'\" te
.\" Copyright (c) 2013 by Turbo Fredriksson <turbo@bayour.com>. All rights reserved.
.\" Portions Copyright 2018 by Richard Elling
.\" The contents of this file are subject to the terms of the Common Development
.\" and Distribution License (the "License").  You may not use this file except
.\" in compliance with the License. You can obtain a copy of the license at
.\" usr/src/OPENSOLARIS.LICENSE or http://www.opensolaris.org/os/licensing.
.\"
.\" See the License for the specific language governing permissions and
.\" limitations under the License. When distributing Covered Code, include this
.\" CDDL HEADER in each file and include the License file at
.\" usr/src/OPENSOLARIS.LICENSE.  If applicable, add the following below this
.\" CDDL HEADER, with the fields enclosed by brackets "[]" replaced with your
.\" own identifying information:
.\" Portions Copyright [yyyy] [name of copyright owner]
.TH ZFS-EVENTS 5 "Oct 24, 2018"
.SH NAME
zfs\-events \- Events created by the ZFS filesystem.
.SH DESCRIPTION
.sp
.LP
Description of the different events generated by the ZFS stack.
.sp
Most of these don't have any description. The events generated by ZFS
have never been publicly documented.  What is here is intended as a
starting point to provide documentation for all possible events.
.sp
To view all events created since the loading of the ZFS infrastructure
(i.e, "the module"), run
.P
.nf
\fBzpool events\fR
.fi
.P
to get a short list, and
.P
.nf
\fBzpool events -v\fR
.fi
.P
to get a full detail of the events and what information
is available about it.
.sp
This man page lists the different subclasses that are issued
in the case of an event. The full event name would be
\fIereport.fs.zfs.SUBCLASS\fR, but we only list the last
part here.

.SS "EVENTS (SUBCLASS)"
.sp
.LP

.sp
.ne 2
.na
\fBchecksum\fR
.ad
.RS 12n
Issued when a checksum error has been detected.
.RE

.sp
.ne 2
.na
\fBio\fR
.ad
.RS 12n
Issued when there is an I/O error in a vdev in the pool.
.RE

.sp
.ne 2
.na
\fBdata\fR
.ad
.RS 12n
Issued when there have been data errors in the pool.
.RE

.sp
.ne 2
.na
\fBdeadman\fR
.ad
.RS 12n
Issued when an I/O is determined to be "hung", this can be caused by lost
completion events due to flaky hardware or drivers.  See the
\fBzfs_deadman_failmode\fR module option description for additional
information regarding "hung" I/O detection and configuration.
.RE

.sp
.ne 2
.na
\fBdelay\fR
.ad
.RS 12n
Issued when a completed I/O exceeds the maximum allowed time specified
by the \fBzio_slow_io_ms\fR module option.  This can be an indicator of
problems with the underlying storage device.  The number of delay events is
ratelimited by the \fBzfs_slow_io_events_per_second\fR module parameter.
.RE

.sp
.ne 2
.na
\fBconfig.sync\fR
.ad
.RS 12n
Issued every time a vdev change have been done to the pool.
.RE

.sp
.ne 2
.na
\fBzpool\fR
.ad
.RS 12n
Issued when a pool cannot be imported.
.RE

.sp
.ne 2
.na
\fBzpool.destroy\fR
.ad
.RS 12n
Issued when a pool is destroyed.
.RE

.sp
.ne 2
.na
\fBzpool.export\fR
.ad
.RS 12n
Issued when a pool is exported.
.RE

.sp
.ne 2
.na
\fBzpool.import\fR
.ad
.RS 12n
Issued when a pool is imported.
.RE

.sp
.ne 2
.na
\fBzpool.reguid\fR
.ad
.RS 12n
Issued when a REGUID (new unique identifier for the pool have been regenerated) have been detected.
.RE

.sp
.ne 2
.na
\fBvdev.unknown\fR
.ad
.RS 12n
Issued when the vdev is unknown. Such as trying to clear device
errors on a vdev that have failed/been kicked from the system/pool
and is no longer available.
.RE

.sp
.ne 2
.na
\fBvdev.open_failed\fR
.ad
.RS 12n
Issued when a vdev could not be opened (because it didn't exist for example).
.RE

.sp
.ne 2
.na
\fBvdev.corrupt_data\fR
.ad
.RS 12n
Issued when corrupt data have been detected on a vdev.
.RE

.sp
.ne 2
.na
\fBvdev.no_replicas\fR
.ad
.RS 12n
Issued when there are no more replicas to sustain the pool.
This would lead to the pool being \fIDEGRADED\fR.
.RE

.sp
.ne 2
.na
\fBvdev.bad_guid_sum\fR
.ad
.RS 12n
Issued when a missing device in the pool have been detected.
.RE

.sp
.ne 2
.na
\fBvdev.too_small\fR
.ad
.RS 12n
Issued when the system (kernel) have removed a device, and ZFS
notices that the device isn't there any more. This is usually
followed by a \fBprobe_failure\fR event.
.RE

.sp
.ne 2
.na
\fBvdev.bad_label\fR
.ad
.RS 12n
Issued when the label is OK but invalid.
.RE

.sp
.ne 2
.na
\fBvdev.bad_ashift\fR
.ad
.RS 12n
Issued when the ashift alignment requirement has increased.
.RE

.sp
.ne 2
.na
\fBvdev.remove\fR
.ad
.RS 12n
Issued when a vdev is detached from a mirror (or a spare detached from a
vdev where it have been used to replace a failed drive - only works if
the original drive have been readded).
.RE

.sp
.ne 2
.na
\fBvdev.clear\fR
.ad
.RS 12n
Issued when clearing device errors in a pool. Such as running \fBzpool clear\fR
on a device in the pool.
.RE

.sp
.ne 2
.na
\fBvdev.check\fR
.ad
.RS 12n
Issued when a check to see if a given vdev could be opened is started.
.RE

.sp
.ne 2
.na
\fBvdev.spare\fR
.ad
.RS 12n
Issued when a spare have kicked in to replace a failed device.
.RE

.sp
.ne 2
.na
\fBvdev.autoexpand\fR
.ad
.RS 12n
Issued when a vdev can be automatically expanded.
.RE

.sp
.ne 2
.na
\fBio_failure\fR
.ad
.RS 12n
Issued when there is an I/O failure in a vdev in the pool.
.RE

.sp
.ne 2
.na
\fBprobe_failure\fR
.ad
.RS 12n
Issued when a probe fails on a vdev. This would occur if a vdev
have been kicked from the system outside of ZFS (such as the kernel
have removed the device).
.RE

.sp
.ne 2
.na
\fBlog_replay\fR
.ad
.RS 12n
Issued when the intent log cannot be replayed.  The can occur in the case
of a missing or damaged log device.
.RE

.sp
.ne 2
.na
\fBresilver.start\fR
.ad
.RS 12n
Issued when a resilver is started.
.RE

.sp
.ne 2
.na
\fBresilver.finish\fR
.ad
.RS 12n
Issued when the running resilver have finished.
.RE

.sp
.ne 2
.na
\fBscrub.start\fR
.ad
.RS 12n
Issued when a scrub is started on a pool.
.RE

.sp
.ne 2
.na
\fBscrub.finish\fR
.ad
.RS 12n
Issued when a pool has finished scrubbing.
.RE

.sp
.ne 2
.na
\fBscrub.abort\fR
.ad
.RS 12n
Issued when a scrub is aborted on a pool.
.RE

.sp
.ne 2
.na
\fBscrub.resume\fR
.ad
.RS 12n
Issued when a scrub is resumed on a pool.
.RE

.sp
.ne 2
.na
\fBscrub.paused\fR
.ad
.RS 12n
Issued when a scrub is paused on a pool.
.RE

.sp
.ne 2
.na
\fBbootfs.vdev.attach\fR
.ad
.RS 12n
.RE

.SS "PAYLOADS"
.sp
.LP
This is the payload (data, information) that accompanies an
event.
.sp
For
.BR zed (8),
these are set to uppercase and prefixed with \fBZEVENT_\fR.

.sp
.ne 2
.na
\fBpool\fR
.ad
.RS 12n
Pool name.
.RE

.sp
.ne 2
.na
\fBpool_failmode\fR
.ad
.RS 12n
Failmode - \fBwait\fR, \fBcontinue\fR or \fBpanic\fR.
See
.BR zpool (8)
(\fIfailmode\fR property) for more information.
.RE

.sp
.ne 2
.na
\fBpool_guid\fR
.ad
.RS 12n
The GUID of the pool.
.RE

.sp
.ne 2
.na
\fBpool_context\fR
.ad
.RS 12n
The load state for the pool (0=none, 1=open, 2=import, 3=tryimport, 4=recover
5=error).
.RE

.sp
.ne 2
.na
\fBvdev_guid\fR
.ad
.RS 12n
The GUID of the vdev in question (the vdev failing or operated upon with
\fBzpool clear\fR etc).
.RE

.sp
.ne 2
.na
\fBvdev_type\fR
.ad
.RS 12n
Type of vdev - \fBdisk\fR, \fBfile\fR, \fBmirror\fR etc. See
.BR zpool (8)
under \fBVirtual Devices\fR for more information on possible values.
.RE

.sp
.ne 2
.na
\fBvdev_path\fR
.ad
.RS 12n
Full path of the vdev, including any \fI-partX\fR.
.RE

.sp
.ne 2
.na
\fBvdev_devid\fR
.ad
.RS 12n
ID of vdev (if any).
.RE

.sp
.ne 2
.na
\fBvdev_fru\fR
.ad
.RS 12n
Physical FRU location.
.RE

.sp
.ne 2
.na
\fBvdev_state\fR
.ad
.RS 12n
State of vdev (0=uninitialized, 1=closed, 2=offline, 3=removed, 4=failed to open, 5=faulted, 6=degraded, 7=healthy).
.RE

.sp
.ne 2
.na
\fBvdev_ashift\fR
.ad
.RS 12n
The ashift value of the vdev.
.RE

.sp
.ne 2
.na
\fBvdev_complete_ts\fR
.ad
.RS 12n
The time the last I/O completed for the specified vdev.
.RE

.sp
.ne 2
.na
\fBvdev_delta_ts\fR
.ad
.RS 12n
The time since the last I/O completed for the specified vdev.
.RE

.sp
.ne 2
.na
\fBvdev_spare_paths\fR
.ad
.RS 12n
List of spares, including full path and any \fI-partX\fR.
.RE

.sp
.ne 2
.na
\fBvdev_spare_guids\fR
.ad
.RS 12n
GUID(s) of spares.
.RE

.sp
.ne 2
.na
\fBvdev_read_errors\fR
.ad
.RS 12n
How many read errors that have been detected on the vdev.
.RE

.sp
.ne 2
.na
\fBvdev_write_errors\fR
.ad
.RS 12n
How many write errors that have been detected on the vdev.
.RE

.sp
.ne 2
.na
\fBvdev_cksum_errors\fR
.ad
.RS 12n
How many checksum errors that have been detected on the vdev.
.RE

.sp
.ne 2
.na
\fBparent_guid\fR
.ad
.RS 12n
GUID of the vdev parent.
.RE

.sp
.ne 2
.na
\fBparent_type\fR
.ad
.RS 12n
Type of parent. See \fBvdev_type\fR.
.RE

.sp
.ne 2
.na
\fBparent_path\fR
.ad
.RS 12n
Path of the vdev parent (if any).
.RE

.sp
.ne 2
.na
\fBparent_devid\fR
.ad
.RS 12n
ID of the vdev parent (if any).
.RE

.sp
.ne 2
.na
\fBzio_objset\fR
.ad
.RS 12n
The object set number for a given I/O.
.RE

.sp
.ne 2
.na
\fBzio_object\fR
.ad
.RS 12n
The object number for a given I/O.
.RE

.sp
.ne 2
.na
\fBzio_level\fR
.ad
.RS 12n
The indirect level for the block. Level 0 is the lowest level and includes
data blocks. Values > 0 indicate metadata blocks at the appropriate level.
.RE

.sp
.ne 2
.na
\fBzio_blkid\fR
.ad
.RS 12n
The block ID for a given I/O.
.RE

.sp
.ne 2
.na
\fBzio_err\fR
.ad
.RS 12n
The errno for a failure when handling a given I/O. The errno is compatible
with \fBerrno\fR(3) with the value for EBADE (0x34) used to indicate ZFS
checksum error.
.RE

.sp
.ne 2
.na
\fBzio_offset\fR
.ad
.RS 12n
The offset in bytes of where to write the I/O for the specified vdev.
.RE

.sp
.ne 2
.na
\fBzio_size\fR
.ad
.RS 12n
The size in bytes of the I/O.
.RE

.sp
.ne 2
.na
\fBzio_flags\fR
.ad
.RS 12n
The current flags describing how the I/O should be handled.  See the
\fBI/O FLAGS\fR section for the full list of I/O flags.
.RE

.sp
.ne 2
.na
\fBzio_stage\fR
.ad
.RS 12n
The current stage of the I/O in the pipeline.  See the \fBI/O STAGES\fR
section for a full list of all the I/O stages.
.RE

.sp
.ne 2
.na
\fBzio_pipeline\fR
.ad
.RS 12n
The valid pipeline stages for the I/O.  See the \fBI/O STAGES\fR section for a
full list of all the I/O stages.
.RE

.sp
.ne 2
.na
\fBzio_delay\fR
.ad
.RS 12n
The time elapsed (in nanoseconds) waiting for the block layer to complete the
I/O.  Unlike \fBzio_delta\fR this does not include any vdev queuing time and is
therefore solely a measure of the block layer performance.
.RE

.sp
.ne 2
.na
\fBzio_timestamp\fR
.ad
.RS 12n
The time when a given I/O was submitted.
.RE

.sp
.ne 2
.na
\fBzio_delta\fR
.ad
.RS 12n
The time required to service a given I/O.
.RE

.sp
.ne 2
.na
\fBprev_state\fR
.ad
.RS 12n
The previous state of the vdev.
.RE

.sp
.ne 2
.na
\fBcksum_expected\fR
.ad
.RS 12n
The expected checksum value for the block.
.RE

.sp
.ne 2
.na
\fBcksum_actual\fR
.ad
.RS 12n
The actual checksum value for an errant block.
.RE

.sp
.ne 2
.na
\fBcksum_algorithm\fR
.ad
.RS 12n
Checksum algorithm used. See \fBzfs\fR(8) for more information on checksum
algorithms available.
.RE

.sp
.ne 2
.na
\fBcksum_byteswap\fR
.ad
.RS 12n
Whether or not the data is byteswapped.
.RE

.sp
.ne 2
.na
\fBbad_ranges\fR
.ad
.RS 12n
[start, end) pairs of corruption offsets. Offsets are always aligned on a
64-bit boundary, and can include some gaps of non-corruption.
(See \fBbad_ranges_min_gap\fR)
.RE

.sp
.ne 2
.na
\fBbad_ranges_min_gap\fR
.ad
.RS 12n
In order to bound the size of the \fBbad_ranges\fR array, gaps of non-corruption
less than or equal to \fBbad_ranges_min_gap\fR bytes have been merged with
adjacent corruption. Always at least 8 bytes, since corruption is detected
on a 64-bit word basis.
.RE

.sp
.ne 2
.na
\fBbad_range_sets\fR
.ad
.RS 12n
This array has one element per range in \fBbad_ranges\fR. Each element contains
the count of bits in that range which were clear in the good data and set
in the bad data.
.RE

.sp
.ne 2
.na
\fBbad_range_clears\fR
.ad
.RS 12n
This array has one element per range in \fBbad_ranges\fR. Each element contains
the count of bits for that range which were set in the good data and clear in
the bad data.
.RE

.sp
.ne 2
.na
\fBbad_set_bits\fR
.ad
.RS 12n
If this field exists, it is an array of: (bad data & ~(good data)); that is,
the bits set in the bad data which are cleared in the good data. Each element
corresponds a byte whose offset is in a range in \fBbad_ranges\fR, and the
array is ordered by offset. Thus, the first element is the first byte in the
first \fBbad_ranges\fR range, and the last element is the last byte in the last
\fBbad_ranges\fR range.
.RE

.sp
.ne 2
.na
\fBbad_cleared_bits\fR
.ad
.RS 12n
Like \fBbad_set_bits\fR, but contains: (good data & ~(bad data)); that is,
the bits set in the good data which are cleared in the bad data.
.RE

.sp
.ne 2
.na
\fBbad_set_histogram\fR
.ad
.RS 12n
If this field exists, it is an array of counters. Each entry counts bits set
in a particular bit of a big-endian uint64 type. The first entry counts bits
set in the high-order bit of the first byte, the 9th byte, etc, and the last
entry counts bits set of the low-order bit of the 8th byte, the 16th byte, etc.
This information is useful for observing a stuck bit in a parallel data path,
such as IDE or parallel SCSI.
.RE

.sp
.ne 2
.na
\fBbad_cleared_histogram\fR
.ad
.RS 12n
If this field exists, it is an array of counters. Each entry counts bit clears
in a particular bit of a big-endian uint64 type. The first entry counts bits
clears of the high-order bit of the first byte, the 9th byte, etc, and the
last entry counts clears of the low-order bit of the 8th byte, the 16th byte,
etc. This information is useful for observing a stuck bit in a parallel data
path, such as IDE or parallel SCSI.
.RE

.SS "I/O STAGES"
.sp
.LP
The ZFS I/O pipeline is comprised of various stages which are defined
below.  The individual stages are used to construct these basic I/O
operations: Read, Write, Free, Claim, and Ioctl.  These stages may be
set on an event to describe the life cycle of a given I/O.

.TS
tab(:);
l l l .
Stage:Bit Mask:Operations
_:_:_
ZIO_STAGE_OPEN:0x00000001:RWFCI

ZIO_STAGE_READ_BP_INIT:0x00000002:R----
ZIO_STAGE_WRITE_BP_INIT:0x00000004:-W---
ZIO_STAGE_FREE_BP_INIT:0x00000008:--F--
ZIO_STAGE_ISSUE_ASYNC:0x00000010:RWF--
ZIO_STAGE_WRITE_COMPRESS:0x00000020:-W---

ZIO_STAGE_ENCRYPT:0x00000040:-W---
ZIO_STAGE_CHECKSUM_GENERATE:0x00000080:-W---

ZIO_STAGE_NOP_WRITE:0x00000100:-W---

ZIO_STAGE_DDT_READ_START:0x00000200:R----
ZIO_STAGE_DDT_READ_DONE:0x00000400:R----
ZIO_STAGE_DDT_WRITE:0x00000800:-W---
ZIO_STAGE_DDT_FREE:0x00001000:--F--

ZIO_STAGE_GANG_ASSEMBLE:0x00002000:RWFC-
ZIO_STAGE_GANG_ISSUE:0x00004000:RWFC-

ZIO_STAGE_DVA_THROTTLE:0x00008000:-W---
ZIO_STAGE_DVA_ALLOCATE:0x00010000:-W---
ZIO_STAGE_DVA_FREE:0x00020000:--F--
ZIO_STAGE_DVA_CLAIM:0x00040000:---C-

ZIO_STAGE_READY:0x00080000:RWFCI

ZIO_STAGE_VDEV_IO_START:0x00100000:RW--I
ZIO_STAGE_VDEV_IO_DONE:0x00200000:RW--I
ZIO_STAGE_VDEV_IO_ASSESS:0x00400000:RW--I

ZIO_STAGE_CHECKSUM_VERIFY:0x00800000:R----

ZIO_STAGE_DONE:0x01000000:RWFCI
.TE

.SS "I/O FLAGS"
.sp
.LP
Every I/O in the pipeline contains a set of flags which describe its
function and are used to govern its behavior.  These flags will be set
in an event as an \fBzio_flags\fR payload entry.

.TS
tab(:);
l l .
Flag:Bit Mask
_:_
ZIO_FLAG_DONT_AGGREGATE:0x00000001
ZIO_FLAG_IO_REPAIR:0x00000002
ZIO_FLAG_SELF_HEAL:0x00000004
ZIO_FLAG_RESILVER:0x00000008
ZIO_FLAG_SCRUB:0x00000010
ZIO_FLAG_SCAN_THREAD:0x00000020
ZIO_FLAG_PHYSICAL:0x00000040

ZIO_FLAG_CANFAIL:0x00000080
ZIO_FLAG_SPECULATIVE:0x00000100
ZIO_FLAG_CONFIG_WRITER:0x00000200
ZIO_FLAG_DONT_RETRY:0x00000400
ZIO_FLAG_DONT_CACHE:0x00000800
ZIO_FLAG_NODATA:0x00001000
ZIO_FLAG_INDUCE_DAMAGE:0x00002000

ZIO_FLAG_IO_ALLOCATING:0x00004000
ZIO_FLAG_IO_RETRY:0x00008000
ZIO_FLAG_PROBE:0x00010000
ZIO_FLAG_TRYHARD:0x00020000
ZIO_FLAG_OPTIONAL:0x00040000

ZIO_FLAG_DONT_QUEUE:0x00080000
ZIO_FLAG_DONT_PROPAGATE:0x00100000
ZIO_FLAG_IO_BYPASS:0x00200000
ZIO_FLAG_IO_REWRITE:0x00400000
ZIO_FLAG_RAW_COMPRESS:0x00800000
ZIO_FLAG_RAW_ENCRYPT:0x01000000

ZIO_FLAG_GANG_CHILD:0x02000000
ZIO_FLAG_DDT_CHILD:0x04000000
ZIO_FLAG_GODFATHER:0x08000000
ZIO_FLAG_NOPWRITE:0x10000000
ZIO_FLAG_REEXECUTED:0x20000000
ZIO_FLAG_DELEGATED:0x40000000
ZIO_FLAG_FASTWRITE:0x80000000
.TE