Add zpool status -s (slow I/Os) and -p (parseable)

This patch adds a new slow I/Os (-s) column to zpool status to show the
number of VDEV slow I/Os. This is the number of I/Os that didn't
complete in zio_slow_io_ms milliseconds. It also adds a new parsable
(-p) flag to display exact values.

 	NAME         STATE     READ WRITE CKSUM  SLOW
 	testpool     ONLINE       0     0     0     -
	  mirror-0   ONLINE       0     0     0     -
 	    loop0    ONLINE       0     0     0    20
 	    loop1    ONLINE       0     0     0     0

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Tony Hutter <hutter2@llnl.gov>
Closes #7756
Closes #6885
This commit is contained in:
Tony Hutter
2018-11-08 16:47:24 -08:00
committed by Brian Behlendorf
parent 877d925a9e
commit ad796b8a3b
16 changed files with 321 additions and 136 deletions
+13 -10
View File
@@ -77,14 +77,14 @@ int vdev_validate_skip = B_FALSE;
int vdev_dtl_sm_blksz = (1 << 12);
/*
* Rate limit delay events to this many IO delays per second.
* Rate limit slow IO (delay) events to this many per second.
*/
unsigned int zfs_delays_per_second = 20;
unsigned int zfs_slow_io_events_per_second = 20;
/*
* Rate limit checksum events after this many checksum errors per second.
*/
unsigned int zfs_checksums_per_second = 20;
unsigned int zfs_checksum_events_per_second = 20;
/*
* Ignore errors during scrub/resilver. Allows to work around resilver
@@ -507,8 +507,10 @@ vdev_alloc_common(spa_t *spa, uint_t id, uint64_t guid, vdev_ops_t *ops)
* and checksum events so that we don't overwhelm ZED with thousands
* of events when a disk is acting up.
*/
zfs_ratelimit_init(&vd->vdev_delay_rl, &zfs_delays_per_second, 1);
zfs_ratelimit_init(&vd->vdev_checksum_rl, &zfs_checksums_per_second, 1);
zfs_ratelimit_init(&vd->vdev_delay_rl, &zfs_slow_io_events_per_second,
1);
zfs_ratelimit_init(&vd->vdev_checksum_rl,
&zfs_checksum_events_per_second, 1);
list_link_init(&vd->vdev_config_dirty_node);
list_link_init(&vd->vdev_state_dirty_node);
@@ -3591,6 +3593,7 @@ vdev_clear(spa_t *spa, vdev_t *vd)
vd->vdev_stat.vs_read_errors = 0;
vd->vdev_stat.vs_write_errors = 0;
vd->vdev_stat.vs_checksum_errors = 0;
vd->vdev_stat.vs_slow_ios = 0;
for (int c = 0; c < vd->vdev_children; c++)
vdev_clear(spa, vd->vdev_child[c]);
@@ -4630,12 +4633,12 @@ module_param(vdev_ms_count_limit, int, 0644);
MODULE_PARM_DESC(vdev_ms_count_limit,
"Practical upper limit of total metaslabs per top-level vdev");
module_param(zfs_delays_per_second, uint, 0644);
MODULE_PARM_DESC(zfs_delays_per_second, "Rate limit delay events to this many "
"IO delays per second");
module_param(zfs_slow_io_events_per_second, uint, 0644);
MODULE_PARM_DESC(zfs_slow_io_events_per_second,
"Rate limit slow IO (delay) events to this many per second");
module_param(zfs_checksums_per_second, uint, 0644);
MODULE_PARM_DESC(zfs_checksums_per_second, "Rate limit checksum events "
module_param(zfs_checksum_events_per_second, uint, 0644);
MODULE_PARM_DESC(zfs_checksum_events_per_second, "Rate limit checksum events "
"to this many checksum errors per second (do not set below zed"
"threshold).");