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
>>
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
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
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
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