diff options
| author | David Wang <00107082@163.com> | 2024-11-08 06:45:00 +0100 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2024-11-13 22:02:19 +0100 |
| commit | bda9c7d92f24b693eaf0262c090de4c8c108a28e (patch) | |
| tree | ddb54108a2b8fa8a1c84d75f50109beede0a4514 /block | |
| parent | block: don't reorder requests in blk_mq_add_to_batch (diff) | |
| download | linux-bda9c7d92f24b693eaf0262c090de4c8c108a28e.tar.xz linux-bda9c7d92f24b693eaf0262c090de4c8c108a28e.zip | |
block/genhd: use seq_put_decimal_ull for diskstats decimal values
seq_printf is costly. For each block device, 19 decimal values are
yielded in /proc/diskstats via seq_printf. On a system with 16 logical
block devices, profiling for open/read/close sequences shows seq_printf
took ~75% samples of diskstats_show:
diskstats_show(92.626% 2269372/2450040)
seq_printf(76.026% 1725313/2269372)
vsnprintf(99.163% 1710866/1725313)
format_decode(26.597% 455040/1710866)
number(19.554% 334542/1710866)
memcpy_orig(4.183% 71570/1710866)
...
srso_return_thunk(0.009% 148/1725313)
part_stat_read_all(8.030% 182236/2269372)
One million rounds of open/read/close /proc/diskstats takes:
real 0m37.687s
user 0m0.264s
sys 0m32.911s
On average, each sequence tooks ~0.032ms
With this patch, most decimal values are yield via seq_put_decimal_ull,
performance is significantly improved:
real 0m20.792s
user 0m0.316s
sys 0m20.463s
On average, each sequence tooks ~0.020ms, a ~37.5% improvement.
Signed-off-by: David Wang <00107082@163.com>
Link: https://lore.kernel.org/r/20241108054500.4251-1-00107082@163.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block')
| -rw-r--r-- | block/genhd.c | 63 |
1 files changed, 29 insertions, 34 deletions
diff --git a/block/genhd.c b/block/genhd.c index 1971c91d6f72..9130e163e191 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1291,40 +1291,35 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_unlock(); } part_stat_read_all(hd, &stat); - seq_printf(seqf, "%4d %7d %pg " - "%lu %lu %lu %u " - "%lu %lu %lu %u " - "%u %u %u " - "%lu %lu %lu %u " - "%lu %u" - "\n", - MAJOR(hd->bd_dev), MINOR(hd->bd_dev), hd, - stat.ios[STAT_READ], - stat.merges[STAT_READ], - stat.sectors[STAT_READ], - (unsigned int)div_u64(stat.nsecs[STAT_READ], - NSEC_PER_MSEC), - stat.ios[STAT_WRITE], - stat.merges[STAT_WRITE], - stat.sectors[STAT_WRITE], - (unsigned int)div_u64(stat.nsecs[STAT_WRITE], - NSEC_PER_MSEC), - inflight, - jiffies_to_msecs(stat.io_ticks), - (unsigned int)div_u64(stat.nsecs[STAT_READ] + - stat.nsecs[STAT_WRITE] + - stat.nsecs[STAT_DISCARD] + - stat.nsecs[STAT_FLUSH], - NSEC_PER_MSEC), - stat.ios[STAT_DISCARD], - stat.merges[STAT_DISCARD], - stat.sectors[STAT_DISCARD], - (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], - NSEC_PER_MSEC), - stat.ios[STAT_FLUSH], - (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], - NSEC_PER_MSEC) - ); + seq_put_decimal_ull_width(seqf, "", MAJOR(hd->bd_dev), 4); + seq_put_decimal_ull_width(seqf, " ", MINOR(hd->bd_dev), 7); + seq_printf(seqf, " %pg", hd); + seq_put_decimal_ull(seqf, " ", stat.ios[STAT_READ]); + seq_put_decimal_ull(seqf, " ", stat.merges[STAT_READ]); + seq_put_decimal_ull(seqf, " ", stat.sectors[STAT_READ]); + seq_put_decimal_ull(seqf, " ", (unsigned int)div_u64(stat.nsecs[STAT_READ], + NSEC_PER_MSEC)); + seq_put_decimal_ull(seqf, " ", stat.ios[STAT_WRITE]); + seq_put_decimal_ull(seqf, " ", stat.merges[STAT_WRITE]); + seq_put_decimal_ull(seqf, " ", stat.sectors[STAT_WRITE]); + seq_put_decimal_ull(seqf, " ", (unsigned int)div_u64(stat.nsecs[STAT_WRITE], + NSEC_PER_MSEC)); + seq_put_decimal_ull(seqf, " ", inflight); + seq_put_decimal_ull(seqf, " ", jiffies_to_msecs(stat.io_ticks)); + seq_put_decimal_ull(seqf, " ", (unsigned int)div_u64(stat.nsecs[STAT_READ] + + stat.nsecs[STAT_WRITE] + + stat.nsecs[STAT_DISCARD] + + stat.nsecs[STAT_FLUSH], + NSEC_PER_MSEC)); + seq_put_decimal_ull(seqf, " ", stat.ios[STAT_DISCARD]); + seq_put_decimal_ull(seqf, " ", stat.merges[STAT_DISCARD]); + seq_put_decimal_ull(seqf, " ", stat.sectors[STAT_DISCARD]); + seq_put_decimal_ull(seqf, " ", (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], + NSEC_PER_MSEC)); + seq_put_decimal_ull(seqf, " ", stat.ios[STAT_FLUSH]); + seq_put_decimal_ull(seqf, " ", (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], + NSEC_PER_MSEC)); + seq_putc(seqf, '\n'); } rcu_read_unlock(); |