cfq-iosched: fix the delay of cfq_group's vdisktime under iops mode

When adding a cfq_group into the cfq service tree, we use CFQ_IDLE_DELAY
as the delay of cfq_group's vdisktime if there have been other cfq_groups
already.

When cfq is under iops mode, commit 9a7f38c42c2b ("cfq-iosched: Convert
from jiffies to nanoseconds") could result in a large iops delay and
lead to an abnormal io schedule delay for the added cfq_group. To fix
it, we just need to revert to the old CFQ_IDLE_DELAY value: HZ / 5
when iops mode is enabled.

Despite having the same value, the delay of a cfq_queue in idle class
and the delay of cfq_group are different things, so I define two new
macros for the delay of a cfq_group under time-slice mode and iops mode.

Fixes: 9a7f38c42c2b ("cfq-iosched: Convert from jiffies to nanoseconds")
Cc: <stable@vger.kernel.org> # 4.8+
Signed-off-by: Hou Tao <houtao1@huawei.com>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index da69b079725fbf62a407db76f7c5c430c52be3f9..b7e9c7feeab2acbd1a846d0c31285460aba076ec 100644 (file)
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -38,9 +38,13 @@ static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
 /*
- * offset from end of service tree
+ * offset from end of queue service tree for idle class
  */
 #define CFQ_IDLE_DELAY         (NSEC_PER_SEC / 5)
+/* offset from end of group service tree under time slice mode */
+#define CFQ_SLICE_MODE_GROUP_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service under IOPS mode */
+#define CFQ_IOPS_MODE_GROUP_DELAY (HZ / 5)
 
 /*
  * below this threshold, we consider thinktime immediate
@@ -1362,6 +1366,14 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
        cfqg->vfraction = max_t(unsigned, vfr, 1);
 }
 
+static inline u64 cfq_get_cfqg_vdisktime_delay(struct cfq_data *cfqd)
+{
+       if (!iops_mode(cfqd))
+               return CFQ_SLICE_MODE_GROUP_DELAY;
+       else
+               return CFQ_IOPS_MODE_GROUP_DELAY;
+}
+
 static void
 cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
@@ -1381,7 +1393,8 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
        n = rb_last(&st->rb);
        if (n) {
                __cfqg = rb_entry_cfqg(n);
-               cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+               cfqg->vdisktime = __cfqg->vdisktime +
+                       cfq_get_cfqg_vdisktime_delay(cfqd);
        } else
                cfqg->vdisktime = st->min_vdisktime;
        cfq_group_service_tree_add(st, cfqg);