Re: [Xen-devel] [PATCH RFC v2 0/5] Multi-queue support for xen-blkfront and xen-blkback

[Rafal Mielniczuk <rafal.mielniczuk@citrix.com>]

On 14/08/15 13:30, Rafal Mielniczuk wrote:
> On 14/08/15 09:31, Bob Liu wrote:
>> On 08/13/2015 12:46 AM, Rafal Mielniczuk wrote:
>>> On 12/08/15 11:17, Bob Liu wrote:
>>>> On 08/12/2015 01:32 AM, Jens Axboe wrote:
>>>>> On 08/11/2015 03:45 AM, Rafal Mielniczuk wrote:
>>>>>> On 11/08/15 07:08, Bob Liu wrote:
>>>>>>> On 08/10/2015 11:52 PM, Jens Axboe wrote:
>>>>>>>> On 08/10/2015 05:03 AM, Rafal Mielniczuk wrote:
>>>> ...
>>>>>>>>> Hello,
>>>>>>>>>
>>>>>>>>> We rerun the tests for sequential reads with the identical settings but with Bob Liu's multiqueue patches reverted from dom0 and guest kernels.
>>>>>>>>> The results we obtained were *better* than the results we got with multiqueue patches applied:
>>>>>>>>>
>>>>>>>>> fio_threads  io_depth  block_size   1-queue_iops  8-queue_iops  *no-mq-patches_iops*
>>>>>>>>>        8           32       512           158K         264K         321K
>>>>>>>>>        8           32        1K           157K         260K         328K
>>>>>>>>>        8           32        2K           157K         258K         336K
>>>>>>>>>        8           32        4K           148K         257K         308K
>>>>>>>>>        8           32        8K           124K         207K         188K
>>>>>>>>>        8           32       16K            84K         105K         82K
>>>>>>>>>        8           32       32K            50K          54K         36K
>>>>>>>>>        8           32       64K            24K          27K         16K
>>>>>>>>>        8           32      128K            11K          13K         11K
>>>>>>>>>
>>>>>>>>> We noticed that the requests are not merged by the guest when the multiqueue patches are applied,
>>>>>>>>> which results in a regression for small block sizes (RealSSD P320h's optimal block size is around 32-64KB).
>>>>>>>>>
>>>>>>>>> We observed similar regression for the Dell MZ-5EA1000-0D3 100 GB 2.5" Internal SSD
>>>>>>>>>
>>>>>>>>> As I understand blk-mq layer bypasses I/O scheduler which also effectively disables merges.
>>>>>>>>> Could you explain why it is difficult to enable merging in the blk-mq layer?
>>>>>>>>> That could help closing the performance gap we observed.
>>>>>>>>>
>>>>>>>>> Otherwise, the tests shows that the multiqueue patches does not improve the performance,
>>>>>>>>> at least when it comes to sequential read/writes operations.
>>>>>>>> blk-mq still provides merging, there should be no difference there. Does the xen patches set BLK_MQ_F_SHOULD_MERGE?
>>>>>>>>
>>>>>>> Yes.
>>>>>>> Is it possible that xen-blkfront driver dequeue requests too fast after we have multiple hardware queues?
>>>>>>> Because new requests don't have the chance merging with old requests which were already dequeued and issued.
>>>>>>>
>>>>>> For some reason we don't see merges even when we set multiqueue to 1.
>>>>>> Below are some stats from the guest system when doing sequential 4KB reads:
>>>>>>
>>>>>> $ fio --name=test --ioengine=libaio --direct=1 --rw=read --numjobs=8
>>>>>>        --iodepth=32 --time_based=1 --runtime=300 --bs=4KB
>>>>>> --filename=/dev/xvdb
>>>>>>
>>>>>> $ iostat -xt 5 /dev/xvdb
>>>>>> avg-cpu:  %user   %nice %system %iowait  %steal   %idle
>>>>>>             0.50    0.00    2.73   85.14    2.00    9.63
>>>>>>
>>>>>> Device:         rrqm/s   wrqm/s       r/s     w/s     rkB/s    wkB/s
>>>>>> avgrq-sz avgqu-sz   await r_await w_await  svctm  %util
>>>>>> xvdb              0.00     0.00 156926.00    0.00 627704.00     0.00
>>>>>> 8.00    30.06    0.19    0.19    0.00   0.01 100.48
>>>>>>
>>>>>> $ cat /sys/block/xvdb/queue/scheduler
>>>>>> none
>>>>>>
>>>>>> $ cat /sys/block/xvdb/queue/nomerges
>>>>>> 0
>>>>>>
>>>>>> Relevant bits from the xenstore configuration on the dom0:
>>>>>>
>>>>>> /local/domain/0/backend/vbd/2/51728/dev = "xvdb"
>>>>>> /local/domain/0/backend/vbd/2/51728/backend-kind = "vbd"
>>>>>> /local/domain/0/backend/vbd/2/51728/type = "phy"
>>>>>> /local/domain/0/backend/vbd/2/51728/multi-queue-max-queues = "1"
>>>>>>
>>>>>> /local/domain/2/device/vbd/51728/multi-queue-num-queues = "1"
>>>>>> /local/domain/2/device/vbd/51728/ring-ref = "9"
>>>>>> /local/domain/2/device/vbd/51728/event-channel = "60"
>>>>> If you add --iodepth-batch=16 to that fio command line? Both mq and non-mq relies on plugging to get
>>>>> batching in the use case above, otherwise IO is dispatched immediately. O_DIRECT is immediate. 
>>>>> I'd be more interested in seeing a test case with buffered IO of a file system on top of the xvdb device,
>>>>> if we're missing merging for that case, then that's a much bigger issue.
>>>>>
>>>>  
>>>> I was using the null block driver for xen blk-mq test.
>>>>
>>>> There were not merges happen any more even after patch: 
>>>> https://lkml.org/lkml/2015/7/13/185
>>>> (Which just converted xen block driver to use blk-mq apis)
>>>>
>>>> Will try a file system soon.
>>>>
>>> I have more results for the guest with and without the patch
>>> https://lkml.org/lkml/2015/7/13/185
>>> applied to the latest stable kernel (4.1.5).
>>>
>> Thank you.
>>
>>> Command line used was:
>>> fio --name=test --ioengine=libaio --rw=read --numjobs=8 \
>>>     --iodepth=32 --time_based=1 --runtime=300 --bs=4KB \
>>>     --filename=/dev/xvdb --direct=(0 and 1) --iodepth_batch=16
>>>
>>> without patch (--direct=1):
>>>   xvdb: ios=18696304/0, merge=75763177/0, ticks=11323872/0, in_queue=11344352, util=100.00%
>>>
>>> with patch (--direct=1):
>>>   xvdb: ios=43709976/0, merge=97/0, ticks=8851972/0, in_queue=8902928, util=100.00%
>>>
>> So request merge can happen just more difficult to be triggered.
>> How about the iops of both cases?
> Without the patch it is 318Kiops, with the patch 146Kiops
>
>>> without patch buffered (--direct=0):
>>>   xvdb: ios=1079051/0, merge=76/0, ticks=749364/0, in_queue=748840, util=94.60
>>>
>>> with patch buffered (--direct=0):
>>>   xvdb: ios=1132932/0, merge=0/0, ticks=689108/0, in_queue=688488, util=93.32%
>>>
> There seems to be very little difference when we measure buffered
> sequential reads.
> Although iostat shows that there are almost no merges happening for both
> cases,
> the avgrq-sz is around 250 sectors (125KB). Does that mean that the
> merges are actually happening
> but on some other layer, not visible to the iostat?
>
> There is a big discrepancy for direct sequential reads and small block
> sizes,
> where we are missing merges that were happening in the version before
> the patch.
> It looks like the request does not reside in the queue for long enough
> to get merged.
>
> One thing I noticed is that in block/blk-mq.c in function
>
> bool blk_mq_attempt_merge(struct request_queue *q,
>                           struct blk_mq_ctx *ctx, struct bio *bio)
>
> The ctx->rq_list queue is mostly empty, the for loop inside the body
> of the function is almost never executed.
>
Hi,

I was able to reproduce Bob's results with nullblk device with default module parameters.

Also, when I increased the completion time of the requests,
I could see merges happening in the version without the patch, which resulted in greater throughput.

Could it be because request had time to accumulate in the queue and had a chance to be merged?
Why merges did not happen in the version with the patch then? Is the patch missing plugging Jens mentioned,
or is it a problem in blk-mq itself?

fio --name=test --ioengine=libaio --rw=read --numjobs=8 --iodepth=32 \
    --time_based=1 --runtime=30 --bs=4KB --filename=/dev/xvdb \
    --direct=1 --group_reporting=1 --iodepth_batch=16

========================================================================
modprobe null_blk
========================================================================
------------------------------------------------------------------------
*no patch* (avgrq-sz = 8.00 avgqu-sz=5.00)
------------------------------------------------------------------------
READ: io=10655MB, aggrb=363694KB/s, minb=363694KB/s, maxb=363694KB/s, mint=30001msec, maxt=30001msec

Disk stats (read/write):
  xvdb: ios=2715852/0, merge=1089/0, ticks=126572/0, in_queue=127456, util=100.00%

------------------------------------------------------------------------
*with patch* (avgrq-sz = 8.00 avgqu-sz=8.00)
------------------------------------------------------------------------
READ: io=20655MB, aggrb=705010KB/s, minb=705010KB/s, maxb=705010KB/s, mint=30001msec, maxt=30001msec

Disk stats (read/write):
  xvdb: ios=5274633/0, merge=22/0, ticks=243208/0, in_queue=242908, util=99.98%

========================================================================
modprobe null_blk irqmode=2 completion_nsec=1000000
========================================================================
------------------------------------------------------------------------
*no patch* (avgrq-sz = 34.00 avgqu-sz=38.00)
------------------------------------------------------------------------
READ: io=10372MB, aggrb=354008KB/s, minb=354008KB/s, maxb=354008KB/s, mint=30003msec, maxt=30003msec

Disk stats (read/write):
  xvdb: ios=621760/0, *merge=1988170/0*, ticks=1136700/0, in_queue=1146020, util=99.76%

------------------------------------------------------------------------
*with patch* (avgrq-sz = 8.00 avgqu-sz=28.00)
------------------------------------------------------------------------
READ: io=2876.8MB, aggrb=98187KB/s, minb=98187KB/s, maxb=98187KB/s, mint=30002msec, maxt=30002msec

Disk stats (read/write):
  xvdb: ios=734048/0, merge=0/0, ticks=843584/0, in_queue=843080, util=99.72%