Re: [bug report] shared tags causes IO hang and performance drop

From: Douglas Gilbert <dgilbert@interlog.com>
To: Bart Van Assche <bvanassche@acm.org>,
	John Garry <john.garry@huawei.com>,
	Ming Lei <ming.lei@redhat.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>,
	linux-block@vger.kernel.org, linux-scsi@vger.kernel.org,
	"Martin K. Petersen" <martin.petersen@oracle.com>,
	Jens Axboe <axboe@kernel.dk>
Subject: Re: [bug report] shared tags causes IO hang and performance drop
Date: Tue, 20 Apr 2021 00:54:49 -0400	[thread overview]
Message-ID: <993c3ae5-a7e2-aa6d-a6f3-147f06e9d015@interlog.com> (raw)
In-Reply-To: <f9b143ac-c5df-eedc-13da-8e0c2399abb4@acm.org>

On 2021-04-19 11:22 p.m., Bart Van Assche wrote:
> On 4/19/21 8:06 PM, Douglas Gilbert wrote:
>> I have always suspected under extreme pressure the block layer (or scsi
>> mid-level) does strange things, like an IO hang, attempts to prove that
>> usually lead back to my own code :-). But I have one example recently
>> where upwards of 10 commands had been submitted (blk_execute_rq_nowait())
>> and the following one stalled (all on the same thread). Seconds later
>> those 10 commands reported DID_TIME_OUT, the stalled thread awoke, and
>> my dd variant went to its conclusion (reporting 10 errors). Following
>> copies showed no ill effects.
>>
>> My weapons of choice are sg_dd, actually sgh_dd and sg_mrq_dd. Those last
>> two monitor for stalls during the copy. Each submitted READ and WRITE
>> command gets its pack_id from an incrementing atomic and a management
>> thread in those copies checks every 300 milliseconds that that atomic
>> value is greater than the previous check. If not, dump the state of the
>> sg driver. The stalled request was in busy state with a timeout of 1
>> nanosecond which indicated that blk_execute_rq_nowait() had not been
>> called. So the chief suspect would be blk_get_request() followed by
>> the bio setup calls IMO.
>>
>> So it certainly looked like an IO hang, not a locking, resource nor
>> corruption issue IMO. That was with a branch off MKP's
>> 5.13/scsi-staging branch taken a few weeks back. So basically
>> lk 5.12.0-rc1 .
> 
> Hi Doug,
> 
> If it would be possible to develop a script that reproduces this hang and
> if that script can be shared I will help with root-causing and fixing this
> hang.

Possible, but not very practical:
    1) apply supplied 83 patches to sg driver
    2) apply pending patch to scsi_debug driver
    3) find a stable kernel platform (perhaps not lk 5.12.0-rc1)
    4) run supplied scripts for three weeks
    5) dig through the output and maybe find one case (there were lots
       of EAGAINs from blk_get_request() but they are expected when
       thrashing the storage layers)

My basic testing strategy may be useful for others:
     sg_dd iflag=random bs=512 of=/dev/sg6
     sg_dd if=/dev/sg6 bs=512 of=/dev/sg7
     sg_dd --verify if=/dev/sg6 bs=512 of=/dev/sg7

If the copy works, so should the verify (compare). The sg_dd utility in
sg3_utils release 1.46 is needed to support iflag=random in the first
line and the --verify in the third line.

If the backing LLD is scsi_debug, then per_host_store=1 is needed. Best
not to use SSDs. The above pattern will work just as well for /dev/sd*
device nodes, but iflag= and oflag= lists must contain the sgio flag.
Then ioctl(/dev/sd*, SG_IO, ...) is used for IO. The limitations of the
third line could be bypassed with something like:
     cmp /dev/sd6 /dev/sd7

If real disks are used, all user data will be trashed.

Doug Gilbert