From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Subject: Re: Large latency on blk_queue_enter To: =?UTF-8?Q?Javier_Gonz=c3=a1lez?= References: <1656B440-3ECA-4F2B-B95C-418CF0F347E9@lightnvm.io> <20170508122738.GC5696@ming.t460p> <76E35BA3-FEC9-46D6-B36F-554F464FA9ED@lightnvm.io> <661d4b67-cf0c-a703-331b-ce24d75e782d@fb.com> <375D00C3-8B76-40FA-BB81-69829270BF5A@lightnvm.io> <576f9601-b0de-c636-8195-07e12fe99734@fb.com> <991bbc1d-1849-94d9-5787-69a630e7e10d@kernel.dk> Cc: Ming Lei , Christoph Hellwig , Dan Williams , linux-block@vger.kernel.org, Linux Kernel Mailing List , =?UTF-8?Q?Matias_Bj=c3=b8rling?= From: Jens Axboe Message-ID: <347b1a1d-de9e-509f-13c2-df0d4c427682@kernel.dk> Date: Mon, 8 May 2017 09:25:44 -0600 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8 List-ID: On 05/08/2017 09:22 AM, Javier González wrote: > > Javier > >> On 8 May 2017, at 17.14, Jens Axboe wrote: >> >> On 05/08/2017 09:08 AM, Jens Axboe wrote: >>> On 05/08/2017 09:02 AM, Javier González wrote: >>>>> On 8 May 2017, at 16.52, Jens Axboe wrote: >>>>> >>>>> On 05/08/2017 08:46 AM, Javier González wrote: >>>>>>> On 8 May 2017, at 16.23, Jens Axboe wrote: >>>>>>> >>>>>>> On 05/08/2017 08:20 AM, Javier González wrote: >>>>>>>>> On 8 May 2017, at 16.13, Jens Axboe wrote: >>>>>>>>> >>>>>>>>> On 05/08/2017 07:44 AM, Javier González wrote: >>>>>>>>>>> On 8 May 2017, at 14.27, Ming Lei wrote: >>>>>>>>>>> >>>>>>>>>>> On Mon, May 08, 2017 at 01:54:58PM +0200, Javier González wrote: >>>>>>>>>>>> Hi, >>>>>>>>>>>> >>>>>>>>>>>> I find an unusual added latency(~20-30ms) on blk_queue_enter when >>>>>>>>>>>> allocating a request directly from the NVMe driver through >>>>>>>>>>>> nvme_alloc_request. I could use some help confirming that this is a bug >>>>>>>>>>>> and not an expected side effect due to something else. >>>>>>>>>>>> >>>>>>>>>>>> I can reproduce this latency consistently on LightNVM when mixing I/O >>>>>>>>>>>> from pblk and I/O sent through an ioctl using liblightnvm, but I don't >>>>>>>>>>>> see anything on the LightNVM side that could impact the request >>>>>>>>>>>> allocation. >>>>>>>>>>>> >>>>>>>>>>>> When I have a 100% read workload sent from pblk, the max. latency is >>>>>>>>>>>> constant throughout several runs at ~80us (which is normal for the media >>>>>>>>>>>> we are using at bs=4k, qd=1). All pblk I/Os reach the nvme_nvm_submit_io >>>>>>>>>>>> function on lightnvm.c., which uses nvme_alloc_request. When we send a >>>>>>>>>>>> command from user space through an ioctl, then the max latency goes up >>>>>>>>>>>> to ~20-30ms. This happens independently from the actual command >>>>>>>>>>>> (IN/OUT). I tracked down the added latency down to the call >>>>>>>>>>>> percpu_ref_tryget_live in blk_queue_enter. Seems that the queue >>>>>>>>>>>> reference counter is not released as it should through blk_queue_exit in >>>>>>>>>>>> blk_mq_alloc_request. For reference, all ioctl I/Os reach the >>>>>>>>>>>> nvme_nvm_submit_user_cmd on lightnvm.c >>>>>>>>>>>> >>>>>>>>>>>> Do you have any idea about why this might happen? I can dig more into >>>>>>>>>>>> it, but first I wanted to make sure that I am not missing any obvious >>>>>>>>>>>> assumption, which would explain the reference counter to be held for a >>>>>>>>>>>> longer time. >>>>>>>>>>> >>>>>>>>>>> You need to check if the .q_usage_counter is working at atomic mode. >>>>>>>>>>> This counter is initialized as atomic mode, and finally switchs to >>>>>>>>>>> percpu mode via percpu_ref_switch_to_percpu() in blk_register_queue(). >>>>>>>>>> >>>>>>>>>> Thanks for commenting Ming. >>>>>>>>>> >>>>>>>>>> The .q_usage_counter is not working on atomic mode. The queue is >>>>>>>>>> initialized normally through blk_register_queue() and the counter is >>>>>>>>>> switched to percpu mode, as you mentioned. As I understand it, this is >>>>>>>>>> how it should be, right? >>>>>>>>> >>>>>>>>> That is how it should be, yes. You're not running with any heavy >>>>>>>>> debugging options, like lockdep or anything like that? >>>>>>>> >>>>>>>> No lockdep, KASAN, kmemleak or any of the other usual suspects. >>>>>>>> >>>>>>>> What's interesting is that it only happens when one of the I/Os comes >>>>>>>> from user space through the ioctl. If I have several pblk instances on >>>>>>>> the same device (which would end up allocating a new request in >>>>>>>> parallel, potentially on the same core), the latency spike does not >>>>>>>> trigger. >>>>>>>> >>>>>>>> I also tried to bind the read thread and the liblightnvm thread issuing >>>>>>>> the ioctl to different cores, but it does not help... >>>>>>> >>>>>>> How do I reproduce this? Off the top of my head, and looking at the code, >>>>>>> I have no idea what is going on here. >>>>>> >>>>>> Using LightNVM and liblightnvm [1] you can reproduce it by: >>>>>> >>>>>> 1. Instantiate a pblk instance on the first channel (luns 0 - 7): >>>>>> sudo nvme lnvm create -d nvme0n1 -n test0 -t pblk -b 0 -e 7 -f >>>>>> 2. Write 5GB to the test0 block device with a normal fio script >>>>>> 3. Read 5GB to verify that latencies are good (max. ~80-90us at bs=4k, qd=1) >>>>>> 4. Re-run 3. and in parallel send a command through liblightnvm to a >>>>>> different channel. A simple command is an erase (erase block 900 on >>>>>> channel 2, lun 0): >>>>>> sudo nvm_vblk line_erase /dev/nvme0n1 2 2 0 0 900 >>>>>> >>>>>> After 4. you should see a ~25-30ms latency on the read workload. >>>>>> >>>>>> I tried to reproduce the ioctl in a more generic way to reach >>>>>> __nvme_submit_user_cmd(), but SPDK steals the whole device. Also, qemu >>>>>> is not reliable for this kind of performance testing. >>>>>> >>>>>> If you have a suggestion on how I can mix an ioctl with normal block I/O >>>>>> read on a standard NVMe device, I'm happy to try it and see if I can >>>>>> reproduce the issue. >>>>> >>>>> Just to rule out this being any hardware related delays in processing >>>>> IO: >>>>> >>>>> 1) Does it reproduce with a simpler command, anything close to a no-op >>>>> that you can test? >>>> >>>> Yes. I tried with a 4KB read and with a fake command I drop right after >>>> allocation. >>>> >>>>> 2) What did you use to time the stall being blk_queue_enter()? >>>> >>>> I have some debug code measuring time with ktime_get() in different >>>> places in the stack, and among other places, around blk_queue_enter(). I >>>> use them then to measure max latency and expose it through sysfs. I can >>>> see that the latency peak is recorded in the probe before >>>> blk_queue_enter() and not in the one after. >>>> >>>> I also did an experiment, where the normal I/O path allocates the >>>> request with BLK_MQ_REQ_NOWAIT. When running the experiment above, the >>>> read test fails since we reach: >>>> if (nowait) >>>> return -EBUSY; >>>> >>>> in blk_queue_enter. >>> >>> OK, that's starting to make more sense, that indicates that there is indeed >>> something wrong with the refs. Does the below help? >> >> No, that can't be right, it does look balanced to begin with. >> blk_mq_alloc_request() always grabs a queue ref, and always drops it. If >> we return with a request succesfully allocated, then we have an extra >> ref on it, which is dropped when it is later freed. > > I agree, it seems more like a reference is put too late. I looked into > into the places where the reference is put, but it all seems normal. In > any case, I run it (just to see), and it did not help. > >> Something smells fishy, I'll dig a bit. > > Thanks! I continue looking into it myself; let me know if I can help > with something more specific. What exact kernel are you running? And does the device have a scheduler attached, or is it set to "none"? -- Jens Axboe