• R/O
  • HTTP
  • SSH
  • HTTPS

jm: Commit

翻訳ドキュメント管理用


Commit MetaInfo

Revision775af457c320f74e4035b2bcd9532a9ad7861733 (tree)
Time2019-07-20 20:17:07
AuthorYuichi SATO <ysato444@ybb....>
CommiterSHIRAKATA Kentaro

Log Message

[JM:01533] sysstat-12.0.5 original and translation_list

Change Summary

Incremental Difference

--- /dev/null
+++ b/manual/sysstat/original/man1/cifsiostat.1
@@ -0,0 +1,194 @@
1+.TH CIFSIOSTAT 1 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+cifsiostat \- Report CIFS statistics.
4+.SH SYNOPSIS
5+.ie 'yes'no' \{
6+.B cifsiostat [ -h ] [ -k | -m ] [ -t ] [ -V ] [ --debuginfo ] [ --dec={ 0 | 1 | 2 } ] [ --human ] [
7+.I interval
8+.B [
9+.I count
10+.B ] ]
11+.\}
12+.el \{
13+.B cifsiostat [ -h ] [ -k | -m ] [ -t ] [ -V ] [ --dec={ 0 | 1 | 2 } ] [ --human ] [
14+.I interval
15+.B [
16+.I count
17+.B ] ]
18+.\}
19+.SH DESCRIPTION
20+The
21+.B cifsiostat
22+command displays statistics about read and write operations
23+on CIFS filesystems.
24+
25+The
26+.I interval
27+parameter specifies the amount of time in seconds between
28+each report. The first report contains statistics for the time since
29+system startup (boot). Each subsequent report contains statistics
30+collected during the interval since the previous report.
31+A report consists of a CIFS header row followed by
32+a line of statistics for each CIFS filesystem that is mounted.
33+The
34+.I count
35+parameter can be specified in conjunction with the
36+.I interval
37+parameter. If the
38+.I count
39+parameter is specified, the value of
40+.I count
41+determines the number of reports generated at
42+.I interval
43+seconds apart. If the
44+.I interval
45+parameter is specified without the
46+.I count
47+parameter, the
48+.B cifsiostat
49+command generates reports continuously.
50+
51+.SH REPORT
52+The CIFS report provides statistics for each mounted CIFS filesystem.
53+The report shows the following fields:
54+
55+.B Filesystem:
56+.RS
57+This columns shows the mount point of the CIFS filesystem.
58+
59+.RE
60+.B rB/s (rkB/s, rMB/s)
61+.RS
62+Indicate the average number of bytes (kilobytes, megabytes) read per second.
63+
64+.RE
65+.B wB/s (wkB/s, wMB/s)
66+.RS
67+Indicate the average number of bytes (kilobytes, megabytes) written per second.
68+
69+.RE
70+.B rop/s
71+.RS
72+Indicate the number of 'read' operations that were issued to the filesystem
73+per second.
74+
75+.RE
76+.B wop/s
77+.RS
78+Indicate the number of 'write' operations that were issued to the filesystem
79+per second.
80+
81+.RE
82+.B fo/s
83+.RS
84+Indicate the number of open files per second.
85+
86+.RE
87+.B fc/s
88+.RS
89+Indicate the number of closed files per second.
90+
91+.RE
92+.B fd/s
93+.RS
94+Indicate the number of deleted files per second.
95+.RE
96+.RE
97+.SH OPTIONS
98+.if 'yes'no' \{
99+.IP --debuginfo
100+Print debug output to stderr.
101+.\}
102+.IP "--dec={ 0 | 1 | 2 }"
103+Specify the number of decimal places to use (0 to 2, default value is 2).
104+.IP -h
105+Make the CIFS report easier to read by a human.
106+.B --human
107+is enabled implicitly with this option.
108+.IP --human
109+Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.)
110+The units displayed with this option supersede any other default units (e.g.
111+kilobytes, sectors...) associated with the metrics.
112+.IP -k
113+Display statistics in kilobytes per second.
114+.IP -m
115+Display statistics in megabytes per second.
116+.IP -t
117+Print the time for each report displayed. The timestamp format may depend
118+on the value of the S_TIME_FORMAT environment variable (see below).
119+.IP -V
120+Print version number then exit.
121+
122+.SH ENVIRONMENT
123+The
124+.B cifsiostat
125+command takes into account the following environment variables:
126+
127+.IP S_COLORS
128+When this variable is set, display statistics in color on the terminal.
129+Possible values for this variable are
130+.IR never ,
131+.IR always
132+or
133+.IR auto
134+(the latter is the default).
135+
136+Please note that the color (being red, yellow, or some other color) used to display a value
137+is not indicative of any kind of issue simply because of the color. It only indicates different
138+ranges of values.
139+
140+.IP S_COLORS_SGR
141+Specify the colors and other attributes used to display statistics on the terminal.
142+Its value is a colon-separated list of capabilities that defaults to
143+.BR I=32;22:N=34;1:Z=34;22 .
144+Supported capabilities are:
145+
146+.RS
147+.TP
148+.B I=
149+SGR substring for filesystem names.
150+
151+.TP
152+.B N=
153+SGR substring for non-zero statistics values.
154+
155+.TP
156+.B Z=
157+SGR substring for zero values.
158+.RE
159+
160+.IP S_TIME_FORMAT
161+If this variable exists and its value is
162+.BR ISO
163+then the current locale will be ignored when printing the date in the report
164+header. The
165+.B cifsiostat
166+command will use the ISO 8601 format (YYYY-MM-DD) instead.
167+The timestamp displayed with option -t will also be compliant with ISO 8601
168+format.
169+
170+.SH BUG
171+.I /proc
172+filesystem must be mounted for
173+.B cifsiostat
174+to work.
175+
176+.SH FILE
177+.I /proc/fs/cifs/Stats
178+contains CIFS statistics.
179+.SH AUTHORS
180+Written by Ivana Varekova (varekova <at> redhat.com)
181+
182+Maintained by Sebastien Godard (sysstat <at> orange.fr)
183+.SH SEE ALSO
184+.BR sar (1),
185+.BR pidstat (1),
186+.BR mpstat (1),
187+.BR vmstat (8),
188+.BR iostat (1),
189+.BR tapestat (1),
190+.BR nfsiostat (1)
191+
192+.I https://github.com/sysstat/sysstat
193+
194+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man1/iostat.1
@@ -0,0 +1,523 @@
1+.TH IOSTAT 1 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+iostat \- Report Central Processing Unit (CPU) statistics and input/output
4+statistics for devices and partitions.
5+.SH SYNOPSIS
6+.ie 'yes'no' \{
7+.B iostat [ -c ] [ -d ] [ -h ] [ -k | -m ] [ -N ] [ -s ] [ -t ] [ -V ] [ -x ] [ -y ] [ -z ]
8+.B [ --dec={ 0 | 1 | 2 } ] [ -j { ID | LABEL | PATH | UUID | ... } ] [ -o JSON ]
9+.B [ [ -H ] -g
10+.I group_name
11+.B ] [ --human ] [ -p [
12+.I device
13+.B [,...] | ALL ] ] [
14+.I device
15+.B [...] | ALL ] [ --debuginfo ] [
16+.I interval
17+.B [
18+.I count
19+.B ] ]
20+.\}
21+.el \{
22+.B iostat [ -c ] [ -d ] [ -h ] [ -k | -m ] [ -N ] [ -s ] [ -t ] [ -V ] [ -x ] [ -y ] [ -z ]
23+.B [ --dec={ 0 | 1 | 2 } ] [ -j { ID | LABEL | PATH | UUID | ... } ] [ -o JSON ]
24+.B [ [ -H ] -g
25+.I group_name
26+.B ] [ --human ] [ -p [
27+.I device
28+.B [,...] | ALL ] ] [
29+.I device
30+.B [...] | ALL ] [
31+.I interval
32+.B [
33+.I count
34+.B ] ]
35+.\}
36+.SH DESCRIPTION
37+The
38+.B iostat
39+command is used for monitoring system input/output device
40+loading by observing the time the devices are active in relation
41+to their average transfer rates. The
42+.B iostat
43+command generates reports
44+that can be used to change system configuration to better balance
45+the input/output load between physical disks.
46+
47+The first report generated by the
48+.B iostat
49+command provides statistics
50+concerning the time since the system was booted, unless the
51+.B -y
52+option is used (in this case, this first report is omitted).
53+Each subsequent report
54+covers the time since the previous report. All statistics are reported
55+each time the
56+.B iostat
57+command is run. The report consists of a
58+CPU header row followed by a row of
59+CPU statistics. On
60+multiprocessor systems, CPU statistics are calculated system-wide
61+as averages among all processors. A device header row is displayed
62+followed by a line of statistics for each device that is configured.
63+
64+The
65+.I interval
66+parameter specifies the amount of time in seconds between
67+each report. The
68+.I count
69+parameter can be specified in conjunction with the
70+.I interval
71+parameter. If the
72+.I count
73+parameter is specified, the value of
74+.I count
75+determines the number of reports generated at
76+.I interval
77+seconds apart. If the
78+.I interval
79+parameter is specified without the
80+.I count
81+parameter, the
82+.B iostat
83+command generates reports continuously.
84+
85+.SH REPORTS
86+The
87+.B iostat
88+command generates two types of reports, the CPU
89+Utilization report and the Device Utilization report.
90+.IP "CPU Utilization Report"
91+The first report generated by the
92+.B iostat
93+command is the CPU
94+Utilization Report. For multiprocessor systems, the CPU values are
95+global averages among all processors.
96+The report has the following format:
97+
98+.B %user
99+.RS
100+.RS
101+Show the percentage of CPU utilization that occurred while
102+executing at the user level (application).
103+.RE
104+
105+.B %nice
106+.RS
107+Show the percentage of CPU utilization that occurred while
108+executing at the user level with nice priority.
109+.RE
110+
111+.B %system
112+.RS
113+Show the percentage of CPU utilization that occurred while
114+executing at the system level (kernel).
115+.RE
116+
117+.B %iowait
118+.RS
119+Show the percentage of time that the CPU or CPUs were idle during which
120+the system had an outstanding disk I/O request.
121+.RE
122+
123+.B %steal
124+.RS
125+Show the percentage of time spent in involuntary wait by the virtual CPU
126+or CPUs while the hypervisor was servicing another virtual processor.
127+.RE
128+
129+.B %idle
130+.RS
131+Show the percentage of time that the CPU or CPUs were idle and the system
132+did not have an outstanding disk I/O request.
133+.RE
134+.RE
135+.IP "Device Utilization Report"
136+The second report generated by the
137+.B iostat
138+command is the Device Utilization
139+Report. The device report provides statistics on a per physical device
140+or partition basis. Block devices and partitions for which statistics are
141+to be displayed may be entered on the command line.
142+If no device nor partition
143+is entered, then statistics are displayed
144+for every device used by the system, and
145+providing that the kernel maintains statistics for it.
146+If the
147+.B ALL
148+keyword is given on the command line, then statistics are
149+displayed for every device defined by the system, including those
150+that have never been used.
151+Transfer rates are shown in 1K blocks by default, unless the environment
152+variable POSIXLY_CORRECT is set, in which case 512-byte blocks are used.
153+The report may show the following fields,
154+depending on the flags used:
155+
156+.B Device:
157+.RS
158+.RS
159+This column gives the device (or partition) name as listed in the /dev
160+directory.
161+
162+.RE
163+.B tps
164+.RS
165+Indicate the number of transfers per second that were issued
166+to the device. A transfer is an I/O request to the
167+device. Multiple logical requests can be combined into a single I/O
168+request to the device. A transfer is of indeterminate size.
169+
170+.RE
171+.B Blk_read/s (kB_read/s, MB_read/s)
172+.RS
173+Indicate the amount of data read from the device expressed in a number of
174+blocks (kilobytes, megabytes) per second. Blocks are equivalent to sectors
175+and therefore have a size of 512 bytes.
176+
177+.RE
178+.B Blk_wrtn/s (kB_wrtn/s, MB_wrtn/s)
179+.RS
180+Indicate the amount of data written to the device expressed in a number of
181+blocks (kilobytes, megabytes) per second.
182+
183+.RE
184+.B Blk_read (kB_read, MB_read)
185+.RS
186+The total number of blocks (kilobytes, megabytes) read.
187+
188+.RE
189+.B Blk_wrtn (kB_wrtn, MB_wrtn)
190+.RS
191+The total number of blocks (kilobytes, megabytes) written.
192+
193+.RE
194+.B r/s
195+.RS
196+The number (after merges) of read requests completed per second for the device.
197+
198+.RE
199+.B w/s
200+.RS
201+The number (after merges) of write requests completed per second for the device.
202+
203+.RE
204+.B sec/s (kB/s, MB/s)
205+.RS
206+The number of sectors (kilobytes, megabytes) read from or written to the device
207+per second.
208+
209+.RE
210+.B rsec/s (rkB/s, rMB/s)
211+.RS
212+The number of sectors (kilobytes, megabytes) read from the device per second.
213+
214+.RE
215+.B wsec/s (wkB/s, wMB/s)
216+.RS
217+The number of sectors (kilobytes, megabytes) written to the device per second.
218+
219+.RE
220+.B rqm/s
221+.RS
222+The number of I/O requests merged per second that were queued to the device.
223+
224+.RE
225+.B rrqm/s
226+.RS
227+The number of read requests merged per second that were queued to the device.
228+
229+.RE
230+.B wrqm/s
231+.RS
232+The number of write requests merged per second that were queued to the device.
233+
234+.RE
235+.B %rrqm
236+.RS
237+The percentage of read requests merged together before being sent to the device.
238+
239+.RE
240+.B %wrqm
241+.RS
242+The percentage of write requests merged together before being sent to the device.
243+
244+.RE
245+.B areq-sz
246+.RS
247+The average size (in kilobytes) of the I/O requests that were issued to the device.
248+.br
249+Note: In previous versions, this field was known as avgrq-sz and was expressed in
250+sectors.
251+
252+.RE
253+.B rareq-sz
254+.RS
255+The average size (in kilobytes) of the read requests that were issued to the
256+device.
257+
258+.RE
259+.B wareq-sz
260+.RS
261+The average size (in kilobytes) of the write requests that were issued to the
262+device.
263+
264+.RE
265+.B await
266+.RS
267+The average time (in milliseconds) for I/O requests issued to the device
268+to be served. This includes the time spent by the requests in queue and
269+the time spent servicing them.
270+
271+.RE
272+.B r_await
273+.RS
274+The average time (in milliseconds) for read requests issued to the device
275+to be served. This includes the time spent by the requests in queue and
276+the time spent servicing them.
277+
278+.RE
279+.B w_await
280+.RS
281+The average time (in milliseconds) for write requests issued to the device
282+to be served. This includes the time spent by the requests in queue and
283+the time spent servicing them.
284+
285+.RE
286+.B aqu-sz
287+.RS
288+The average queue length of the requests that were issued to the device.
289+.br
290+Note: In previous versions, this field was known as avgqu-sz.
291+
292+.RE
293+.B svctm
294+.RS
295+The average service time (in milliseconds) for I/O requests that were issued
296+to the device. Warning! Do not trust this field any more.
297+This field will be removed in a future sysstat version.
298+
299+.RE
300+.B %util
301+.RS
302+Percentage of elapsed time during which I/O requests were issued to the device
303+(bandwidth utilization for the device). Device saturation occurs when this
304+value is close to 100% for devices serving requests serially.
305+But for devices serving requests in parallel, such as RAID arrays and
306+modern SSDs, this number does not reflect their performance limits.
307+.RE
308+.RE
309+.SH OPTIONS
310+.IP -c
311+Display the CPU utilization report.
312+.IP -d
313+Display the device utilization report.
314+.if 'yes'no' \{
315+.IP --debuginfo
316+Print debug output to stderr.
317+.\}
318+.IP "--dec={ 0 | 1 | 2 }"
319+Specify the number of decimal places to use (0 to 2, default value is 2).
320+.IP "-g group_name { device [...] | ALL }
321+Display statistics for a group of devices.
322+The
323+.B iostat
324+command reports statistics for each individual device in the list
325+then a line of global statistics for the group displayed as
326+.B group_name
327+and made up of all the devices in the list. The
328+.B ALL
329+keyword means that all the block devices defined by the system shall be
330+included in the group.
331+.IP -H
332+This option must be used with option -g and indicates that only global
333+statistics for the group are to be displayed, and not statistics for
334+individual devices in the group.
335+.IP -h
336+Make the Device Utilization Report easier to read by a human.
337+.B --human
338+is enabled implicitly with this option.
339+.IP --human
340+Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.)
341+The units displayed with this option supersede any other default units (e.g.
342+kilobytes, sectors...) associated with the metrics.
343+.IP "-j { ID | LABEL | PATH | UUID | ... } [ device [...] | ALL ]"
344+Display persistent device names. Options
345+.BR ID ,
346+.BR LABEL ,
347+etc. specify the type of the persistent name. These options are not limited,
348+only prerequisite is that directory with required persistent names is present in
349+.IR /dev/disk .
350+Optionally, multiple devices can be specified in the chosen persistent name type.
351+Because persistent device names are usually long, option
352+.IP -k
353+Display statistics in kilobytes per second.
354+.IP -m
355+Display statistics in megabytes per second.
356+.IP -N
357+Display the registered device mapper names for any device mapper devices.
358+Useful for viewing LVM2 statistics.
359+.IP "-o JSON"
360+Display the statistics in JSON (Javascript Object Notation) format.
361+JSON output field order is undefined, and new fields may be added
362+in the future.
363+.IP "-p [ { device [,...] | ALL } ]"
364+The -p option displays statistics for
365+block devices and all their partitions that are used by the system.
366+If a device name is entered on the command line, then statistics for it
367+and all its partitions are displayed. Last, the
368+.B ALL
369+keyword indicates that statistics have to be displayed for all the block
370+devices and partitions defined by the system, including those that have
371+never been used. If option
372+.B -j
373+is defined before this option, devices entered on the command line can be
374+specified with the chosen persistent name type.
375+.IP -s
376+Display a short (narrow) version of the report that should fit in 80
377+characters wide screens.
378+.IP -t
379+Print the time for each report displayed. The timestamp format may depend
380+on the value of the S_TIME_FORMAT environment variable (see below).
381+.IP -V
382+Print version number then exit.
383+.IP -x
384+Display extended statistics.
385+.IP -y
386+Omit first report with statistics since system boot, if displaying
387+multiple records at given interval.
388+.IP -z
389+Tell
390+.B iostat
391+to omit output for any devices for which there was no activity
392+during the sample period.
393+
394+.SH ENVIRONMENT
395+The
396+.B iostat
397+command takes into account the following environment variables:
398+
399+.IP POSIXLY_CORRECT
400+When this variable is set, transfer rates are shown in 512-byte blocks instead
401+of the default 1K blocks.
402+
403+.IP S_COLORS
404+When this variable is set, display statistics in color on the terminal.
405+Possible values for this variable are
406+.IR never ,
407+.IR always
408+or
409+.IR auto
410+(the latter is the default).
411+
412+Please note that the color (being red, yellow, or some other color) used to display a value
413+is not indicative of any kind of issue simply because of the color. It only indicates different
414+ranges of values.
415+
416+.IP S_COLORS_SGR
417+Specify the colors and other attributes used to display statistics on the terminal.
418+Its value is a colon-separated list of capabilities that defaults to
419+.BR H=31;1:I=32;22:M=35;1:N=34;1:Z=34;22 .
420+Supported capabilities are:
421+
422+.RS
423+.TP
424+.B H=
425+SGR (Select Graphic Rendition) substring for percentage values greater than or equal to 75%.
426+
427+.TP
428+.B I=
429+SGR substring for device names.
430+
431+.TP
432+.B M=
433+SGR substring for percentage values in the range from 50% to 75%.
434+
435+.TP
436+.B N=
437+SGR substring for non-zero statistics values.
438+
439+.TP
440+.B Z=
441+SGR substring for zero values.
442+.RE
443+
444+.IP S_TIME_FORMAT
445+If this variable exists and its value is
446+.BR ISO
447+then the current locale will be ignored when printing the date in the report
448+header. The
449+.B iostat
450+command will use the ISO 8601 format (YYYY-MM-DD) instead.
451+The timestamp displayed with option -t will also be compliant with ISO 8601
452+format.
453+
454+.SH EXAMPLES
455+.B iostat
456+.RS
457+Display a single history since boot report for all CPU and Devices.
458+
459+.RE
460+.B iostat -d 2
461+.RS
462+Display a continuous device report at two second intervals.
463+
464+.RE
465+.B iostat -d 2 6
466+.RS
467+Display six reports at two second intervals for all devices.
468+
469+.RE
470+.B iostat -x sda sdb 2 6
471+.RS
472+Display six reports of extended statistics at two second intervals for devices
473+sda and sdb.
474+
475+.RE
476+.B iostat -p sda 2 6
477+.RS
478+Display six reports at two second intervals for device sda and all its
479+partitions (sda1, etc.)
480+.SH BUGS
481+.I /proc
482+filesystem must be mounted for
483+.B iostat
484+to work.
485+
486+Kernels older than 2.6.x are no longer supported.
487+
488+The average service time (svctm field) value is meaningless,
489+as I/O statistics are now calculated at block level, and we don't know
490+when the disk driver starts to process a request. For this reason,
491+this field will be removed in a future sysstat version.
492+.SH FILES
493+.I /proc/stat
494+contains system statistics.
495+
496+.I /proc/uptime
497+contains system uptime.
498+
499+.I /proc/diskstats
500+contains disks statistics.
501+
502+.I /sys
503+contains statistics for block devices.
504+
505+.I /proc/self/mountstats
506+contains statistics for network filesystems.
507+
508+.I /dev/disk
509+contains persistent device names.
510+.SH AUTHOR
511+Sebastien Godard (sysstat <at> orange.fr)
512+.SH SEE ALSO
513+.BR sar (1),
514+.BR pidstat (1),
515+.BR mpstat (1),
516+.BR vmstat (8),
517+.BR tapestat (1),
518+.BR nfsiostat (1),
519+.BR cifsiostat (1)
520+
521+.I https://github.com/sysstat/sysstat
522+
523+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man1/mpstat.1
@@ -0,0 +1,307 @@
1+.TH MPSTAT 1 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+mpstat \- Report processors related statistics.
4+.SH SYNOPSIS
5+.B mpstat [ -A ] [ --dec={ 0 | 1 | 2 } ] [ -n ] [ -u ] [ -V ] [ -I {
6+.I keyword
7+.B [,...] | ALL } ] [ -N {
8+.I node_list
9+.B | ALL } ] [ -o JSON ] [ -P {
10+.I cpu_list
11+.B | ALL } ] [
12+.I interval
13+.B [
14+.I count
15+.B ] ]
16+.SH DESCRIPTION
17+The
18+.B mpstat
19+command writes to standard output activities for each available processor,
20+processor 0 being the first one.
21+Global average activities among all processors are also reported.
22+The
23+.B mpstat
24+command can be used both on SMP and UP machines, but in the latter, only global
25+average activities will be printed. If no activity has been selected, then the
26+default report is the CPU utilization report.
27+
28+The
29+.I interval
30+parameter specifies the amount of time in seconds between each report.
31+A value of 0 (or no parameters at all) indicates that processors statistics are
32+to be reported for the time since system startup (boot).
33+The
34+.I count
35+parameter can be specified in conjunction with the
36+.I interval
37+parameter if this one is not set to zero. The value of
38+.I count
39+determines the number of reports generated at
40+.I interval
41+seconds apart. If the
42+.I interval
43+parameter is specified without the
44+.I count
45+parameter, the
46+.B mpstat
47+command generates reports continuously.
48+
49+.SH OPTIONS
50+.IP -A
51+This option is equivalent to specifying
52+.BR "-n -u -I ALL -N ALL -P ALL"
53+.IP "--dec={ 0 | 1 | 2 }"
54+Specify the number of decimal places to use (0 to 2, default value is 2).
55+.IP "-I { keyword [,...] | ALL }"
56+Report interrupts statistics.
57+
58+Possible keywords are
59+.BR CPU ,
60+.BR SCPU ,
61+and
62+.BR SUM .
63+
64+With the
65+.B CPU
66+keyword, the number of each individual interrupt received per
67+second by the CPU or CPUs is displayed. Interrupts are those listed
68+in /proc/interrupts file.
69+
70+With the
71+.B SCPU
72+keyword, the number of each individual software interrupt received per
73+second by the CPU or CPUs is displayed. This option works only
74+with kernels 2.6.31 and later. Software interrupts are those listed
75+in /proc/softirqs file.
76+
77+With the
78+.B SUM
79+keyword, the
80+.B mpstat
81+command reports the total number of interrupts per processor.
82+The following values are displayed:
83+
84+.B CPU
85+.RS
86+.RS
87+Processor number. The keyword
88+.I all
89+indicates that statistics are calculated as averages among all
90+processors.
91+.RE
92+
93+.B intr/s
94+.RS
95+Show the total number of interrupts received per second by
96+the CPU or CPUs.
97+.RE
98+
99+The
100+.B ALL
101+keyword is equivalent to specifying all the keywords above and
102+therefore all the interrupts statistics are displayed.
103+.RE
104+.RE
105+.IP "-N { node_list | ALL }"
106+Indicate the NUMA nodes for which statistics are to be reported.
107+.I node_list
108+is a list of comma-separated values or range of values (e.g.,
109+.BR 0,2,4-7,12- ).
110+Note that node
111+.B all
112+is the global average among all nodes. The
113+.B ALL
114+keyword indicates that statistics are to be reported for all nodes.
115+.IP -n
116+Report summary CPU statistics based on NUMA node placement. The following
117+values are displayed:
118+
119+.B NODE
120+.RS
121+.RS
122+Node number. The keyword
123+.I all
124+indicates that statistics are calculated as averages among all nodes.
125+.RE
126+
127+All the other fields are the same as those displayed with option -u
128+(see below).
129+.RE
130+.IP "-o JSON"
131+Display the statistics in JSON (Javascript Object Notation) format.
132+JSON output field order is undefined, and new fields may be added
133+in the future.
134+.IP "-P { cpu_list | ALL }"
135+Indicate the processors for which statistics are to be reported.
136+.I cpu_list
137+is a list of comma-separated values or range of values (e.g.,
138+.BR 0,2,4-7,12- ).
139+Note that processor 0 is the first processor, and processor
140+.B all
141+is the global average among all processors.
142+The
143+.B ALL
144+keyword indicates that statistics are to be reported for all processors.
145+Offline processors are not displayed.
146+.IP -u
147+Report CPU utilization. The following values are displayed:
148+
149+.B CPU
150+.RS
151+.RS
152+Processor number. The keyword
153+.I all
154+indicates that statistics are calculated as averages among all
155+processors.
156+.RE
157+
158+.B %usr
159+.RS
160+Show the percentage of CPU utilization that occurred while
161+executing at the user level (application).
162+.RE
163+
164+.B %nice
165+.RS
166+Show the percentage of CPU utilization that occurred while
167+executing at the user level with nice priority.
168+.RE
169+
170+.B %sys
171+.RS
172+Show the percentage of CPU utilization that occurred while
173+executing at the system level (kernel). Note that this does not
174+include time spent servicing hardware and software interrupts.
175+.RE
176+
177+.B %iowait
178+.RS
179+Show the percentage of time that the CPU or CPUs were idle during which
180+the system had an outstanding disk I/O request.
181+.RE
182+
183+.B %irq
184+.RS
185+Show the percentage of time spent by the CPU or CPUs to service hardware
186+interrupts.
187+.RE
188+
189+.B %soft
190+.RS
191+Show the percentage of time spent by the CPU or CPUs to service software
192+interrupts.
193+.RE
194+
195+.B %steal
196+.RS
197+Show the percentage of time spent in involuntary wait by the virtual CPU
198+or CPUs while the hypervisor was servicing another virtual processor.
199+.RE
200+
201+.B %guest
202+.RS
203+Show the percentage of time spent by the CPU or CPUs to run a virtual
204+processor.
205+.RE
206+
207+.B %gnice
208+.RS
209+Show the percentage of time spent by the CPU or CPUs to run a niced
210+guest.
211+.RE
212+
213+.B %idle
214+.RS
215+Show the percentage of time that the CPU or CPUs were idle and the system
216+did not have an outstanding disk I/O request.
217+.RE
218+.RE
219+.IP -V
220+Print version number then exit.
221+
222+.SH ENVIRONMENT
223+The
224+.B mpstat
225+command takes into account the following environment variable:
226+
227+.IP S_COLORS
228+When this variable is set, display statistics in color on the terminal.
229+Possible values for this variable are
230+.IR never ,
231+.IR always
232+or
233+.IR auto
234+(the latter is the default).
235+
236+Please note that the color (being red, yellow, or some other color) used to display a value
237+is not indicative of any kind of issue simply because of the color. It only indicates different
238+ranges of values.
239+
240+.IP S_COLORS_SGR
241+Specify the colors and other attributes used to display statistics on the terminal.
242+Its value is a colon-separated list of capabilities that defaults to
243+.BR H=31;1:I=32;22:M=35;1:N=34;1:Z=34;22 .
244+Supported capabilities are:
245+
246+.RS
247+.TP
248+.B H=
249+SGR (Select Graphic Rendition) substring for percentage values greater than or equal to 75%.
250+
251+.TP
252+.B I=
253+SGR substring for CPU number.
254+
255+.TP
256+.B M=
257+SGR substring for percentage values in the range from 50% to 75%.
258+
259+.TP
260+.B N=
261+SGR substring for non-zero statistics values.
262+
263+.TP
264+.B Z=
265+SGR substring for zero values.
266+.RE
267+
268+.IP S_TIME_FORMAT
269+If this variable exists and its value is
270+.BR ISO
271+then the current locale will be ignored when printing the date in the report header.
272+The
273+.B mpstat
274+command will use the ISO 8601 format (YYYY-MM-DD) instead.
275+The timestamp will also be compliant with ISO 8601 format.
276+
277+.SH EXAMPLES
278+.B mpstat 2 5
279+.RS
280+Display five reports of global statistics among all processors at two second intervals.
281+.RE
282+
283+.B mpstat -P ALL 2 5
284+.RS
285+Display five reports of statistics for all processors at two second intervals.
286+
287+.SH BUGS
288+.I /proc
289+filesystem must be mounted for the
290+.B mpstat
291+command to work.
292+
293+.SH FILES
294+.IR /proc
295+contains various files with system statistics.
296+
297+.SH AUTHOR
298+Sebastien Godard (sysstat <at> orange.fr)
299+.SH SEE ALSO
300+.BR sar (1),
301+.BR pidstat (1),
302+.BR iostat (1),
303+.BR vmstat (8)
304+
305+.I https://github.com/sysstat/sysstat
306+
307+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man1/pidstat.1
@@ -0,0 +1,673 @@
1+.TH PIDSTAT 1 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+pidstat \- Report statistics for Linux tasks.
4+.SH SYNOPSIS
5+.B pidstat [ -d ] [ -H ] [ -h ] [ -I ] [ -l ] [ -R ] [ -r ] [ -s ] [ -t ] [ -U [
6+.I username
7+.B ] ] [ -u ] [ -V ] [ -v ]
8+.B [ -w ] [ -C
9+.I comm
10+.B ] [ -G
11+.I process_name
12+.B ] [ --dec={ 0 | 1 | 2 } ] [ --human ] [ -p {
13+.I pid
14+.B [,...] | SELF | ALL } ] [ -T { TASK | CHILD | ALL } ] [
15+.I interval
16+.B [
17+.I count
18+.B ] ] [ -e
19+.I program
20+.I args
21+.B ]
22+.SH DESCRIPTION
23+The
24+.B pidstat
25+command is used for monitoring individual tasks currently being managed
26+by the Linux kernel.
27+It writes to standard output activities for every task selected with option
28+.B -p
29+or for every task managed by the Linux kernel if option
30+.B -p ALL
31+has been used. Not selecting any tasks is equivalent to specifying
32+.B -p ALL
33+but only active tasks (tasks with non-zero statistics values)
34+will appear in the report.
35+
36+The
37+.B pidstat
38+command can also be used for monitoring the child processes of selected tasks.
39+Read about option
40+.B -T
41+below.
42+
43+The
44+.I interval
45+parameter specifies the amount of time in seconds between each report.
46+A value of 0 (or no parameters at all) indicates that tasks statistics are
47+to be reported for the time since system startup (boot).
48+The
49+.I count
50+parameter can be specified in conjunction with the
51+.I interval
52+parameter if this one is not set to zero. The value of
53+.I count
54+determines the number of reports generated at
55+.I interval
56+seconds apart. If the
57+.I interval
58+parameter is specified without the
59+.I count
60+parameter, the
61+.B pidstat
62+command generates reports continuously.
63+
64+You can select information about specific task activities using flags.
65+Not specifying any flags selects only CPU activity.
66+
67+.SH OPTIONS
68+.IP "-C comm"
69+Display only tasks whose command name includes the string
70+.IR comm .
71+This string can be a regular expression.
72+.IP -d
73+Report I/O statistics (kernels 2.6.20 and later only).
74+The following values may be displayed:
75+
76+.B UID
77+.RS
78+.RS
79+The real user identification number of the task being monitored.
80+.RE
81+
82+.B USER
83+.RS
84+The name of the real user owning the task being monitored.
85+.RE
86+
87+.B PID
88+.RS
89+The identification number of the task being monitored.
90+.RE
91+
92+.B kB_rd/s
93+.RS
94+Number of kilobytes the task has caused to be read from disk
95+per second.
96+.RE
97+
98+.B kB_wr/s
99+.RS
100+Number of kilobytes the task has caused, or shall cause to be
101+written to disk per second.
102+.RE
103+
104+.B kB_ccwr/s
105+.RS
106+Number of kilobytes whose writing to disk has been cancelled by
107+the task. This may occur when the task truncates some
108+dirty pagecache. In this case, some IO which another task has
109+been accounted for will not be happening.
110+.RE
111+
112+.B iodelay
113+.RS
114+Block I/O delay of the task being monitored,
115+measured in clock ticks. This metric includes the delays spent
116+waiting for sync block I/O completion and for swapin block I/O
117+completion.
118+.RE
119+
120+.B Command
121+.RS
122+The command name of the task.
123+.RE
124+.RE
125+.IP "--dec={ 0 | 1 | 2 }"
126+Specify the number of decimal places to use (0 to 2, default value is 2).
127+.IP "-e program args"
128+Execute
129+.IR program
130+with given arguments
131+.IR args
132+and monitor it with
133+.B pidstat.
134+.B pidstat
135+stops when
136+.IR program
137+terminates.
138+.IP "-G process_name"
139+Display only processes whose command name includes the string
140+.IR process_name .
141+This string can be a regular expression. If option -t is used
142+together with option -G then the threads belonging to that
143+process are also displayed (even if their command name doesn't
144+include the string
145+.IR process_name ).
146+.IP -H
147+Display timestamp in seconds since the epoch.
148+.IP -h
149+Display all activities horizontally on a single line, with no
150+average statistics at the end of the report. This is
151+intended to make it easier to be parsed by other programs.
152+.IP --human
153+Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.)
154+The units displayed with this option supersede any other default units (e.g.
155+kilobytes, sectors...) associated with the metrics.
156+.IP -I
157+In an SMP environment, indicate that tasks CPU usage
158+(as displayed by option
159+.B -u
160+) should be divided by the total number of processors.
161+.IP -l
162+Display the process command name and all its arguments.
163+.IP "-p { pid [,...] | SELF | ALL }"
164+Select tasks (processes) for which statistics are to be reported.
165+.I pid
166+is the process identification number. The
167+.B SELF
168+keyword indicates that statistics are to be reported for the
169+.B pidstat
170+process itself, whereas the
171+.B ALL
172+keyword indicates that statistics are to be reported for all the
173+tasks managed by the system.
174+.IP -R
175+Report realtime priority and scheduling policy information.
176+The following values may be displayed:
177+
178+.B UID
179+.RS
180+.RS
181+The real user identification number of the task being monitored.
182+.RE
183+
184+.B USER
185+.RS
186+The name of the real user owning the task being monitored.
187+.RE
188+
189+.B PID
190+.RS
191+The identification number of the task being monitored.
192+.RE
193+
194+.B prio
195+.RS
196+The realtime priority of the task being monitored.
197+.RE
198+
199+.B policy
200+.RS
201+The scheduling policy of the task being monitored.
202+.RE
203+
204+.B Command
205+.RS
206+The command name of the task.
207+.RE
208+.RE
209+.IP -r
210+Report page faults and memory utilization.
211+
212+When reporting statistics for individual tasks,
213+the following values may be displayed:
214+
215+.B UID
216+.RS
217+.RS
218+The real user identification number of the task being monitored.
219+.RE
220+
221+.B USER
222+.RS
223+The name of the real user owning the task being monitored.
224+.RE
225+
226+.B PID
227+.RS
228+The identification number of the task being monitored.
229+.RE
230+
231+.B minflt/s
232+.RS
233+Total number of minor faults the task has made per second, those
234+which have not required loading a memory page from disk.
235+.RE
236+
237+.B majflt/s
238+.RS
239+Total number of major faults the task has made per second, those
240+which have required loading a memory page from disk.
241+.RE
242+
243+.B VSZ
244+.RS
245+Virtual Size: The virtual memory usage of entire task in kilobytes.
246+.RE
247+
248+.B RSS
249+.RS
250+Resident Set Size: The non-swapped physical memory
251+used by the task in kilobytes.
252+.RE
253+
254+.B %MEM
255+.RS
256+The tasks's currently used share of available physical memory.
257+.RE
258+
259+.B Command
260+.RS
261+The command name of the task.
262+.RE
263+
264+When reporting global statistics for tasks and all their children,
265+the following values may be displayed:
266+
267+.B UID
268+.RS
269+The real user identification number of the task which is being monitored
270+together with its children.
271+.RE
272+
273+.B USER
274+.RS
275+The name of the real user owning the task which is being monitored
276+together with its children.
277+.RE
278+
279+.B PID
280+.RS
281+The identification number of the task which is being monitored
282+together with its children.
283+.RE
284+
285+.B minflt-nr
286+.RS
287+Total number of minor faults made by the task and all its children,
288+and collected during the interval of time.
289+.RE
290+
291+.B majflt-nr
292+.RS
293+Total number of major faults made by the task and all its children,
294+and collected during the interval of time.
295+.RE
296+
297+.B Command
298+.RS
299+The command name of the task which is being monitored
300+together with its children.
301+.RE
302+.RE
303+.IP -s
304+Report stack utilization.
305+The following values may be displayed:
306+
307+.B UID
308+.RS
309+.RS
310+The real user identification number of the task being monitored.
311+.RE
312+
313+.B USER
314+.RS
315+The name of the real user owning the task being monitored.
316+.RE
317+
318+.B PID
319+.RS
320+The identification number of the task being monitored.
321+.RE
322+
323+.B StkSize
324+.RS
325+The amount of memory in kilobytes reserved for the task as stack,
326+but not necessarily used.
327+.RE
328+
329+.B StkRef
330+.RS
331+The amount of memory in kilobytes used as stack, referenced by the task.
332+.RE
333+
334+.B Command
335+.RS
336+The command name of the task.
337+.RE
338+.RE
339+.IP "-T { TASK | CHILD | ALL }"
340+This option specifies what has to be monitored by the
341+.B pidstat
342+command. The
343+.B TASK
344+keyword indicates that statistics are to be reported for individual tasks
345+(this is the default option) whereas the
346+.B CHILD
347+keyword indicates that statistics are to be globally reported for the
348+selected tasks and all their children. The
349+.B ALL
350+keyword indicates that statistics are to be reported for
351+individual tasks and globally for the selected
352+tasks and their children.
353+
354+Note: Global statistics for tasks and all their children are not available
355+for all options of
356+.B pidstat.
357+Also these statistics are not necessarily relevant to current time interval:
358+The statistics of a child process are collected only when it finishes or
359+it is killed.
360+.IP -t
361+Also display statistics for threads associated with selected tasks.
362+
363+This option adds the following values to the reports:
364+
365+.B TGID
366+.RS
367+.RS
368+The identification number of the thread group leader.
369+.RE
370+
371+.B TID
372+.RS
373+The identification number of the thread being monitored.
374+.RE
375+.RE
376+.IP "-U [ username ]"
377+Display the real user name of the tasks being monitored instead of the UID.
378+If
379+.I username
380+is specified, then only tasks belonging to the specified user are displayed.
381+.IP -u
382+Report CPU utilization.
383+
384+When reporting statistics for individual tasks,
385+the following values may be displayed:
386+
387+.B UID
388+.RS
389+.RS
390+The real user identification number of the task being monitored.
391+.RE
392+
393+.B USER
394+.RS
395+The name of the real user owning the task being monitored.
396+.RE
397+
398+.B PID
399+.RS
400+The identification number of the task being monitored.
401+.RE
402+
403+.B %usr
404+.RS
405+Percentage of CPU used by the task while executing at the user level
406+(application), with or without nice priority. Note that this field
407+does NOT include time spent running a virtual processor.
408+.RE
409+
410+.B %system
411+.RS
412+Percentage of CPU used by the task while executing at the system level
413+(kernel).
414+.RE
415+
416+.B %guest
417+.RS
418+Percentage of CPU spent by the task in virtual machine (running a virtual
419+processor).
420+.RE
421+
422+.B %wait
423+.RS
424+Percentage of CPU spent by the task while waiting to run.
425+.RE
426+
427+.B %CPU
428+.RS
429+Total percentage of CPU time used by the task. In an SMP environment,
430+the task's CPU usage will be divided by the total number of CPU's if
431+option
432+.B -I
433+has been entered on the command line.
434+.RE
435+
436+.B CPU
437+.RS
438+Processor number to which the task is attached.
439+.RE
440+
441+.B Command
442+.RS
443+The command name of the task.
444+.RE
445+
446+When reporting global statistics for tasks and all their children,
447+the following values may be displayed:
448+
449+.B UID
450+.RS
451+The real user identification number of the task which is being monitored
452+together with its children.
453+.RE
454+
455+.B USER
456+.RS
457+The name of the real user owning the task which is being monitored
458+together with its children.
459+.RE
460+
461+.B PID
462+.RS
463+The identification number of the task which is being monitored
464+together with its children.
465+.RE
466+
467+.B usr-ms
468+.RS
469+Total number of milliseconds spent
470+by the task and all its children while executing at the
471+user level (application), with or without nice priority, and
472+collected during the interval of time. Note that this field does
473+NOT include time spent running a virtual processor.
474+.RE
475+
476+.B system-ms
477+.RS
478+Total number of milliseconds spent
479+by the task and all its children while executing at the
480+system level (kernel), and collected during the interval of time.
481+.RE
482+
483+.B guest-ms
484+.RS
485+Total number of milliseconds spent
486+by the task and all its children in virtual machine (running a virtual
487+processor).
488+.RE
489+
490+.B Command
491+.RS
492+The command name of the task which is being monitored
493+together with its children.
494+.RE
495+.RE
496+.IP -V
497+Print version number then exit.
498+.IP -v
499+Report values of some kernel tables. The following values may be displayed:
500+
501+.B UID
502+.RS
503+.RS
504+The real user identification number of the task being monitored.
505+.RE
506+
507+.B USER
508+.RS
509+The name of the real user owning the task being monitored.
510+.RE
511+
512+.B PID
513+.RS
514+The identification number of the task being monitored.
515+.RE
516+
517+.B threads
518+.RS
519+Number of threads associated with current task.
520+.RE
521+
522+.B fd-nr
523+.RS
524+Number of file descriptors associated with current task.
525+.RE
526+
527+.B Command
528+.RS
529+The command name of the task.
530+.RE
531+.RE
532+.IP -w
533+Report task switching activity (kernels 2.6.23 and later only).
534+The following values may be displayed:
535+
536+.B UID
537+.RS
538+.RS
539+The real user identification number of the task being monitored.
540+.RE
541+
542+.B USER
543+.RS
544+The name of the real user owning the task being monitored.
545+.RE
546+
547+.B PID
548+.RS
549+The identification number of the task being monitored.
550+.RE
551+
552+.B cswch/s
553+.RS
554+Total number of voluntary context switches the task made per second.
555+A voluntary context switch occurs when a task blocks because it
556+requires a resource that is unavailable.
557+.RE
558+
559+.B nvcswch/s
560+.RS
561+Total number of non voluntary context switches the task made per second.
562+A involuntary context switch takes place when a task executes
563+for the duration of its time slice and then is forced to relinquish the
564+processor.
565+.RE
566+
567+.B Command
568+.RS
569+The command name of the task.
570+.RE
571+.RE
572+.SH ENVIRONMENT
573+The
574+.B pidstat
575+command takes into account the following environment variables:
576+
577+.IP S_COLORS
578+When this variable is set, display statistics in color on the terminal.
579+Possible values for this variable are
580+.IR never ,
581+.IR always
582+or
583+.IR auto
584+(the latter is the default).
585+
586+Please note that the color (being red, yellow, or some other color) used to display a value
587+is not indicative of any kind of issue simply because of the color. It only indicates different
588+ranges of values.
589+
590+.IP S_COLORS_SGR
591+Specify the colors and other attributes used to display statistics on the terminal.
592+Its value is a colon-separated list of capabilities that defaults to
593+.BR H=31;1:I=32;22:M=35;1:N=34;1:Z=34;22 .
594+Supported capabilities are:
595+
596+.RS
597+.TP
598+.B H=
599+SGR (Select Graphic Rendition) substring for percentage values greater than or equal to 75%.
600+
601+.TP
602+.B I=
603+SGR substring for item values like PID, UID or CPU number.
604+
605+.TP
606+.B M=
607+SGR substring for percentage values in the range from 50% to 75%.
608+
609+.TP
610+.B N=
611+SGR substring for non-zero statistics values and for tasks names.
612+
613+.TP
614+.B Z=
615+SGR substring for zero values and for threads names.
616+.RE
617+
618+.IP S_TIME_FORMAT
619+If this variable exists and its value is
620+.BR ISO
621+then the current locale will be ignored when printing the date in the report header.
622+The
623+.B pidstat
624+command will use the ISO 8601 format (YYYY-MM-DD) instead.
625+The timestamp will also be compliant with ISO 8601 format.
626+
627+.SH EXAMPLES
628+.B pidstat 2 5
629+.RS
630+Display five reports of CPU statistics for every active task in the system
631+at two second intervals.
632+.RE
633+
634+.B pidstat -r -p 1643 2 5
635+.RS
636+Display five reports of page faults and memory statistics for
637+PID 1643 at two second intervals.
638+.RE
639+
640+.B pidstat -C """fox|bird"" -r -p ALL
641+.RS
642+Display global page faults and memory statistics for all the
643+processes whose command name includes the string "fox" or "bird".
644+.RE
645+
646+.B pidstat -T CHILD -r 2 5
647+.RS
648+Display five reports of page faults statistics at two second intervals
649+for the child processes of all tasks in the system. Only child processes
650+with non-zero statistics values are displayed.
651+.SH BUGS
652+.I /proc
653+filesystem must be mounted for the
654+.B pidstat
655+command to work.
656+
657+.SH FILES
658+.IR /proc
659+contains various files with system statistics.
660+
661+.SH AUTHOR
662+Sebastien Godard (sysstat <at> orange.fr)
663+.SH SEE ALSO
664+.BR sar (1),
665+.BR top (1),
666+.BR ps (1),
667+.BR mpstat (1),
668+.BR iostat (1),
669+.BR vmstat (8)
670+
671+.I https://github.com/sysstat/sysstat
672+
673+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man1/sadf.1
@@ -0,0 +1,348 @@
1+.TH SADF 1 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+sadf \- Display data collected by sar in multiple formats.
4+.SH SYNOPSIS
5+.B sadf [ -C ] [ -c | -d | -g | -j | -p | -r | -x ] [ -H ] [ -h ] [ -T | -t | -U ] [ -V ] [ -O
6+.I opts
7+.B [,...] ] [ -P {
8+.I cpu_list
9+.B | ALL } ] [ -s [
10+.I hh:mm[:ss]
11+.B ] ] [ -e [
12+.I hh:mm[:ss]
13+.B ] ] [ --dev=
14+.I dev_list
15+.B ] [ --fs=
16+.I fs_list
17+.B ] [ --iface=
18+.I iface_list
19+.B ] [ --
20+.I sar_options
21+.B ] [
22+.I interval
23+.B [
24+.I count
25+.B ] ] [
26+.I datafile
27+|
28+.I -[0-9]+
29+.B ]
30+.SH DESCRIPTION
31+The
32+.B sadf
33+command is used for displaying the contents of data files created by the
34+.BR sar (1)
35+command. But unlike
36+.BR sar ,
37+.B sadf
38+can write its data in many different formats (CSV, XML, etc.)
39+The default format is one that can
40+easily be handled by pattern processing commands like awk (see option -p).
41+The
42+.B sadf
43+command can also be used to draw graphs for the various activities collected
44+by
45+.B sar
46+and display them as SVG (Scalable Vector Graphics) graphics in your web browser
47+(see option -g).
48+
49+The
50+.B sadf
51+command extracts and writes to standard output records saved in the
52+.I datafile
53+file. This file must have been created by a version of
54+.B sar
55+which is compatible with that of
56+.B sadf.
57+If
58+.I datafile
59+is omitted,
60+.B sadf
61+uses the standard system activity daily data file.
62+It is also possible to enter -1, -2 etc. as an argument to
63+.B sadf
64+to display data of that days ago.
65+For example, -1 will point at the standard system
66+activity file of yesterday.
67+
68+The standard system activity daily data file is named
69+.I saDD
70+or
71+.IR saYYYYMMDD ,
72+where YYYY stands for the current year, MM for the current month and
73+DD for the current day.
74+.B sadf
75+will look for the most recent of
76+.I saDD
77+and
78+.IR saYYYYMMDD ,
79+and use it. By default it is located in the
80+.I /var/log/sa
81+directory. Yet it is possible to specify an alternate location for it:
82+If
83+.I datafile
84+is a directory (instead of a plain file) then it will be considered as
85+the directory where the standard system activity daily data file is
86+located.
87+
88+The
89+.I interval
90+and
91+.I count
92+parameters are used to tell
93+.B sadf
94+to select
95+.I count
96+records at
97+.I interval
98+seconds apart. If the
99+.I count
100+parameter is not set, then all the records saved in the data file will be
101+displayed.
102+
103+All the activity flags of
104+.B sar
105+may be entered on the command line to indicate which
106+activities are to be reported. Before specifying them, put a pair of
107+dashes (--) on the command line in order not to confuse the flags
108+with those of
109+.B sadf.
110+Not specifying any flags selects only CPU activity.
111+
112+.SH OPTIONS
113+.IP -C
114+Tell
115+.B sadf
116+to display comments present in file.
117+.IP -c
118+Convert an old system activity binary datafile (version 9.1.6 and later)
119+to current up-to-date format. Use the following syntax:
120+
121+.B sadf -c old_datafile > new_datafile
122+
123+.IP -d
124+Print the contents of the data file in a format that can easily
125+be ingested by a relational database system. The output consists
126+of fields separated by a semicolon. Each record contains
127+the hostname of the host where the file was created, the interval value
128+(or -1 if not applicable), the timestamp in a form easily acceptable by
129+most databases, and additional semicolon separated data fields as specified
130+by
131+.I sar_options
132+command line options.
133+Note that timestamp output can be controlled by options -T, -t and -U.
134+.IP --dev=dev_list
135+Specify the block devices for which statistics are to be displayed by
136+.BR sadf .
137+.IR dev_list
138+is a list of comma-separated device names. Useful with option -d from
139+.BR sar .
140+.IP "-e [ hh:mm[:ss] ]"
141+Set the ending time of the report, given in local time. The default ending
142+time is 18:00:00. Hours must be given in 24-hour format.
143+.IP --fs=fs_list
144+Specify the filesystems for which statistics are to be displayed by
145+.BR sadf .
146+.IR fs_list
147+is a list of comma-separated filesystem names or mountpoints. Useful with
148+option -F from
149+.BR sar .
150+.IP -g
151+Print the contents of the data file in SVG (Scalable Vector Graphics) format.
152+This option enables you to display some fancy graphs in your web browser.
153+Use the following syntax:
154+
155+.B sadf -g your_datafile [ --
156+.I sar_options
157+.B ] > output.svg
158+
159+and open the resulting SVG file in your favorite web browser.
160+.IP -H
161+Display only the header of the report (when applicable). If no format has
162+been specified, then the header data (metadata) of the data file are displayed.
163+.IP -h
164+When used in conjunction with option -d, all activities
165+will be displayed horizontally on a single line.
166+.IP --iface=iface_list
167+Specify the network interfaces for which statistics are to be displayed by
168+.BR sadf .
169+.IR iface_list
170+is a list of comma-separated interface names. Useful with options -n DEV and
171+-n EDEV from
172+.BR sar .
173+.IP -j
174+Print the contents of the data file in JSON (JavaScript Object Notation)
175+format. Timestamps can be controlled by options -T and -t.
176+.IP "-O opts [,...]"
177+Use the specified options to control the output of
178+.BR sadf .
179+The following options are used to control SVG output displayed by
180+.BR "sadf -g":
181+
182+.B autoscale
183+.RS
184+.RS
185+Draw all the graphs of a given view as large as possible based on current
186+view's scale. To do this, a factor (10, 100, 1000...) is used to
187+enlarge the graph drawing.
188+This option may be interesting when several graphs are drawn on the same
189+view, some with only very small values, and others with high ones,
190+the latter making the former hardly visible.
191+.RE
192+
193+.BR height= value
194+.RS
195+Set SVG canvas height to
196+.IR value .
197+.RE
198+
199+.B oneday
200+.RS
201+Display graphs data over a period of 24 hours. Note that hours are still
202+printed in UTC by default: You should use option -T to print them in local
203+time and get a time window starting from midnight.
204+.RE
205+
206+.B packed
207+.RS
208+Group all views from the same activity (and for the same device) on the same row.
209+.RE
210+
211+.B showidle
212+.RS
213+Also display %idle state in graphs for CPU statistics.
214+.RE
215+
216+.B showinfo
217+.RS
218+Display additional information (such as the date and the host name) on each view.
219+.RE
220+
221+.B showtoc
222+.RS
223+Add a table of contents at the beginning of the SVG output, consisting of links
224+pointing at the first graph of each activity.
225+.RE
226+
227+.B skipempty
228+.RS
229+Do not display views where all graphs have only zero values.
230+.RE
231+
232+The following option is used to control raw output displayed by
233+.BR "sadf -r":
234+
235+.B debug
236+.RS
237+Display additional information, mainly useful for debugging purpose.
238+.RE
239+.RE
240+.IP "-P { cpu_list | ALL }"
241+Tell
242+.B sadf
243+that processor dependent statistics are to be reported only for the
244+specified processor or processors.
245+.I cpu_list
246+is a list of comma-separated values or range of values (e.g.,
247+.BR 0,2,4-7,12- ).
248+Note that processor 0 is the first processor, and processor
249+.B all
250+is the global average among all processors.
251+Specifying the
252+.B ALL
253+keyword reports statistics for each individual processor, and globally for
254+all processors.
255+.IP -p
256+Print the contents of the data file in a format that can
257+easily be handled by pattern processing commands like awk.
258+The output consists of fields separated by a tab. Each record contains the
259+hostname of the host where the file was created, the interval value
260+(or -1 if not applicable), the timestamp,
261+the device name (or - if not applicable),
262+the field name and its value.
263+Note that timestamp output can be controlled by options -T, -t and -U.
264+.IP -r
265+Print the raw contents of the data file. With this format, the values for
266+all the counters are displayed as read from the kernel, which means e.g., that
267+no average values are calculated over the elapsed time interval.
268+.IP "-s [ hh:mm[:ss] ]"
269+Set the starting time of the data (given in local time), causing the
270+.B sadf
271+command to extract records time-tagged at, or following, the time
272+specified. The default starting time is 08:00:00.
273+Hours must be given in 24-hour format.
274+.IP -T
275+Display timestamp in local time instead of UTC (Coordinated Universal Time).
276+.IP -t
277+Display timestamp in the original local time of the data file creator
278+instead of UTC (Coordinated Universal Time).
279+.IP -U
280+Display timestamp (UTC - Coordinated Universal Time) in seconds from
281+the epoch.
282+.IP -V
283+Print version number then exit.
284+.IP -x
285+Print the contents of the data file in XML format.
286+Timestamps can be controlled by options -T and -t.
287+The corresponding
288+DTD (Document Type Definition) and XML Schema are included in the sysstat
289+source package. They are also available at
290+.I http://pagesperso-orange.fr/sebastien.godard/download.html
291+
292+.SH ENVIRONMENT
293+The
294+.B sadf
295+command takes into account the following environment variable:
296+
297+.IP S_TIME_DEF_TIME
298+If this variable exists and its value is
299+.BR UTC
300+then
301+.B sadf
302+will use UTC time instead of local time to determine the current daily data
303+file located in the
304+.IR /var/log/sa
305+directory.
306+.SH EXAMPLES
307+.B sadf -d /var/log/sa/sa21 -- -r -n DEV
308+.RS
309+Extract memory and network statistics from system activity
310+file 'sa21', and display them in a format that can be ingested by a
311+database.
312+.RE
313+
314+.B sadf -p -P 1
315+.RS
316+Extract CPU statistics for processor 1 (the second processor) from current
317+daily data file, and display them in a format that can easily be handled
318+by a pattern processing command.
319+.RE
320+
321+.SH BUGS
322+SVG output (as created by option -g) is fully compliant with SVG 1.1 standard.
323+Graphics have been successfully displayed in various web browsers, including
324+Firefox, Chrome and Opera. Yet SVG rendering is broken on Microsoft browsers
325+(tested on Internet Explorer 11 and Edge 13.1): So please don't use them.
326+
327+.SH FILES
328+.I /var/log/sa/saDD
329+.br
330+.I /var/log/sa/saYYYYMMDD
331+.RS
332+The standard system activity daily data files and their default location.
333+YYYY stands for the current year, MM for the current month and DD for the
334+current day.
335+
336+.RE
337+.SH AUTHOR
338+Sebastien Godard (sysstat <at> orange.fr)
339+.SH SEE ALSO
340+.BR sar (1),
341+.BR sadc (8),
342+.BR sa1 (8),
343+.BR sa2 (8),
344+.BR sysstat (5)
345+
346+.I https://github.com/sysstat/sysstat
347+
348+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man1/sar.1
@@ -0,0 +1,2427 @@
1+.TH SAR 1 "APRIL 2019" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+sar \- Collect, report, or save system activity information.
4+.SH SYNOPSIS
5+.B sar [ -A ] [ -B ] [ -b ] [ -C ] [ -D ] [ -d ] [ -F [ MOUNT ] ] [ -H ] [ -h ] [ -p ] [ -q ]
6+.B [ -r [ ALL ] ] [ -S ] [ -t ] [ -u [ ALL ] ] [ -V ] [ -v ] [ -W ] [ -w ] [ -y ] [ -z ]
7+.B [ --dec={ 0 | 1 | 2 } ] [ --dev=
8+.I dev_list
9+.B ] [ --fs=
10+.I fs_list
11+.B ] [ --help ] [ --human ] [ --iface=
12+.I iface_list
13+.B ] [ --sadc ]
14+.B [ -I {
15+.I int_list
16+.B | SUM | ALL } ] [ -P {
17+.I cpu_list
18+.B | ALL } ]
19+.B [ -m {
20+.I keyword
21+.B [,...] | ALL } ]
22+.B [ -n {
23+.I keyword
24+.B [,...] | ALL } ]
25+.B [ -j { ID | LABEL | PATH | UUID | ... } ]
26+.B [ -f [
27+.I filename
28+.B ] | -o [
29+.I filename
30+.B ] | -[0-9]+ ]
31+.B [ -i
32+.I interval
33+.B ] [ -s [
34+.I hh:mm[:ss]
35+.B ] ] [ -e [
36+.I hh:mm[:ss]
37+.B ] ] [
38+.I interval
39+.B [
40+.I count
41+.B ] ]
42+.SH DESCRIPTION
43+The
44+.B sar
45+command writes to standard output the contents of selected
46+cumulative activity counters in the operating system. The accounting
47+system, based on the values in the
48+.I count
49+and
50+.I interval
51+parameters, writes information the specified number of times spaced
52+at the specified intervals in seconds.
53+If the
54+.I interval
55+parameter is set to zero, the
56+.B sar
57+command displays the average statistics for the time
58+since the system was started. If the
59+.I interval
60+parameter is specified without the
61+.I count
62+parameter, then reports are generated continuously.
63+The collected data can also
64+be saved in the file specified by the -o
65+.I filename
66+flag, in addition to being displayed onto the screen. If
67+.I filename
68+is omitted,
69+.B sar
70+uses the standard system activity daily data file (see below).
71+By default all the data available from the kernel are saved in the
72+data file.
73+
74+The
75+.B sar
76+command extracts and writes to standard output records previously
77+saved in a file. This file can be either the one specified by the
78+-f flag or, by default, the standard system activity daily data file.
79+It is also possible to enter -1, -2 etc. as an argument to
80+.B sar
81+to display data
82+of that days ago. For example, -1 will point at the standard system
83+activity file of yesterday.
84+
85+Standard system activity daily data files are named
86+.I saDD
87+or
88+.IR saYYYYMMDD ,
89+where YYYY stands for the current year, MM for the current month and
90+DD for the current day. They are the default files used by
91+.B sar
92+only when no filename has been explicitly specified.
93+When used to write data to files (with its option -o),
94+.B sar
95+will use
96+.I saYYYYMMDD
97+if option -D has also been specified, else it will use
98+.IR saDD .
99+When used to display the records previously saved in a file,
100+.B sar
101+will look for the most recent of
102+.I saDD
103+and
104+.IR saYYYYMMDD ,
105+and use it.
106+
107+Standard system activity daily data files are located in the
108+.I /var/log/sa
109+directory by default. Yet it is possible to specify an alternate
110+location for them: If a directory (instead of a plain file) is used
111+with options -f or -o
112+then it will be considered as the directory containing the data files.
113+
114+Without the -P flag, the
115+.B sar
116+command reports system-wide (global among all processors) statistics,
117+which are calculated as averages for values expressed as percentages,
118+and as sums otherwise. If the -P
119+flag is given, the
120+.B sar
121+command reports activity which relates to the specified processor or
122+processors. If -P ALL
123+is given, the
124+.B sar
125+command reports statistics for each individual processor and global
126+statistics among all processors. Offline processors are not displayed.
127+
128+You can select information about specific system activities using
129+flags. Not specifying any flags selects only CPU activity.
130+Specifying the -A
131+flag selects all possible activities.
132+
133+The default version of the
134+.B sar
135+command (CPU utilization report) might be one of the first facilities
136+the user runs to begin system activity investigation, because it
137+monitors major system resources. If CPU utilization is near 100 percent
138+(user + nice + system), the workload sampled is CPU-bound.
139+
140+If multiple samples and multiple reports are desired, it is convenient
141+to specify an output file for the
142+.B sar
143+command.
144+Run the
145+.B sar
146+command as a background process. The syntax for this is:
147+
148+.B sar -o datafile interval count >/dev/null 2>&1 &
149+
150+All data are captured in binary form and saved to a file (datafile).
151+The data can then be selectively displayed with the
152+.B sar
153+command using the -f
154+option. Set the
155+.I interval
156+and
157+.I count
158+parameters to select
159+.I count
160+records at
161+.I interval
162+second intervals. If the
163+.I count
164+parameter is not set, all the records saved in the
165+file will be selected.
166+Collection of data in this manner is useful to characterize
167+system usage over a period of time and determine peak usage hours.
168+
169+Note: The
170+.B sar
171+command only reports on local activities.
172+
173+.SH OPTIONS
174+.IP -A
175+This is equivalent to specifying
176+.BR "-bBdFHqSvwWy -I SUM -I ALL -m ALL -n ALL -r ALL -u ALL -P ALL".
177+.IP -B
178+Report paging statistics.
179+The following values are displayed:
180+
181+.B pgpgin/s
182+.RS
183+.RS
184+Total number of kilobytes the system paged in from disk per second.
185+.RE
186+
187+.B pgpgout/s
188+.RS
189+Total number of kilobytes the system paged out to disk per second.
190+.RE
191+
192+.B fault/s
193+.RS
194+Number of page faults (major + minor) made by the system per second.
195+This is not a count of page faults that generate I/O, because some page
196+faults can be resolved without I/O.
197+.RE
198+
199+.B majflt/s
200+.RS
201+Number of major faults the system has made per second, those which
202+have required loading a memory page from disk.
203+.RE
204+
205+.B pgfree/s
206+.RS
207+Number of pages placed on the free list by the system per second.
208+.RE
209+
210+.B pgscank/s
211+.RS
212+Number of pages scanned by the kswapd daemon per second.
213+.RE
214+
215+.B pgscand/s
216+.RS
217+Number of pages scanned directly per second.
218+.RE
219+
220+.B pgsteal/s
221+.RS
222+Number of pages the system has reclaimed from cache (pagecache and
223+swapcache) per second to satisfy its memory demands.
224+.RE
225+
226+.B %vmeff
227+.RS
228+Calculated as pgsteal / pgscan, this is a metric of the efficiency of
229+page reclaim. If it is near 100% then almost every page coming off the
230+tail of the inactive list is being reaped. If it gets too low (e.g. less
231+than 30%) then the virtual memory is having some difficulty.
232+This field is displayed as zero if no pages have been scanned during the
233+interval of time.
234+.RE
235+.RE
236+.IP -b
237+Report I/O and transfer rate statistics.
238+The following values are displayed:
239+
240+.B tps
241+.RS
242+.RS
243+Total number of transfers per second that were issued to physical devices.
244+A transfer is an I/O request to a physical device. Multiple logical
245+requests can be combined into a single I/O request to the device.
246+A transfer is of indeterminate size.
247+.RE
248+
249+.B rtps
250+.RS
251+Total number of read requests per second issued to physical devices.
252+.RE
253+
254+.B wtps
255+.RS
256+Total number of write requests per second issued to physical devices.
257+.RE
258+
259+.B bread/s
260+.RS
261+Total amount of data read from the devices in blocks per second.
262+Blocks are equivalent to sectors
263+and therefore have a size of 512 bytes.
264+.RE
265+
266+.B bwrtn/s
267+.RS
268+Total amount of data written to devices in blocks per second.
269+.RE
270+.RE
271+.IP -C
272+When reading data from a file, tell
273+.B sar
274+to display comments that have been inserted by
275+.BR sadc .
276+.IP -D
277+Use
278+.I saYYYYMMDD
279+instead of
280+.I saDD
281+as the standard system activity daily data file name. This option
282+works only when used in conjunction with option -o
283+to save data to file.
284+.IP -d
285+Report activity for each block device.
286+When data are displayed, the device specification
287+.I devM-n
288+is generally used (DEV column).
289+M is the major number of the device and n
290+its minor number.
291+Device names may also be pretty-printed if option -p
292+is used or persistent device names can be printed if option -j is used
293+(see below). Statistics for all devices are displayed unless
294+a restricted list is specified using option
295+.BR --dev=
296+(see corresponding option entry).
297+Note that disk activity depends on
298+.B sadc
299+options
300+.B "-S DISK"
301+and
302+.B "-S XDISK"
303+to be collected. The following values are displayed:
304+
305+.B tps
306+.RS
307+.RS
308+Total number of transfers per second that were issued to physical devices.
309+A transfer is an I/O request to a physical device. Multiple logical
310+requests can be combined into a single I/O request to the device.
311+A transfer is of indeterminate size.
312+.RE
313+
314+.B rkB/s
315+.RS
316+Number of kilobytes read from the device per second.
317+.RE
318+
319+.B wkB/s
320+.RS
321+Number of kilobytes written to the device per second.
322+.RE
323+
324+.B areq-sz
325+.RS
326+The average size (in kilobytes) of the I/O requests that were issued to the device.
327+.br
328+Note: In previous versions, this field was known as avgrq-sz and was expressed in sectors.
329+.RE
330+
331+.B aqu-sz
332+.RS
333+The average queue length of the requests that were issued to the device.
334+.br
335+Note: In previous versions, this field was known as avgqu-sz.
336+.RE
337+
338+.B await
339+.RS
340+The average time (in milliseconds) for I/O requests issued to the device
341+to be served. This includes the time spent by the requests in queue and
342+the time spent servicing them.
343+.RE
344+
345+.B svctm
346+.RS
347+The average service time (in milliseconds) for I/O requests that were issued
348+to the device. Warning! Do not trust this field any more. This field will be
349+removed in a future sysstat version.
350+.RE
351+
352+.B %util
353+.RS
354+Percentage of elapsed time during which I/O requests were issued to the device
355+(bandwidth utilization for the device). Device saturation occurs when this
356+value is close to 100% for devices serving requests serially. But for
357+devices serving requests in parallel, such as RAID arrays and modern SSDs,
358+this number does not reflect their performance limits.
359+.RE
360+.RE
361+.IP "--dec={ 0 | 1 | 2 }"
362+Specify the number of decimal places to use (0 to 2, default value is 2).
363+.IP --dev=dev_list
364+Specify the block devices for which statistics are to be displayed by
365+.BR sar .
366+.IR dev_list
367+is a list of comma-separated device names.
368+.IP "-e [ hh:mm[:ss] ]"
369+Set the ending time of the report. The default ending time is
370+18:00:00. Hours must be given in 24-hour format.
371+This option can be used when data are read from
372+or written to a file (options -f or -o).
373+.IP "-F [ MOUNT ]"
374+Display statistics for currently mounted filesystems. Pseudo-filesystems are
375+ignored. At the end of the report,
376+.B sar
377+will display a summary of all those filesystems.
378+Use of the
379+.B MOUNT
380+parameter keyword indicates that mountpoint will be reported instead of
381+filesystem device. Statistics for all filesystems are displayed unless
382+a restricted list is specified using option
383+.BR --fs=
384+(see corresponding option entry).
385+Note that filesystems statistics depend on
386+.B sadc
387+option
388+.B "-S XDISK"
389+to be collected.
390+
391+The following values are displayed:
392+
393+.B MBfsfree
394+.RS
395+.RS
396+Total amount of free space in megabytes (including space available only to privileged user).
397+.RE
398+
399+.B MBfsused
400+.RS
401+Total amount of space used in megabytes.
402+.RE
403+
404+.B %fsused
405+.RS
406+Percentage of filesystem space used, as seen by a privileged user.
407+.RE
408+
409+.B %ufsused
410+.RS
411+Percentage of filesystem space used, as seen by an unprivileged user.
412+.RE
413+
414+.B Ifree
415+.RS
416+Total number of free file nodes in filesystem.
417+.RE
418+
419+.B Iused
420+.RS
421+Total number of file nodes used in filesystem.
422+.RE
423+
424+.B %Iused
425+.RS
426+Percentage of file nodes used in filesystem.
427+.RE
428+.RE
429+.IP "-f [ filename ]"
430+Extract records from
431+.I filename
432+(created by the -o
433+.I filename
434+flag). The default value of the
435+.I filename
436+parameter is the current standard system activity daily data file.
437+If
438+.I filename
439+is a directory instead of a plain file then it is considered as the
440+directory where the standard system activity daily data files are
441+located. The -f option is exclusive of the -o option.
442+.IP --fs=fs_list
443+Specify the filesystems for which statistics are to be displayed by
444+.BR sar .
445+.IR fs_list
446+is a list of comma-separated filesystem names or mountpoints.
447+.IP -H
448+Report hugepages utilization statistics.
449+The following values are displayed:
450+
451+.B kbhugfree
452+.RS
453+.RS
454+Amount of hugepages memory in kilobytes that is not yet allocated.
455+.RE
456+
457+.B kbhugused
458+.RS
459+Amount of hugepages memory in kilobytes that has been allocated.
460+.RE
461+
462+.B %hugused
463+.RS
464+Percentage of total hugepages memory that has been allocated.
465+.RE
466+.RE
467+.IP -h
468+Make the output of sar easier to read by a human. Options
469+.B --human
470+and
471+.B -p
472+(pretty-print) are enabled implicitly with this option.
473+This option may be especially useful when displaying e.g., network interfaces
474+or block devices statistics.
475+.IP --help
476+Display a short help message then exit.
477+.IP --human
478+Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.)
479+The units displayed with this option supersede any other default units (e.g.
480+kilobytes, sectors...) associated with the metrics.
481+.IP "-I { int_list | SUM | ALL }"
482+Report statistics for interrupts.
483+.I int_list
484+is a list of comma-separated values or range of values (e.g.,
485+.BR 0-16,35,400- ).
486+The
487+.B SUM
488+keyword indicates that the total number of interrupts received per second
489+is to be displayed. The
490+.B ALL
491+keyword indicates that statistics from all interrupts, including potential
492+APIC interrupt sources, are to be reported.
493+Note that interrupt statistics depend on
494+.B sadc
495+option "-S INT"
496+to be collected.
497+.IP "-i interval"
498+Select data records at seconds as close as possible to the number specified
499+by the
500+.I interval
501+parameter.
502+.IP --iface=iface_list
503+Specify the network interfaces for which statistics are to be displayed by
504+.BR sar .
505+.IR iface_list
506+is a list of comma-separated interface names.
507+.IP "-j { ID | LABEL | PATH | UUID | ... }"
508+Display persistent device names. Use this option in conjunction with option -d.
509+Options
510+.BR ID ,
511+.BR LABEL ,
512+etc. specify the type of the persistent name. These options are not limited,
513+only prerequisite is that directory with required persistent names is present in
514+.IR /dev/disk .
515+If persistent name is not found for the device, the device name
516+is pretty-printed (see option -p below).
517+.IP "-m { keyword [,...] | ALL }"
518+Report power management statistics.
519+Note that these statistics depend on
520+.BR sadc 's
521+option "-S POWER" to be collected.
522+
523+Possible keywords are
524+.BR CPU ,
525+.BR FAN ,
526+.BR FREQ ,
527+.BR IN ,
528+.BR TEMP
529+and
530+.BR USB .
531+
532+With the
533+.B CPU
534+keyword, statistics about CPU are reported.
535+The following value is displayed:
536+
537+.B MHz
538+.RS
539+.RS
540+Instantaneous CPU clock frequency in MHz.
541+.RE
542+
543+With the
544+.B FAN
545+keyword, statistics about fans speed are reported.
546+The following values are displayed:
547+
548+.B rpm
549+.RS
550+Fan speed expressed in revolutions per minute.
551+.RE
552+
553+.B drpm
554+.RS
555+This field is calculated as the difference between current fan speed (rpm)
556+and its low limit (fan_min).
557+.RE
558+
559+.B DEVICE
560+.RS
561+Sensor device name.
562+.RE
563+
564+With the
565+.B FREQ
566+keyword, statistics about CPU clock frequency are reported.
567+The following value is displayed:
568+
569+.B wghMHz
570+.RS
571+Weighted average CPU clock frequency in MHz.
572+Note that the cpufreq-stats driver must be compiled in the
573+kernel for this option to work.
574+.RE
575+
576+With the
577+.B IN
578+keyword, statistics about voltage inputs are reported.
579+The following values are displayed:
580+
581+.B inV
582+.RS
583+Voltage input expressed in Volts.
584+.RE
585+
586+.B %in
587+.RS
588+Relative input value. A value of 100% means that
589+voltage input has reached its high limit (in_max) whereas
590+a value of 0% means that it has reached its low limit (in_min).
591+.RE
592+
593+.B DEVICE
594+.RS
595+Sensor device name.
596+.RE
597+
598+With the
599+.B TEMP
600+keyword, statistics about devices temperature are reported.
601+The following values are displayed:
602+
603+.B degC
604+.RS
605+Device temperature expressed in degrees Celsius.
606+.RE
607+
608+.B %temp
609+.RS
610+Relative device temperature. A value of 100% means that
611+temperature has reached its high limit (temp_max).
612+.RE
613+
614+.B DEVICE
615+.RS
616+Sensor device name.
617+.RE
618+
619+With the
620+.B USB
621+keyword, the
622+.B sar
623+command takes a snapshot of all the USB devices currently plugged into
624+the system. At the end of the report,
625+.B sar
626+will display a summary of all those USB devices.
627+The following values are displayed:
628+
629+.B BUS
630+.RS
631+Root hub number of the USB device.
632+.RE
633+
634+.B idvendor
635+.RS
636+Vendor ID number (assigned by USB organization).
637+.RE
638+
639+.B idprod
640+.RS
641+Product ID number (assigned by Manufacturer).
642+.RE
643+
644+.B maxpower
645+.RS
646+Maximum power consumption of the device (expressed in mA).
647+.RE
648+
649+.B manufact
650+.RS
651+Manufacturer name.
652+.RE
653+
654+.B product
655+.RS
656+Product name.
657+.RE
658+
659+The
660+.B ALL
661+keyword is equivalent to specifying all the keywords above and therefore all the power
662+management statistics are reported.
663+.RE
664+.RE
665+.IP "-n { keyword [,...] | ALL }"
666+Report network statistics.
667+
668+Possible keywords are
669+.BR DEV ,
670+.BR EDEV ,
671+.BR FC ,
672+.BR ICMP ,
673+.BR EICMP ,
674+.BR ICMP6 ,
675+.BR EICMP6 ,
676+.BR IP ,
677+.BR EIP ,
678+.BR IP6 ,
679+.BR EIP6 ,
680+.BR NFS ,
681+.BR NFSD ,
682+.BR SOCK ,
683+.BR SOCK6 ,
684+.BR SOFT ,
685+.BR TCP ,
686+.BR ETCP ,
687+.BR UDP
688+and
689+.BR UDP6 .
690+
691+With the
692+.B DEV
693+keyword, statistics from the network devices are reported.
694+Statistics for all network interfaces are displayed unless
695+a restricted list is specified using option
696+.BR --iface=
697+(see corresponding option entry).
698+The following values are displayed:
699+
700+.B IFACE
701+.RS
702+.RS
703+Name of the network interface for which statistics are reported.
704+.RE
705+
706+.B rxpck/s
707+.RS
708+Total number of packets received per second.
709+.RE
710+
711+.B txpck/s
712+.RS
713+Total number of packets transmitted per second.
714+.RE
715+
716+.B rxkB/s
717+.RS
718+Total number of kilobytes received per second.
719+.RE
720+
721+.B txkB/s
722+.RS
723+Total number of kilobytes transmitted per second.
724+.RE
725+
726+.B rxcmp/s
727+.RS
728+Number of compressed packets received per second (for cslip etc.).
729+.RE
730+
731+.B txcmp/s
732+.RS
733+Number of compressed packets transmitted per second.
734+.RE
735+
736+.B rxmcst/s
737+.RS
738+Number of multicast packets received per second.
739+.RE
740+
741+.B %ifutil
742+.RS
743+Utilization percentage of the network interface. For half-duplex interfaces,
744+utilization is calculated using the sum of rxkB/s and txkB/s as a percentage
745+of the interface speed. For full-duplex, this is the greater of rxkB/S or txkB/s.
746+.RE
747+
748+With the
749+.B EDEV
750+keyword, statistics on failures (errors) from the network devices are reported.
751+Statistics for all network interfaces are displayed unless
752+a restricted list is specified using option
753+.BR --iface=
754+(see corresponding option entry).
755+The following values are displayed:
756+
757+.B IFACE
758+.RS
759+Name of the network interface for which statistics are reported.
760+.RE
761+
762+.B rxerr/s
763+.RS
764+Total number of bad packets received per second.
765+.RE
766+
767+.B txerr/s
768+.RS
769+Total number of errors that happened per second while transmitting packets.
770+.RE
771+
772+.B coll/s
773+.RS
774+Number of collisions that happened per second while transmitting packets.
775+.RE
776+
777+.B rxdrop/s
778+.RS
779+Number of received packets dropped per second because of a lack of space in linux buffers.
780+.RE
781+
782+.B txdrop/s
783+.RS
784+Number of transmitted packets dropped per second because of a lack of space in linux buffers.
785+.RE
786+
787+.B txcarr/s
788+.RS
789+Number of carrier-errors that happened per second while transmitting packets.
790+.RE
791+
792+.B rxfram/s
793+.RS
794+Number of frame alignment errors that happened per second on received packets.
795+.RE
796+
797+.B rxfifo/s
798+.RS
799+Number of FIFO overrun errors that happened per second on received packets.
800+.RE
801+
802+.B txfifo/s
803+.RS
804+Number of FIFO overrun errors that happened per second on transmitted packets.
805+.RE
806+
807+With the
808+.B FC
809+keyword, statistics about fibre channel traffic are reported.
810+Note that fibre channel statistics depend on
811+.BR sadc 's
812+option "-S DISK" to be collected.
813+The following values are displayed:
814+
815+.B FCHOST
816+.RS
817+Name of the fibre channel host bus adapter (HBA) interface for which statistics are reported.
818+.RE
819+
820+.B fch_rxf/s
821+.RS
822+The total number of frames received per second.
823+.RE
824+
825+.B fch_txf/s
826+.RS
827+The total number of frames transmitted per second.
828+.RE
829+
830+.B fch_rxw/s
831+.RS
832+The total number of transmission words received per second.
833+.RE
834+
835+.B fch_txw/s
836+.RS
837+The total number of transmission words transmitted per second.
838+.RE
839+
840+With the
841+.B ICMP
842+keyword, statistics about ICMPv4 network traffic are reported.
843+Note that ICMPv4 statistics depend on
844+.BR sadc 's
845+option "-S SNMP"
846+to be collected.
847+The following values are displayed (formal SNMP names between
848+square brackets):
849+
850+.B imsg/s
851+.RS
852+The total number of ICMP messages which the entity
853+received per second [icmpInMsgs].
854+Note that this counter includes all those counted by ierr/s.
855+.RE
856+
857+.B omsg/s
858+.RS
859+The total number of ICMP messages which this entity
860+attempted to send per second [icmpOutMsgs].
861+Note that this counter includes all those counted by oerr/s.
862+.RE
863+
864+.B iech/s
865+.RS
866+The number of ICMP Echo (request) messages received per second [icmpInEchos].
867+.RE
868+
869+.B iechr/s
870+.RS
871+The number of ICMP Echo Reply messages received per second [icmpInEchoReps].
872+.RE
873+
874+.B oech/s
875+.RS
876+The number of ICMP Echo (request) messages sent per second [icmpOutEchos].
877+.RE
878+
879+.B oechr/s
880+.RS
881+The number of ICMP Echo Reply messages sent per second [icmpOutEchoReps].
882+.RE
883+
884+.B itm/s
885+.RS
886+The number of ICMP Timestamp (request) messages received per second [icmpInTimestamps].
887+.RE
888+
889+.B itmr/s
890+.RS
891+The number of ICMP Timestamp Reply messages received per second [icmpInTimestampReps].
892+.RE
893+
894+.B otm/s
895+.RS
896+The number of ICMP Timestamp (request) messages sent per second [icmpOutTimestamps].
897+.RE
898+
899+.B otmr/s
900+.RS
901+The number of ICMP Timestamp Reply messages sent per second [icmpOutTimestampReps].
902+.RE
903+
904+.B iadrmk/s
905+.RS
906+The number of ICMP Address Mask Request messages received per second [icmpInAddrMasks].
907+.RE
908+
909+.B iadrmkr/s
910+.RS
911+The number of ICMP Address Mask Reply messages received per second [icmpInAddrMaskReps].
912+.RE
913+
914+.B oadrmk/s
915+.RS
916+The number of ICMP Address Mask Request messages sent per second [icmpOutAddrMasks].
917+.RE
918+
919+.B oadrmkr/s
920+.RS
921+The number of ICMP Address Mask Reply messages sent per second [icmpOutAddrMaskReps].
922+.RE
923+
924+With the
925+.B EICMP
926+keyword, statistics about ICMPv4 error messages are reported.
927+Note that ICMPv4 statistics depend on
928+.BR sadc 's
929+option "-S SNMP" to be collected.
930+The following values are displayed (formal SNMP names between
931+square brackets):
932+
933+.B ierr/s
934+.RS
935+The number of ICMP messages per second which the entity received but
936+determined as having ICMP-specific errors (bad ICMP
937+checksums, bad length, etc.) [icmpInErrors].
938+.RE
939+
940+.B oerr/s
941+.RS
942+The number of ICMP messages per second which this entity did not send
943+due to problems discovered within ICMP such as a lack of buffers [icmpOutErrors].
944+.RE
945+
946+.B idstunr/s
947+.RS
948+The number of ICMP Destination Unreachable messages
949+received per second [icmpInDestUnreachs].
950+.RE
951+
952+.B odstunr/s
953+.RS
954+The number of ICMP Destination Unreachable messages sent per second [icmpOutDestUnreachs].
955+.RE
956+
957+.B itmex/s
958+.RS
959+The number of ICMP Time Exceeded messages received per second [icmpInTimeExcds].
960+.RE
961+
962+.B otmex/s
963+.RS
964+The number of ICMP Time Exceeded messages sent per second [icmpOutTimeExcds].
965+.RE
966+
967+.B iparmpb/s
968+.RS
969+The number of ICMP Parameter Problem messages received per second [icmpInParmProbs].
970+.RE
971+
972+.B oparmpb/s
973+.RS
974+The number of ICMP Parameter Problem messages sent per second [icmpOutParmProbs].
975+.RE
976+
977+.B isrcq/s
978+.RS
979+The number of ICMP Source Quench messages received per second [icmpInSrcQuenchs].
980+.RE
981+
982+.B osrcq/s
983+.RS
984+The number of ICMP Source Quench messages sent per second [icmpOutSrcQuenchs].
985+.RE
986+
987+.B iredir/s
988+.RS
989+The number of ICMP Redirect messages received per second [icmpInRedirects].
990+.RE
991+
992+.B oredir/s
993+.RS
994+The number of ICMP Redirect messages sent per second [icmpOutRedirects].
995+.RE
996+
997+With the
998+.B ICMP6
999+keyword, statistics about ICMPv6 network traffic are reported.
1000+Note that ICMPv6 statistics depend on
1001+.BR sadc 's
1002+option "-S IPV6" to be collected.
1003+The following values are displayed (formal SNMP names between
1004+square brackets):
1005+
1006+.B imsg6/s
1007+.RS
1008+The total number of ICMP messages received
1009+by the interface per second which includes all those
1010+counted by ierr6/s [ipv6IfIcmpInMsgs].
1011+.RE
1012+
1013+.B omsg6/s
1014+.RS
1015+The total number of ICMP messages which this
1016+interface attempted to send per second [ipv6IfIcmpOutMsgs].
1017+.RE
1018+
1019+.B iech6/s
1020+.RS
1021+The number of ICMP Echo (request) messages
1022+received by the interface per second [ipv6IfIcmpInEchos].
1023+.RE
1024+
1025+.B iechr6/s
1026+.RS
1027+The number of ICMP Echo Reply messages received
1028+by the interface per second [ipv6IfIcmpInEchoReplies].
1029+.RE
1030+
1031+.B oechr6/s
1032+.RS
1033+The number of ICMP Echo Reply messages sent
1034+by the interface per second [ipv6IfIcmpOutEchoReplies].
1035+.RE
1036+
1037+.B igmbq6/s
1038+.RS
1039+The number of ICMPv6 Group Membership Query
1040+messages received by the interface per second
1041+[ipv6IfIcmpInGroupMembQueries].
1042+.RE
1043+
1044+.B igmbr6/s
1045+.RS
1046+The number of ICMPv6 Group Membership Response messages
1047+received by the interface per second
1048+[ipv6IfIcmpInGroupMembResponses].
1049+.RE
1050+
1051+.B ogmbr6/s
1052+.RS
1053+The number of ICMPv6 Group Membership Response
1054+messages sent per second
1055+[ipv6IfIcmpOutGroupMembResponses].
1056+.RE
1057+
1058+.B igmbrd6/s
1059+.RS
1060+The number of ICMPv6 Group Membership Reduction messages
1061+received by the interface per second
1062+[ipv6IfIcmpInGroupMembReductions].
1063+.RE
1064+
1065+.B ogmbrd6/s
1066+.RS
1067+The number of ICMPv6 Group Membership Reduction
1068+messages sent per second
1069+[ipv6IfIcmpOutGroupMembReductions].
1070+.RE
1071+
1072+.B irtsol6/s
1073+.RS
1074+The number of ICMP Router Solicit messages
1075+received by the interface per second
1076+[ipv6IfIcmpInRouterSolicits].
1077+.RE
1078+
1079+.B ortsol6/s
1080+.RS
1081+The number of ICMP Router Solicitation messages
1082+sent by the interface per second
1083+[ipv6IfIcmpOutRouterSolicits].
1084+.RE
1085+
1086+.B irtad6/s
1087+.RS
1088+The number of ICMP Router Advertisement messages
1089+received by the interface per second
1090+[ipv6IfIcmpInRouterAdvertisements].
1091+.RE
1092+
1093+.B inbsol6/s
1094+.RS
1095+The number of ICMP Neighbor Solicit messages
1096+received by the interface per second
1097+[ipv6IfIcmpInNeighborSolicits].
1098+.RE
1099+
1100+.B onbsol6/s
1101+.RS
1102+The number of ICMP Neighbor Solicitation
1103+messages sent by the interface per second
1104+[ipv6IfIcmpOutNeighborSolicits].
1105+.RE
1106+
1107+.B inbad6/s
1108+.RS
1109+The number of ICMP Neighbor Advertisement
1110+messages received by the interface per second
1111+[ipv6IfIcmpInNeighborAdvertisements].
1112+.RE
1113+
1114+.B onbad6/s
1115+.RS
1116+The number of ICMP Neighbor Advertisement
1117+messages sent by the interface per second
1118+[ipv6IfIcmpOutNeighborAdvertisements].
1119+.RE
1120+
1121+With the
1122+.B EICMP6
1123+keyword, statistics about ICMPv6 error messages are reported.
1124+Note that ICMPv6 statistics depend on
1125+.BR sadc 's
1126+option "-S IPV6" to be collected.
1127+The following values are displayed (formal SNMP names between
1128+square brackets):
1129+
1130+.B ierr6/s
1131+.RS
1132+The number of ICMP messages per second which the interface
1133+received but determined as having ICMP-specific
1134+errors (bad ICMP checksums, bad length, etc.)
1135+[ipv6IfIcmpInErrors]
1136+.RE
1137+
1138+.B idtunr6/s
1139+.RS
1140+The number of ICMP Destination Unreachable
1141+messages received by the interface per second
1142+[ipv6IfIcmpInDestUnreachs].
1143+.RE
1144+
1145+.B odtunr6/s
1146+.RS
1147+The number of ICMP Destination Unreachable
1148+messages sent by the interface per second
1149+[ipv6IfIcmpOutDestUnreachs].
1150+.RE
1151+
1152+.B itmex6/s
1153+.RS
1154+The number of ICMP Time Exceeded messages
1155+received by the interface per second
1156+[ipv6IfIcmpInTimeExcds].
1157+.RE
1158+
1159+.B otmex6/s
1160+.RS
1161+The number of ICMP Time Exceeded messages sent
1162+by the interface per second
1163+[ipv6IfIcmpOutTimeExcds].
1164+.RE
1165+
1166+.B iprmpb6/s
1167+.RS
1168+The number of ICMP Parameter Problem messages
1169+received by the interface per second
1170+[ipv6IfIcmpInParmProblems].
1171+.RE
1172+
1173+.B oprmpb6/s
1174+.RS
1175+The number of ICMP Parameter Problem messages
1176+sent by the interface per second
1177+[ipv6IfIcmpOutParmProblems].
1178+.RE
1179+
1180+.B iredir6/s
1181+.RS
1182+The number of Redirect messages received
1183+by the interface per second
1184+[ipv6IfIcmpInRedirects].
1185+.RE
1186+
1187+.B oredir6/s
1188+.RS
1189+The number of Redirect messages sent by
1190+the interface by second
1191+[ipv6IfIcmpOutRedirects].
1192+.RE
1193+
1194+.B ipck2b6/s
1195+.RS
1196+The number of ICMP Packet Too Big messages
1197+received by the interface per second
1198+[ipv6IfIcmpInPktTooBigs].
1199+.RE
1200+
1201+.B opck2b6/s
1202+.RS
1203+The number of ICMP Packet Too Big messages sent
1204+by the interface per second
1205+[ipv6IfIcmpOutPktTooBigs].
1206+.RE
1207+
1208+With the
1209+.B IP
1210+keyword, statistics about IPv4 network traffic are reported.
1211+Note that IPv4 statistics depend on
1212+.BR sadc 's
1213+option "-S SNMP"
1214+to be collected.
1215+The following values are displayed (formal SNMP names between
1216+square brackets):
1217+
1218+.B irec/s
1219+.RS
1220+The total number of input datagrams received from interfaces
1221+per second, including those received in error [ipInReceives].
1222+.RE
1223+
1224+.B fwddgm/s
1225+.RS
1226+The number of input datagrams per second, for which this entity was not
1227+their final IP destination, as a result of which an attempt
1228+was made to find a route to forward them to that final
1229+destination [ipForwDatagrams].
1230+.RE
1231+
1232+.B idel/s
1233+.RS
1234+The total number of input datagrams successfully delivered per second
1235+to IP user-protocols (including ICMP) [ipInDelivers].
1236+.RE
1237+
1238+.B orq/s
1239+.RS
1240+The total number of IP datagrams which local IP user-protocols (including ICMP)
1241+supplied per second to IP in requests for transmission [ipOutRequests].
1242+Note that this counter does not include any datagrams counted in fwddgm/s.
1243+.RE
1244+
1245+.B asmrq/s
1246+.RS
1247+The number of IP fragments received per second which needed to be
1248+reassembled at this entity [ipReasmReqds].
1249+.RE
1250+
1251+.B asmok/s
1252+.RS
1253+The number of IP datagrams successfully re-assembled per second [ipReasmOKs].
1254+.RE
1255+
1256+.B fragok/s
1257+.RS
1258+The number of IP datagrams that have been successfully
1259+fragmented at this entity per second [ipFragOKs].
1260+.RE
1261+
1262+.B fragcrt/s
1263+.RS
1264+The number of IP datagram fragments that have been
1265+generated per second as a result of fragmentation at this entity [ipFragCreates].
1266+.RE
1267+
1268+With the
1269+.B EIP
1270+keyword, statistics about IPv4 network errors are reported.
1271+Note that IPv4 statistics depend on
1272+.BR sadc 's
1273+option "-S SNMP" to be collected.
1274+The following values are displayed (formal SNMP names between
1275+square brackets):
1276+
1277+.B ihdrerr/s
1278+.RS
1279+The number of input datagrams discarded per second due to errors in
1280+their IP headers, including bad checksums, version number
1281+mismatch, other format errors, time-to-live exceeded, errors
1282+discovered in processing their IP options, etc. [ipInHdrErrors]
1283+.RE
1284+
1285+.B iadrerr/s
1286+.RS
1287+The number of input datagrams discarded per second because the IP
1288+address in their IP header's destination field was not a
1289+valid address to be received at this entity. This count
1290+includes invalid addresses (e.g., 0.0.0.0) and addresses of
1291+unsupported Classes (e.g., Class E). For entities which are
1292+not IP routers and therefore do not forward datagrams, this
1293+counter includes datagrams discarded because the destination
1294+address was not a local address [ipInAddrErrors].
1295+.RE
1296+
1297+.B iukwnpr/s
1298+.RS
1299+The number of locally-addressed datagrams received
1300+successfully but discarded per second because of an unknown or
1301+unsupported protocol [ipInUnknownProtos].
1302+.RE
1303+
1304+.B idisc/s
1305+.RS
1306+The number of input IP datagrams per second for which no problems were
1307+encountered to prevent their continued processing, but which
1308+were discarded (e.g., for lack of buffer space) [ipInDiscards].
1309+Note that this counter does not include any datagrams discarded while
1310+awaiting re-assembly.
1311+.RE
1312+
1313+.B odisc/s
1314+.RS
1315+The number of output IP datagrams per second for which no problem was
1316+encountered to prevent their transmission to their
1317+destination, but which were discarded (e.g., for lack of
1318+buffer space) [ipOutDiscards].
1319+Note that this counter would include
1320+datagrams counted in fwddgm/s if any such packets met
1321+this (discretionary) discard criterion.
1322+.RE
1323+
1324+.B onort/s
1325+.RS
1326+The number of IP datagrams discarded per second because no route could
1327+be found to transmit them to their destination [ipOutNoRoutes].
1328+Note that this counter includes any packets counted in fwddgm/s
1329+which meet this 'no-route' criterion.
1330+Note that this includes any datagrams which a host cannot route because all
1331+of its default routers are down.
1332+.RE
1333+
1334+.B asmf/s
1335+.RS
1336+The number of failures detected per second by the IP re-assembly
1337+algorithm (for whatever reason: timed out, errors, etc) [ipReasmFails].
1338+Note that this is not necessarily a count of discarded IP
1339+fragments since some algorithms can lose track of the number of
1340+fragments by combining them as they are received.
1341+.RE
1342+
1343+.B fragf/s
1344+.RS
1345+The number of IP datagrams that have been discarded per second because
1346+they needed to be fragmented at this entity but could not
1347+be, e.g., because their Don't Fragment flag was set [ipFragFails].
1348+.RE
1349+
1350+With the
1351+.B IP6
1352+keyword, statistics about IPv6 network traffic are reported.
1353+Note that IPv6 statistics depend on
1354+.BR sadc 's
1355+option "-S IPV6" to be collected.
1356+The following values are displayed (formal SNMP names between
1357+square brackets):
1358+
1359+.B irec6/s
1360+.RS
1361+The total number of input datagrams received from
1362+interfaces per second, including those received in error
1363+[ipv6IfStatsInReceives].
1364+.RE
1365+
1366+.B fwddgm6/s
1367+.RS
1368+The number of output datagrams per second which this
1369+entity received and forwarded to their final
1370+destinations [ipv6IfStatsOutForwDatagrams].
1371+.RE
1372+
1373+.B idel6/s
1374+.RS
1375+The total number of datagrams successfully
1376+delivered per second to IPv6 user-protocols (including ICMP)
1377+[ipv6IfStatsInDelivers].
1378+.RE
1379+
1380+.B orq6/s
1381+.RS
1382+The total number of IPv6 datagrams which local IPv6
1383+user-protocols (including ICMP) supplied per second to IPv6 in
1384+requests for transmission [ipv6IfStatsOutRequests].
1385+Note that this counter
1386+does not include any datagrams counted in fwddgm6/s.
1387+.RE
1388+
1389+.B asmrq6/s
1390+.RS
1391+The number of IPv6 fragments received per second which needed
1392+to be reassembled at this interface [ipv6IfStatsReasmReqds].
1393+.RE
1394+
1395+.B asmok6/s
1396+.RS
1397+The number of IPv6 datagrams successfully
1398+reassembled per second [ipv6IfStatsReasmOKs].
1399+.RE
1400+
1401+.B imcpck6/s
1402+.RS
1403+The number of multicast packets received per second
1404+by the interface [ipv6IfStatsInMcastPkts].
1405+.RE
1406+
1407+.B omcpck6/s
1408+.RS
1409+The number of multicast packets transmitted per second
1410+by the interface [ipv6IfStatsOutMcastPkts].
1411+.RE
1412+
1413+.B fragok6/s
1414+.RS
1415+The number of IPv6 datagrams that have been
1416+successfully fragmented at this output interface per second
1417+[ipv6IfStatsOutFragOKs].
1418+.RE
1419+
1420+.B fragcr6/s
1421+.RS
1422+The number of output datagram fragments that have
1423+been generated per second as a result of fragmentation at
1424+this output interface [ipv6IfStatsOutFragCreates].
1425+.RE
1426+
1427+With the
1428+.B EIP6
1429+keyword, statistics about IPv6 network errors are reported.
1430+Note that IPv6 statistics depend on
1431+.BR sadc 's
1432+option "-S IPV6" to be collected.
1433+The following values are displayed (formal SNMP names between
1434+square brackets):
1435+
1436+.B ihdrer6/s
1437+.RS
1438+The number of input datagrams discarded per second due to
1439+errors in their IPv6 headers, including version
1440+number mismatch, other format errors, hop count
1441+exceeded, errors discovered in processing their
1442+IPv6 options, etc. [ipv6IfStatsInHdrErrors]
1443+.RE
1444+
1445+.B iadrer6/s
1446+.RS
1447+The number of input datagrams discarded per second because
1448+the IPv6 address in their IPv6 header's destination
1449+field was not a valid address to be received at
1450+this entity. This count includes invalid
1451+addresses (e.g., ::0) and unsupported addresses
1452+(e.g., addresses with unallocated prefixes). For
1453+entities which are not IPv6 routers and therefore
1454+do not forward datagrams, this counter includes
1455+datagrams discarded because the destination address
1456+was not a local address [ipv6IfStatsInAddrErrors].
1457+.RE
1458+
1459+.B iukwnp6/s
1460+.RS
1461+The number of locally-addressed datagrams
1462+received successfully but discarded per second because of an
1463+unknown or unsupported protocol [ipv6IfStatsInUnknownProtos].
1464+.RE
1465+
1466+.B i2big6/s
1467+.RS
1468+The number of input datagrams that could not be
1469+forwarded per second because their size exceeded the link MTU
1470+of outgoing interface [ipv6IfStatsInTooBigErrors].
1471+.RE
1472+
1473+.B idisc6/s
1474+.RS
1475+The number of input IPv6 datagrams per second for which no
1476+problems were encountered to prevent their
1477+continued processing, but which were discarded
1478+(e.g., for lack of buffer space)
1479+[ipv6IfStatsInDiscards]. Note that this
1480+counter does not include any datagrams discarded
1481+while awaiting re-assembly.
1482+.RE
1483+
1484+.B odisc6/s
1485+.RS
1486+The number of output IPv6 datagrams per second for which no
1487+problem was encountered to prevent their
1488+transmission to their destination, but which were
1489+discarded (e.g., for lack of buffer space)
1490+[ipv6IfStatsOutDiscards]. Note
1491+that this counter would include datagrams counted
1492+in fwddgm6/s if any such packets
1493+met this (discretionary) discard criterion.
1494+.RE
1495+
1496+.B inort6/s
1497+.RS
1498+The number of input datagrams discarded per second because no
1499+route could be found to transmit them to their
1500+destination [ipv6IfStatsInNoRoutes].
1501+.RE
1502+
1503+.B onort6/s
1504+.RS
1505+The number of locally generated IP datagrams discarded per second
1506+because no route could be found to transmit them to their
1507+destination [unknown formal SNMP name].
1508+.RE
1509+
1510+.B asmf6/s
1511+.RS
1512+The number of failures detected per second by the IPv6
1513+re-assembly algorithm (for whatever reason: timed
1514+out, errors, etc.) [ipv6IfStatsReasmFails].
1515+Note that this is not
1516+necessarily a count of discarded IPv6 fragments
1517+since some algorithms
1518+can lose track of the number of fragments
1519+by combining them as they are received.
1520+.RE
1521+
1522+.B fragf6/s
1523+.RS
1524+The number of IPv6 datagrams that have been
1525+discarded per second because they needed to be fragmented
1526+at this output interface but could not be
1527+[ipv6IfStatsOutFragFails].
1528+.RE
1529+
1530+.B itrpck6/s
1531+.RS
1532+The number of input datagrams discarded per second because
1533+datagram frame didn't carry enough data
1534+[ipv6IfStatsInTruncatedPkts].
1535+.RE
1536+
1537+With the
1538+.B NFS
1539+keyword, statistics about NFS client activity are reported.
1540+The following values are displayed:
1541+
1542+.B call/s
1543+.RS
1544+Number of RPC requests made per second.
1545+.RE
1546+
1547+.B retrans/s
1548+.RS
1549+Number of RPC requests per second, those which needed to be retransmitted (for
1550+example because of a server timeout).
1551+.RE
1552+
1553+.B read/s
1554+.RS
1555+Number of 'read' RPC calls made per second.
1556+.RE
1557+
1558+.B write/s
1559+.RS
1560+Number of 'write' RPC calls made per second.
1561+.RE
1562+
1563+.B access/s
1564+.RS
1565+Number of 'access' RPC calls made per second.
1566+.RE
1567+
1568+.B getatt/s
1569+.RS
1570+Number of 'getattr' RPC calls made per second.
1571+.RE
1572+
1573+With the
1574+.B NFSD
1575+keyword, statistics about NFS server activity are reported.
1576+The following values are displayed:
1577+
1578+.B scall/s
1579+.RS
1580+Number of RPC requests received per second.
1581+.RE
1582+
1583+.B badcall/s
1584+.RS
1585+Number of bad RPC requests received per second, those whose
1586+processing generated an error.
1587+.RE
1588+
1589+.B packet/s
1590+.RS
1591+Number of network packets received per second.
1592+.RE
1593+
1594+.B udp/s
1595+.RS
1596+Number of UDP packets received per second.
1597+.RE
1598+
1599+.B tcp/s
1600+.RS
1601+Number of TCP packets received per second.
1602+.RE
1603+
1604+.B hit/s
1605+.RS
1606+Number of reply cache hits per second.
1607+.RE
1608+
1609+.B miss/s
1610+.RS
1611+Number of reply cache misses per second.
1612+.RE
1613+
1614+.B sread/s
1615+.RS
1616+Number of 'read' RPC calls received per second.
1617+.RE
1618+
1619+.B swrite/s
1620+.RS
1621+Number of 'write' RPC calls received per second.
1622+.RE
1623+
1624+.B saccess/s
1625+.RS
1626+Number of 'access' RPC calls received per second.
1627+.RE
1628+
1629+.B sgetatt/s
1630+.RS
1631+Number of 'getattr' RPC calls received per second.
1632+.RE
1633+
1634+With the
1635+.B SOCK
1636+keyword, statistics on sockets in use are reported
1637+(IPv4).
1638+The following values are displayed:
1639+
1640+.B totsck
1641+.RS
1642+Total number of sockets used by the system.
1643+.RE
1644+
1645+.B tcpsck
1646+.RS
1647+Number of TCP sockets currently in use.
1648+.RE
1649+
1650+.B udpsck
1651+.RS
1652+Number of UDP sockets currently in use.
1653+.RE
1654+
1655+.B rawsck
1656+.RS
1657+Number of RAW sockets currently in use.
1658+.RE
1659+
1660+.B ip-frag
1661+.RS
1662+Number of IP fragments currently in queue.
1663+.RE
1664+
1665+.B tcp-tw
1666+.RS
1667+Number of TCP sockets in TIME_WAIT state.
1668+.RE
1669+
1670+With the
1671+.B SOCK6
1672+keyword, statistics on sockets in use are reported (IPv6).
1673+Note that IPv6 statistics depend on
1674+.BR sadc 's
1675+option "-S IPV6" to be collected.
1676+The following values are displayed:
1677+
1678+.B tcp6sck
1679+.RS
1680+Number of TCPv6 sockets currently in use.
1681+.RE
1682+
1683+.B udp6sck
1684+.RS
1685+Number of UDPv6 sockets currently in use.
1686+.RE
1687+
1688+.B raw6sck
1689+.RS
1690+Number of RAWv6 sockets currently in use.
1691+.RE
1692+
1693+.B ip6-frag
1694+.RS
1695+Number of IPv6 fragments currently in use.
1696+.RE
1697+
1698+With the
1699+.B SOFT
1700+keyword, statistics about software-based network processing are reported.
1701+The following values are displayed:
1702+
1703+.B total/s
1704+.RS
1705+The total number of network frames processed per second.
1706+.RE
1707+
1708+.B dropd/s
1709+.RS
1710+The total number of network frames dropped per second because there
1711+was no room on the processing queue.
1712+.RE
1713+
1714+.B squeezd/s
1715+.RS
1716+The number of times the softirq handler function terminated per second
1717+because its budget was consumed or the time limit was reached, but more
1718+work could have been done.
1719+.RE
1720+
1721+.B rx_rps/s
1722+.RS
1723+The number of times the CPU has been woken up per second
1724+to process packets via an inter-processor interrupt.
1725+.RE
1726+
1727+.B flw_lim/s
1728+.RS
1729+The number of times the flow limit has been reached per second.
1730+Flow limiting is an optional RPS feature that can be used to limit the number of
1731+packets queued to the backlog for each flow to a certain amount.
1732+This can help ensure that smaller flows are processed even though
1733+much larger flows are pushing packets in.
1734+.RE
1735+
1736+With the
1737+.B TCP
1738+keyword, statistics about TCPv4 network traffic are reported.
1739+Note that TCPv4 statistics depend on
1740+.BR sadc 's
1741+option "-S SNMP" to be collected.
1742+The following values are displayed (formal SNMP names between
1743+square brackets):
1744+
1745+.B active/s
1746+.RS
1747+The number of times TCP connections have made a direct
1748+transition to the SYN-SENT state from the CLOSED state per second [tcpActiveOpens].
1749+.RE
1750+
1751+.B passive/s
1752+.RS
1753+The number of times TCP connections have made a direct
1754+transition to the SYN-RCVD state from the LISTEN state per second [tcpPassiveOpens].
1755+.RE
1756+
1757+.B iseg/s
1758+.RS
1759+The total number of segments received per second, including those
1760+received in error [tcpInSegs]. This count includes segments received on
1761+currently established connections.
1762+.RE
1763+
1764+.B oseg/s
1765+.RS
1766+The total number of segments sent per second, including those on
1767+current connections but excluding those containing only
1768+retransmitted octets [tcpOutSegs].
1769+.RE
1770+
1771+With the
1772+.B ETCP
1773+keyword, statistics about TCPv4 network errors are reported.
1774+Note that TCPv4 statistics depend on
1775+.BR sadc 's
1776+option "-S SNMP" to be collected.
1777+The following values are displayed (formal SNMP names between
1778+square brackets):
1779+
1780+.B atmptf/s
1781+.RS
1782+The number of times per second TCP connections have made a direct
1783+transition to the CLOSED state from either the SYN-SENT
1784+state or the SYN-RCVD state, plus the number of times per second TCP
1785+connections have made a direct transition to the LISTEN
1786+state from the SYN-RCVD state [tcpAttemptFails].
1787+.RE
1788+
1789+.B estres/s
1790+.RS
1791+The number of times per second TCP connections have made a direct
1792+transition to the CLOSED state from either the ESTABLISHED
1793+state or the CLOSE-WAIT state [tcpEstabResets].
1794+.RE
1795+
1796+.B retrans/s
1797+.RS
1798+The total number of segments retransmitted per second - that is, the
1799+number of TCP segments transmitted containing one or more
1800+previously transmitted octets [tcpRetransSegs].
1801+.RE
1802+
1803+.B isegerr/s
1804+.RS
1805+The total number of segments received in error (e.g., bad
1806+TCP checksums) per second [tcpInErrs].
1807+.RE
1808+
1809+.B orsts/s
1810+.RS
1811+The number of TCP segments sent per second containing the RST flag [tcpOutRsts].
1812+.RE
1813+
1814+With the
1815+.B UDP
1816+keyword, statistics about UDPv4 network traffic are reported.
1817+Note that UDPv4 statistics depend on
1818+.BR sadc's
1819+option "-S SNMP" to be collected.
1820+The following values are displayed (formal SNMP names between
1821+square brackets):
1822+
1823+.B idgm/s
1824+.RS
1825+The total number of UDP datagrams delivered per second to UDP users [udpInDatagrams].
1826+.RE
1827+
1828+.B odgm/s
1829+.RS
1830+The total number of UDP datagrams sent per second from this entity [udpOutDatagrams].
1831+.RE
1832+
1833+.B noport/s
1834+.RS
1835+The total number of received UDP datagrams per second for which there
1836+was no application at the destination port [udpNoPorts].
1837+.RE
1838+
1839+.B idgmerr/s
1840+.RS
1841+The number of received UDP datagrams per second that could not be
1842+delivered for reasons other than the lack of an application
1843+at the destination port [udpInErrors].
1844+.RE
1845+
1846+With the
1847+.B UDP6
1848+keyword, statistics about UDPv6 network traffic are reported.
1849+Note that UDPv6 statistics depend on
1850+.BR sadc 's
1851+option "-S IPV6" to be collected.
1852+The following values are displayed (formal SNMP names between
1853+square brackets):
1854+
1855+.B idgm6/s
1856+.RS
1857+The total number of UDP datagrams delivered per second to UDP users
1858+[udpInDatagrams].
1859+.RE
1860+
1861+.B odgm6/s
1862+.RS
1863+The total number of UDP datagrams sent per second from this
1864+entity [udpOutDatagrams].
1865+.RE
1866+
1867+.B noport6/s
1868+.RS
1869+The total number of received UDP datagrams per second for which there
1870+was no application at the destination port [udpNoPorts].
1871+.RE
1872+
1873+.B idgmer6/s
1874+.RS
1875+The number of received UDP datagrams per second that could not be
1876+delivered for reasons other than the lack of an application
1877+at the destination port [udpInErrors].
1878+.RE
1879+
1880+The
1881+.B ALL
1882+keyword is equivalent to specifying all the keywords above and therefore all the network
1883+activities are reported.
1884+.RE
1885+.RE
1886+.IP "-o [ filename ]"
1887+Save the readings in the file in binary form. Each reading
1888+is in a separate record. The default value of the
1889+.I filename
1890+parameter is the current standard system activity daily data file.
1891+If
1892+.I filename
1893+is a directory instead of a plain file then it is considered as the directory
1894+where the standard system activity daily data files are located.
1895+The -o option is exclusive of the -f option.
1896+All the data available from the kernel are saved in the file (in fact,
1897+.B sar
1898+calls its data collector
1899+.B sadc
1900+with the option "-S ALL".
1901+See
1902+.BR sadc (8)
1903+manual page).
1904+.IP "-P { cpu_list | ALL }"
1905+Report per-processor statistics for the specified processor or processors.
1906+.I cpu_list
1907+is a list of comma-separated values or range of values (e.g.,
1908+.BR 0,2,4-7,12- ).
1909+Note that processor 0 is the first processor, and processor
1910+.B all
1911+is the global average among all processors.
1912+Specifying the
1913+.B ALL
1914+keyword reports statistics for each individual processor, and globally for
1915+all processors. Offline processors are not displayed.
1916+.IP -p
1917+Pretty-print device names. Use this option in conjunction with option -d.
1918+By default names are printed as
1919+.I devM-n
1920+where M and n are the major and minor numbers for the device.
1921+Use of this option displays the names of the devices as they (should) appear
1922+in /dev. Name mappings are controlled by
1923+.IR /etc/sysconfig/sysstat.ioconf .
1924+.IP -q
1925+Report queue length and load averages. The following values are displayed:
1926+
1927+.B runq-sz
1928+.RS
1929+.RS
1930+Run queue length (number of tasks waiting for run time).
1931+.RE
1932+
1933+.B plist-sz
1934+.RS
1935+Number of tasks in the task list.
1936+.RE
1937+
1938+.B ldavg-1
1939+.RS
1940+System load average for the last minute.
1941+The load average is calculated as the average number of runnable or
1942+running tasks (R state), and the number of tasks in uninterruptible
1943+sleep (D state) over the specified interval.
1944+.RE
1945+
1946+.B ldavg-5
1947+.RS
1948+System load average for the past 5 minutes.
1949+.RE
1950+
1951+.B ldavg-15
1952+.RS
1953+System load average for the past 15 minutes.
1954+.RE
1955+
1956+.B blocked
1957+.RS
1958+Number of tasks currently blocked, waiting for I/O to complete.
1959+.RE
1960+.RE
1961+.IP "-r [ ALL ]"
1962+Report memory utilization statistics. The
1963+.B ALL
1964+keyword indicates that all the memory fields should be displayed.
1965+The following values may be displayed:
1966+
1967+.B kbmemfree
1968+.RS
1969+.RS
1970+Amount of free memory available in kilobytes.
1971+.RE
1972+
1973+.B kbavail
1974+.RS
1975+Estimate of how much memory in kilobytes is available for starting new
1976+applications, without swapping.
1977+The estimate takes into account that the system needs some page cache to
1978+function well, and that not all reclaimable slab will be reclaimable,
1979+due to items being in use. The impact of those factors will vary from
1980+system to system.
1981+.RE
1982+
1983+.B kbmemused
1984+.RS
1985+Amount of used memory in kilobytes (calculated as total installed memory -
1986+.B kbmemfree
1987+-
1988+.B kbbuffers
1989+-
1990+.B kbcached
1991+-
1992+.BR kbslab ).
1993+.RE
1994+
1995+.B %memused
1996+.RS
1997+Percentage of used memory.
1998+.RE
1999+
2000+.B kbbuffers
2001+.RS
2002+Amount of memory used as buffers by the kernel in kilobytes.
2003+.RE
2004+
2005+.B kbcached
2006+.RS
2007+Amount of memory used to cache data by the kernel in kilobytes.
2008+.RE
2009+
2010+.B kbcommit
2011+.RS
2012+Amount of memory in kilobytes needed for current workload. This is an estimate of how much
2013+RAM/swap is needed to guarantee that there never is out of memory.
2014+.RE
2015+
2016+.B %commit
2017+.RS
2018+Percentage of memory needed for current workload in relation to the total amount of memory (RAM+swap).
2019+This number may be greater than 100% because the kernel usually overcommits memory.
2020+.RE
2021+
2022+.B kbactive
2023+.RS
2024+Amount of active memory in kilobytes (memory that has been used more recently
2025+and usually not reclaimed unless absolutely necessary).
2026+.RE
2027+
2028+.B kbinact
2029+.RS
2030+Amount of inactive memory in kilobytes (memory which has been less recently
2031+used. It is more eligible to be reclaimed for other purposes).
2032+.RE
2033+
2034+.B kbdirty
2035+.RS
2036+Amount of memory in kilobytes waiting to get written back to the disk.
2037+.RE
2038+
2039+.B kbanonpg
2040+.RS
2041+Amount of non-file backed pages in kilobytes mapped into userspace page tables.
2042+.RE
2043+
2044+.B kbslab
2045+.RS
2046+Amount of memory in kilobytes used by the kernel to cache data structures for its own use.
2047+.RE
2048+
2049+.B kbkstack
2050+.RS
2051+Amount of memory in kilobytes used for kernel stack space.
2052+.RE
2053+
2054+.B kbpgtbl
2055+.RS
2056+Amount of memory in kilobytes dedicated to the lowest level of page tables.
2057+.RE
2058+
2059+.B kbvmused
2060+.RS
2061+Amount of memory in kilobytes of used virtual address space.
2062+.RE
2063+.RE
2064+.IP -S
2065+Report swap space utilization statistics.
2066+The following values are displayed:
2067+
2068+.B kbswpfree
2069+.RS
2070+.RS
2071+Amount of free swap space in kilobytes.
2072+.RE
2073+
2074+.B kbswpused
2075+.RS
2076+Amount of used swap space in kilobytes.
2077+.RE
2078+
2079+.B %swpused
2080+.RS
2081+Percentage of used swap space.
2082+.RE
2083+
2084+.B kbswpcad
2085+.RS
2086+Amount of cached swap memory in kilobytes.
2087+This is memory that once was swapped out, is swapped back in
2088+but still also is in the swap area (if memory is needed it doesn't need
2089+to be swapped out again because it is already in the swap area. This
2090+saves I/O).
2091+.RE
2092+
2093+.B %swpcad
2094+.RS
2095+Percentage of cached swap memory in relation to the amount of used swap space.
2096+.RE
2097+.RE
2098+.IP "-s [ hh:mm[:ss] ]"
2099+Set the starting time of the data, causing the
2100+.B sar
2101+command to extract records time-tagged at, or following, the time
2102+specified. The default starting time is 08:00:00.
2103+Hours must be given in 24-hour format. This option can be
2104+used only when data are read from a file (option -f).
2105+.IP "--sadc"
2106+Indicate which data collector is called by
2107+.BR sar .
2108+If the data collector is sought in PATH then enter "which sadc" to
2109+know where it is located.
2110+.IP -t
2111+When reading data from a daily data file, indicate that
2112+.B sar
2113+should display the timestamps in the original local time of
2114+the data file creator. Without this option, the
2115+.B sar
2116+command displays the timestamps in the user's locale time.
2117+.IP "-u [ ALL ]"
2118+Report CPU utilization. The
2119+.B ALL
2120+keyword indicates that all the CPU fields should be displayed.
2121+The report may show the following fields:
2122+
2123+.B %user
2124+.RS
2125+.RS
2126+Percentage of CPU utilization that occurred while executing at the user
2127+level (application). Note that this field includes time spent running
2128+virtual processors.
2129+.RE
2130+
2131+.B %usr
2132+.RS
2133+Percentage of CPU utilization that occurred while executing at the user
2134+level (application). Note that this field does NOT include time spent
2135+running virtual processors.
2136+.RE
2137+
2138+.B %nice
2139+.RS
2140+Percentage of CPU utilization that occurred while executing at the user
2141+level with nice priority.
2142+.RE
2143+
2144+.B %system
2145+.RS
2146+Percentage of CPU utilization that occurred while executing at the system
2147+level (kernel). Note that this field includes time spent servicing
2148+hardware and software interrupts.
2149+.RE
2150+
2151+.B %sys
2152+.RS
2153+Percentage of CPU utilization that occurred while executing at the system
2154+level (kernel). Note that this field does NOT include time spent servicing
2155+hardware or software interrupts.
2156+.RE
2157+
2158+.B %iowait
2159+.RS
2160+Percentage of time that the CPU or CPUs were idle during which
2161+the system had an outstanding disk I/O request.
2162+.RE
2163+
2164+.B %steal
2165+.RS
2166+Percentage of time spent in involuntary wait by the virtual CPU
2167+or CPUs while the hypervisor was servicing another virtual processor.
2168+.RE
2169+
2170+.B %irq
2171+.RS
2172+Percentage of time spent by the CPU or CPUs to service hardware interrupts.
2173+.RE
2174+
2175+.B %soft
2176+.RS
2177+Percentage of time spent by the CPU or CPUs to service software interrupts.
2178+.RE
2179+
2180+.B %guest
2181+.RS
2182+Percentage of time spent by the CPU or CPUs to run a virtual processor.
2183+.RE
2184+
2185+.B %gnice
2186+.RS
2187+Percentage of time spent by the CPU or CPUs to run a niced guest.
2188+.RE
2189+
2190+.B %idle
2191+.RS
2192+Percentage of time that the CPU or CPUs were idle and the system
2193+did not have an outstanding disk I/O request.
2194+.RE
2195+.RE
2196+.IP -V
2197+Print version number then exit.
2198+.IP -v
2199+Report status of inode, file and other kernel tables.
2200+The following values are displayed:
2201+
2202+.B dentunusd
2203+.RS
2204+.RS
2205+Number of unused cache entries in the directory cache.
2206+.RE
2207+
2208+.B file-nr
2209+.RS
2210+Number of file handles used by the system.
2211+.RE
2212+
2213+.B inode-nr
2214+.RS
2215+Number of inode handlers used by the system.
2216+.RE
2217+
2218+.B pty-nr
2219+.RS
2220+Number of pseudo-terminals used by the system.
2221+.RE
2222+.RE
2223+.IP -W
2224+Report swapping statistics. The following values are displayed:
2225+
2226+.B pswpin/s
2227+.RS
2228+.RS
2229+Total number of swap pages the system brought in per second.
2230+.RE
2231+
2232+.B pswpout/s
2233+.RS
2234+Total number of swap pages the system brought out per second.
2235+.RE
2236+.RE
2237+.IP -w
2238+Report task creation and system switching activity.
2239+
2240+.B proc/s
2241+.RS
2242+.RS
2243+Total number of tasks created per second.
2244+.RE
2245+
2246+.B cswch/s
2247+.RS
2248+Total number of context switches per second.
2249+.RE
2250+.RE
2251+.IP -y
2252+Report TTY devices activity. The following values are displayed:
2253+
2254+.B rcvin/s
2255+.RS
2256+.RS
2257+Number of receive interrupts per second for current serial line. Serial line number
2258+is given in the TTY column.
2259+.RE
2260+
2261+.B xmtin/s
2262+.RS
2263+Number of transmit interrupts per second for current serial line.
2264+.RE
2265+
2266+.B framerr/s
2267+.RS
2268+Number of frame errors per second for current serial line.
2269+.RE
2270+
2271+.B prtyerr/s
2272+.RS
2273+Number of parity errors per second for current serial line.
2274+.RE
2275+
2276+.B brk/s
2277+.RS
2278+Number of breaks per second for current serial line.
2279+.RE
2280+
2281+.B ovrun/s
2282+.RS
2283+Number of overrun errors per second for current serial line.
2284+.RE
2285+.RE
2286+.IP -z
2287+Tell
2288+.B sar
2289+to omit output for any devices for which there was no activity during the
2290+sample period.
2291+
2292+.SH ENVIRONMENT
2293+The
2294+.B sar
2295+command takes into account the following environment variables:
2296+
2297+.IP S_COLORS
2298+When this variable is set, display statistics in color on the terminal.
2299+Possible values for this variable are
2300+.IR never ,
2301+.IR always
2302+or
2303+.IR auto
2304+(the latter is the default).
2305+
2306+Please note that the color (being red, yellow, or some other color) used to display a value
2307+is not indicative of any kind of issue simply because of the color. It only indicates different
2308+ranges of values.
2309+
2310+.IP S_COLORS_SGR
2311+Specify the colors and other attributes used to display statistics on the terminal.
2312+Its value is a colon-separated list of capabilities that defaults to
2313+.BR C=33;22:H=31;1:I=32;22:M=35;1:N=34;1:R=31;22:Z=34;22 .
2314+Supported capabilities are:
2315+
2316+.RS
2317+.TP
2318+.B C=
2319+SGR (Select Graphic Rendition) substring for comments inserted in the binary daily
2320+data files.
2321+
2322+.TP
2323+.B H=
2324+SGR substring for percentage values greater than or equal to 75%.
2325+
2326+.TP
2327+.B I=
2328+SGR substring for item names or values (eg. network interfaces, CPU number...)
2329+
2330+.TP
2331+.B M=
2332+SGR substring for percentage values in the range from 50% to 75%.
2333+
2334+.TP
2335+.B N=
2336+SGR substring for non-zero statistics values.
2337+
2338+.TP
2339+.B R=
2340+SGR substring for restart messages.
2341+
2342+.TP
2343+.B Z=
2344+SGR substring for zero values.
2345+.RE
2346+
2347+.IP S_TIME_DEF_TIME
2348+If this variable exists and its value is
2349+.B UTC
2350+then
2351+.B sar
2352+will save its data in UTC time (data will still be displayed in local time).
2353+.B sar
2354+will also use UTC time instead of local time to determine the current daily
2355+data file located in the
2356+.IR /var/log/sa
2357+directory. This variable may be useful for servers with users located across
2358+several timezones.
2359+
2360+.IP S_TIME_FORMAT
2361+If this variable exists and its value is
2362+.B ISO
2363+then the current locale will be ignored when printing the date in the report header.
2364+The
2365+.B sar
2366+command will use the ISO 8601 format (YYYY-MM-DD) instead.
2367+The timestamp will also be compliant with ISO 8601 format.
2368+.SH EXAMPLES
2369+.B sar -u 2 5
2370+.RS
2371+Report CPU utilization for each 2 seconds. 5 lines are displayed.
2372+.RE
2373+
2374+.B sar -I 14 -o int14.file 2 10
2375+.RS
2376+Report statistics on IRQ 14 for each 2 seconds. 10 lines are displayed.
2377+Data are stored in a file called
2378+.IR int14.file .
2379+.RE
2380+
2381+.B sar -r -n DEV -f /var/log/sa/sa16
2382+.RS
2383+Display memory and network statistics saved in daily data file 'sa16'.
2384+.RE
2385+
2386+.B sar -A
2387+.RS
2388+Display all the statistics saved in current daily data file.
2389+.SH BUGS
2390+.I /proc
2391+filesystem must be mounted for the
2392+.B sar
2393+command to work.
2394+
2395+All the statistics are not necessarily available, depending on the kernel version used.
2396+.B sar
2397+assumes that you are using at least a 2.6 kernel.
2398+.SH FILES
2399+.I /var/log/sa/saDD
2400+.br
2401+.I /var/log/sa/saYYYYMMDD
2402+.RS
2403+The standard system activity daily data files and their default location.
2404+YYYY stands for the current year, MM for the current month and DD for the
2405+current day.
2406+
2407+.RE
2408+.I /proc
2409+and
2410+.I /sys
2411+contain various files with system statistics.
2412+.SH AUTHOR
2413+Sebastien Godard (sysstat <at> orange.fr)
2414+.SH SEE ALSO
2415+.BR sadc (8),
2416+.BR sa1 (8),
2417+.BR sa2 (8),
2418+.BR sadf (1),
2419+.BR sysstat (5),
2420+.BR pidstat (1),
2421+.BR mpstat (1),
2422+.BR iostat (1),
2423+.BR vmstat (8)
2424+
2425+.I https://github.com/sysstat/sysstat
2426+
2427+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man1/tapestat.1
@@ -0,0 +1,263 @@
1+.TH TAPESTAT 1 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+tapestat \- Report tape statistics.
4+.SH SYNOPSIS
5+.B tapestat [ -k | -m ] [ -t ] [ -V ] [ -y ] [ -z ] [ --human ] [
6+.I interval
7+.B [
8+.I count
9+.B ] ]
10+.SH DESCRIPTION
11+The
12+.B tapestat
13+command is used for monitoring the activity of tape drives connected to a system.
14+
15+The first report generated by the
16+.B tapestat
17+command provides statistics
18+concerning the time since the system was booted, unless the
19+.B -y
20+option is used, when this first report is omitted.
21+Each subsequent report
22+covers the time since the previous report.
23+
24+The
25+.I interval
26+parameter specifies the amount of time in seconds between
27+each report.
28+The
29+.I count
30+parameter can be specified in conjunction with the
31+.I interval
32+parameter. If the
33+.I count
34+parameter is specified, the value of
35+.I count
36+determines the number of reports generated at
37+.I interval
38+seconds apart. If the
39+.I interval
40+parameter is specified without the
41+.I count
42+parameter, the
43+.B tapestat
44+command generates reports continuously.
45+
46+.SH REPORT
47+The
48+.B tapestat
49+report provides statistics for each tape drive connected to the system.
50+The following data are displayed:
51+
52+.B r/s
53+.RS
54+The number of reads issued expressed as the number per second averaged over the interval.
55+
56+.RE
57+.B w/s
58+.RS
59+The number of writes issued expressed as the number per second averaged over the interval.
60+
61+.RE
62+.B kB_read/s | MB_read/s
63+.RS
64+The amount of data read expressed in kilobytes (by default or if option -k used) or
65+megabytes (if option -m used) per second averaged over the interval.
66+
67+.RE
68+.B kB_wrtn/s | MB_wrtn/s
69+.RS
70+The amount of data written expressed in kilobytes (by default or if option -k used) or
71+megabytes (if option -m used) per second averaged over the interval.
72+
73+.RE
74+.B %Rd
75+.RS
76+Read percentage wait - The percentage of time over the interval spent waiting for read requests
77+to complete.
78+The time is measured from when the request is dispatched to the SCSI mid-layer until it signals
79+that it completed.
80+
81+.RE
82+.B %Wr
83+.RS
84+Write percentage wait - The percentage of time over the interval spent waiting for write requests
85+to complete. The time is measured from when the request is dispatched to the SCSI mid-layer until
86+it signals that it completed.
87+
88+.RE
89+.B %Oa
90+.RS
91+Overall percentage wait - The percentage of time over the interval spent waiting for any
92+I/O request to complete (read, write, and other).
93+
94+.RE
95+.B Rs/s
96+.RS
97+The number of I/Os, expressed as the number per second averaged over the interval, where
98+a non-zero residual value was encountered.
99+
100+.RE
101+.B Ot/s
102+.RS
103+The number of I/Os, expressed as the number per second averaged over the interval, that
104+were included as "other". Other I/O includes ioctl calls made to the tape driver and
105+implicit operations performed by the tape driver such as rewind on close
106+(for tape devices that implement rewind on close). It does not include any I/O performed
107+using methods outside of the tape driver (e.g. via sg ioctls).
108+.RE
109+.RE
110+.SH OPTIONS
111+.IP --human
112+Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.)
113+The units displayed with this option supersede any other default units (e.g.
114+kilobytes, sectors...) associated with the metrics.
115+.IP -k
116+Show the amount of data written or read in kilobytes per second instead of megabytes.
117+This option is mutually exclusive with -m.
118+.IP -m
119+Show the amount of data written or read in megabytes per second instead of kilobytes.
120+This option is mutually exclusive with -k.
121+.IP -t
122+Display time stamps. The time stamp format may depend
123+on the value of the S_TIME_FORMAT environment variable (see below).
124+.IP -V
125+Print version and exit.
126+.IP -y
127+Omit the initial statistic showing values since boot.
128+.IP -z
129+Tell
130+.B tapestat
131+to omit output for any tapes for which there was no activity
132+during the sample period.
133+
134+.SH CONSIDERATIONS
135+It is possible for a percentage value (read, write, or other) to be greater than 100 percent
136+(the
137+.B tapestat
138+command will never show a percentage value more than 999).
139+If rewinding a tape takes 40 seconds where the interval time is 5 seconds the %Oa value
140+would show as 0 in the intervals before the rewind completed and then show as approximately
141+800 percent when the rewind completes.
142+
143+Similar values will be observed for %Rd and %Wr if a tape drive stops reading or writing
144+and then restarts (that is it stopped streaming). In such a case you may see the r/s or w/s drop to zero and the %Rd/%Wr value could be higher than 100 when reading or writing continues
145+(depending on how long it takes to restart writing or reading).
146+This is only an issue if it happens a lot as it may cause tape wear and will impact
147+on the backup times.
148+
149+For fast tape drives you may see low percentage wait times.
150+This does not indicate an issue with the tape drive. For a slower tape drive (e.g. an older
151+generation DDS drive) the speed of the tape (and tape drive) is much slower than filesystem I/O,
152+percent wait times are likely to be higher. For faster tape drives (e.g. LTO) the percentage
153+wait times are likely to be lower as program writing to or reading from tape is going
154+to be doing a lot more filesystem I/O because of the higher throughput.
155+
156+Although tape statistics are implemented in the kernel using atomic variables they cannot be
157+read atomically as a group. All of the statistics values are read from different files under
158+/sys, because of this there may be I/O completions while reading the different files for the
159+one tape drive. This may result in a set of statistics for a device that contain some values
160+before an I/O completed and some after.
161+
162+This command uses rounding down as the rounding method when calculating per second statistics.
163+If, for example, you are using dd to copy one tape to another and running
164+.B tapestat
165+with an interval of 5 seconds and over the interval there were 3210 writes and 3209 reads
166+then w/s would show 642 and r/s 641 (641.8 rounded down to 641). In such a case if it was
167+a tar archive being copied (with a 10k block size) you would also see a difference between
168+the kB_read/s and kB_wrtn/s of 2 (one I/O 10k in size divided by the interval period of 5
169+seconds). If instead there were 3210 writes and 3211 reads both w/s and r/s would both show
170+642 but you would still see a difference between the kB_read/s and kB_wrtn/s values of 2 kB/s.
171+
172+This command is provided with an interval in seconds. However internally the interval is
173+tracked per device and can potentially have an effect on the per second statistics reported.
174+The time each set of statistics is captured is kept with those statistics. The difference
175+between the current and previous time is converted to milliseconds for use in calculations.
176+We can look at how this can impact the statistics reported if we use an example of a tar
177+archive being copied between two tape drives using dd. If both devices reported 28900 kilobytes
178+transferred and the reading tape drive had an interval of 5001 milliseconds and the writing
179+tape drive 5000 milliseconds that would calculate out as 5778 kB_read/s and 5780 kB_wrtn/s.
180+
181+The impact of some retrieving statistics during an I/O completion, rounding down, and small differences in the interval period on the statistics calculated should be minimal but may be non-zero.
182+.SH ENVIRONMENT
183+The
184+.B tapestat
185+command takes into account the following environment variables:
186+
187+.IP S_COLORS
188+When this variable is set, display statistics in color on the terminal.
189+Possible values for this variable are
190+.IR never ,
191+.IR always
192+or
193+.IR auto
194+(the latter is the default).
195+
196+Please note that the color (being red, yellow, or some other color) used to display a value
197+is not indicative of any kind of issue simply because of the color. It only indicates different
198+ranges of values.
199+
200+.IP S_COLORS_SGR
201+Specify the colors and other attributes used to display statistics on the terminal.
202+Its value is a colon-separated list of capabilities that defaults to
203+.BR H=31;1:I=32;22:M=35;1:N=34;1:Z=34;22 .
204+Supported capabilities are:
205+
206+.RS
207+.TP
208+.B H=
209+SGR (Select Graphic Rendition) substring for percentage values greater than or equal to 75%.
210+
211+.TP
212+.B I=
213+SGR substring for tape names.
214+
215+.TP
216+.B M=
217+SGR substring for percentage values in the range from 50% to 75%.
218+
219+.TP
220+.B N=
221+SGR substring for non-zero statistics values.
222+
223+.TP
224+.B Z=
225+SGR substring for zero values.
226+.RE
227+
228+.IP S_TIME_FORMAT
229+If this variable exists and its value is
230+.BR ISO
231+then the current locale will be ignored when printing the date in the report
232+header. The
233+.B tapestat
234+command will use the ISO 8601 format (YYYY-MM-DD) instead.
235+The timestamp displayed with option -t will also be compliant with ISO 8601
236+format.
237+
238+.SH BUGS
239+.I /sys
240+filesystem must be mounted for
241+.B tapestat
242+to work. It will not work on kernels that do not have sysfs support
243+
244+This command requires kernel version 4.2 or later
245+(or tape statistics support backported for an earlier kernel version).
246+
247+.SH FILES
248+.I /sys/class/scsi_tape/st<num>/stats/*
249+Statistics files for tape devices.
250+
251+.I /proc/uptime
252+contains system uptime.
253+.SH AUTHOR
254+Initial revision by Shane M. SEYMOUR (shane.seymour <at> hpe.com)
255+.br
256+Modified for sysstat by Sebastien Godard (sysstat <at> orange.fr)
257+.SH SEE ALSO
258+.BR iostat (1),
259+.BR mpstat (1)
260+
261+.I https://github.com/sysstat/sysstat
262+
263+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man5/sysstat.5
@@ -0,0 +1,179 @@
1+.TH SYSSTAT 5 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+sysstat \- sysstat configuration file.
4+.SH DESCRIPTION
5+This file is read by
6+.BR sa1 (8)
7+and
8+.BR sa2 (8)
9+shell scripts from the sysstat's set of tools.
10+It consists of a sequence of shell variable assignments used to
11+configure sysstat logging.
12+The variables and their meanings are:
13+.TP
14+.B COMPRESSAFTER
15+Number of days after which daily data files are to be compressed.
16+The compression program is given in the
17+.B ZIP
18+variable.
19+
20+.TP
21+.B HISTORY
22+The number of days during which a daily data file or a report
23+should be kept. Data files or reports older than this number of
24+days will be removed by the
25+.BR sa2 (8)
26+shell script.
27+Data files and reports are normally saved in the /var/log/sa directory,
28+under the name
29+.IR saDD
30+(for data files) or
31+.IR sarDD
32+(for reports), where the DD parameter indicates the current day.
33+
34+The number of files actually kept in the /var/log/sa directory may be
35+slightly higher than the
36+.B HISTORY
37+value due to the way the
38+.B sa2
39+script figures
40+out which files are to be removed (see below "How the
41+.BR sa2 (8)
42+script applies
43+.B HISTORY
44+value"). Using a value of 28 keeps a whole month's worth of data. If
45+you set
46+.B HISTORY
47+to a value greater than 28 then you should consider using
48+.BR sadc 's
49+option -D to prevent older data files from being overwritten (see
50+.BR sadc (8)
51+manual page). In this latter case data files are named
52+.IR saYYYYMMDD
53+and reports
54+.IR sarYYYYMMDD ,
55+where YYYY stands for the current year, MM for the
56+current month and DD for the current day.
57+
58+How the
59+.BR sa2 (8)
60+script applies
61+.B HISTORY
62+value
63+
64+The
65+.B sa2
66+script uses the "find" command with the "-mtime" option to figure
67+out which files are to be removed. The "find" command interprets this value
68+as "N 24 hour periods", ignoring any fractional part. This means that the
69+last modified time of a given sa[r]DD data or report file, using a
70+.B HISTORY
71+of 1, has to have been modified at least two days ago before it will be
72+removed. And for a
73+.B HISTORY
74+of 28 that would mean 29 days ago.
75+
76+To figure out how a
77+.B HISTORY
78+of 28 is applied in practice, we need to
79+consider that the
80+.B sa2
81+script that issues the "find" command to remove the
82+old files typically runs just before mid-night on a given system, and since
83+the first record from
84+.B sadc
85+can also be written to the previous day's data file
86+(thereby moving its modification time up a bit), the
87+.B sa2
88+script will leave
89+30 files untouched. So for a setting of 28, and counting the data file of
90+the current day, there will always be 31 files (or 30 files, depending on the
91+number of days in a month) in the /var/log/sa directory during the majority
92+of a given day. E.g.:
93+
94+April 30th: 31 files (Apr 30th-1st, Mar 31th)
95+.br
96+May 1st: 30 files (May 1st, Apr 30th-2nd)
97+
98+Yet we can note the following exceptions (as inspected at Noon of the given
99+day):
100+
101+February 28th: 31 files (Feb 28th-1st, Jan 31st, 30th & 29th)
102+.br
103+March 1st: 30 files (Mar 1st, Feb 28th-2nd, Jan 31st & 30th)
104+.br
105+March 2nd: 29 files (Mar 1st & 2nd, Feb 28th-3rd, Jan. 31st)
106+.br
107+March 3rd: 28 files (Mar 1st-3rd, Feb 28th-4th)
108+.br
109+March 4th - March 28th: 28 files
110+.br
111+March 29th: 29 files
112+.br
113+March 30th: 30 files
114+.br
115+March 31st: 31 files
116+
117+(Determining the number of files in March on a leap year is left as an
118+exercise for the reader).
119+
120+Things are simpler if you use the sa[r]YYYYMMDD name format.
121+Apply the same logic as above in this case and you will find that there
122+are always
123+.B HISTORY
124++ 3 files in the
125+.IR /var/log/sa
126+directory during the majority of a given day.
127+
128+.TP
129+.B REPORTS
130+Set this variable to false to prevent the
131+.B sa2
132+script from generating reports (the
133+.IR sarDD
134+files).
135+
136+.TP
137+.B SA_DIR
138+Directory where the standard system activity daily data and report files
139+are saved. Its default value is
140+.IR /var/log/sa .
141+
142+.TP
143+.B SADC_OPTIONS
144+Options that should be passed to
145+.BR sadc (8).
146+With these options (see
147+.BR sadc (8)
148+manual page), you can select some additional data which are going to be saved in
149+daily data files.
150+These options are used only when a new data file is created. They will be
151+ignored with an already existing one.
152+
153+.TP
154+.B YESTERDAY
155+By default
156+.BR sa2
157+script generates yesterday's summary, since the cron job
158+usually runs right after midnight. If you want
159+.BR sa2
160+to generate the summary of the same day (for example when cron
161+job runs at 23:53) set this variable to no.
162+
163+.TP
164+.B ZIP
165+Program used to compress data and report files.
166+
167+.SH FILES
168+.IR /etc/sysconfig/sysstat
169+
170+.SH AUTHOR
171+Sebastien Godard (sysstat <at> orange.fr)
172+.SH SEE ALSO
173+.BR sadc (8),
174+.BR sa1 (8),
175+.BR sa2 (8)
176+
177+.I https://github.com/sysstat/sysstat
178+
179+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man8/sa1.8
@@ -0,0 +1,86 @@
1+.TH SA1 8 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+sa1 \- Collect and store binary data in the system activity daily data file.
4+.SH SYNOPSIS
5+.B /usr/lib64/sa/sa1 [ --boot |
6+.I interval
7+.I count
8+.B ]
9+.SH DESCRIPTION
10+The
11+.B sa1
12+command is a shell procedure variant of the
13+.B sadc
14+command and handles all of the flags and parameters of that command. The
15+.B sa1
16+command collects and stores binary data in the current standard
17+system activity daily data file.
18+
19+The standard system activity daily data file is named
20+.I saDD
21+unless
22+.BR sadc 's
23+option
24+.B -D
25+is used, in which case its name is
26+.IR saYYYYMMDD ,
27+where YYYY stands for the current year, MM for the current month
28+and DD for the current day. By default it is located in the
29+.I /var/log/sa
30+directory.
31+
32+The
33+.I interval
34+and
35+.I count
36+parameters specify that the record should be written
37+.I count
38+times at
39+.I interval
40+seconds. If no arguments are given to
41+.B sa1
42+then a single record is written.
43+
44+The
45+.B sa1
46+command is designed to be started automatically by the cron command.
47+
48+.SH OPTIONS
49+.IP --boot
50+This option tells
51+.B sa1
52+that the
53+.B sadc
54+command should be called without specifying the
55+.I interval
56+and
57+.I count
58+parameters in order to insert a dummy record, marking the time when the counters
59+restart from 0.
60+
61+.SH EXAMPLE
62+To collect data (including those from disks) every 10 minutes,
63+place the following entry in your root crontab file:
64+
65+.B 0,10,20,30,40,50 * * * * /usr/lib64/sa/sa1 1 1 -S DISK
66+
67+.SH FILES
68+.I /var/log/sa/saDD
69+.br
70+.I /var/log/sa/saYYYYMMDD
71+.RS
72+The standard system activity daily data files and their default location.
73+YYYY stands for the current year, MM for the current month and DD for the
74+current day.
75+.SH AUTHOR
76+Sebastien Godard (sysstat <at> orange.fr)
77+.SH SEE ALSO
78+.BR sar (1),
79+.BR sadc (8),
80+.BR sa2 (8),
81+.BR sadf (1),
82+.BR sysstat (5)
83+
84+.I https://github.com/sysstat/sysstat
85+
86+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man8/sa2.8
@@ -0,0 +1,72 @@
1+.TH SA2 8 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+sa2 \- Create a report from the current standard system activity daily data file.
4+.SH SYNOPSIS
5+.B /usr/lib64/sa/sa2
6+.SH DESCRIPTION
7+The
8+.B sa2
9+command is a shell procedure variant of the
10+.B sar
11+command which writes a daily report in the
12+.I sarDD
13+or the
14+.I sarYYYYMMDD
15+file, where YYYY stands for the current year, MM for the current month
16+and DD for the current day.
17+By default the report is saved in the
18+.I /var/log/sa
19+directory.
20+The
21+.B sa2
22+command will also remove reports more than one week old by default.
23+You can however keep reports for a longer (or a shorter) period by setting
24+the
25+.B HISTORY
26+environment variable. Read the
27+.BR sysstat (5)
28+manual page for details.
29+
30+The
31+.B sa2
32+command accepts most of the flags and parameters of the
33+.B sar
34+command.
35+
36+The
37+.B sa2
38+command is designed to be started automatically by the cron command.
39+
40+.SH EXAMPLES
41+To run the
42+.B sa2
43+command daily, place the following entry in your root crontab file:
44+
45+.B 5 19 * * 1-5 /usr/lib64/sa/sa2 -A &
46+
47+This will generate by default a daily report called
48+.I sarDD
49+in the
50+.I /var/log/sa
51+directory, where the DD parameter is a number representing the day of the
52+month.
53+.SH FILES
54+.I /var/log/sa/sarDD
55+.br
56+.I /var/log/sa/sarYYYYMMDD
57+.RS
58+The standard system activity daily report files and their default location.
59+YYYY stands for the current year, MM for the current month and DD for the
60+current day.
61+.SH AUTHOR
62+Sebastien Godard (sysstat <at> orange.fr)
63+.SH SEE ALSO
64+.BR sar (1),
65+.BR sadc (8),
66+.BR sa1 (8),
67+.BR sadf (1),
68+.BR sysstat (5)
69+
70+.I https://github.com/sysstat/sysstat
71+
72+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/man8/sadc.8
@@ -0,0 +1,244 @@
1+.TH SADC 8 "JULY 2018" Linux "Linux User's Manual" -*- nroff -*-
2+.SH NAME
3+sadc \- System activity data collector.
4+.SH SYNOPSIS
5+.B /usr/lib64/sa/sadc [ -C
6+.I comment
7+.B ] [ -D ] [ -F ] [ -L ] [ -V ] [ -S { keyword [,...] | ALL | XALL } ] [
8+.I interval
9+.B [
10+.I count
11+.B ] ] [
12+.I outfile
13+.B ]
14+.SH DESCRIPTION
15+The
16+.B sadc
17+command samples system data a specified number of times
18+(\fIcount\fR) at a specified interval measured in seconds
19+(\fIinterval\fR). It writes in binary format to the specified
20+.I outfile
21+or to standard output. If
22+.I outfile
23+is set to -, then
24+.B sadc
25+uses the standard system activity daily data file (see below).
26+In this case, if the file already exists,
27+.B sadc
28+will overwrite it if it is from a previous month.
29+By default
30+.B sadc
31+collects most of the data available from the kernel.
32+But there are also optional metrics, for which the
33+relevant options must be explicitly passed to
34+.B sadc
35+to be collected (see option -S below).
36+
37+The standard system activity daily data file is named
38+.I saDD
39+unless option
40+.B -D
41+is used, in which case its name is
42+.IR saYYYYMMDD ,
43+where YYYY stands for the current year, MM for the current month
44+and DD for the current day.
45+By default it is located in the
46+.I /var/log/sa
47+directory. Yet it is possible to specify an alternate location for
48+it: If
49+.I outfile
50+is a directory (instead of a plain file) then it will be considered
51+as the directory where the standard system activity daily data file
52+will be saved.
53+
54+When the
55+.I count
56+parameter is not specified,
57+.B sadc
58+writes its data endlessly.
59+When both
60+.I interval
61+and
62+.I count
63+are not specified, and option -C is not used,
64+a dummy record, which is used at system startup to mark
65+the time when the counter restarts from 0, will be written.
66+For example, one of the system startup script may write the restart mark to
67+the daily data file by the command entry:
68+
69+.B "/usr/lib64/sa/sadc -"
70+
71+The
72+.B sadc
73+command is intended to be used as a backend to the
74+.B sar
75+command.
76+
77+Note: The
78+.B sadc
79+command only reports on local activities.
80+
81+.SH OPTIONS
82+.IP "-C comment"
83+When neither the
84+.I interval
85+nor the
86+.I count
87+parameters are specified, this option tells
88+.B sadc
89+to write a dummy record containing the specified
90+.I comment
91+string.
92+This comment can then be displayed with option -C of
93+.BR sar .
94+.IP -D
95+Use
96+.I saYYYYMMDD
97+instead of
98+.I saDD
99+as the standard system activity daily data file name.
100+.IP -F
101+The creation of
102+.I outfile
103+will be forced. If the file already exists and has a format unknown to
104+.B sadc
105+then it will be truncated. This may be useful for daily data files
106+created by an older version of
107+.B sadc
108+and whose format is no longer compatible with current one.
109+.IP -L
110+.B sadc
111+will try to get an exclusive lock on the
112+.I outfile
113+before writing to it or truncating it. Failure to get the lock is fatal,
114+except in the case of trying to write a normal (i.e. not a dummy and not
115+a header) record to an existing file, in which case
116+.B sadc
117+will try again at the next interval. Usually, the only reason a lock
118+would fail would be if another
119+.B sadc
120+process were also writing to the file. This can happen when cron is used
121+to launch
122+.BR sadc .
123+If the system is under heavy load, an old
124+.B sadc
125+might still be running when cron starts a new one. Without locking,
126+this situation can result in a corrupted system activity file.
127+.IP "-S { keyword [,...] | ALL | XALL }"
128+Possible keywords are DISK, INT, IPV6, POWER, SNMP, XDISK, ALL, and XALL.
129+
130+Specify which optional activities should be collected by
131+.BR sadc .
132+Some activities are optional to prevent data files from growing too large.
133+The
134+.B DISK
135+keyword indicates that
136+.B sadc
137+should collect data for block devices.
138+The
139+.B INT
140+keyword indicates that
141+.B sadc
142+should collect data for system interrupts.
143+The
144+.B IPV6
145+keyword indicates that IPv6 statistics should be
146+collected by
147+.BR sadc .
148+The
149+.B POWER
150+keyword indicates that
151+.B sadc
152+should collect power management statistics.
153+The
154+.B SNMP
155+keyword indicates that SNMP statistics should be
156+collected by
157+.BR sadc .
158+The
159+.B ALL
160+keyword is equivalent to specifying all the keywords above and therefore
161+all previous activities are collected.
162+
163+The
164+.B XDISK
165+keyword is an extension to the
166+.B DISK
167+one and indicates that partitions and filesystems statistics should be collected by
168+.B sadc
169+in addition to disk statistics. This option works only with kernels 2.6.25
170+and later.
171+The
172+.B XALL
173+keyword is equivalent to specifying all the keywords above (including
174+keyword extensions) and therefore all possible activities are collected.
175+
176+Important note: The activities (including optional ones) saved in an existing
177+data file prevail over those selected with option -S.
178+As a consequence, appending data to an existing data file will result in
179+option -S being ignored.
180+.IP -V
181+Print version number then exit.
182+
183+.SH ENVIRONMENT
184+The
185+.B sadc
186+command takes into account the following environment variable:
187+
188+.IP S_TIME_DEF_TIME
189+If this variable exists and its value is
190+.BR UTC
191+then
192+.B sadc
193+will save its data in UTC time.
194+.B sadc
195+will also use UTC time instead of local time to determine the current
196+daily data file located in the
197+.IR /var/log/sa
198+directory.
199+.SH EXAMPLES
200+.B /usr/lib64/sa/sadc 1 10 /tmp/datafile
201+.RS
202+Write 10 records of one second intervals to the /tmp/datafile binary file.
203+.RE
204+
205+.B /usr/lib64/sa/sadc -C Backup_Start /tmp/datafile
206+.RS
207+Insert the comment Backup_Start into the file /tmp/datafile.
208+.RE
209+.SH BUGS
210+The
211+.I /proc
212+filesystem must be mounted for the
213+.B sadc
214+command to work.
215+
216+All the statistics are not necessarily available, depending on the kernel version used.
217+.B sadc
218+assumes that you are using at least a 2.6 kernel.
219+.SH FILES
220+.I /var/log/sa/saDD
221+.br
222+.I /var/log/sa/saYYYYMMDD
223+.RS
224+The standard system activity daily data files and their default location.
225+YYYY stands for the current year, MM for the current month and DD for the
226+current day.
227+
228+.RE
229+.I /proc
230+and
231+.I /sys
232+contain various files with system statistics.
233+.SH AUTHOR
234+Sebastien Godard (sysstat <at> orange.fr)
235+.SH SEE ALSO
236+.BR sar (1),
237+.BR sa1 (8),
238+.BR sa2 (8),
239+.BR sadf (1),
240+.BR sysstat (5)
241+
242+.I https://github.com/sysstat/sysstat
243+
244+.I http://pagesperso-orange.fr/sebastien.godard/
--- /dev/null
+++ b/manual/sysstat/original/sysstat-12.0.5.lsm
@@ -0,0 +1,35 @@
1+Begin4
2+Title: sysstat - the sar, sadf, mpstat, iostat, tapestat, pidstat and cifsiostat commands for Linux
3+Version: 12.0.5
4+Entered-date: 2019-05-31
5+Description: The sysstat package contains the sar, sadf, mpstat, iostat, tapestat,
6+ pidstat, cifsiostat and sa tools for Linux.
7+ The sar command collects and reports system activity
8+ information.
9+ The information collected by sar can be saved in a file
10+ in a binary format for future inspection.
11+ The statistics reported by sar concern I/O transfer rates,
12+ paging activity, process-related activities, interrupts,
13+ network activity, memory and swap space utilization, CPU
14+ utilization, kernel activities and TTY statistics, among
15+ others. Both UP and SMP machines are fully supported.
16+ The sadf command is used to display data collected by sar in various
17+ formats (XML, database-friendly, etc.) and to draw graphs (SVG).
18+ The mpstat command reports global and per-processor statistics.
19+ The iostat command reports CPU utilization and I/O statistics
20+ for disks.
21+ The tapestat command reports statistics for tape drives connected
22+ to the system.
23+ The pidstat command reports statistics for Linux tasks (processes).
24+ The cifsiostat command reports I/O statistics for CIFS filesystems.
25+ NB: Send bugs, patches, suggestions and/or questions to
26+ (sysstat [at] orange.fr).
27+ URL: http://pagesperso-orange.fr/sebastien.godard/
28+Keywords: system administration, system monitoring, sar, sadf, iostat, mpstat, tapestat, pidstat, system accounting, performance, tuning
29+Author: sysstat@NOSPAM.orange.fr (Sebastien Godard)
30+Maintained-by: sysstat@NOSPAM.orange.fr (Sebastien Godard)
31+Primary-site: http://pagesperso-orange.fr/sebastien.godard/
32+ 536kiB sysstat-12.0.5.tar.xz
33+Alternate-site:
34+Copying-policy: GPL
35+End
--- /dev/null
+++ b/manual/sysstat/translation_list
@@ -0,0 +1,11 @@
1+●:sysstat:12.0.5:2018/07/01:cifsiostat:1:2019/07/07::ysato444@ybb.ne.jp:Yuichi SATO:
2+●:sysstat:12.0.5:2018/07/01:iostat:1:2019/07/06::ysato444@ybb.ne.jp:Yuichi SATO:
3+●:sysstat:12.0.5:2018/07/01:mpstat:1:2019/07/06::ysato444@ybb.ne.jp:Yuichi SATO:
4+●:sysstat:12.0.5:2018/07/01:pidstat:1:2019/07/07::ysato444@ybb.ne.jp:Yuichi SATO:
5+●:sysstat:12.0.5:2018/07/01:sadf:1:2019/07/08::ysato444@ybb.ne.jp:Yuichi SATO:
6+●:sysstat:12.0.5:2019/04/01:sar:1:2019/07/06::ysato444@ybb.ne.jp:Yuichi SATO:
7+×:sysstat:12.0.5:2018/07/01:tapestat:1:::::
8+●:sysstat:12.0.5:2018/07/01:sysstat:5:2019/07/09::ysato444@ybb.ne.jp:Yuichi SATO:
9+●:sysstat:12.0.5:2018/07/01:sa1:8:2019/07/09::ysato444@ybb.ne.jp:Yuichi SATO:
10+●:sysstat:12.0.5:2018/07/01:sa2:8:2019/07/09::ysato444@ybb.ne.jp:Yuichi SATO:
11+●:sysstat:12.0.5:2018/07/01:sadc:8:2019/07/09::ysato444@ybb.ne.jp:Yuichi SATO:
Show on old repository browser