From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tejun Heo Subject: Re: [PATCH] cgroups: Do not show inactive devices in cgroups statistics Date: Wed, 26 Jun 2013 18:23:47 -0700 Message-ID: <20130627012347.GH4536@htj.dyndns.org> References: <1372274770-30679-1-git-send-email-anatol.pomozov@gmail.com> <20130626204540.GA4536@htj.dyndns.org> <20130626210820.GA17564@redhat.com> <20130627012304.GG4536@htj.dyndns.org> Mime-Version: 1.0 Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:date:from:to:cc:subject:message-id:references:mime-version :content-type:content-disposition:in-reply-to:user-agent; bh=GcIA8hGkPBi4NTj2e/Pk7jF+5FJiHuvOWda8JvYV8yg=; b=uWVF0umlj7EstGCwm/+X6FoFTDvgUz7FojkU0/aYZ7fFKE6iTLdTNv3sWZzOa1xdWn dvUaN43MFcsmqqmukiUV68DEA3ip4yBCxcn2/FZUkg3mBEqJ/oAnkkcIg5kBBkGKYaOJ S0mOoE0AILa7RwiIUK891Dsv8qeNHanaTcZ2RLoLrTaRwRfRJ6Ai0aHFTH2QSRHeC+J7 2qBtkFMpTpISovTKDh6uhiuFgUE3hODzLaQdR07ywvHwThHIiYWP6iOpsIq4vtTjElGV SVfqvC2eCqjyvVp8YaeXjuUP8vBDzxG7UzKklUAoUZXa7jCvoVGAVJ5dVbVoglQkAdBS gKCQ== Content-Disposition: inline In-Reply-To: <20130627012304.GG4536-Gd/HAXX7CRxy/B6EtB590w@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Anatol Pomozov Cc: Vivek Goyal , Cgroups , Jens Axboe On Wed, Jun 26, 2013 at 06:23:04PM -0700, Tejun Heo wrote: > Hello, > > On Wed, Jun 26, 2013 at 05:37:38PM -0700, Anatol Pomozov wrote: > > Bottom line: when we set weight for a device then it creates cfq_group > > and initializes device stats with zero. Later that zero stat is shown > > even if no activity happened on the device. Both CFQ and our custom IO > > scheduler have this problem. And because we write set weight for all > > devices in all cgroups we endup with a lot of zero useless stats. > > > > What is the right fix in this situation? > > Yeah, I think yours is fine. You're just configuring each blkg during > init. Please just update the u64 case and repost. BTW, if there are a lot of users which ignore 0 u64, it may be cleaner to introduce a wrapper around the existing prfill. Thanks. -- tejun