From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Subject: Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues() To: Ming Lei Cc: Jens Axboe , linux-block@vger.kernel.org, Christoph Hellwig , Stefan Haberland , Christoph Hellwig References: <20180329114313.GC17537@ming.t460p> <20180330025340.GB12412@ming.t460p> <20180405160503.GA20818@ming.t460p> <20180405161142.GA20972@ming.t460p> <3a72f42f-db90-6092-5e1b-0579d2095daa@de.ibm.com> <20180406084106.GA8940@ming.t460p> <20180406092309.GB9605@ming.t460p> From: Christian Borntraeger Date: Fri, 6 Apr 2018 13:37:37 +0200 MIME-Version: 1.0 In-Reply-To: <20180406092309.GB9605@ming.t460p> Content-Type: text/plain; charset=utf-8 Message-Id: <60132d0b-51a8-d5dc-e6f9-6cf5f5b3d8b4@de.ibm.com> List-ID: On 04/06/2018 11:23 AM, Ming Lei wrote: > On Fri, Apr 06, 2018 at 10:51:28AM +0200, Christian Borntraeger wrote: >> >> >> On 04/06/2018 10:41 AM, Ming Lei wrote: >>> On Thu, Apr 05, 2018 at 07:39:56PM +0200, Christian Borntraeger wrote: >>>> >>>> >>>> On 04/05/2018 06:11 PM, Ming Lei wrote: >>>>>> >>>>>> Could you please apply the following patch and provide the dmesg boot log? >>>>> >>>>> And please post out the 'lscpu' log together from the test machine too. >>>> >>>> attached. >>>> >>>> As I said before this seems to go way with CONFIG_NR_CPUS=64 or smaller. >>>> We have 282 nr_cpu_ids here (max 141CPUs on that z13 with SMT2) but only 8 Cores >>>> == 16 threads. >>> >>> OK, thanks! >>> >>> The most weird thing is that hctx->next_cpu is computed as 512 since >>> nr_cpu_id is 282, and hctx->next_cpu should have pointed to one of >>> possible CPU. >>> >>> Looks like it is a s390 specific issue, since I can setup one queue >>> which has same mapping with yours: >>> >>> - nr_cpu_id is 282 >>> - CPU 0~15 is online >>> - 64 queues null_blk >>> - still run all hw queues in .complete handler >>> >>> But can't reproduce this issue at all. >>> >>> So please test the following patch, which may tell us why hctx->next_cpu >>> is computed wrong: >> >> I see things like >> >> [ 8.196907] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196910] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196912] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196913] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196914] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196915] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196916] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196916] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196917] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> [ 8.196918] wrong next_cpu 512, blk_mq_map_swqueue, first_and >> >> which is exactly what happens if the find and and operation fails (returns size of bitmap). > > Given both 'cpu_online_mask' and 'hctx->cpumask' are shown as correct > in your previous debug log, it means the following function returns > totally wrong result on S390. > > cpumask_first_and(hctx->cpumask, cpu_online_mask); > > The debugfs log shows that each hctx->cpumask includes one online > CPU(0~15). > > So looks it isn't one issue in block MQ core. So I checked further and printed the mask I think I can ignore the next_and cases. It is totally valid to get 512 here (as we might start with an offset that is already the last cpu and we need to wrap with first_and)). So the first_and and the first cases are really the interesting one. And I think the code is perfectly right, there is no bit after and for these cases: [ 3.220021] wrong next_cpu 512, blk_mq_map_swqueue, first_and [ 3.220023] 1: 0000000000010000 0000000000010000 0000000000010000 0000000000010000 0000000000010000 0000000000000000 0000000000000000 0000000000000000 [ 3.220025] 2: 000000000000ffff 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 3.220027] wrong next_cpu 512, blk_mq_map_swqueue, first_and [ 3.220028] 1: 0000000000020000 0000000000020000 0000000000020000 0000000000020000 0000000000020000 0000000000000000 0000000000000000 0000000000000000 [ 3.220030] wrong next_cpu 512, blk_mq_map_swqueue, first_and [ 3.220032] 1: 0000000000010000 0000000000010000 0000000000010000 0000000000010000 0000000000010000 0000000000000000 0000000000000000 0000000000000000 [ 3.220033] 2: 000000000000ffff 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 3.220035] wrong next_cpu 512, blk_mq_map_swqueue, first_and [ 3.220036] 2: 000000000000ffff 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 3.220037] wrong next_cpu 512, blk_mq_map_swqueue, first_and [ 3.220039] 1: 0000000000040000 0000000000040000 0000000000040000 0000000000040000 0000000000040000 0000000000000000 0000000000000000 0000000000000000 [ 3.220040] 2: 000000000000ffff 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 3.220042] wrong next_cpu 512, blk_mq_map_swqueue, first_and [ 3.220062] 1: 0000000000020000 0000000000020000 0000000000020000 0000000000020000 0000000000020000 0000000000000000 0000000000000000 0000000000000000 [ 3.220063] 2: 000000000000ffff 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 3.220064] wrong next_cpu 512, blk_mq_map_swqueue, first_and [ 3.220066] 1: 0000000000080000 0000000000080000 0000000000080000 0000000000080000 0000000000080000 0000000000000000 0000000000000000 0000000000000000 [ 3.220067] 2: 000000000000ffff 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000