raidz_test.1: modernise
Also re-add articles left out by the slav who wrote this Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz> Closes #12125
This commit is contained in:
наб
Brian Behlendorf
parent
defa5a0ae5
commit
3365d2cf71
|
|
@ -1,4 +1,3 @@
|
|||
'\" t
|
||||
.\"
|
||||
.\" CDDL HEADER START
|
||||
.\"
|
||||
|
|
@ -19,88 +18,84 @@
|
|||
.\"
|
||||
.\" CDDL HEADER END
|
||||
.\"
|
||||
.\"
|
||||
.\" Copyright (c) 2016 Gvozden Nešković. All rights reserved.
|
||||
.\"
|
||||
.TH RAIDZ_TEST 1 "Aug 24, 2020" OpenZFS
|
||||
|
||||
.SH NAME
|
||||
\fBraidz_test\fR \- raidz implementation verification and benchmarking tool
|
||||
.SH SYNOPSIS
|
||||
.LP
|
||||
.BI "raidz_test <options>"
|
||||
.SH DESCRIPTION
|
||||
.LP
|
||||
This manual page documents briefly the \fBraidz_test\fR command.
|
||||
.LP
|
||||
Purpose of this tool is to run all supported raidz implementation and verify
|
||||
results of all methods. Tool also contains a parameter sweep option where all
|
||||
parameters affecting RAIDZ block are verified (like ashift size, data offset,
|
||||
data size, etc...).
|
||||
The tool also supports a benchmarking mode using -B option.
|
||||
.SH OPTION
|
||||
.HP
|
||||
.BI "\-h" ""
|
||||
.IP
|
||||
.Dd May 26, 2021
|
||||
.Dt RAIDZ_TEST 1
|
||||
.Os
|
||||
.
|
||||
.Sh NAME
|
||||
.Nm raidz_test
|
||||
.Nd raidz implementation verification and benchmarking tool
|
||||
.Sh SYNOPSIS
|
||||
.Nm
|
||||
.Op Fl StBevTD
|
||||
.Op Fl a Ar ashift
|
||||
.Op Fl o Ar zio_off_shift
|
||||
.Op Fl d Ar raidz_data_disks
|
||||
.Op Fl s Ar zio_size_shift
|
||||
.Op Fl r Ar reflow_offset
|
||||
.
|
||||
.Sh DESCRIPTION
|
||||
The purpose of this tool is to run all supported raidz implementation and verify
|
||||
the results of all methods.
|
||||
It also contains a parameter sweep option where all
|
||||
parameters affecting a RAIDZ block are verified (like ashift size, data offset,
|
||||
data size, etc.).
|
||||
The tool also supports a benchmarking mode using the
|
||||
.Fl B
|
||||
option.
|
||||
.
|
||||
.Sh OPTION
|
||||
.Bl -tag -width "-B(enchmark)"
|
||||
.It Fl h
|
||||
Print a help summary.
|
||||
.HP
|
||||
.BI "\-a" " ashift (default: 9)"
|
||||
.IP
|
||||
.It Fl a Ar ashift No (default: Sy 9 )
|
||||
Ashift value.
|
||||
.HP
|
||||
.BI "\-o" " zio_off_shift" " (default: 0)"
|
||||
.IP
|
||||
Zio offset for raidz block. Offset value is 1 << (zio_off_shift)
|
||||
.HP
|
||||
.BI "\-d" " raidz_data_disks" " (default: 8)"
|
||||
.IP
|
||||
Number of raidz data disks to use. Additional disks for parity will be used
|
||||
during testing.
|
||||
.HP
|
||||
.BI "\-s" " zio_size_shift" " (default: 19)"
|
||||
.IP
|
||||
Size of data for raidz block. Size is 1 << (zio_size_shift).
|
||||
.HP
|
||||
.BI "\-r" " reflow_offset" " (default: uint max)"
|
||||
.IP
|
||||
Set raidz expansion offset. The expanded raidz map allocation function will
|
||||
.It Fl o Ar zio_off_shift No (default: Sy 0 )
|
||||
ZIO offset for each raidz block.
|
||||
The offset's value is
|
||||
.Sy 1 << zio_off_shift .
|
||||
.It Fl d Ar raidz_data_disks No (default: Sy 8 )
|
||||
Number of raidz data disks to use.
|
||||
Additional disks will be used for parity.
|
||||
.It Fl s Ar zio_size_shift No (default: Sy 19 )
|
||||
Size of data for raidz block.
|
||||
The real size is
|
||||
.Sy 1 << zio_size_shift .
|
||||
.It Fl r Ar reflow_offset No (default: Sy uint max )
|
||||
Set raidz expansion offset.
|
||||
The expanded raidz map allocation function will
|
||||
produce different map configurations depending on this value.
|
||||
.HP
|
||||
.BI "\-S(weep)"
|
||||
.IP
|
||||
Sweep parameter space while verifying the raidz implementations. This option
|
||||
will exhaust all most of valid values for -a -o -d -s options. Runtime using
|
||||
this option will be long.
|
||||
.HP
|
||||
.BI "\-t(imeout)"
|
||||
.IP
|
||||
Wall time for sweep test in seconds. The actual runtime could be longer.
|
||||
.HP
|
||||
.BI "\-B(enchmark)"
|
||||
.IP
|
||||
This options starts the benchmark mode. All implementations are benchmarked
|
||||
using increasing per disk data size. Results are given as throughput per disk,
|
||||
measured in MiB/s.
|
||||
.HP
|
||||
.BI "\-e(xpansion)"
|
||||
.IP
|
||||
.It Fl S Ns No (weep)
|
||||
Sweep parameter space while verifying the raidz implementations.
|
||||
This option
|
||||
will exhaust all most of valid values for the
|
||||
.Fl aods
|
||||
options.
|
||||
Runtime using this option will be long.
|
||||
.It Fl t Ns No (imeout)
|
||||
Wall time for sweep test in seconds.
|
||||
The actual runtime could be longer.
|
||||
.It Fl B Ns No (enchmark)
|
||||
All implementations are benchmarked using increasing per disk data size.
|
||||
Results are given as throughput per disk, measured in MiB/s.
|
||||
.It Fl e Ns No (xpansion)
|
||||
Use expanded raidz map allocation function.
|
||||
.HP
|
||||
.BI "\-v(erbose)"
|
||||
.IP
|
||||
.It Fl v Ns No (erbose)
|
||||
Increase verbosity.
|
||||
.HP
|
||||
.BI "\-T(est the test)"
|
||||
.IP
|
||||
Debugging option. When this option is specified tool is supposed to fail
|
||||
all tests. This is to check if tests would properly verify bit-exactness.
|
||||
.HP
|
||||
.BI "\-D(ebug)"
|
||||
.IP
|
||||
Debugging option. Specify to attach gdb when SIGSEGV or SIGABRT are received.
|
||||
.HP
|
||||
|
||||
.SH "SEE ALSO"
|
||||
.BR "ztest (1)"
|
||||
.SH "AUTHORS"
|
||||
vdev_raidz, created for OpenZFS by Gvozden Nešković <neskovic@gmail.com>
|
||||
.It Fl T Ns No (est the test)
|
||||
Debugging option: fail all tests.
|
||||
This is to check if tests would properly verify bit-exactness.
|
||||
.It Fl D Ns No (ebug)
|
||||
Debugging option: attach
|
||||
.Xr gdb 1
|
||||
when
|
||||
.Sy SIGSEGV
|
||||
or
|
||||
.Sy SIGABRT
|
||||
are received.
|
||||
.El
|
||||
.
|
||||
.Sh "SEE ALSO"
|
||||
.Xr ztest 1
|
||||
|
|
|
|||
Loading…
Reference in New Issue