From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Mon, 30 Jul 2018 06:43:24 +0800 From: Ming Lei To: Omar Sandoval Cc: Omar Sandoval , Jens Axboe , linux-block@vger.kernel.org Subject: Re: [PATCH] block/023: performance test on queue creation & cleanup Message-ID: <20180729224322.GB30770@ming.t460p> References: <20180704052956.5110-1-ming.lei@redhat.com> <20180725213314.GD16847@vader> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20180725213314.GD16847@vader> List-ID: On Wed, Jul 25, 2018 at 02:33:14PM -0700, Omar Sandoval wrote: > On Wed, Jul 04, 2018 at 01:29:56PM +0800, Ming Lei wrote: > > SCSI may have lots of channels, targets or LUNs, so it may > > take long time for creating and cleaning up queues. > > > > So introduce block/023 and uses null_blk to run this test > > on both blk-mq and legacy mode, then compare both and check > > the difference. > > > > Signed-off-by: Ming Lei > > --- > > tests/block/023 | 101 ++++++++++++++++++++++++++++++++++++++++++++++++++++ > > tests/block/023.out | 2 ++ > > 2 files changed, 103 insertions(+) > > create mode 100755 tests/block/023 > > create mode 100755 tests/block/023.out > > Hi, Ming, is this a regression test for "blk-mq: remove > synchronize_rcu() from blk_mq_del_queue_tag_set()" and "blk-mq: avoid to > synchronize rcu inside blk_cleanup_queue()"? Yeah, it is. It also shows that destroying queue may take much more time than creating queue, and seems no solution for this one now. Thanks, Ming