Blob Blame History Raw
From 86d7331299fda7634b11c1b7c911432679d525a5 Mon Sep 17 00:00:00 2001
From: Zhang Wensheng <zhangwensheng5@huawei.com>
Date: Thu, 17 Feb 2022 14:42:47 +0800
Subject: [PATCH] block: update io_ticks when io hang
Git-commit: 86d7331299fda7634b11c1b7c911432679d525a5
Patch-mainline: v5.18-rc1
References: bsc#1197817

When the inflight IOs are slow and no new IOs are issued, we expect
iostat could manifest the IO hang problem. However after
commit 5b18b5a73760 ("block: delete part_round_stats and switch to less
precise counting"), io_tick and time_in_queue will not be updated until
the end of IO, and the avgqu-sz and %util columns of iostat will be zero.

Because it has using stat.nsecs accumulation to express time_in_queue
which is not suitable to change, and may %util will express the status
better when io hang occur. To fix io_ticks, we use update_io_ticks and
inflight to update io_ticks when diskstats_show and part_stat_show
been called.

Fixes: 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting")
Signed-off-by: Zhang Wensheng <zhangwensheng5@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220217064247.4041435-1-zhangwensheng5@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Acked-by: Jan Kara <jack@suse.cz>

---
 block/blk-core.c |    3 +--
 block/blk.h      |    2 ++
 block/genhd.c    |   14 ++++++++++++--
 3 files changed, 15 insertions(+), 4 deletions(-)

--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1234,8 +1234,7 @@ unsigned int blk_rq_err_bytes(const stru
 }
 EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 
-static void update_io_ticks(struct block_device *part, unsigned long now,
-		bool end)
+void update_io_ticks(struct block_device *part, unsigned long now, bool end)
 {
 	unsigned long stamp;
 again:
--- a/block/blk.h
+++ b/block/blk.h
@@ -246,6 +246,8 @@ static inline bool blk_do_io_stat(struct
 	return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT);
 }
 
+void update_io_ticks(struct block_device *part, unsigned long now, bool end);
+
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 {
 	req->cmd_flags |= REQ_NOMERGE;
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -896,12 +896,17 @@ ssize_t part_stat_show(struct device *de
 	struct disk_stats stat;
 	unsigned int inflight;
 
-	part_stat_read_all(bdev, &stat);
 	if (queue_is_mq(q))
 		inflight = blk_mq_in_flight(q, bdev);
 	else
 		inflight = part_in_flight(bdev);
 
+	if (inflight) {
+		part_stat_lock();
+		update_io_ticks(bdev, jiffies, true);
+		part_stat_unlock();
+	}
+	part_stat_read_all(bdev, &stat);
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
@@ -1140,12 +1145,17 @@ static int diskstats_show(struct seq_fil
 	xa_for_each(&gp->part_tbl, idx, hd) {
 		if (bdev_is_partition(hd) && !bdev_nr_sectors(hd))
 			continue;
-		part_stat_read_all(hd, &stat);
 		if (queue_is_mq(gp->queue))
 			inflight = blk_mq_in_flight(gp->queue, hd);
 		else
 			inflight = part_in_flight(hd);
 
+		if (inflight) {
+			part_stat_lock();
+			update_io_ticks(hd, jiffies, true);
+			part_stat_unlock();
+		}
+		part_stat_read_all(hd, &stat);
 		seq_printf(seqf, "%4d %7d %s "
 			   "%lu %lu %lu %u "
 			   "%lu %lu %lu %u "