Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756238Ab0DFPaS (ORCPT ); Tue, 6 Apr 2010 11:30:18 -0400 Received: from mx1.redhat.com ([209.132.183.28]:29658 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755528Ab0DFPaP (ORCPT ); Tue, 6 Apr 2010 11:30:15 -0400 Date: Tue, 6 Apr 2010 11:30:01 -0400 From: Vivek Goyal To: Divyesh Shah Cc: jens.axboe@oracle.com, linux-kernel@vger.kernel.org, nauman@google.com, ctalbott@google.com Subject: Re: [PATCH 3/3][v3] blkio: Increment the blkio cgroup stats for real now. Message-ID: <20100406153001.GC3029@redhat.com> References: <20100406032630.23464.24685.stgit@austin.mtv.corp.google.com> <20100406033706.23464.76477.stgit@austin.mtv.corp.google.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100406033706.23464.76477.stgit@austin.mtv.corp.google.com> User-Agent: Mutt/1.5.19 (2009-01-05) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 9957 Lines: 281 On Mon, Apr 05, 2010 at 08:37:38PM -0700, Divyesh Shah wrote: > We also add start_time_ns and io_start_time_ns fields to struct request > here to record the time when a request is created and when it is > dispatched to device. We use ns uints here as ms and jiffies are > not very useful for non-rotational media. > > Signed-off-by: Divyesh Shah Looks good to me. Acked-by: Vivek Goyal Vivek > --- > > block/blk-cgroup.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++-- > block/blk-cgroup.h | 15 ++++++++++-- > block/blk-core.c | 6 +++-- > block/cfq-iosched.c | 7 +++++- > include/linux/blkdev.h | 38 +++++++++++++++++++++++++++++++ > 5 files changed, 115 insertions(+), 9 deletions(-) > > diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c > index d585a05..8bd607c 100644 > --- a/block/blk-cgroup.c > +++ b/block/blk-cgroup.c > @@ -15,6 +15,7 @@ > #include > #include > #include > +#include > #include "blk-cgroup.h" > > #define MAX_KEY_LEN 100 > @@ -63,6 +64,23 @@ void blkio_group_init(struct blkio_group *blkg) > } > EXPORT_SYMBOL_GPL(blkio_group_init); > > +/* > + * Add to the appropriate stat variable depending on the request type. > + * This should be called with the blkg->stats_lock held. > + */ > +static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction, > + bool sync) > +{ > + if (direction) > + stat[BLKIO_STAT_WRITE] += add; > + else > + stat[BLKIO_STAT_READ] += add; > + if (sync) > + stat[BLKIO_STAT_SYNC] += add; > + else > + stat[BLKIO_STAT_ASYNC] += add; > +} > + > void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) > { > unsigned long flags; > @@ -73,6 +91,42 @@ void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) > } > EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used); > > +void blkiocg_update_dispatch_stats(struct blkio_group *blkg, > + uint64_t bytes, bool direction, bool sync) > +{ > + struct blkio_group_stats *stats; > + unsigned long flags; > + > + spin_lock_irqsave(&blkg->stats_lock, flags); > + stats = &blkg->stats; > + stats->sectors += bytes >> 9; > + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction, > + sync); > + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes, > + direction, sync); > + spin_unlock_irqrestore(&blkg->stats_lock, flags); > +} > +EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats); > + > +void blkiocg_update_completion_stats(struct blkio_group *blkg, > + uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) > +{ > + struct blkio_group_stats *stats; > + unsigned long flags; > + unsigned long long now = sched_clock(); > + > + spin_lock_irqsave(&blkg->stats_lock, flags); > + stats = &blkg->stats; > + if (time_after64(now, io_start_time)) > + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME], > + now - io_start_time, direction, sync); > + if (time_after64(io_start_time, start_time)) > + blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME], > + io_start_time - start_time, direction, sync); > + spin_unlock_irqrestore(&blkg->stats_lock, flags); > +} > +EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats); > + > void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, > struct blkio_group *blkg, void *key, dev_t dev) > { > @@ -315,12 +369,12 @@ SHOW_FUNCTION_PER_GROUP(dequeue, BLKIO_STAT_DEQUEUE, 0); > #undef SHOW_FUNCTION_PER_GROUP > > #ifdef CONFIG_DEBUG_BLK_CGROUP > -void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, > +void blkiocg_update_dequeue_stats(struct blkio_group *blkg, > unsigned long dequeue) > { > blkg->stats.dequeue += dequeue; > } > -EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats); > +EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats); > #endif > > struct cftype blkio_files[] = { > diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h > index a4bc4bb..b22e553 100644 > --- a/block/blk-cgroup.h > +++ b/block/blk-cgroup.h > @@ -125,12 +125,12 @@ static inline char *blkg_path(struct blkio_group *blkg) > { > return blkg->path; > } > -void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, > +void blkiocg_update_dequeue_stats(struct blkio_group *blkg, > unsigned long dequeue); > #else > static inline char *blkg_path(struct blkio_group *blkg) { return NULL; } > -static inline void blkiocg_update_blkio_group_dequeue_stats( > - struct blkio_group *blkg, unsigned long dequeue) {} > +static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg, > + unsigned long dequeue) {} > #endif > > #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) > @@ -144,6 +144,10 @@ extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, > void blkio_group_init(struct blkio_group *blkg); > void blkiocg_update_timeslice_used(struct blkio_group *blkg, > unsigned long time); > +void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes, > + bool direction, bool sync); > +void blkiocg_update_completion_stats(struct blkio_group *blkg, > + uint64_t start_time, uint64_t io_start_time, bool direction, bool sync); > #else > struct cgroup; > static inline struct blkio_cgroup * > @@ -160,5 +164,10 @@ static inline struct blkio_group * > blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; } > static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg, > unsigned long time) {} > +static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg, > + uint64_t bytes, bool direction, bool sync) {} > +static inline void blkiocg_update_completion_stats(struct blkio_group *blkg, > + uint64_t start_time, uint64_t io_start_time, bool direction, > + bool sync) {} > #endif > #endif /* _BLK_CGROUP_H */ > diff --git a/block/blk-core.c b/block/blk-core.c > index 9fe174d..1d94f15 100644 > --- a/block/blk-core.c > +++ b/block/blk-core.c > @@ -127,6 +127,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq) > rq->tag = -1; > rq->ref_count = 1; > rq->start_time = jiffies; > + set_start_time_ns(rq); > } > EXPORT_SYMBOL(blk_rq_init); > > @@ -1855,8 +1856,10 @@ void blk_dequeue_request(struct request *rq) > * and to it is freed is accounted as io that is in progress at > * the driver side. > */ > - if (blk_account_rq(rq)) > + if (blk_account_rq(rq)) { > q->in_flight[rq_is_sync(rq)]++; > + set_io_start_time_ns(rq); > + } > } > > /** > @@ -2517,4 +2520,3 @@ int __init blk_dev_init(void) > > return 0; > } > - > diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c > index cf11548..9102ffc 100644 > --- a/block/cfq-iosched.c > +++ b/block/cfq-iosched.c > @@ -854,7 +854,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg) > if (!RB_EMPTY_NODE(&cfqg->rb_node)) > cfq_rb_erase(&cfqg->rb_node, st); > cfqg->saved_workload_slice = 0; > - blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1); > + blkiocg_update_dequeue_stats(&cfqg->blkg, 1); > } > > static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq) > @@ -1865,6 +1865,8 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) > elv_dispatch_sort(q, rq); > > cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++; > + blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq), > + rq_data_dir(rq), rq_is_sync(rq)); > } > > /* > @@ -3285,6 +3287,9 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) > WARN_ON(!cfqq->dispatched); > cfqd->rq_in_driver--; > cfqq->dispatched--; > + blkiocg_update_completion_stats(&cfqq->cfqg->blkg, rq_start_time_ns(rq), > + rq_io_start_time_ns(rq), rq_data_dir(rq), > + rq_is_sync(rq)); > > cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; > > diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h > index ebd22db..ac1f30d 100644 > --- a/include/linux/blkdev.h > +++ b/include/linux/blkdev.h > @@ -193,7 +193,10 @@ struct request { > > struct gendisk *rq_disk; > unsigned long start_time; > - > +#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) > + unsigned long long start_time_ns; > + unsigned long long io_start_time_ns; /* when passed to hardware */ > +#endif > /* Number of scatter-gather DMA addr+len pairs after > * physical address coalescing is performed. > */ > @@ -1219,6 +1222,39 @@ static inline void put_dev_sector(Sector p) > struct work_struct; > int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); > > +#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) > +static inline void set_start_time_ns(struct request *req) > +{ > + req->start_time_ns = sched_clock(); > +} > + > +static inline void set_io_start_time_ns(struct request *req) > +{ > + req->io_start_time_ns = sched_clock(); > +} > + > +static inline uint64_t rq_start_time_ns(struct request *req) > +{ > + return req->start_time_ns; > +} > + > +static inline uint64_t rq_io_start_time_ns(struct request *req) > +{ > + return req->io_start_time_ns; > +} > +#else > +static inline void set_start_time_ns(struct request *req) {} > +static inline void set_io_start_time_ns(struct request *req) {} > +static inline uint64_t rq_start_time_ns(struct request *req) > +{ > + return 0; > +} > +static inline uint64_t rq_io_start_time_ns(struct request *req) > +{ > + return 0; > +} > +#endif > + > #define MODULE_ALIAS_BLOCKDEV(major,minor) \ > MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) > #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/