From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1762576AbZENC0U (ORCPT ); Wed, 13 May 2009 22:26:20 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754287AbZENC0H (ORCPT ); Wed, 13 May 2009 22:26:07 -0400 Received: from cn.fujitsu.com ([222.73.24.84]:65221 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1752705AbZENC0E (ORCPT ); Wed, 13 May 2009 22:26:04 -0400 Message-ID: <4A0B8100.1090007@cn.fujitsu.com> Date: Thu, 14 May 2009 10:25:04 +0800 From: Gui Jianfeng User-Agent: Thunderbird 2.0.0.5 (Windows/20070716) MIME-Version: 1.0 To: Vivek Goyal CC: nauman@google.com, dpshah@google.com, lizf@cn.fujitsu.com, mikew@google.com, fchecconi@gmail.com, paolo.valente@unimore.it, jens.axboe@oracle.com, ryov@valinux.co.jp, fernando@oss.ntt.co.jp, s-uchida@ap.jp.nec.com, taka@valinux.co.jp, jmoyer@redhat.com, dhaval@linux.vnet.ibm.com, balbir@linux.vnet.ibm.com, linux-kernel@vger.kernel.org, containers@lists.linux-foundation.org, righi.andrea@gmail.com, agk@redhat.com, dm-devel@redhat.com, snitzer@redhat.com, m-ikeda@ds.jp.nec.com, akpm@linux-foundation.org Subject: Re: [PATCH] IO Controller: Add per-device weight and ioprio_class handling References: <1241553525-28095-1-git-send-email-vgoyal@redhat.com> <4A0A29B5.7030109@cn.fujitsu.com> <20090513155900.GA15623@redhat.com> In-Reply-To: <20090513155900.GA15623@redhat.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Vivek Goyal wrote: ... > Hi Gui, > > It might make sense to also store the device name or device major and > minor number in io_group while creating the io group. This will help us > to display io.disk_time and io.disk_sector statistics per device instead > of aggregate. > > I am attaching a patch I was playing around with to display per device > statistics instead of aggregate one. So if user has specified the per > device rule. > > Thanks > Vivek > > > o Currently the statistics exported through cgroup are aggregate of statistics > on all devices for that cgroup. Instead of aggregate, make these per device. > > o Also export another statistics io.disk_dequeue. This keeps a count of how > many times a particular group got out of race for the disk. This is a > debugging aid to keep a track how often we could create continuously > backlogged queues. > > Signed-off-by: Vivek Goyal > --- > block/elevator-fq.c | 127 +++++++++++++++++++++++++++++++++------------------- > block/elevator-fq.h | 3 + > 2 files changed, 85 insertions(+), 45 deletions(-) > > Index: linux14/block/elevator-fq.h > =================================================================== > --- linux14.orig/block/elevator-fq.h 2009-05-13 11:40:32.000000000 -0400 > +++ linux14/block/elevator-fq.h 2009-05-13 11:40:57.000000000 -0400 > @@ -250,6 +250,9 @@ struct io_group { > > #ifdef CONFIG_DEBUG_GROUP_IOSCHED > unsigned short iocg_id; > + dev_t dev; > + /* How many times this group has been removed from active tree */ > + unsigned long dequeue; > #endif > }; > > Index: linux14/block/elevator-fq.c > =================================================================== > --- linux14.orig/block/elevator-fq.c 2009-05-13 11:40:53.000000000 -0400 > +++ linux14/block/elevator-fq.c 2009-05-13 11:40:57.000000000 -0400 > @@ -12,6 +12,7 @@ > #include "elevator-fq.h" > #include > #include > +#include > > /* Values taken from cfq */ > const int elv_slice_sync = HZ / 10; > @@ -758,6 +759,18 @@ int __bfq_deactivate_entity(struct io_en > BUG_ON(sd->active_entity == entity); > BUG_ON(sd->next_active == entity); > > +#ifdef CONFIG_DEBUG_GROUP_IOSCHED > + { > + struct io_group *iog = io_entity_to_iog(entity); > + /* > + * Keep track of how many times a group has been removed > + * from active tree because it did not have any active > + * backlogged ioq under it > + */ > + if (iog) > + iog->dequeue++; > + } > +#endif > return ret; > } > > @@ -1126,90 +1139,103 @@ STORE_FUNCTION(weight, 0, WEIGHT_MAX); > STORE_FUNCTION(ioprio_class, IOPRIO_CLASS_RT, IOPRIO_CLASS_IDLE); > #undef STORE_FUNCTION > > -/* > - * traverse through all the io_groups associated with this cgroup and calculate > - * the aggr disk time received by all the groups on respective disks. > - */ > -static u64 calculate_aggr_disk_time(struct io_cgroup *iocg) > +static int io_cgroup_disk_time_read(struct cgroup *cgroup, > + struct cftype *cftype, struct seq_file *m) > { > + struct io_cgroup *iocg; > struct io_group *iog; > struct hlist_node *n; > - u64 disk_time = 0; > + > + if (!cgroup_lock_live_group(cgroup)) > + return -ENODEV; > + > + iocg = cgroup_to_io_cgroup(cgroup); > > rcu_read_lock(); > + spin_lock_irq(&iocg->lock); > hlist_for_each_entry_rcu(iog, n, &iocg->group_data, group_node) { > /* > * There might be groups which are not functional and > * waiting to be reclaimed upon cgoup deletion. > */ > - if (rcu_dereference(iog->key)) > - disk_time += iog->entity.total_service; > + if (rcu_dereference(iog->key)) { > + seq_printf(m, "%u %u %lu\n", MAJOR(iog->dev), > + MINOR(iog->dev), > + iog->entity.total_service); Hi Vivek, I think it's easier for users if device name is also shown here. > + } > } > + spin_unlock_irq(&iocg->lock); > rcu_read_unlock(); > > - return disk_time; > + cgroup_unlock(); > + > + return 0; > } > -- Regards Gui Jianfeng