Re: softirq->blk_mq_make_request deadlocks

On Tue, May 22, 2018 at 10:44 AM, Jens Axboe wrote: > Please don't top post, thanks. > > On 5/22/18 8:36 AM, Vitaly Mayatskih wrote: >> I submit with BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, that never >> locked in my testing done on a couple of different configurations. Of >>

Re: softirq->blk_mq_make_request deadlocks

Please don't top post, thanks. On 5/22/18 8:36 AM, Vitaly Mayatskih wrote: > I submit with BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, that never > locked in my testing done on a couple of different configurations. Of > course, it does not say it won't lock elsewhere ;) BLK_MQ_REQ_RESERVED is not

Re: softirq->blk_mq_make_request deadlocks

I submit with BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, that never locked in my testing done on a couple of different configurations. Of course, it does not say it won't lock elsewhere ;) Unfortunately any queuing is chewing up performance, so I'm trying to find ways around. On Tue, May 22, 2018

Re: softirq->blk_mq_make_request deadlocks

On 5/22/18 8:29 AM, Vitaly Mayatskih wrote: > Hi, > > I'm working on a new network block device and see occasional deadlocks > when trying to submit_bio from softirq (network rcv handler). This may > be a new use case for blk-mq, but I think context spinlock should be > really taken with bh

softirq->blk_mq_make_request deadlocks

Hi, I'm working on a new network block device and see occasional deadlocks when trying to submit_bio from softirq (network rcv handler). This may be a new use case for blk-mq, but I think context spinlock should be really taken with bh disabled. I *seem* can avoid the deadlock if bio has