Re: No protection on the hctx->dispatch_busy

2018-08-27 Thread Ming Lei
On Mon, Aug 27, 2018 at 03:25:50PM +0800, jianchao.wang wrote: > > > On 08/27/2018 03:00 PM, Ming Lei wrote: > > On Mon, Aug 27, 2018 at 01:56:39PM +0800, jianchao.wang wrote: > >> Hi Ming > >> > >> Currently, blk_mq_update_dispatch_busy is hooked in blk_mq_dispatch_rq_list > >> and __blk_mq_issu

Re: No protection on the hctx->dispatch_busy

2018-08-27 Thread jianchao.wang
On 08/27/2018 03:00 PM, Ming Lei wrote: > On Mon, Aug 27, 2018 at 01:56:39PM +0800, jianchao.wang wrote: >> Hi Ming >> >> Currently, blk_mq_update_dispatch_busy is hooked in blk_mq_dispatch_rq_list >> and __blk_mq_issue_directly. blk_mq_update_dispatch_busy could be invoked on >> multiple >> cp

Re: No protection on the hctx->dispatch_busy

2018-08-27 Thread Ming Lei
On Mon, Aug 27, 2018 at 01:56:39PM +0800, jianchao.wang wrote: > Hi Ming > > Currently, blk_mq_update_dispatch_busy is hooked in blk_mq_dispatch_rq_list > and __blk_mq_issue_directly. blk_mq_update_dispatch_busy could be invoked on > multiple > cpus concurrently. But there is not any protection o

No protection on the hctx->dispatch_busy

2018-08-26 Thread jianchao.wang
Hi Ming Currently, blk_mq_update_dispatch_busy is hooked in blk_mq_dispatch_rq_list and __blk_mq_issue_directly. blk_mq_update_dispatch_busy could be invoked on multiple cpus concurrently. But there is not any protection on the hctx->dispatch_busy. We cannot ensure the update on the dispatch_bus