From: Vivek Goyal <vgoyal@redhat.com>
To: linux-kernel@vger.kernel.org, axboe@kernel.dk
Cc: nauman@google.com, dpshah@google.com, guijianfeng@cn.fujitsu.com,
jmoyer@redhat.com, czoccolo@gmail.com, vgoyal@redhat.com
Subject: [PATCH 2/3] cfq-iosched: Implement a tunable group_idle
Date: Wed, 21 Jul 2010 15:06:20 -0400 [thread overview]
Message-ID: <1279739181-24482-3-git-send-email-vgoyal@redhat.com> (raw)
In-Reply-To: <1279739181-24482-1-git-send-email-vgoyal@redhat.com>
o Implement a new tunable group_idle, which allows idling on the group
instead of a cfq queue. Hence one can set slice_idle = 0 and not idle
on the individual queues but idle on the group. This way on fast storage
we can get fairness between groups at the same time overall throughput
improves.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
---
block/cfq-iosched.c | 60 +++++++++++++++++++++++++++++++++++++++++++++------
1 files changed, 53 insertions(+), 7 deletions(-)
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 4671c51..8ca5c39 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -30,6 +30,7 @@ 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;
+static int cfq_group_idle = HZ / 125;
static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
static const int cfq_hist_divisor = 4;
@@ -198,6 +199,8 @@ struct cfq_group {
struct hlist_node cfqd_node;
atomic_t ref;
#endif
+ /* number of requests that are on the dispatch list or inside driver */
+ int dispatched;
};
/*
@@ -271,6 +274,7 @@ struct cfq_data {
unsigned int cfq_slice[2];
unsigned int cfq_slice_async_rq;
unsigned int cfq_slice_idle;
+ unsigned int cfq_group_idle;
unsigned int cfq_latency;
unsigned int cfq_group_isolation;
@@ -1861,6 +1865,9 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
BUG_ON(!service_tree);
BUG_ON(!service_tree->count);
+ if (!cfqd->cfq_slice_idle)
+ return false;
+
/* We never do for idle class queues. */
if (prio == IDLE_WORKLOAD)
return false;
@@ -1885,7 +1892,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
{
struct cfq_queue *cfqq = cfqd->active_queue;
struct cfq_io_context *cic;
- unsigned long sl;
+ unsigned long sl, group_idle = 0;
/*
* SSD device without seek penalty, disable idling. But only do so
@@ -1901,8 +1908,13 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
/*
* idle is disabled, either manually or by past process history
*/
- if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
- return;
+ if (!cfq_should_idle(cfqd, cfqq)) {
+ /* no queue idling. Check for group idling */
+ if (cfqd->cfq_group_idle)
+ group_idle = cfqd->cfq_group_idle;
+ else
+ return;
+ }
/*
* still active requests from this queue, don't idle
@@ -1929,13 +1941,21 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
return;
}
+ /* There are other queues in the group, don't do group idle */
+ if (group_idle && cfqq->cfqg->nr_cfqq > 1)
+ return;
+
cfq_mark_cfqq_wait_request(cfqq);
- sl = cfqd->cfq_slice_idle;
+ if (group_idle)
+ sl = cfqd->cfq_group_idle;
+ else
+ sl = cfqd->cfq_slice_idle;
mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
cfq_blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg);
- cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
+ cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+ group_idle ? 1 : 0);
}
/*
@@ -1951,6 +1971,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
cfq_remove_request(rq);
cfqq->dispatched++;
+ (RQ_CFQG(rq))->dispatched++;
elv_dispatch_sort(q, rq);
cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
@@ -2220,7 +2241,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
cfqq = NULL;
goto keep_queue;
} else
- goto expire;
+ goto check_group_idle;
}
/*
@@ -2254,6 +2275,17 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
goto keep_queue;
}
+ /*
+ * If group idle is enabled and there are requests dispatched from
+ * this group, wait for requests to complete.
+ */
+check_group_idle:
+ if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1
+ && cfqq->cfqg->dispatched) {
+ cfqq = NULL;
+ goto keep_queue;
+ }
+
expire:
cfq_slice_expired(cfqd, 0);
new_queue:
@@ -3396,6 +3428,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
WARN_ON(!cfqq->dispatched);
cfqd->rq_in_driver--;
cfqq->dispatched--;
+ (RQ_CFQG(rq))->dispatched--;
cfq_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));
@@ -3425,7 +3458,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
* the queue.
*/
if (cfq_should_wait_busy(cfqd, cfqq)) {
- cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+ unsigned long extend_sl = cfqd->cfq_slice_idle;
+ if (!cfqd->cfq_slice_idle)
+ extend_sl = cfqd->cfq_group_idle;
+ cfqq->slice_end = jiffies + extend_sl;
cfq_mark_cfqq_wait_busy(cfqq);
cfq_log_cfqq(cfqd, cfqq, "will busy wait");
}
@@ -3870,6 +3906,7 @@ static void *cfq_init_queue(struct request_queue *q)
cfqd->cfq_slice[1] = cfq_slice_sync;
cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
cfqd->cfq_slice_idle = cfq_slice_idle;
+ cfqd->cfq_group_idle = cfq_group_idle;
cfqd->cfq_latency = 1;
cfqd->cfq_group_isolation = 0;
cfqd->hw_tag = -1;
@@ -3942,6 +3979,7 @@ SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1);
SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0);
SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
+SHOW_FUNCTION(cfq_group_idle_show, cfqd->cfq_group_idle, 1);
SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
@@ -3974,6 +4012,7 @@ STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1,
UINT_MAX, 0);
STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
+STORE_FUNCTION(cfq_group_idle_store, &cfqd->cfq_group_idle, 0, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
@@ -3995,6 +4034,7 @@ static struct elv_fs_entry cfq_attrs[] = {
CFQ_ATTR(slice_async),
CFQ_ATTR(slice_async_rq),
CFQ_ATTR(slice_idle),
+ CFQ_ATTR(group_idle),
CFQ_ATTR(low_latency),
CFQ_ATTR(group_isolation),
__ATTR_NULL
@@ -4048,6 +4088,12 @@ static int __init cfq_init(void)
if (!cfq_slice_idle)
cfq_slice_idle = 1;
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ if (!cfq_group_idle)
+ cfq_group_idle = 1;
+#else
+ cfq_group_idle = 0;
+#endif
if (cfq_slab_setup())
return -ENOMEM;
--
1.7.1.1
next prev parent reply other threads:[~2010-07-21 19:06 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-21 19:06 [RFC PATCH] cfq-iosced: Implement IOPS mode and group_idle tunable V3 Vivek Goyal
2010-07-21 19:06 ` [PATCH 1/3] cfq-iosched: Implment IOPS mode Vivek Goyal
2010-07-21 20:33 ` Jeff Moyer
2010-07-21 20:57 ` Vivek Goyal
2010-07-21 19:06 ` Vivek Goyal [this message]
2010-07-21 19:40 ` [PATCH 2/3] cfq-iosched: Implement a tunable group_idle Jeff Moyer
2010-07-21 20:13 ` Vivek Goyal
2010-07-21 20:54 ` Jeff Moyer
2010-07-21 19:06 ` [PATCH 3/3] cfq-iosched: Print number of sectors dispatched per cfqq slice Vivek Goyal
2010-07-22 5:56 ` [RFC PATCH] cfq-iosced: Implement IOPS mode and group_idle tunable V3 Christoph Hellwig
2010-07-22 14:00 ` Vivek Goyal
2010-07-24 8:51 ` Christoph Hellwig
2010-07-24 9:07 ` Corrado Zoccolo
2010-07-26 14:30 ` Vivek Goyal
2010-07-26 21:21 ` Tuning IO scheduler (Was: Re: [RFC PATCH] cfq-iosced: Implement IOPS mode and group_idle tunable V3) Vivek Goyal
2010-07-26 14:33 ` [RFC PATCH] cfq-iosced: Implement IOPS mode and group_idle tunable V3 Vivek Goyal
2010-07-29 19:57 ` Corrado Zoccolo
2010-07-26 13:51 ` Vivek Goyal
2010-07-22 20:54 ` Vivek Goyal
2010-07-22 7:08 ` Gui Jianfeng
2010-07-22 14:49 ` Vivek Goyal
2010-07-22 23:53 ` Gui Jianfeng
2010-07-26 6:58 ` Gui Jianfeng
2010-07-26 14:10 ` Vivek Goyal
2010-07-27 8:33 ` 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=1279739181-24482-3-git-send-email-vgoyal@redhat.com \
--to=vgoyal@redhat.com \
--cc=axboe@kernel.dk \
--cc=czoccolo@gmail.com \
--cc=dpshah@google.com \
--cc=guijianfeng@cn.fujitsu.com \
--cc=jmoyer@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nauman@google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.