Skip to contentSkip to conversation

block: update hctx map when use multiple maps

PATCH Applied Weiping Zhang 3 participants 3 messages Jun 17, 2020 – Jun 18, 2020 Block layer

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 block: update hctx map when use multiple maps

There is an issue when tune the number for read and write queues, if the total queue count was not changed. The hctx->type cannot be updated, since __blk_mq_update_nr_hw_queues will return directly if the total queue count has not been changed.

Reproduce:

dmesg | grep "default/read/poll"

[    2.607459] nvme nvme0: 48/0/0 default/read/poll queues

cat /sys/kernel/debug/block/nvme0n1/hctx*/type | sort | uniq -c
48 default

tune the write queues to 24:
echo 24 > /sys/module/nvme/parameters/write_queues echo 1 > /sys/block/nvme0n1/device/reset_controller

dmesg | grep "default/read/poll"

[  433.547235] nvme nvme0: 24/24/0 default/read/poll queues

cat /sys/kernel/debug/block/nvme0n1/hctx*/type | sort | uniq -c
48 default

The driver's hardware queue mapping is not same as block layer.

---
 block/blk-mq.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
block/blk-mq.c +3 -1
index 4f57d27bfa73..a9aa6d1e44cf 100644
@@ -3479,7 +3479,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids)
 		nr_hw_queues = nr_cpu_ids;
-	if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
+	if (nr_hw_queues < 1)
+		return;
+	if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
 		return;
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
Signature · 1 line
2.18.2
Reviewed-by on v1 1/1
#1 lore raw
Quoted 47 lines · Weiping Zhang

There is an issue when tune the number for read and write queues, if the total queue count was not changed. The hctx->type cannot be updated, since __blk_mq_update_nr_hw_queues will return directly if the total queue count has not been changed.

Reproduce:

dmesg | grep "default/read/poll"

[    2.607459] nvme nvme0: 48/0/0 default/read/poll queues

cat /sys/kernel/debug/block/nvme0n1/hctx*/type | sort | uniq -c
48 default

tune the write queues to 24:
echo 24 > /sys/module/nvme/parameters/write_queues echo 1 > /sys/block/nvme0n1/device/reset_controller

dmesg | grep "default/read/poll"

[  433.547235] nvme nvme0: 24/24/0 default/read/poll queues

cat /sys/kernel/debug/block/nvme0n1/hctx*/type | sort | uniq -c
48 default

The driver's hardware queue mapping is not same as block layer.

---
 block/blk-mq.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
block/blk-mq.c +3 -1
index 4f57d27bfa73..a9aa6d1e44cf 100644
@@ -3479,7 +3479,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids)
 		nr_hw_queues = nr_cpu_ids;
-	if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
+	if (nr_hw_queues < 1)
+		return;
+	if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
 		return;
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
Signature · 1 line
2.18.2
Signature · 1 line
Ming
maintainer Applied
#2 lore raw
In reply to Weiping Zhang
Quoted 16 lines · Weiping Zhang

There is an issue when tune the number for read and write queues, if the total queue count was not changed. The hctx->type cannot be updated, since __blk_mq_update_nr_hw_queues will return directly if the total queue count has not been changed.

Reproduce:

dmesg | grep "default/read/poll"

[    2.607459] nvme nvme0: 48/0/0 default/read/poll queues

cat /sys/kernel/debug/block/nvme0n1/hctx*/type | sort | uniq -c
48 default

tune the write queues to 24:
echo 24 > /sys/module/nvme/parameters/write_queues echo 1 > /sys/block/nvme0n1/device/reset_controller

Quoted 7 lines

dmesg | grep "default/read/poll"

[  433.547235] nvme nvme0: 24/24/0 default/read/poll queues

cat /sys/kernel/debug/block/nvme0n1/hctx*/type | sort | uniq -c
48 default

The driver's hardware queue mapping is not same as block layer.

Applied, thanks.

Signature · 1 line
Jens Axboe