1 .TH BTREPLAY 1 "December 8, 2007" "blktrace git\-20071207142532" ""
5 btreplay \- recreate IO loads recorded by blktrace
11 btreplay [ \fIoptions\fR ] <\fIdev\fR...>
17 The \fIbtrecord\fR and \fIbtreplay\fR tools provide the ability to
18 record and replay IOs captured by the \fIblktrace\fR utility. Attempts
19 are made to maintain ordering, CPU mappings and time-separation of IOs.
23 The \fIblktrace\fR utility provides the ability to collect detailed
24 traces from the kernel for each IO processed by the block IO layer. The
25 traces provide a complete timeline for each IO processed, including
26 detailed information concerning when an IO was first received by the block
27 IO layer \(em indicating the device, CPU number, time stamp, IO direction,
28 sector number and IO size (number of sectors). Using this information,
29 one is able to \fBreplay\fR the IO again on the same machine or another
33 The basic operating work-flow to replay IOs would be something like:
36 Run \fIblktrace\fR to collect traces. Here you specify the
37 device or devices that you wish to trace and later replay IOs upon. Note:
38 the only traces you are interested in are \fBQUEUE\fR requests \(em
39 thus, to save system resources (including storage for traces), one could
40 specify the \fI-a queue\fR command line option to \fIblktrace\fR.
43 While \fIblktrace\fR is running, you run the workload that you
47 When the work load has completed, you stop the \fIblktrace\fR
48 utility (thus saving all traces over the complete workload).
51 You extract the pertinent IO information from the traces saved by
52 \fIblktrace\fR using the \fIbtrecord\fR utility. This will parse
53 each trace file created by \fIblktrace\fR, and crafty IO descriptions
54 to be used in the next phase of the workload processing.
57 Once \fIbtrecord\fR has successfully created a series of data
58 files to be processed, you can run the \fIbtreplay\fR utility which
59 attempts to generate the same IOs seen during the sample workload phase.
68 Set number of CPUs to use.
73 \-\-input\-directory=<\fIdir\fR>
76 This option requires a single parameter providing the directory
77 name for where input files are to be found. The default directory is the
78 current directory (\fI.\fR).
85 Find record files automatically
86 This option instructs \fIbtreplay\fR to go find all the record files in the
87 directory specified (either via the \fI-d\fR option, or in the default
100 \-\-input\-base=<\fIbasename\fR>
102 Set base name for input files.
103 Each input file has 3 fields:
105 Device identifier (taken directly from the device name of the
106 \fIblktrace\fR output file).
108 \fIbtrecord\fR base name \(em by default ``replay''.
110 The CPU number (again, taken directly from the
111 \fIblktrace\fR output file name).
113 This option requires a single parameter that will override the default name
114 (replay), and replace it with the specified value.
119 \-\-iterations=<\fInum\fR>
121 Set number of iterations to run.
122 This option requires a single parameter which specifies the number of times
123 to run through the input files. The default value is 1
128 \-\-map\-devs=<\fIfilename\fR>
130 Specify device mappings.
131 This option requires a single paramter which specifies the name of a
132 file contain device mappings. The file must be very simply managed, with
133 just two pieces of data per line:
136 The device name on the recorded system (with the '\fI/dev/\fR'
137 removed). Example: \fI/dev/sda\fR would just be \fIsda\fR.
140 The device name on the replay system to use (again, without the
141 '\fI/dev/\fR' path prepended).
144 An example file for when one would map devices \fI/dev/sda\fR and
145 \fI/dev/sdb\fR on the recorded system to \fIdev/sdg\fR and
146 \fIsdh\fR on the replay system would be:
155 The only entries in the file that are allowed are these two element lines \(em
156 we do not (yet?) support the notion of blank lines, or comment lines, or the
160 The utility allows for multiple \fI-M\fR options to be
161 supplied on the command line.
168 Disable pre-bunch stalls.
169 When specified on the command line, all pre-bunch stall indicators will be
170 ignored. IOs will be replayed without inter-bunch delays.
177 Enable verbose output.
178 When specified on the command line, this option instructs \fIbtreplay\fR
179 to store information concerning each \fBstall\fR and IO operation
180 performed by \fIbtreplay\fR. The name of each file so created will be
181 the input file name used with an extension of \fI.rep\fR appended onto
182 it. Thus, an input file of the name \fIsdab.replay.3\fR would generate a
183 verbose output file with the name \fIsdab.replay.3.rep\fR in the
184 directory specified for input files.
186 In addition, \fIbtreplay\fR will also output to \fIstderr\fR the
187 names of the input files being processed.
194 Show version number and exit.
201 Enable writing during replay.
202 As a precautionary measure, by default \texttt{btreplay} will not
203 process \fBwrite requests. In order to enable \fIbtreplay\fR to
204 actually \fBwrite\fR to devices one must explicitly specify the
210 \fIbtreplay\fR was written by Alan D. Brunelle. This
211 man page was created from the \fIbtreplay\fR documentation by Bas Zoetekouw.
215 Report bugs to <linux\-btrace@vger.kernel.org>
218 Copyright \(co 2007 Alan D. Brunelle, Alan D. Brunelle and Nathan Scott.
220 This is free software. You may redistribute copies of it under the terms of
221 the GNU General Public License <http://www.gnu.org/licenses/gpl.html>.
222 There is NO WARRANTY, to the extent permitted by law.
224 This manual page was created for Debian by Bas Zoetekouw. It was derived from
225 the documentation provided by the authors and it may be used, distributed and
226 modified under the terms of the GNU General Public License, version 2.
228 On Debian systems, the text of the GNU General Public License can be found in
229 /usr/share/common\-licenses/GPL\-2.
232 The full documentation for btreplay can be found in /usr/share/doc/blktrace on Debian systems.
234 blktrace (8), blkparse (1), btrecord (8)