c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-22 02:27:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Avoid posting duplicate zpool events

Browse Source 
Duplicate io and checksum ereport events can misrepresent that 
things are worse than they seem. Ideally the zpool events and the 
corresponding vdev stat error counts in a zpool status should be 
for unique errors -- not the same error being counted over and over. 
This can be demonstrated in a simple example. With a single bad 
block in a datafile and just 5 reads of the file we end up with a 
degraded vdev, even though there is only one unique error in the pool.

The proposed solution to the above issue, is to eliminate duplicates 
when posting events and when updating vdev error stats. We now save 
recent error events of interest when posting events so that we can 
easily check for duplicates when posting an error. 

Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Don Brady <don.brady@delphix.com>
Closes #10861
This commit is contained in:
Don Brady
2020-09-04 11:34:28 -06:00
committed by GitHub
parent 3808032489
commit 4f07282786
22 changed files with 799 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/vdev_raidz.c
+18 -17
View File
@@ -21,7 +21,7 @@
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2012, 2019 by Delphix. All rights reserved.
* Copyright (c) 2012, 2020 by Delphix. All rights reserved.
* Copyright (c) 2016 Gvozden Nešković. All rights reserved.
*/
@@ -1790,16 +1790,17 @@ raidz_checksum_error(zio_t *zio, raidz_col_t *rc, abd_t *bad_data)
zio_bad_cksum_t zbc;
raidz_map_t *rm = zio->io_vsd;
mutex_enter(&vd->vdev_stat_lock);
vd->vdev_stat.vs_checksum_errors++;
mutex_exit(&vd->vdev_stat_lock);
zbc.zbc_has_cksum = 0;
zbc.zbc_injected = rm->rm_ecksuminjected;
(void) zfs_ereport_post_checksum(zio->io_spa, vd,
int ret = zfs_ereport_post_checksum(zio->io_spa, vd,
&zio->io_bookmark, zio, rc->rc_offset, rc->rc_size,
rc->rc_abd, bad_data, &zbc);
if (ret != EALREADY) {
mutex_enter(&vd->vdev_stat_lock);
vd->vdev_stat.vs_checksum_errors++;
mutex_exit(&vd->vdev_stat_lock);
}
}
}
@@ -2279,21 +2280,21 @@ vdev_raidz_io_done(zio_t *zio)
vdev_t *cvd;
rc = &rm->rm_col[c];
cvd = vd->vdev_child[rc->rc_devidx];
if (rc->rc_error == 0) {
zio_bad_cksum_t zbc;
zbc.zbc_has_cksum = 0;
zbc.zbc_injected =
rm->rm_ecksuminjected;
if (rc->rc_error != 0)
continue;
zio_bad_cksum_t zbc;
zbc.zbc_has_cksum = 0;
zbc.zbc_injected = rm->rm_ecksuminjected;
int ret = zfs_ereport_start_checksum(
zio->io_spa, cvd, &zio->io_bookmark, zio,
rc->rc_offset, rc->rc_size,
(void *)(uintptr_t)c, &zbc);
if (ret != EALREADY) {
mutex_enter(&cvd->vdev_stat_lock);
cvd->vdev_stat.vs_checksum_errors++;
mutex_exit(&cvd->vdev_stat_lock);
zfs_ereport_start_checksum(
zio->io_spa, cvd,
&zio->io_bookmark, zio,
rc->rc_offset, rc->rc_size,
(void *)(uintptr_t)c, &zbc);
}
}
}