On 12/11/23 15:31, Damien Le Moal wrote:
On 12/12/23 08:14, Bart Van Assche wrote:
+ /*
+ * If REQ_OP_WRITE or REQ_OP_WRITE_ZEROES operations for the same zone
+ * originate from different cgroups that could result in different
+ * priorities being assigned to these operations. Do not modify the I/O
+ * priority of these write operations to prevent that these would be
+ * executed in the wrong order when using the mq-deadline I/O
+ * scheduler.
+ */
+ if (bdev_op_is_zoned_write(bio->bi_bdev, bio_op(bio)))
Ideally, we want the bio equivalent of blk_rq_is_seq_zoned_write() here so that
writes to conventional zones are not affected (these can be reordered).
How about the patch below?
Thanks,
Bart.
[PATCH] block/blk-ioprio: Skip zoned writes that are not append operations
If REQ_OP_WRITE or REQ_OP_WRITE_ZEROES operations for the same zone
originate from different cgroups that could result in different priorities
being assigned to these operations. Do not modify the I/O priority of
these write operations to prevent them from being executed in the wrong
order when using the mq-deadline I/O scheduler.
Cc: Damien Le Moal <dlemoal@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
---
block/blk-ioprio.c | 11 +++++++++++
include/linux/blk-mq.h | 17 +++++++++++++++++
2 files changed, 28 insertions(+)
diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c
index 4051fada01f1..96b46d34e3d6 100644
--- a/block/blk-ioprio.c
+++ b/block/blk-ioprio.c
@@ -192,6 +192,17 @@ void blkcg_set_ioprio(struct bio *bio)
if (!blkcg || blkcg->prio_policy == POLICY_NO_CHANGE)
return;
+ /*
+ * If REQ_OP_WRITE or REQ_OP_WRITE_ZEROES operations for the same zone
+ * originate from different cgroups that could result in different
+ * priorities being assigned to these operations. Do not modify the I/O
+ * priority of these write operations to prevent that these would be
+ * executed in the wrong order when using the mq-deadline I/O
+ * scheduler.
+ */
+ if (blk_bio_is_seq_zoned_write(bio))
+ return;
+
if (blkcg->prio_policy == POLICY_PROMOTE_TO_RT ||
blkcg->prio_policy == POLICY_NONE_TO_RT) {
/*
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1ab3081c82ed..90907d9001c0 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -1149,6 +1149,18 @@ static inline unsigned int blk_rq_zone_no(struct request *rq)
return disk_zone_no(rq->q->disk, blk_rq_pos(rq));
}
+/**
+ * blk_bio_is_seq_zoned_write() - Check if @bio requires write serialization.
+ * @bio: Bio to examine.
+ *
+ * Note: REQ_OP_ZONE_APPEND bios do not require serialization.
+ */
+static inline bool blk_bio_is_seq_zoned_write(struct bio *bio)
+{
+ return op_needs_zoned_write_locking(bio_op(bio)) &&
+ disk_zone_is_seq(bio->bi_disk, bio.bi_iter.bi_sector);
+}
+
static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
{
return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq));
@@ -1196,6 +1208,11 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
return !blk_req_zone_is_write_locked(rq);
}
#else /* CONFIG_BLK_DEV_ZONED */
+static inline bool blk_bio_is_seq_zoned_write(struct bio *bio)
+{
+ return false;
+}
+
static inline bool blk_rq_is_seq_zoned_write(struct request *rq)
{
return false;
