From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Return-Path: Sender: Tejun Heo Date: Mon, 6 Nov 2017 08:30:40 -0800 From: Tejun Heo To: Paolo Valente Cc: Jens Axboe , linux-block , Luca Miccio , Ulf Hansson , Linus Walleij , Mark Brown , dhowells@redhat.com, hpa@zytor.com, akinobu.mita@gmail.com Subject: Re: high overhead of functions blkg_*stats_* in bfq Message-ID: <20171106163040.GC3252168@devbig577.frc2.facebook.com> References: <20171018131918.GB1302522@devbig577.frc2.facebook.com> <76CAD24C-BE7A-4AE0-A207-0FDD0E6506DD@linaro.org> <83aaaeb1-2e04-33ed-193a-7d36024fc9dd@kernel.dk> <20171106150002.GY3252168@devbig577.frc2.facebook.com> <01f923d7-f263-0664-e214-3d37c63dbfaa@kernel.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: List-ID: Hello, On Mon, Nov 06, 2017 at 05:26:38PM +0100, Paolo Valente wrote: > Yes. DEBUG_BLK_CGROUP will just serve to keep the for-debugging > subset switched off even when the dynamic parameter is on. > > We'll wait for possible counter-arguments from Tejun, and then start > to work on what you propose. So, I think the only *really* required ones are io_serviced and the corresponding byte counts, which are tracked by blk-cgroup core anyway. Everything else can be hidden behind an obviously debug boot param, say, bfq.__DEBUG__extra_stats or whatever. Thanks. -- tejun