From: Gui Jianfeng <guijianfeng@cn.fujitsu.com>
To: Vivek Goyal <vgoyal@redhat.com>
Cc: linux-kernel@vger.kernel.org,
containers@lists.linux-foundation.org, dm-devel@redhat.com,
jens.axboe@oracle.com, nauman@google.com, dpshah@google.com,
lizf@cn.fujitsu.com, mikew@google.com, fchecconi@gmail.com,
paolo.valente@unimore.it, 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, righi.andrea@gmail.com,
m-ikeda@ds.jp.nec.com, jbaron@redhat.com, agk@redhat.com,
snitzer@redhat.com, akpm@linux-foundation.org,
peterz@infradead.org
Subject: Re: [PATCH 04/19] io-controller: Modify cfq to make use of flat elevator fair queuing
Date: Mon, 15 Jun 2009 16:56:50 +0800 [thread overview]
Message-ID: <4A360CD2.8060707@cn.fujitsu.com> (raw)
In-Reply-To: <1244513342-11758-5-git-send-email-vgoyal@redhat.com>
Vivek Goyal wrote:
> This patch changes cfq to use fair queuing code from elevator layer.
>
> Signed-off-by: Nauman Rafique <nauman@google.com>
> Signed-off-by: Fabio Checconi <fabio@gandalf.sssup.it>
> Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
> Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com>
> Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
> ---
> block/Kconfig.iosched | 3 +-
> block/cfq-iosched.c | 1097 +++++++++------------------------------------
> include/linux/iocontext.h | 4 -
> 3 files changed, 219 insertions(+), 885 deletions(-)
>
> diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
> index 3398134..dd5224d 100644
> --- a/block/Kconfig.iosched
> +++ b/block/Kconfig.iosched
> @@ -3,7 +3,7 @@ if BLOCK
> menu "IO Schedulers"
>
> config ELV_FAIR_QUEUING
> - bool "Elevator Fair Queuing Support"
> + bool
> default n
> ---help---
> Traditionally only cfq had notion of multiple queues and it did
> @@ -46,6 +46,7 @@ config IOSCHED_DEADLINE
>
> config IOSCHED_CFQ
> tristate "CFQ I/O scheduler"
> + select ELV_FAIR_QUEUING
> default y
> ---help---
> The CFQ I/O scheduler tries to distribute bandwidth equally
> diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
> index a55a9bd..f90c534 100644
> --- a/block/cfq-iosched.c
> +++ b/block/cfq-iosched.c
> @@ -12,7 +12,6 @@
> #include <linux/rbtree.h>
> #include <linux/ioprio.h>
> #include <linux/blktrace_api.h>
> -
> /*
> * tunables
> */
> @@ -23,15 +22,7 @@ static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
> static const int cfq_back_max = 16 * 1024;
> /* penalty of a backwards seek */
> static const int cfq_back_penalty = 2;
> -static const int cfq_slice_sync = HZ / 10;
> -static int cfq_slice_async = HZ / 25;
> static const int cfq_slice_async_rq = 2;
> -static int cfq_slice_idle = HZ / 125;
> -
> -/*
> - * offset from end of service tree
> - */
> -#define CFQ_IDLE_DELAY (HZ / 5)
>
> /*
> * below this threshold, we consider thinktime immediate
> @@ -43,7 +34,7 @@ static int cfq_slice_idle = HZ / 125;
>
> #define RQ_CIC(rq) \
> ((struct cfq_io_context *) (rq)->elevator_private)
> -#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2)
> +#define RQ_CFQQ(rq) (struct cfq_queue *) (ioq_sched_queue((rq)->ioq))
>
> static struct kmem_cache *cfq_pool;
> static struct kmem_cache *cfq_ioc_pool;
> @@ -53,8 +44,6 @@ static struct completion *ioc_gone;
> static DEFINE_SPINLOCK(ioc_gone_lock);
>
> #define CFQ_PRIO_LISTS IOPRIO_BE_NR
> -#define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
> -#define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
>
> #define sample_valid(samples) ((samples) > 80)
>
> @@ -75,12 +64,6 @@ struct cfq_rb_root {
> */
> struct cfq_data {
> struct request_queue *queue;
> -
> - /*
> - * rr list of queues with requests and the count of them
> - */
> - struct cfq_rb_root service_tree;
> -
> /*
> * Each priority tree is sorted by next_request position. These
> * trees are used when determining if two or more queues are
> @@ -88,39 +71,10 @@ struct cfq_data {
> */
> struct rb_root prio_trees[CFQ_PRIO_LISTS];
>
> - unsigned int busy_queues;
> - /*
> - * Used to track any pending rt requests so we can pre-empt current
> - * non-RT cfqq in service when this value is non-zero.
> - */
> - unsigned int busy_rt_queues;
> -
> - int rq_in_driver;
> int sync_flight;
>
> - /*
> - * queue-depth detection
> - */
> - int rq_queued;
> - int hw_tag;
> - int hw_tag_samples;
> - int rq_in_driver_peak;
> -
> - /*
> - * idle window management
> - */
> - struct timer_list idle_slice_timer;
> - struct work_struct unplug_work;
> -
> - struct cfq_queue *active_queue;
> struct cfq_io_context *active_cic;
>
> - /*
> - * async queue for each priority case
> - */
> - struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR];
> - struct cfq_queue *async_idle_cfqq;
> -
> sector_t last_position;
> unsigned long last_end_request;
>
> @@ -131,9 +85,7 @@ struct cfq_data {
> unsigned int cfq_fifo_expire[2];
> unsigned int cfq_back_penalty;
> unsigned int cfq_back_max;
> - unsigned int cfq_slice[2];
> unsigned int cfq_slice_async_rq;
> - unsigned int cfq_slice_idle;
>
> struct list_head cic_list;
> };
> @@ -142,16 +94,11 @@ struct cfq_data {
> * Per process-grouping structure
> */
> struct cfq_queue {
> - /* reference count */
> - atomic_t ref;
> + struct io_queue *ioq;
> /* various state flags, see below */
> unsigned int flags;
> /* parent cfq_data */
> struct cfq_data *cfqd;
> - /* service_tree member */
> - struct rb_node rb_node;
> - /* service_tree key */
> - unsigned long rb_key;
> /* prio tree member */
> struct rb_node p_node;
> /* prio tree root we belong to, if any */
> @@ -167,33 +114,23 @@ struct cfq_queue {
> /* fifo list of requests in sort_list */
> struct list_head fifo;
>
> - unsigned long slice_end;
> - long slice_resid;
> unsigned int slice_dispatch;
>
> /* pending metadata requests */
> int meta_pending;
> - /* number of requests that are on the dispatch list or inside driver */
> - int dispatched;
>
> /* io prio of this group */
> - unsigned short ioprio, org_ioprio;
> - unsigned short ioprio_class, org_ioprio_class;
> + unsigned short org_ioprio;
> + unsigned short org_ioprio_class;
>
> pid_t pid;
> };
>
> enum cfqq_state_flags {
> - CFQ_CFQQ_FLAG_on_rr = 0, /* on round-robin busy list */
> - CFQ_CFQQ_FLAG_wait_request, /* waiting for a request */
> - CFQ_CFQQ_FLAG_must_dispatch, /* must be allowed a dispatch */
> CFQ_CFQQ_FLAG_must_alloc, /* must be allowed rq alloc */
> CFQ_CFQQ_FLAG_must_alloc_slice, /* per-slice must_alloc flag */
> CFQ_CFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */
> - CFQ_CFQQ_FLAG_idle_window, /* slice idling enabled */
> CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */
> - CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */
> - CFQ_CFQQ_FLAG_sync, /* synchronous queue */
> CFQ_CFQQ_FLAG_coop, /* has done a coop jump of the queue */
> };
>
> @@ -211,16 +148,10 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq) \
> return ((cfqq)->flags & (1 << CFQ_CFQQ_FLAG_##name)) != 0; \
> }
>
> -CFQ_CFQQ_FNS(on_rr);
> -CFQ_CFQQ_FNS(wait_request);
> -CFQ_CFQQ_FNS(must_dispatch);
> CFQ_CFQQ_FNS(must_alloc);
> CFQ_CFQQ_FNS(must_alloc_slice);
> CFQ_CFQQ_FNS(fifo_expire);
> -CFQ_CFQQ_FNS(idle_window);
> CFQ_CFQQ_FNS(prio_changed);
> -CFQ_CFQQ_FNS(slice_new);
> -CFQ_CFQQ_FNS(sync);
> CFQ_CFQQ_FNS(coop);
> #undef CFQ_CFQQ_FNS
>
> @@ -259,66 +190,32 @@ static inline int cfq_bio_sync(struct bio *bio)
> return 0;
> }
>
> -/*
> - * scheduler run of queue, if there are requests pending and no one in the
> - * driver that will restart queueing
> - */
> -static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
> +static inline struct io_group *cfqq_to_io_group(struct cfq_queue *cfqq)
> {
> - if (cfqd->busy_queues) {
> - cfq_log(cfqd, "schedule dispatch");
> - kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
> - }
> + return ioq_to_io_group(cfqq->ioq);
> }
>
> -static int cfq_queue_empty(struct request_queue *q)
> +static inline int cfq_class_idle(struct cfq_queue *cfqq)
> {
> - struct cfq_data *cfqd = q->elevator->elevator_data;
> -
> - return !cfqd->busy_queues;
> + return elv_ioq_class_idle(cfqq->ioq);
> }
>
> -/*
> - * Scale schedule slice based on io priority. Use the sync time slice only
> - * if a queue is marked sync and has sync io queued. A sync queue with async
> - * io only, should not get full sync slice length.
> - */
> -static inline int cfq_prio_slice(struct cfq_data *cfqd, int sync,
> - unsigned short prio)
> -{
> - const int base_slice = cfqd->cfq_slice[sync];
> -
> - WARN_ON(prio >= IOPRIO_BE_NR);
> -
> - return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
> -}
> -
> -static inline int
> -cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
> +static inline int cfq_class_rt(struct cfq_queue *cfqq)
> {
> - return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
> + return elv_ioq_class_rt(cfqq->ioq);
> }
Hi Vivek,
cfq_class_rt isn't needed now, clean it up.
Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com>
---
block/cfq-iosched.c | 5 -----
1 files changed, 0 insertions(+), 5 deletions(-)
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 705e7ba..23b24b9 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -234,11 +234,6 @@ static inline int cfq_class_idle(struct cfq_queue *cfqq)
return elv_ioq_class_idle(cfqq->ioq);
}
-static inline int cfq_class_rt(struct cfq_queue *cfqq)
-{
- return elv_ioq_class_rt(cfqq->ioq);
-}
-
static inline int cfq_cfqq_sync(struct cfq_queue *cfqq)
{
return elv_ioq_sync(cfqq->ioq);
--
1.5.4.rc3
next prev parent reply other threads:[~2009-06-15 8:59 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-09 2:08 [RFC] IO scheduler based IO controller V4 Vivek Goyal
2009-06-09 2:08 ` [PATCH 01/19] io-controller: Documentation Vivek Goyal
2009-06-09 2:08 ` [PATCH 02/19] io-controller: Common flat fair queuing code in elevaotor layer Vivek Goyal
2009-06-09 8:45 ` Gui Jianfeng
2009-06-16 3:54 ` Gui Jianfeng
2009-06-16 13:02 ` Vivek Goyal
2009-06-16 19:44 ` Divyesh Shah
2009-06-17 12:59 ` Vivek Goyal
2009-06-09 2:08 ` [PATCH 03/19] io-controller: Charge for time slice based on average disk rate Vivek Goyal
2009-06-09 2:08 ` [PATCH 04/19] io-controller: Modify cfq to make use of flat elevator fair queuing Vivek Goyal
2009-06-11 6:12 ` Gui Jianfeng
2009-06-11 14:21 ` Vivek Goyal
2009-06-15 8:56 ` Gui Jianfeng [this message]
2009-06-15 13:02 ` Vivek Goyal
2009-06-17 2:22 ` Gui Jianfeng
2009-06-17 13:00 ` Vivek Goyal
2009-06-09 2:08 ` [PATCH 05/19] io-controller: Common hierarchical fair queuing code in elevaotor layer Vivek Goyal
2009-06-09 2:08 ` [PATCH 06/19] io-controller: cfq changes to use " Vivek Goyal
2009-06-09 2:08 ` [PATCH 07/19] io-controller: Export disk time used and nr sectors dipatched through cgroups Vivek Goyal
2009-06-09 2:08 ` [PATCH 08/19] io-controller: idle for sometime on sync queue before expiring it Vivek Goyal
2009-06-09 2:08 ` [PATCH 09/19] io-controller: Separate out queue and data Vivek Goyal
2009-06-09 2:08 ` [PATCH 10/19] io-conroller: Prepare elevator layer for single queue schedulers Vivek Goyal
2009-06-11 8:10 ` Gui Jianfeng
2009-06-11 14:41 ` Vivek Goyal
2009-06-12 0:37 ` Gui Jianfeng
2009-06-15 13:00 ` Vivek Goyal
2009-06-09 2:08 ` [PATCH 11/19] io-controller: noop changes for hierarchical fair queuing Vivek Goyal
2009-06-09 2:08 ` [PATCH 12/19] io-controller: deadline " Vivek Goyal
2009-06-09 2:08 ` [PATCH 13/19] io-controller: anticipatory " Vivek Goyal
2009-06-09 2:08 ` [PATCH 14/19] blkio_cgroup patches from Ryo to track async bios Vivek Goyal
2009-06-09 2:08 ` [PATCH 15/19] io-controller: map async requests to appropriate cgroup Vivek Goyal
2009-06-17 9:17 ` Gui Jianfeng
2009-06-17 13:00 ` Vivek Goyal
2009-06-09 2:08 ` [PATCH 16/19] io-controller: Per cgroup request descriptor support Vivek Goyal
2009-06-09 2:09 ` [PATCH 17/19] io-controller: Support per cgroup per device weights and io class Vivek Goyal
2009-06-10 7:44 ` Gui Jianfeng
2009-06-10 13:22 ` Vivek Goyal
2009-06-09 2:09 ` [PATCH 18/19] io-controller: Debug hierarchical IO scheduling Vivek Goyal
2009-06-19 1:40 ` Gui Jianfeng
2009-06-19 14:05 ` Vivek Goyal
2009-06-19 6:26 ` Gui Jianfeng
2009-06-19 14:08 ` Vivek Goyal
2009-06-09 2:09 ` [PATCH 19/19] io-controller: experimental debug patch for async queue wait before expiry Vivek Goyal
2009-06-09 4:22 ` [RFC] IO scheduler based IO controller V4 Gui Jianfeng
2009-06-09 13:52 ` Vivek Goyal
2009-06-10 1:05 ` Gui Jianfeng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4A360CD2.8060707@cn.fujitsu.com \
--to=guijianfeng@cn.fujitsu.com \
--cc=agk@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=balbir@linux.vnet.ibm.com \
--cc=containers@lists.linux-foundation.org \
--cc=dhaval@linux.vnet.ibm.com \
--cc=dm-devel@redhat.com \
--cc=dpshah@google.com \
--cc=fchecconi@gmail.com \
--cc=fernando@oss.ntt.co.jp \
--cc=jbaron@redhat.com \
--cc=jens.axboe@oracle.com \
--cc=jmoyer@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lizf@cn.fujitsu.com \
--cc=m-ikeda@ds.jp.nec.com \
--cc=mikew@google.com \
--cc=nauman@google.com \
--cc=paolo.valente@unimore.it \
--cc=peterz@infradead.org \
--cc=righi.andrea@gmail.com \
--cc=ryov@valinux.co.jp \
--cc=s-uchida@ap.jp.nec.com \
--cc=snitzer@redhat.com \
--cc=taka@valinux.co.jp \
--cc=vgoyal@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox