From: John Garry <john.garry@huawei.com>
To: Ming Lei <ming.lei@redhat.com>
Cc: Bart Van Assche <bvanassche@acm.org>,
Hannes Reinecke <hare@suse.com>,
Kashyap Desai <kashyap.desai@broadcom.com>,
"Martin K . Petersen" <martin.petersen@oracle.com>,
"James E.J. Bottomley" <jejb@linux.ibm.com>,
Christoph Hellwig <hch@lst.de>,
"linux-scsi@vger.kernel.org" <linux-scsi@vger.kernel.org>,
Sathya Prakash <sathya.prakash@broadcom.com>,
Sreekanth Reddy <sreekanth.reddy@broadcom.com>,
Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>,
PDL-MPT-FUSIONLINUX <MPT-FusionLinux.pdl@broadcom.com>,
chenxiang <chenxiang66@hisilicon.com>
Subject: Re: About scsi device queue depth
Date: Tue, 12 Jan 2021 17:44:14 +0000 [thread overview]
Message-ID: <9241f2fa-3143-7aae-ee21-71e31e363c9a@huawei.com> (raw)
In-Reply-To: <20210112090634.GA97446@T590>
>>>> sdev qdepth fio number jobs* 1 10 20
>>>> 16 1590 1654 1660
>>>> 32 1545 1646 1654
>>>> 64 1436 1085 1070
>>>> 254 (default) 1436 1070 1050
>>> What does the performance number mean? IOPS or others? What is the fio
>>> io test? random IO or sequential IO?
>> So those figures are x1K IOPs read performance; so 1590, above, is 1.59M
>> IOPs read. Here's the fio script:
>>
>> [global]
>> rw=read
>> direct=1
>> ioengine=libaio
>> iodepth=40
>> numjobs=20
>> bs=4k
>> ;size=10240000m
>> ;zero_buffers=1
>> group_reporting=1
>> ;ioscheduler=noop
>> ;cpumask=0xffe
>> ;cpus_allowed=1-47
>> ;gtod_reduce=1
>> ;iodepth_batch=2
>> ;iodepth_batch_complete=2
>> runtime=60
>> ;thread
>> loops = 10000
> Is there any effect on random read IOPS when you decrease sdev queue
> depth? For sequential IO, IO merge can be enhanced by that way.
>
Hi Ming,
fio randread results:
fio queue depth 40
sdev qdepth fio number jobs* 1 10 20
8 1308K 831K 814K
16 1435K 1073K 988K
32 1438K 1065K 990K
64 1432K 1061K 1020K
254 (default) 1439K 1099K 1083K
fio queue depth 128
sdev qdepth fio number jobs* 1 10 20
8 1310K 860K 849K
16 1435K 1048K 958K
32 1438K 1140K 951K
64 1438K 1065K 953k
254 (default) 1439K 1140K 1056K
So randread goes in the opposite direction (to read wrt queue depth).
Thanks,
John
next prev parent reply other threads:[~2021-01-12 17:46 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-11 16:21 About scsi device queue depth John Garry
2021-01-11 16:40 ` James Bottomley
2021-01-11 17:11 ` John Garry
2021-01-12 6:35 ` James Bottomley
2021-01-12 10:27 ` John Garry
2021-01-12 16:40 ` Bryan Gurney
2021-01-12 16:47 ` James Bottomley
2021-01-12 17:20 ` Bryan Gurney
2021-01-11 17:31 ` Douglas Gilbert
2021-01-13 6:07 ` Martin K. Petersen
2021-01-13 6:36 ` Damien Le Moal
2021-01-12 1:42 ` Ming Lei
2021-01-12 8:56 ` John Garry
2021-01-12 9:06 ` Ming Lei
2021-01-12 9:23 ` John Garry
2021-01-12 11:44 ` Kashyap Desai
2021-01-13 12:17 ` John Garry
2021-01-13 13:34 ` Kashyap Desai
2021-01-13 15:39 ` John Garry
2021-01-12 17:44 ` John Garry [this message]
2021-01-12 7:23 ` Hannes Reinecke
2021-01-12 9:15 ` John Garry
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=9241f2fa-3143-7aae-ee21-71e31e363c9a@huawei.com \
--to=john.garry@huawei.com \
--cc=MPT-FusionLinux.pdl@broadcom.com \
--cc=bvanassche@acm.org \
--cc=chenxiang66@hisilicon.com \
--cc=hare@suse.com \
--cc=hch@lst.de \
--cc=jejb@linux.ibm.com \
--cc=kashyap.desai@broadcom.com \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=sathya.prakash@broadcom.com \
--cc=sreekanth.reddy@broadcom.com \
--cc=suganath-prabu.subramani@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).