freebsd-nq/man/man1/ztest.1
Brian Behlendorf aa0ac7caa4 Make user stack limit configurable
To aid in detecting and debugging stack overflow issues make the
user space stack limit configurable via a new ZFS_STACK_SIZE
environment variable.  The value assigned to ZFS_STACK_SIZE will
be used as the default stack size in bytes.

Because this is mainly useful as a debugging aid in conjunction
with ztest the stack limit is disabled by default.  See the ztest(1)
man page for additional details on using the ZFS_STACK_SIZE
environment variable.

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ned Bass <bass6@llnl.gov>
Closes #2743
Issue #2293
2014-09-30 10:46:55 -07:00

170 lines
5.1 KiB
Groff

'\" t
.\"
.\" CDDL HEADER START
.\"
.\" 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]
.\"
.\" CDDL HEADER END
.\"
.\"
.\" Copyright (c) 2009 Oracle and/or its affiliates. All rights reserved.
.\" Copyright (c) 2009 Michael Gebetsroither <michael.geb@gmx.at>. All rights
.\" reserved.
.\"
.TH ztest 1 "2009 NOV 01" "ZFS on Linux" "User Commands"
.SH NAME
\fBztest\fR \- was written by the ZFS Developers as a ZFS unit test.
.SH SYNOPSIS
.LP
.BI "ztest <options>"
.SH DESCRIPTION
.LP
This manual page documents briefly the \fBztest\fR command.
.LP
\fBztest\fR was written by the ZFS Developers as a ZFS unit test. The
tool was developed in tandem with the ZFS functionality and was
executed nightly as one of the many regression test against the daily
build. As features were added to ZFS, unit tests were also added to
\fBztest\fR. In addition, a separate test development team wrote and
executed more functional and stress tests.
.LP
By default \fBztest\fR runs for ten minutes and uses block files
(stored in /tmp) to create pools rather than using physical disks.
Block files afford \fBztest\fR its flexibility to play around with
zpool components without requiring large hardware configurations.
However, storing the block files in /tmp may not work for you if you
have a small tmp directory.
.LP
By default is non-verbose. This is why entering the command above will
result in \fBztest\fR quietly executing for 5 minutes. The -V option
can be used to increase the verbosity of the tool. Adding multiple -V
option is allowed and the more you add the more chatty \fBztest\fR
becomes.
.LP
After the \fBztest\fR run completes, you should notice many ztest.*
files lying around. Once the run completes you can safely remove these
files. Note that you shouldn't remove these files during a run. You
can re-use these files in your next \fBztest\fR run by using the -E
option.
.SH OPTIONS
.HP
.BI "\-?" ""
.IP
Print a help summary.
.HP
.BI "\-v" " vdevs" " (default: 5)
.IP
Number of vdevs.
.HP
.BI "\-s" " size_of_each_vdev" " (default: 64M)"
.IP
Size of each vdev.
.HP
.BI "\-a" " alignment_shift" " (default: 9) (use 0 for random)"
.IP
Used alignment in test.
.HP
.BI "\-m" " mirror_copies" " (default: 2)"
.IP
Number of mirror copies.
.HP
.BI "\-r" " raidz_disks" " (default: 4)"
.IP
Number of raidz disks.
.HP
.BI "\-R" " raidz_parity" " (default: 1)"
.IP
Raidz parity.
.HP
.BI "\-d" " datasets" " (default: 7)"
.IP
Number of datasets.
.HP
.BI "\-t" " threads" " (default: 23)"
.IP
Number of threads.
.HP
.BI "\-g" " gang_block_threshold" " (default: 32K)"
.IP
Gang block threshold.
.HP
.BI "\-i" " initialize_pool_i_times" " (default: 1)"
.IP
Number of pool initialisations.
.HP
.BI "\-k" " kill_percentage" " (default: 70%)"
.IP
Kill percentage.
.HP
.BI "\-p" " pool_name" " (default: ztest)"
.IP
Pool name.
.HP
.BI "\-V(erbose)"
.IP
Verbose (use multiple times for ever more blather).
.HP
.BI "\-E(xisting)"
.IP
Use existing pool (use existing pool instead of creating new one).
.HP
.BI "\-T" " time" " (default: 300 sec)"
.IP
Total test run time.
.HP
.BI "\-z" " zil_failure_rate" " (default: fail every 2^5 allocs)
.IP
Injected failure rate.
.SH "EXAMPLES"
.LP
To override /tmp as your location for block files, you can use the -f
option:
.IP
ztest -f /
.LP
To get an idea of what ztest is actually testing try this:
.IP
ztest -f / -VVV
.LP
Maybe you'd like to run ztest for longer? To do so simply use the -T
option and specify the runlength in seconds like so:
.IP
ztest -f / -V -T 120
.SH "ENVIRONMENT VARIABLES"
.TP
.B "ZFS_STACK_SIZE=stacksize"
Limit the default stack size to \fBstacksize\fR bytes for the purpose of
detecting and debugging kernel stack overflows. For x86_64 platforms this
value should be set as follows to simulate these platforms: \fB8192\fR
(Linux), \fB20480\fR (Illumos), \fB16384\fR (FreeBSD).
In practice you may need to set these value slightly higher because
differences in stack usage between kernel and user space can lead to spurious
stack overflows (especially when debugging is enabled). The specified value
will be rounded up to a floor of PTHREAD_STACK_MIN which is the minimum stack
required for a NULL procedure in user space.
By default the stack size is limited to 256K.
.SH "SEE ALSO"
.BR "zpool (1)" ","
.BR "zfs (1)" ","
.BR "zdb (1)" ","
.SH "AUTHOR"
This manual page was transvered to asciidoc by Michael Gebetsroither
<gebi@grml.org> from http://opensolaris.org/os/community/zfs/ztest/