1PCP-ATOPSAR(1) General Commands Manual PCP-ATOPSAR(1)
2
3
4
6 pcp-atopsar - Advanced System Activity Report (pcp-atop related)
7
9 pcp [pcp options] atopsar [atop options] [-r file|date] [-h host] [-R
10 cnt] [-b hh:mm] [-e hh:mm]
11 pcp [pcp options] atopsar [atop options] interval [samples]
12
14 The pcp-atopsar program can be used to report statistics at the system
15 level.
16
17 In the first synopsis line (no sampling interval specified), pcp-atop‐
18 sar extracts data from a raw logfile that has been recorded previously
19 by pmlogger(1) (or via the -w option of the pcp-atop program).
20 You can specify the name of the logfile with the -r option of the pcp-
21 atopsar program. When a pmlogger daily logfile is used, named
22 $PCP_LOG_DIR/pmlogger/[host]/YYYYMMDD (where YYYYMMDD reflects the
23 date), the required date of the form YYYYMMDD can be specified with the
24 -r option instead of the filename, or the symbolic name 'y' can be used
25 for yesterday's daily logfile (this can be repeated so 'yyyy' indicates
26 the logfile of four days ago). If the -r option is not specified at
27 all, today's daily logfile is used by default.
28 By default, the hostname of the localhost will be used when resolving
29 pmlogger archives, however an alternative host can be specified using
30 the -h option.
31 The starting and ending times of the report can be defined using the
32 options -b and -e followed by a time argument of the form hh:mm.
33
34 In the second synopsis line, pcp-atopsar reads actual activity counters
35 from the kernel with the specified interval (in seconds) and the speci‐
36 fied number of samples (optionally). When pcp-atopsar is activated in
37 this way it immediately sends the output for every requested report to
38 standard output. If only one type of report is requested, the header
39 is printed once and after every interval seconds the statistical coun‐
40 ters are shown for that period. If several reports are requested, a
41 header is printed per sample followed by the statistical counters for
42 that period.
43
44 When invoked via the pcp(1) command, the PCPIntro(1) options -h/--host,
45 -a/--archive, -O/--origin, -s/--samples, -t/--interval, -Z/--timezone
46 and several other pcp options become indirectly available.
47
48 Some generic flags can be specified to influence the behaviour of the
49 pcp-atopsar program:
50
51 -S By default the timestamp at the beginning of a line is suppressed
52 if more lines are shown for one interval. With this flag a time‐
53 stamp is given for every output-line (easier for post-processing).
54
55 -a By default certain resources as disks and network interfaces are
56 only shown when they were active during the interval. With this
57 flag all resources of a given type are shown, even if they were
58 inactive during the interval.
59
60 -x By default pcp-atopsar only uses colors if output is directed to a
61 terminal (window). These colors might indicate that a critical
62 occupation percentage has been reached (red) or has been almost
63 reached (cyan) for a particular resource. See the man-page of
64 atop for a detailed description of this feature (section COLORS).
65 With the flag -x the use of colors is suppressed unconditionally.
66
67 -C By default pcp-atopsar only uses colors if output is directed to a
68 terminal (window). These colors might indicate that a critical
69 occupation percentage has been reached (red) or has been almost
70 reached (cyan) for a particular resource. See the man-page of
71 atop for a detailed description of this feature (section COLORS).
72 With the flag -C colors will always be used, even if output is not
73 directed to a terminal.
74
75 -M Use markers at the end of a line to indicate that a critical occu‐
76 pation percentage has been reached ('*') or has been almost
77 reached ('+') for particular resources. The marker '*' is similar
78 to the color red and the marker '+' to the color cyan. See the
79 man-page of atop for a detailed description of these colors (sec‐
80 tion COLORS).
81
82 -H Repeat the header line within a report for every N detail lines.
83 The value of N is determined dynamically in case of output to a
84 tty/window (depending on the number of lines); for output to a
85 file or pipe this value is 23.
86
87 -R Summarize cnt samples into one sample. When the logfile contains
88 e.g. samples of 10 minutes, the use of the flag '-R 6' shows a
89 report with one sample for every hour.
90
91 Other flags are used to define which reports are required:
92
93 -A Show all possible reports.
94
95 -c Report about CPU utilization (in total and per cpu).
96
97 -g Report about GPU utilization (per GPU).
98
99 -p Report about processor-related matters, like load-averages and
100 hardware interrupts.
101
102 -P Report about processes.
103
104 -m Current memory- and swap-occupation.
105
106 -s Report about paging- and swapping-activity, and overcommitment.
107
108 -B Report about Pressure Stall Information (PSI).
109
110 -l Report about utilization of logical volumes.
111
112 -f Report about utilization of multiple devices.
113
114 -d Report about utilization of disks.
115
116 -n Report about NFS mounted filesystems on NFS client.
117
118 -j Report about NFS client activity.
119
120 -J Report about NFS server activity.
121
122 -i Report about the network interfaces.
123
124 -I Report about errors for network-interfaces.
125
126 -w Report about IP version 4 network traffic.
127
128 -W Report about errors for IP version 4 traffic.
129
130 -y General report about ICMP version 4 layer activity.
131
132 -Y Per-type report about ICMP version 4 layer activity.
133
134 -u Report about UDP version 4 network traffic.
135
136 -z Report about IP version 6 network traffic.
137
138 -Z Report about errors for IP version 6 traffic.
139
140 -k General report about ICMP version 6 layer activity.
141
142 -K Per-type report about ICMP version 6 layer activity.
143
144 -U Report about UDP version 6 network traffic.
145
146 -t Report about TCP network traffic.
147
148 -T Report about errors for TCP-traffic.
149
150 -h Report about Infiniband utilization.
151
152 -O Report about top-3 processes consuming most processor capacity.
153 This report is only available when using a log file (not when
154 specifying an interval).
155
156 -G Report about top-3 processes consuming most resident memory. This
157 report is only available when using a log file (not when specify‐
158 ing an interval).
159
160 -D Report about top-3 processes issueing most disk transfers. This
161 report is only available when using a log file (not when specify‐
162 ing an interval).
163
164 -N Report about top-3 processes issueing most IPv4/IPv6 socket trans‐
165 fers. This report is only available when using a log file (not
166 when specifying an interval).
167
169 Depending on the requested report, a number of columns with output val‐
170 ues are produced. The values are mostly presented as a number of
171 events per second.
172
173 The output for the flag -c contains the following columns per cpu:
174
175 usr% Percentage of cpu-time consumed in user mode (program text)
176 for all active processes running with a nice value of zero
177 (default) or a negative nice value (which means a higher
178 priority than usual). The cpu consumption in user mode of
179 processes with a nice value larger than zero (lower prior‐
180 ity) is indicated in the nice%-column.
181
182 nice% Percentage of cpu time consumed in user mode (i.e. program
183 text) for all processes running witn a nice value larger
184 than zero (which means with a lower priority than average).
185
186 sys% Percentage of cpu time consumed in system mode (kernel
187 text) for all active processes. A high percentage usually
188 indicates a lot of system calls being issued.
189
190 irq% Percentage of cpu time consumed for handling of device
191 interrupts.
192
193 softirq% Percentage of cpu time consumed for soft interrupt han‐
194 dling.
195
196 steal% Percentage of cpu time stolen by other virtual machines
197 running on the same hardware.
198
199 guest% Percentage of cpu time used by other virtual machines run‐
200 ning on the same hardware (overlaps with usr%/nice%).
201
202 wait% Percentage of unused cpu time while at least one of the
203 processes in wait-state awaits completion of disk I/O.
204
205 idle% Percentage of unused cpu time because all processes are in
206 a wait-state but not waiting for disk-I/O.
207
208 The output for the flag -g contains the following columns per GPU:
209
210 busaddr GPU number and bus-ID (separated by '/').
211
212 gpubusy GPU busy percentage during interval.
213
214 membusy GPU memory busy percentage during interval, i.e. time to
215 issue read and write accesses on memory.
216
217 memocc Percentage of memory occupation at this moment.
218
219 memtot Total memory available.
220
221 memuse Used GPU memory at this moment.
222
223 gputype Type of GPU.
224
225 The output for the flag -p contains the following values:
226
227 pswch/s Number of process switches (also called context switches)
228 per second on this cpu. A process switch occurs at the
229 moment that an active thread (i.e. the thread using a cpu)
230 enters a wait state or has used its time slice completely;
231 another thread will then be chosen to use the cpu.
232
233 devintr/s Number of hardware interrupts handled per second on this
234 cpu.
235
236 clones/s The number of new threads started per second.
237
238 loadavg1 Load average reflecting the average number of threads in
239 the runqueue or in non-interruptible wait state (usually
240 waiting for disk or tape I/O) during the last minute.
241
242 loadavg5 Load average reflecting the average number of threads in
243 the runqueue or in non-interruptible wait state (usually
244 waiting for disk or tape I/O) during the last 5 minutes.
245
246 loadavg15 Load average reflecting the average number of threads in
247 the runqueue or in non-interruptible wait state (usually
248 waiting for disk or tape I/O) during the last 15 minutes.
249
250 The output for the flag -P contains information about the processes and
251 threads:
252
253 clones/s The number of new threads started per second.
254
255 pexit/s
256
257 curproc Total number of processes present in the system.
258
259 curzomb Number of zombie processes present in the system.
260
261 thrrun Total number of threads present in the system in state
262 'running'.
263
264 thrslpi Total number of threads present in the system in state
265 'interruptible sleeping'.
266
267 thrslpu Total number of threads present in the system in state
268 'uninterruptible sleeping'.
269
270 The output for the flag -m contains information about the memory- and
271 swap-utilization:
272
273 memtotal Total usable main memory size.
274
275 memfree Available main memory size at this moment (snapshot).
276
277 buffers Main memory used at this moment to cache metadata-blocks
278 (snapshot).
279
280 cached Main memory used at this moment to cache data-blocks (snap‐
281 shot).
282
283 dirty Amount of memory in the page cache that still has to be
284 flushed to disk at this moment (snapshot).
285
286 slabmem Main memory used at this moment for dynamically allocated
287 memory by the kernel (snapshot).
288
289 swptotal Total swap space size at this moment (snapshot).
290
291 swpfree Available swap space at this moment (snapshot).
292
293 The output for the flag -s contains information about the frequency of
294 swapping:
295
296 pagescan/s Number of scanned pages per second due to the fact that
297 free memory drops below a particular threshold.
298
299 swapin/s The number of memory-pages the system read from the swap-
300 device per second.
301
302 swapout/s The number of memory-pages the system wrote to the swap-
303 device per second.
304
305 commitspc The committed virtual memory space i.e. the reserved vir‐
306 tual space for all allocations of private memory space for
307 processes.
308
309 commitlim The maximum limit for the committed space, which is by
310 default swap size plus 50% of memory size. The kernel only
311 verifies whether the committed space exceeds the limit if
312 strict overcommit handling is configured (vm.overcom‐
313 mit_memory is 2).
314
315 The output for the flag -B contains the Pressure Stall Information
316 (PSI):
317
318 cs_10_60_300
319 Average pressure percentage over the last 10, 60 and 300
320 seconds for the category 'CPU some'.
321
322 ms_10_60_300
323 Average pressure percentage over the last 10, 60 and 300
324 seconds for the category 'memory some'.
325
326 mf_10_60_300
327 Average pressure percentage over the last 10, 60 and 300
328 seconds for the category 'memory full'.
329
330 is_10_60_300
331 Average pressure percentage over the last 10, 60 and 300
332 seconds for the category 'I/O some'.
333
334 if_10_60_300
335 Average pressure percentage over the last 10, 60 and 300
336 seconds for the category 'I/O full'.
337
338 The output for the flags -l (LVM), -f (MD), and -d (hard disk) contains
339 the following columns per active unit:
340
341 disk Name.
342
343 busy Busy-percentage of the unit (i.e. the portion of time that
344 the device was busy handling requests).
345
346 read/s Number of read-requests issued per second on this unit.
347
348 KB/read Average number of Kbytes transferred per read-request for
349 this unit.
350
351 writ/s Number of write-requests issued per second on this unit.
352
353 KB/writ Average number of Kbytes transferred per write-request for
354 this unit.
355
356 avque Average number of requests outstanding in the queue during
357 the time that the unit is busy.
358
359 avserv Average number of milliseconds needed by a request on this
360 unit (seek, latency and data-transfer).
361
362 The output for the flag -n contains information about activity on NFS
363 mounted filesystems (client):
364
365 mounted_device
366 Mounted device containing server name and server directory
367 being mounted.
368
369 physread/s Kilobytes data physically read from the NFS server by pro‐
370 cesses running on the NFS client.
371
372 KBwrite/s Kilobytes data physically written to the NFS server by pro‐
373 cesses running on the NFS client.
374 When the NFS filesystem was mounted during the interval,
375 the state 'M' is shown.
376
377 The output for the flag -j contains information about NFS client activ‐
378 ity:
379
380 rpc/s Number of RPC calls per second issued to NFS server(s).
381
382 rpcread/s Number of read RPC calls per second issued to NFS
383 server(s).
384
385 rpcwrite/s Number of write RPC calls per second issued to NFS
386 server(s).
387
388 retrans/s Number of retransmitted RPC calls per second.
389
390 autrefresh/s
391 Number of authorization refreshes per second.
392
393 The output for the flag -J contains information about NFS server activ‐
394 ity:
395
396 rpc/s Number of RPC calls per second received from NFS client(s).
397
398 rpcread/s Number of read RPC calls per second received from NFS
399 client(s).
400
401 rpcwrite/s Number of write RPC calls per second received from NFS
402 client(s).
403
404 MBcr/s Number of Megabytes per second returned to read requests by
405 clients.
406
407 MBcw/s Number of Megabytes per second passed in write requests by
408 clients.
409
410 nettcp/s Number of requests per second handled via TCP.
411
412 netudp/s Number of requests per second handled via UDP.
413
414 The output for the flag -i provides information about utilization of
415 network interfaces:
416
417 interf Name of interface.
418
419 busy Busy percentage for this interface. If the linespeed of
420 this interface could not be determined (e.g. for virtual
421 interfaces), a question mark is shown.
422
423 ipack/s Number of packets received from this interface per second.
424
425 opack/s Number of packets transmitted to this interface per second.
426
427 iKbyte/s Number of Kbytes received from this interface per second.
428
429 oKbyte/s Number of Kbytes transmitted via this interface per second.
430
431 imbps/s Effective number of megabits received per second.
432
433 ombps/s Effective number of megabits transmitted per second.
434
435 maxmbps/s Linespeed as number of megabits per second. If the line‐
436 speed could not be determined (e.g. virtual interfaces),
437 value 0 is shown.
438 The linespeed is followed by the indication 'f' (full
439 duplex) or 'h' (half duplex).
440
441 The output for the flag -I provides information about the failures that
442 were detected for network interfaces:
443
444 interf Name of interface.
445
446 ierr/s Number of bad packets received from this interface per sec‐
447 ond.
448
449 oerr/s Number of times that packet transmission to this interface
450 failed per second.
451
452 coll/s Number of collisions encountered per second while transmit‐
453 ting packets.
454
455 idrop/s Number of received packets dropped per second due to lack
456 of buffer-space in the local system.
457
458 odrop/s Number of transmitted packets dropped per second due to
459 lack of buffer-space in the local system.
460
461 iframe/s Number of frame alignment-errors encountered per second on
462 received packets.
463
464 ocarrier/s Number of carrier-errors encountered per second on trans‐
465 mitted packets.
466
467 The output for the flag -w provides information about the utilization
468 of the IPv4-layer (formal SNMP-names between brackets):
469
470 inrecv/s Number of IP datagrams received from interfaces per second,
471 including those received in error (ipInReceives).
472
473 outreq/s Number of IP datagrams that local higher-layer protocols
474 supplied to IP in requests for transmission per second
475 (ipOutRequests).
476
477 indeliver/s Number of received IP datagrams that have been successfully
478 delivered to higher protocol-layers per second (ipInDeliv‐
479 ers).
480
481 forward/s Number of received IP datagrams per second for which this
482 entity was not their final IP destination, as a result of
483 which an attempt was made to forward (ipForwDatagrams).
484
485 reasmok/s Number of IP datagrams successfully reassembled per second
486 (ipReasmOKs).
487
488 fragcreat/s Number of IP datagram fragments generated per second at
489 this entity (ipFragCreates).
490
491 The output for the flag -W provides information about the failures that
492 were detected in the IPv4-layer (formal SNMP-names between brackets):
493
494 in: dsc/s Number of input IP datagrams per second for which no prob‐
495 lems were encountered to prevent their continued processing
496 but that were discarded, e.g. for lack of buffer space
497 (ipInDiscards).
498
499 in: hder/s Number of input IP datagrams per second discarded due to
500 errors in the IP header (ipInHdrErrors).
501
502 in: ader/s Number of input IP datagrams per second discarded because
503 the IP address in the destination field was not valid to be
504 received by this entity (ipInAddrErrors).
505
506 in: unkp/s Number of inbound packets per second that were discarded
507 because of an unknown or unsupported protocol (ipInUnknown‐
508 Protos).
509
510 in: ratim/s Number of timeout-situations per second while other frag‐
511 ments were expected for successful reassembly (ipReasmTime‐
512 out).
513
514 in: rfail/s Number of failures detected per second by the IP reassembly
515 algorithm (ipReasmFails).
516
517 out: dsc/s Number of output IP datagrams per second for which no prob‐
518 lems were encountered to prevent their continued processing
519 but that were discarded, e.g. for lack of buffer space
520 (ipOutDiscards).
521
522 out: nrt/s Number of IP datagrams per second discarded because no
523 route could be found (ipOutNoRoutes).
524
525 The output for the flag -y provides information about the general uti‐
526 lization of the ICMPv4-layer and some information per type of ICMP-mes‐
527 sage (formal SNMP-names between brackets):
528
529 intot/s Number of ICMP messages (any type) received per second at
530 this entity (icmpInMsgs).
531
532 outtot/s Number of ICMP messages (any type) transmitted per second
533 from this entity (icmpOutMsgs).
534
535 inecho/s Number of ICMP Echo (request) messages received per second
536 (icmpInEchos).
537
538 inerep/s Number of ICMP Echo-Reply messages received per second
539 (icmpInEchoReps).
540
541 otecho/s Number of ICMP Echo (request) messages transmitted per sec‐
542 ond (icmpOutEchos).
543
544 oterep/s Number of ICMP Echo-Reply messages transmitted per second
545 (icmpOutEchoReps).
546
547 The output for the flag -Y provides information about other types of
548 ICMPv4-messages (formal SNMP-names between brackets):
549
550 ierr/s Number of ICMP messages received per second but determined
551 to have ICMP-specific errors (icmpInErrors).
552
553 isq/s Number of ICMP Source Quench messages received per second
554 (icmpInSrcQuenchs).
555
556 ird/s Number of ICMP Redirect messages received per second (icmp‐
557 InRedirects).
558
559 idu/s Number of ICMP Destination Unreachable messages received
560 per second (icmpInDestUnreachs).
561
562 ite/s Number of ICMP Time Exceeded messages received per second
563 (icmpOutTimeExcds).
564
565 oerr/s Number of ICMP messages transmitted per second but deter‐
566 mined to have ICMP-specific errors (icmpOutErrors).
567
568 osq/s Number of ICMP Source Quench messages transmitted per sec‐
569 ond (icmpOutSrcQuenchs).
570
571 ord/s Number of ICMP Redirect messages transmitted per second
572 (icmpOutRedirects).
573
574 odu/s Number of ICMP Destination Unreachable messages transmitted
575 per second (icmpOutDestUnreachs).
576
577 ote/s Number of ICMP Time Exceeded messages transmitted per sec‐
578 ond (icmpOutTimeExcds).
579
580 The output for the flag -u provides information about the utilization
581 of the UDPv4-layer (formal SNMP-names between brackets):
582
583 indgram/s Number of UDP datagrams per second delivered to UDP users
584 (udpInDatagrams).
585
586 outdgram/s Number of UDP datagrams transmitted per second from this
587 entity (udpOutDatagrams).
588
589 inerr/s Number of received UDP datagrams per second that could not
590 be delivered for reasons other than the lack of an applica‐
591 tion at the destination port (udpInErrors).
592
593 noport/s Number of received UDP datagrams per second for which there
594 was no application at the destination port (udpNoPorts).
595
596 The output for the flag -z provides information about the utilization
597 of the IPv6-layer (formal SNMP-names between brackets):
598
599 inrecv/s Number of input IPv6-datagrams received from interfaces per
600 second, including those received in error (ipv6IfStatsInRe‐
601 ceives).
602
603 outreq/s Number of IPv6-datagrams per second that local higher-layer
604 protocols supplied to IP in requests for transmission
605 (ipv6IfStatsOutRequests). This counter does not include
606 any forwarded datagrams.
607
608 inmc/s Number of multicast packets per second that have been
609 received by the interface (ipv6IfStatsInMcastPkts).
610
611 outmc/s Number of multicast packets per second that have been
612 transmitted to the interface (ipv6IfStatsOutMcastPkts).
613
614 indeliv/s Number of IP datagrams successfully delivered per second to
615 IPv6 user-protocols, including ICMP (ipv6IfStatsInDeliv‐
616 ers).
617
618 reasmok/s Number of IPv6 datagrams successfully reassembled per sec‐
619 ond (ipv6IfStatsReasmOKs).
620
621 fragcre/s Number of IPv6 datagram fragments generated per second at
622 this entity (ipv6IfStatsOutFragCreates).
623
624 The output for the flag -Z provides information about the failures that
625 were detected in the IPv6-layer (formal SNMP-names between brackets):
626
627 in: dsc/s Number of input IPv6 datagrams per second for which no
628 problems were encountered to prevent their continued pro‐
629 cessing but that were discarded, e.g. for lack of buffer
630 space (ipv6IfStatsInDiscards).
631
632 in: hder/s Number of input datagrams per second discarded due to
633 errors in the IPv6 header (ipv6IfStatsInHdrErrors).
634
635 in: ader/s Number of input datagrams per second discarded because the
636 IPv6 address in the destination field was not valid to be
637 received by this entity (ipv6IfStatsInAddrErrors).
638
639 in: unkp/s Number of locally-addressed datagrams per second that were
640 discarded because of an unknown or unsupported protocol
641 (ipv6IfStatsInUnknownProtos).
642
643 in: ratim/s Number of timeout-situations per second while other IPv6
644 fragments were expected for successful reassembly
645 (ipv6ReasmTimeout).
646
647 in: rfail/s Number of failures detected per second by the IPv6 reassem‐
648 bly-algorithm (ipv6IfStatsReasmFails).
649
650 out: dsc/s Number of output IPv6 datagrams per second for which no
651 problems were encountered to prevent their continued pro‐
652 cessing but that were discarded, e.g. for lack of buffer
653 space (ipv6IfStatsOutDiscards).
654
655 out: nrt/s Number of IPv6 datagrams per second discarded because no
656 route could be found (ipv6IfStatsInNoRoutes).
657
658 The output for the flag -k provides information about the general uti‐
659 lization of the ICMPv6-layer and some information per type of ICMP-mes‐
660 sage (formal SNMP-names between brackets):
661
662 intot/s Number of ICMPv6 messages (any type) received per second at
663 the interface (ipv6IfIcmpInMsgs).
664
665 outtot/s Number of ICMPv6 messages (any type) transmitted per second
666 from this entity (ipv6IfIcmpOutMsgs).
667
668 inerr/s Number of ICMPv6 messages received per second that had
669 ICMP-specific errors, such as bad ICMP checksums, bad
670 length, etc (ipv6IfIcmpInErrors).
671
672 innsol/s Number of ICMP Neighbor Solicit messages received per sec‐
673 ond (ipv6IfIcmpInNeighborSolicits).
674
675 innadv/s Number of ICMP Neighbor Advertisement messages received per
676 second (ipv6IfIcmpInNeighborAdvertisements).
677
678 otnsol/s Number of ICMP Neighbor Solicit messages transmitted per
679 second (ipv6IfIcmpOutNeighborSolicits).
680
681 otnadv/s Number of ICMP Neighbor Advertisement messages transmitted
682 per second (ipv6IfIcmpOutNeighborAdvertisements).
683
684 The output for the flag -K provides information about other types of
685 ICMPv6-messages (formal SNMP-names between brackets):
686
687 iecho/s Number of ICMP Echo (request) messages received per second
688 (ipv6IfIcmpInEchos).
689
690 ierep/s Number of ICMP Echo-Reply messages received per second
691 (ipv6IfIcmpInEchoReplies).
692
693 oerep/s Number of ICMP Echo-Reply messages transmitted per second
694 (ipv6IfIcmpOutEchoReplies).
695
696 idu/s Number of ICMP Destination Unreachable messages received
697 per second (ipv6IfIcmpInDestUnreachs).
698
699 odu/s Number of ICMP Destination Unreachable messages transmitted
700 per second (ipv6IfIcmpOutDestUnreachs).
701
702 ird/s Number of ICMP Redirect messages received per second
703 (ipv6IfIcmpInRedirects).
704
705 ord/s Number of ICMP Redirect messages transmitted per second
706 (ipv6IfIcmpOutRedirect).
707
708 ite/s Number of ICMP Time Exceeded messages received per second
709 (ipv6IfIcmpInTimeExcds).
710
711 ote/s Number of ICMP Time Exceeded messages transmitted per sec‐
712 ond (ipv6IfIcmpOutTimeExcds).
713
714 The output for the flag -U provides information about the utilization
715 of the UDPv6-layer (formal SNMP-names between brackets):
716
717 indgram/s Number of UDPv6 datagrams per second delivered to UDP users
718 (udpInDatagrams),
719
720 outdgram/s Number of UDPv6 datagrams transmitted per second from this
721 entity (udpOutDatagrams),
722
723 inerr/s Number of received UDPv6 datagrams per second that could
724 not be delivered for reasons other than the lack of an
725 application at the destination port (udpInErrors).
726
727 noport/s Number of received UDPv6 datagrams per second for which
728 there was no application at the destination port (udpNo‐
729 Ports).
730
731 The output for the flag -t provides information about the utilization
732 of the TCP-layer (formal SNMP-names between brackets):
733
734 insegs/s Number of received segments per second, including those
735 received in error (tcpInSegs).
736
737 outsegs/s Number of transmitted segments per second, excluding those
738 containing only retransmitted octets (tcpOutSegs).
739
740 actopen/s Number of active opens per second that have been supported
741 by this entity (tcpActiveOpens).
742
743 pasopen/s Number of passive opens per second that have been supported
744 by this entity (tcpPassiveOpens).
745
746 nowopen Number of connections currently open (snapshot), for which
747 the state is either ESTABLISHED or CLOSE-WAIT (tcpCur‐
748 rEstab).
749
750 The output for the flag -T provides information about the failures that
751 were detected in the TCP-layer (formal SNMP-names between brackets):
752
753 inerr/s Number of received segments per second received in error
754 (tcpInErrs).
755
756 retrans/s Number of retransmitted segments per second (tcpRe‐
757 transSegs).
758
759 attfail/s Number of failed connection attempts per second that have
760 occurred at this entity (tcpAttemptFails).
761
762 estabreset/s
763 Number of resets per second that have occurred at this
764 entity (tcpEstabResets).
765
766 outreset/s Number of transmitted segments per second containing the
767 RST flag (tcpOutRsts).
768
769 The output for the flag -h provides information about utilization of
770 Infiniband ports:
771
772 controller Name of controller.
773
774 port Controller port.
775
776 busy Busy percentage for this port.
777
778 ipack/s Number of packets received from this port per second.
779
780 opack/s Number of packets transmitted to this port per second.
781
782 igbps/s Effective number of gigabits received per second.
783
784 ogbps/s Effective number of gigabits transmitted per second.
785
786 maxgbps/s Maximum rate as number of gigabits per second.
787
788 lanes Number of lanes.
789
790 The output for the flag -O provides information about the top-3 of pro‐
791 cesses with the highest processor consumption:
792
793 pid Process-id (if zero, the process has exited while the pid
794 could not be determined).
795
796 command The name of the process.
797
798 cpu% The percentage of cpu-capacity being consumed. This value
799 can exceed 100% for a multithreaded process running on a
800 multiprocessor machine.
801
802 The output for the flag -G provides information about the top-3 of pro‐
803 cesses with the highest memory consumption:
804
805 pid Process-id (if zero, the process has exited while the pid
806 could not be determined).
807
808 command The name of the process.
809
810 mem% The percentage of resident memory-utilization by this
811 process.
812
813 The output for the flag -D provides information about the top-3 of pro‐
814 cesses that issue the most read and write accesses to disk:
815
816 pid Process-id (if zero, the process has exited while the pid
817 could not be determined).
818
819 command The name of the process.
820
821 dsk% The percentage of read and write accesses related to the
822 total number of read and write accesses issued on disk by
823 all processes, so a high percentage does not imply a high
824 disk load on system level.
825
826 The output for the flag -N provides information about the top-3 of pro‐
827 cesses that issue the most socket transfers for IPv4/IPv6:
828
829 pid Process-id (if zero, the process has exited while the pid
830 could not be determined).
831
832 command The name of the process.
833
834 net% The percentage of socket transfers related to the total
835 number of transfers issued by all processes, so a high per‐
836 centage does not imply a high network load on system level.
837
839 To see today's cpu-activity so far (supposed that atop is logging in
840 the background):
841
842 pcp-atopsar
843
844 To see the memory occupation for June 5, 2018 between 10:00 and 12:30
845 (supposed that pmlogger has been logging daily in the background on
846 host acme.com):
847
848 pcp-atopsar -m -r $PCP_LOG_DIR/pmlogger/acme.com/20180605 -b 10:00 -e
849 12:30
850
851 or
852
853 pcp-atopsar -m -r 20180605 -b 10:00 -e 12:30
854
855 or, suppose it is June 8, 2018 at this moment
856
857 pcp-atopsar -m -r yyy -b 10:00 -e 12:30
858
859 Write a logfile with atop to record the system behaviour for 30 minutes
860 (30 samples of one minute) and produce all available reports after‐
861 wards:
862
863 pcp-atop -w /tmp/atoplog 60 30
864
865 pcp-atopsar -A -r /tmp/atoplog
866
867 To watch TCP activity evolve for ten minutes (10 samples with sixty
868 seconds interval):
869
870 pcp-atopsar -t 60 10
871
872 To watch the header-lines ('_' as last character) of all reports with
873 only the detail-lines showing critical resource consumption (marker '*'
874 or '+' as last character):
875
876 pcp-atopsar -AM | grep '[_*+]$'
877
879 /etc/atoprc
880 Configuration file containing system-wide default values (mainly
881 flags). See related man-page.
882
883 ~/.atoprc
884 Configuration file containing personal default values (mainly
885 flags). See related man-page.
886
887 $PCP_LOG_DIR/pmlogger/HOST/YYYYMMDD
888 Daily data file, where YYYYMMDD are digits representing the date,
889 and HOST is the hostname of the machine being logged.
890
892 pcp(1), pcp-atop(1), mkaf(1), pmlogger(1), pmlogger_daily(1), PCPIn‐
893 tro(1) and pcp-atoprc(5).
894
895
896
897Performance Co-Pilot PCP PCP-ATOPSAR(1)