mq, but
I doubt that this is a common use case.
> What we _do_ have, though, is a 'poll' queue mechanism, allowing to
> separate out one (or several) queues for polling, to allow for ..
> indeed, high-IOPs.
Any examples or references for this?
> So it would be interesting to figure out if we don't get similar
> performance by using the 'poll' queue implementation from blk-mq instead
> of the current one.
I thought that this driver/or mpt3sas already used a polling mode.
And for these low-latency queues, I figure that the issue is not just
polling vs interrupt, but indeed how fast the HW queue can consume SQEs.
A HW queue may only be able to consume at a limited rate - that's why we
segregate.
As an aside, that is actually an issue for blk-mq. For 1 to many HW
queue-to-CPU mapping, limiting many CPUs a single queue can limit IOPs
since HW queues can only consume at a limited rate.
>
> Which would also have the benefit that we could support the io_uring
> interface natively with megaraid_sas, which I think would be a benefit
> on its own.
>
thanks,
John
next prev parent reply other threads:[~2020-03-02 9:51 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-14 11:21 [PATCH v2 00/11] megaraid_sas: driver updates to 07.713.01.00-rc1 Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 01/11] megaraid_sas: Reset adapter if FW is not in READY state after device resume Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 02/11] megaraid_sas: Set no_write_same only for Virtual Disk Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 03/11] megaraid_sas: Update optimal queue depth for SAS and NVMe devices Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 04/11] megaraid_sas: Do not kill host bus adapter, if adapter is already dead Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 05/11] megaraid_sas: Do not kill HBA if JBOD Seqence map or RAID map is disabled Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 06/11] megaraid_sas: Do not set HBA Operational if FW is not in operational state Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 07/11] megaraid_sas: Re-Define enum DCMD_RETURN_STATUS Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 08/11] megaraid_sas: Do not initiate OCR if controller is not in ready state Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 09/11] megaraid_sas: Limit the number of retries for the IOCTLs causing firmware fault Anand Lodnoor
2020-01-14 11:21 ` [PATCH v2 10/11] megaraid_sas: Use Block layer API to check SCSI device in-flight IO requests Anand Lodnoor
2020-01-16 12:30 ` Hannes Reinecke
2020-01-17 11:19 ` Anand Lodnoor
2020-02-26 16:19 ` John Garry
[not found] ` <CAAO+jF-P3MkB2mo6pmYH1ihjRGpfjkkgXZg9dAZ29nYmU6T2=A@mail.gmail.com>
2020-02-27 12:32 ` John Garry
2020-03-02 9:17 ` Hannes Reinecke
2020-03-02 9:51 ` John Garry [this message]
2020-03-02 18:37 ` Sumit Saxena
2020-03-03 11:53 ` John Garry
2020-03-03 11:56 ` Hannes Reinecke
2020-03-03 17:04 ` Sumit Saxena
2020-03-04 9:39 ` John Garry
2020-01-14 11:21 ` [PATCH v2 11/11] megaraid_sas: Update driver version to 07.713.01.00-rc1 Anand Lodnoor
2020-01-16 4:21 ` [PATCH v2 00/11] megaraid_sas: driver updates " Martin K. Petersen
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=5ac6fd4f-eef8-700b-89d2-c8b3cd6e12ca@huawei.com \
--to=john.garry@huawei.com \
--cc=anand.lodnoor@broadcom.com \
--cc=bvanassche@acm.org \
--cc=chandrakanth.patil@broadcom.com \
--cc=hare@suse.de \
--cc=kashyap.desai@broadcom.com \
--cc=kiran-kumar.kasturi@broadcom.com \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=sankar.patra@broadcom.com \
--cc=sasikumar.pc@broadcom.com \
--cc=shivasharan.srikanteshwara@broadcom.com \
--cc=sumit.saxena@broadcom.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 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).