From: Zhang Wensheng zhangwensheng5@huawei.com
hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8M01Q CVE: NA
--------------------------------
After introducing commit 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting"), '%util' accounted by iostat will be over reality data. In fact, the device is quite idle, but iostat may show '%util' as a big number (e.g. 50%). It can produce by fio:
fio --name=1 --direct=1 --bs=4k --rw=read --filename=/dev/sda \ --thinktime=4ms --runtime=180 We fix this by using a switch(precise_iostat=1) to control whether or not acconut ioticks precisely.
fixes: 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting") Signed-off-by: Zhang Wensheng zhangwensheng5@huawei.com Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com
Conflicts: block/blk-core.c block/blk-merge.c block/genhd.c include/linux/blkdev.h Signed-off-by: Li Lingfeng lilingfeng3@huawei.com --- block/blk-core.c | 25 +++++++++++++++++++++++-- block/blk-merge.c | 2 ++ block/blk-mq.c | 4 ++++ block/genhd.c | 2 +- include/linux/blkdev.h | 2 ++ 5 files changed, 32 insertions(+), 3 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c index fdf25b8d6e78..16d645532ce9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -61,6 +61,22 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert);
static DEFINE_IDA(blk_queue_ida);
+bool precise_iostat; + +static int __init precise_iostat_setup(char *str) +{ + bool precise; + + if (!strtobool(str, &precise)) { + precise_iostat = precise; + pr_info("precise iostat %d\n", precise_iostat); + } + + return 1; +} +__setup("precise_iostat=", precise_iostat_setup); + + /* * For queue allocation */ @@ -940,9 +956,14 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end) unsigned long stamp; again: stamp = READ_ONCE(part->bd_stamp); - if (unlikely(time_after(now, stamp))) { - if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) + if (unlikely(time_after(now, stamp)) && + likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) { + if (precise_iostat) { + if (end || part_in_flight(part)) + __part_stat_add(part, io_ticks, now - stamp); + } else { __part_stat_add(part, io_ticks, end ? now - stamp : 1); + } } if (part->bd_partno) { part = bdev_whole(part); diff --git a/block/blk-merge.c b/block/blk-merge.c index 65e75efa9bd3..463611c7c944 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -783,6 +783,8 @@ static void blk_account_io_merge_request(struct request *req) if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); + if (precise_iostat) + part_stat_local_dec(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } diff --git a/block/blk-mq.c b/block/blk-mq.c index 6ab7f360ff2a..387528a9f3df 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -994,6 +994,8 @@ static inline void blk_account_io_done(struct request *req, u64 now) update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); + if (precise_iostat) + part_stat_local_dec(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } @@ -1016,6 +1018,8 @@ static inline void blk_account_io_start(struct request *req)
part_stat_lock(); update_io_ticks(req->part, jiffies, false); + if (precise_iostat) + part_stat_local_inc(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } diff --git a/block/genhd.c b/block/genhd.c index cc32a0c704eb..8cf16dc7e195 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -118,7 +118,7 @@ static void part_stat_read_all(struct block_device *part, } }
-static unsigned int part_in_flight(struct block_device *part) +unsigned int part_in_flight(struct block_device *part) { unsigned int inflight = 0; int cpu; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index eef450f25982..99c2e6aa5e10 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include <linux/uuid.h> #include <linux/xarray.h>
+extern bool precise_iostat; struct module; struct request_queue; struct elevator_queue; @@ -832,6 +833,7 @@ dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); void blk_request_module(dev_t devt);
+extern unsigned int part_in_flight(struct block_device *part); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); void submit_bio_noacct(struct bio *bio);
-
Li Lingfeng