Re: [PATCH V2 00/20] blk-mq-sched: improve SCSI-MQ performance

[Paolo Valente <paolo.valente@linaro.org>]

> Il giorno 08 ago 2017, alle ore 11:09, Ming Lei <ming.lei@redhat.com> =
ha scritto:
>=20
> On Tue, Aug 08, 2017 at 10:09:57AM +0200, Paolo Valente wrote:
>>=20
>>> Il giorno 05 ago 2017, alle ore 08:56, Ming Lei =
<ming.lei@redhat.com> ha scritto:
>>>=20
>>> In Red Hat internal storage test wrt. blk-mq scheduler, we
>>> found that I/O performance is much bad with mq-deadline, especially
>>> about sequential I/O on some multi-queue SCSI devcies(lpfc, qla2xxx,
>>> SRP...)
>>>=20
>>> Turns out one big issue causes the performance regression: requests
>>> are still dequeued from sw queue/scheduler queue even when ldd's
>>> queue is busy, so I/O merge becomes quite difficult to make, then
>>> sequential IO degrades a lot.
>>>=20
>>> The 1st five patches improve this situation, and brings back
>>> some performance loss.
>>>=20
>>> But looks they are still not enough. It is caused by
>>> the shared queue depth among all hw queues. For SCSI devices,
>>> .cmd_per_lun defines the max number of pending I/O on one
>>> request queue, which is per-request_queue depth. So during
>>> dispatch, if one hctx is too busy to move on, all hctxs can't
>>> dispatch too because of the per-request_queue depth.
>>>=20
>>> Patch 6 ~ 14 use per-request_queue dispatch list to avoid
>>> to dequeue requests from sw/scheduler queue when lld queue
>>> is busy.
>>>=20
>>> Patch 15 ~20 improve bio merge via hash table in sw queue,
>>> which makes bio merge more efficient than current approch
>>> in which only the last 8 requests are checked. Since patch
>>> 6~14 converts to the scheduler way of dequeuing one request
>>> from sw queue one time for SCSI device, and the times of
>>> acquring ctx->lock is increased, and merging bio via hash
>>> table decreases holding time of ctx->lock and should eliminate
>>> effect from patch 14.=20
>>>=20
>>> With this changes, SCSI-MQ sequential I/O performance is
>>> improved much, for lpfc, it is basically brought back
>>> compared with block legacy path[1], especially mq-deadline
>>> is improved by > X10 [1] on lpfc and by > 3X on SCSI SRP,
>>> For mq-none it is improved by 10% on lpfc, and write is
>>> improved by > 10% on SRP too.
>>>=20
>>> Also Bart worried that this patchset may affect SRP, so provide
>>> test data on SCSI SRP this time:
>>>=20
>>> - fio(libaio, bs:4k, dio, queue_depth:64, 64 jobs)
>>> - system(16 cores, dual sockets, mem: 96G)
>>>=20
>>>             |v4.13-rc3     |v4.13-rc3     | v4.13-rc3+patches |
>>>             |blk-legacy dd |blk-mq none   | blk-mq none  |
>>> -----------------------------------------------------------| =20
>>> read     :iops|         587K |         526K |         537K |
>>> randread :iops|         115K |         140K |         139K |
>>> write    :iops|         596K |         519K |         602K |
>>> randwrite:iops|         103K |         122K |         120K |
>>>=20
>>>=20
>>>             |v4.13-rc3     |v4.13-rc3     | v4.13-rc3+patches
>>>             |blk-legacy dd |blk-mq dd     | blk-mq dd    |
>>> ------------------------------------------------------------
>>> read     :iops|         587K |         155K |         522K |
>>> randread :iops|         115K |         140K |         141K |
>>> write    :iops|         596K |         135K |         587K |
>>> randwrite:iops|         103K |         120K |         118K |
>>>=20
>>> V2:
>>> 	- dequeue request from sw queues in round roubin's style
>>> 	as suggested by Bart, and introduces one helper in sbitmap
>>> 	for this purpose
>>> 	- improve bio merge via hash table from sw queue
>>> 	- add comments about using DISPATCH_BUSY state in lockless way,
>>> 	simplifying handling on busy state,
>>> 	- hold ctx->lock when clearing ctx busy bit as suggested
>>> 	by Bart
>>>=20
>>>=20
>>=20
>> Hi,
>> I've performance-tested Ming's patchset with the dbench4 test in
>> MMTests, and with the mq-deadline and bfq schedulers.  Max latencies,
>> have decreased dramatically: up to 32 times.  Very good results for
>> average latencies as well.
>>=20
>> For brevity, here are only results for deadline.  You can find full
>> results with bfq in the thread that triggered my testing of Ming's
>> patches [1].
>>=20
>> MQ-DEADLINE WITHOUT MING'S PATCHES
>>=20
>> Operation                Count    AvgLat    MaxLat
>> --------------------------------------------------
>> Flush                    13760    90.542 13221.495
>> Close                   137654     0.008    27.133
>> LockX                      640     0.009     0.115
>> Rename                    8064     1.062   246.759
>> ReadX                   297956     0.051   347.018
>> WriteX                   94698   425.636 15090.020
>> Unlink                   35077     0.580   208.462
>> UnlockX                    640     0.007     0.291
>> FIND_FIRST               66630     0.566   530.339
>> SET_FILE_INFORMATION     16000     1.419   811.494
>> QUERY_FILE_INFORMATION   30717     0.004     1.108
>> QUERY_PATH_INFORMATION  176153     0.182   517.419
>> QUERY_FS_INFORMATION     30857     0.018    18.562
>> NTCreateX               184145     0.281   582.076
>>=20
>> Throughput 8.93961 MB/sec  64 clients  64 procs  =
max_latency=3D15090.026 ms
>>=20
>> MQ-DEADLINE WITH MING'S PATCHES
>>=20
>> Operation                Count    AvgLat    MaxLat
>> --------------------------------------------------
>> Flush                    13760    48.650   431.525
>> Close                   144320     0.004     7.605
>> LockX                      640     0.005     0.019
>> Rename                    8320     0.187     5.702
>> ReadX                   309248     0.023   216.220
>> WriteX                   97176   338.961  5464.995
>> Unlink                   39744     0.454   315.207
>> UnlockX                    640     0.004     0.027
>> FIND_FIRST               69184     0.042    17.648
>> SET_FILE_INFORMATION     16128     0.113   134.464
>> QUERY_FILE_INFORMATION   31104     0.004     0.370
>> QUERY_PATH_INFORMATION  187136     0.031   168.554
>> QUERY_FS_INFORMATION     33024     0.009     2.915
>> NTCreateX               196672     0.152   163.835
>=20
> Hi Paolo,
>=20
> Thanks very much for testing this patchset!
>=20
> BTW, could you share us which kind of disk you are using
> in this test?
>=20

Absolutely:

ATA device, with non-removable media
	Model Number:       HITACHI HTS727550A9E364                =20
	Serial Number:      J3370082G622JD
	Firmware Revision:  JF3ZD0H0
	Transport:          Serial, ATA8-AST, SATA 1.0a, SATA II =
Extensions, SATA Rev 2.5, SATA Rev 2.6; Revision: ATA8-AST T13 Project =
D1697 Revision 0b

Thanks,
Paolo

> Thanks,
> Ming