1ATOPSAR(1) General Commands Manual ATOPSAR(1)
2
6 atopsar - Advanced System Activity Report (atop related)
7
9 atopsar [-flags...] [-r file|date ] [-R cnt ] [-b hh:mm ] [-e hh:mm ]
10 atopsar [-flags...] interval [ samples ]
11
13 The program atopsar can be used to report statistics on system level.
14 In the first synopsis line (no sampling interval specified), atopsar
16 extracts data from a raw logfile that has been recorded previously by
17 the program atop (option -w of the atop program).
18 You can specify the name of the logfile with the -r option of the atop‐
19 sar program. When a daily logfile of atop is used, named
20 /var/log/atop/atop_YYYYMMDD (where YYYYMMDD reflects the date), the
21 required date of the form YYYYMMDD can be specified with the -r option
22 instead of the filename, or the symbolic name 'y' can be used for yes‐
23 terday's daily logfile (this can be repeated so 'yyyy' indicates the
24 logfile of four days ago). If the -r option is not specified at all,
25 today's daily logfile is used by default.
26 The starting and ending times of the report can be defined using the
27 options -b and -e followed by a time argument of the form hh:mm.
28 In the second synopsis line, atopsar reads actual activity counters
30 from the kernel with the specified interval (in seconds) and the speci‐
31 fied number of samples (optionally). When atopsar is activated in this
32 way it immediately sends the output for every requested report to stan‐
33 dard output. If only one type of report is requested, the header is
34 printed once and after every interval seconds the statistical counters
35 are shown for that period. If several reports are requested, a header
36 is printed per sample followed by the statistical counters for that
37 period.
38 Some generic flags can be specified to influence the behaviour of the
40 atopsar program:
41 -S By default the timestamp at the beginning of a line is suppressed
43 if more lines are shown for one interval. With this flag a time‐
44 stamp is given for every output-line (easier for post-processing).
45 -a By default certain resources as disks and network interfaces are
47 only shown when they were active during the interval. With this
48 flag all resources of a given type are shown, even if they were
49 inactive during the interval.
50 -x By default atopsar only uses colors if output is directed to a
52 terminal (window). These colors might indicate that a critical
53 occupation percentage has been reached (red) or has been almost
54 reached (cyan) for a particular resource. See the man-page of
55 atop for a detailed description of this feature (section COLORS).
56 With the flag -x the use of colors is suppressed unconditionally.
57 -C By default atopsar only uses colors if output is directed to a
59 terminal (window). These colors might indicate that a critical
60 occupation percentage has been reached (red) or has been almost
61 reached (cyan) for a particular resource. See the man-page of
62 atop for a detailed description of this feature (section COLORS).
63 With the flag -C colors will always be used, even if output is not
64 directed to a terminal.
65 -M Use markers at the end of a line to indicate that a critical occu‐
67 pation percentage has been reached ('*') or has been almost
68 reached ('+') for particular resources. The marker '*' is similar
69 to the color red and the marker '+' to the color cyan. See the
70 man-page of atop for a detailed description of these colors (sec‐
71 tion COLORS).
72 -H Repeat the header line within a report for every N detail lines.
74 The value of N is determined dynamically in case of output to a
75 tty/window (depending on the number of lines); for output to a
76 file or pipe this value is 23.
77 -R Summarize cnt samples into one sample. When the logfile contains
79 e.g. samples of 10 minutes, the use of the flag '-R 6' shows a
80 report with one sample for every hour.
81 Other flags are used to define which reports are required:
83 -A Show all possible reports.
85 -c Report about CPU utilization (in total and per cpu).
87 -g Report about GPU utilization (per GPU).
89 -p Report about processor-related matters, like load-averages and
91 hardware interrupts.
92 -P Report about processes.
94 -m Current memory- and swap-occupation.
96 -s Report about paging- and swapping-activity, and overcommitment.
98 -B Report about Pressure Stall Information (PSI).
100 -l Report about utilization of logical volumes.
102 -f Report about utilization of multiple devices.
104 -d Report about utilization of disks.
106 -n Report about NFS mounted filesystems on NFS client.
108 -j Report about NFS client activity.
110 -J Report about NFS server activity.
112 -i Report about the network interfaces.
114 -I Report about errors for network-interfaces.
116 -w Report about IP version 4 network traffic.
118 -W Report about errors for IP version 4 traffic.
120 -y General report about ICMP version 4 layer activity.
122 -Y Per-type report about ICMP version 4 layer activity.
124 -u Report about UDP version 4 network traffic.
126 -z Report about IP version 6 network traffic.
128 -Z Report about errors for IP version 6 traffic.
130 -k General report about ICMP version 6 layer activity.
132 -K Per-type report about ICMP version 6 layer activity.
134 -U Report about UDP version 6 network traffic.
136 -t Report about TCP network traffic.
138 -T Report about errors for TCP-traffic.
140 -h Report about Infiniband utilization.
142 -O Report about top-3 processes consuming most processor capacity.
144 This report is only available when using a log file (not when
145 specifying an interval).
146 -G Report about top-3 processes consuming most resident memory. This
148 report is only available when using a log file (not when specify‐
149 ing an interval).
150 -D Report about top-3 processes issueing most disk transfers. This
152 report is only available when using a log file (not when specify‐
153 ing an interval).
154 -N Report about top-3 processes issueing most IPv4/IPv6 socket trans‐
156 fers. This report is only available when using a log file (not
157 when specifying an interval).
158
160 Depending on the requested report, a number of columns with output val‐
161 ues are produced. The values are mostly presented as a number of
162 events per second.
163 The output for the flag -c contains the following columns per cpu:
165 usr% Percentage of cpu-time consumed in user mode (program text)
167 for all active processes running with a nice value of zero
168 (default) or a negative nice value (which means a higher
169 priority than usual). The cpu consumption in user mode of
170 processes with a nice value larger than zero (lower prior‐
171 ity) is indicated in the nice%-column.
172 nice% Percentage of cpu time consumed in user mode (i.e. program
174 text) for all processes running witn a nice value larger
175 than zero (which means with a lower priority than average).
176 sys% Percentage of cpu time consumed in system mode (kernel
178 text) for all active processes. A high percentage usually
179 indicates a lot of system calls being issued.
180 irq% Percentage of cpu time consumed for handling of device
182 interrupts.
183 softirq% Percentage of cpu time consumed for soft interrupt han‐
185 dling.
186 steal% Percentage of cpu time stolen by other virtual machines
188 running on the same hardware.
189 guest% Percentage of cpu time used by other virtual machines run‐
191 ning on the same hardware (overlaps with usr%/nice%).
192 wait% Percentage of unused cpu time while at least one of the
194 processes in wait-state awaits completion of disk I/O.
195 idle% Percentage of unused cpu time because all processes are in
197 a wait-state but not waiting for disk-I/O.
198 The output for the flag -g contains the following columns per GPU:
200 busaddr GPU number and bus-ID (separated by '/').
202 gpubusy GPU busy percentage during interval.
204 membusy GPU memory busy percentage during interval, i.e. time to
206 issue read and write accesses on memory.
207 memocc Percentage of memory occupation at this moment.
209 memtot Total memory available.
211 memuse Used GPU memory at this moment.
213 gputype Type of GPU.
215 The output for the flag -p contains the following values:
217 pswch/s Number of process switches (also called context switches)
219 per second on this cpu. A process switch occurs at the
220 moment that an active thread (i.e. the thread using a cpu)
221 enters a wait state or has used its time slice completely;
222 another thread will then be chosen to use the cpu.
223 devintr/s Number of hardware interrupts handled per second on this
225 cpu.
226 clones/s The number of new threads started per second.
228 loadavg1 Load average reflecting the average number of threads in
230 the runqueue or in non-interruptible wait state (usually
231 waiting for disk or tape I/O) during the last minute.
232 loadavg5 Load average reflecting the average number of threads in
234 the runqueue or in non-interruptible wait state (usually
235 waiting for disk or tape I/O) during the last 5 minutes.
236 loadavg15 Load average reflecting the average number of threads in
238 the runqueue or in non-interruptible wait state (usually
239 waiting for disk or tape I/O) during the last 15 minutes.
240 The output for the flag -P contains information about the processes and
242 threads:
243 clones/s The number of new threads started per second.
245 pexit/s
247 curproc Total number of processes present in the system.
249 curzomb Number of zombie processes present in the system.
251 thrrun Total number of threads present in the system in state
253 'running'.
254 thrslpi Total number of threads present in the system in state
256 'interruptible sleeping'.
257 thrslpu Total number of threads present in the system in state
259 'uninterruptible sleeping'.
260 The output for the flag -m contains information about the memory- and
262 swap-utilization:
263 memtotal Total usable main memory size.
265 memfree Available main memory size at this moment (snapshot).
267 buffers Main memory used at this moment to cache metadata-blocks
269 (snapshot).
270 cached Main memory used at this moment to cache data-blocks (snap‐
272 shot).
273 dirty Amount of memory in the page cache that still has to be
275 flushed to disk at this moment (snapshot).
276 slabmem Main memory used at this moment for dynamically allocated
278 memory by the kernel (snapshot).
279 swptotal Total swap space size at this moment (snapshot).
281 swpfree Available swap space at this moment (snapshot).
283 The output for the flag -s contains information about the frequency of
285 swapping:
286 pagescan/s Number of scanned pages per second due to the fact that
288 free memory drops below a particular threshold.
289 swapin/s The number of memory-pages the system read from the swap-
291 device per second.
292 swapout/s The number of memory-pages the system wrote to the swap-
294 device per second.
295 commitspc The committed virtual memory space i.e. the reserved vir‐
297 tual space for all allocations of private memory space for
298 processes.
299 commitlim The maximum limit for the committed space, which is by
301 default swap size plus 50% of memory size. The kernel only
302 verifies whether the committed space exceeds the limit if
303 strict overcommit handling is configured (vm.overcom‐
304 mit_memory is 2).
305 The output for the flag -B contains the Pressure Stall Information
307 (PSI):
308 cs_10_60_300
310 Average pressure percentage over the last 10, 60 and 300
311 seconds for the category 'CPU some'.
312 ms_10_60_300
314 Average pressure percentage over the last 10, 60 and 300
315 seconds for the category 'memory some'.
316 mf_10_60_300
318 Average pressure percentage over the last 10, 60 and 300
319 seconds for the category 'memory full'.
320 is_10_60_300
322 Average pressure percentage over the last 10, 60 and 300
323 seconds for the category 'I/O some'.
324 if_10_60_300
326 Average pressure percentage over the last 10, 60 and 300
327 seconds for the category 'I/O full'.
328 The output for the flags -l (LVM), -f (MD), and -d (hard disk) contains
330 the following columns per active unit:
331 disk Name.
333 busy Busy-percentage of the unit (i.e. the portion of time that
335 the device was busy handling requests).
336 read/s Number of read-requests issued per second on this unit.
338 KB/read Average number of Kbytes transferred per read-request for
340 this unit.
341 writ/s Number of write-requests issued per second on this unit.
343 KB/writ Average number of Kbytes transferred per write-request for
345 this unit.
346 avque Average number of requests outstanding in the queue during
348 the time that the unit is busy.
349 avserv Average number of milliseconds needed by a request on this
351 unit (seek, latency and data-transfer).
352 The output for the flag -n contains information about activity on NFS
354 mounted filesystems (client):
355 mounted_device
357 Mounted device containing server name and server directory
358 being mounted.
359 physread/s Kilobytes data physically read from the NFS server by pro‐
361 cesses running on the NFS client.
362 KBwrite/s Kilobytes data physically written to the NFS server by pro‐
364 cesses running on the NFS client.
365 When the NFS filesystem was mounted during the interval,
366 the state 'M' is shown.
367 The output for the flag -j contains information about NFS client activ‐
369 ity:
370 rpc/s Number of RPC calls per second issued to NFS server(s).
372 rpcread/s Number of read RPC calls per second issued to NFS
374 server(s).
375 rpcwrite/s Number of write RPC calls per second issued to NFS
377 server(s).
378 retrans/s Number of retransmitted RPC calls per second.
380 autrefresh/s
382 Number of authorization refreshes per second.
383 The output for the flag -J contains information about NFS server activ‐
385 ity:
386 rpc/s Number of RPC calls per second received from NFS client(s).
388 rpcread/s Number of read RPC calls per second received from NFS
390 client(s).
391 rpcwrite/s Number of write RPC calls per second received from NFS
393 client(s).
394 MBcr/s Number of Megabytes per second returned to read requests by
396 clients.
397 MBcw/s Number of Megabytes per second passed in write requests by
399 clients.
400 nettcp/s Number of requests per second handled via TCP.
402 netudp/s Number of requests per second handled via UDP.
404 The output for the flag -i provides information about utilization of
406 network interfaces:
407 interf Name of interface.
409 busy Busy percentage for this interface. If the linespeed of
411 this interface could not be determined (for virtual inter‐
412 faces or in case that atop or atopsar had no root-privi‐
413 leges), a question mark is shown.
414 ipack/s Number of packets received from this interface per second.
416 opack/s Number of packets transmitted to this interface per second.
418 iKbyte/s Number of Kbytes received from this interface per second.
420 oKbyte/s Number of Kbytes transmitted via this interface per second.
422 imbps/s Effective number of megabits received per second.
424 ombps/s Effective number of megabits transmitted per second.
426 maxmbps/s Linespeed as number of megabits per second. If the line‐
428 speed could not be determined (for virtual interfaces or in
429 case that atop or atopsar had no root-privileges), value 0
430 is shown.
431 The linespeed is followed by the indication 'f' (full
432 duplex) or 'h' (half duplex).
433 The output for the flag -I provides information about the failures that
435 were detected for network interfaces:
436 interf Name of interface.
438 ierr/s Number of bad packets received from this interface per sec‐
440 ond.
441 oerr/s Number of times that packet transmission to this interface
443 failed per second.
444 coll/s Number of collisions encountered per second while transmit‐
446 ting packets.
447 idrop/s Number of received packets dropped per second due to lack
449 of buffer-space in the local system.
450 odrop/s Number of transmitted packets dropped per second due to
452 lack of buffer-space in the local system.
453 iframe/s Number of frame alignment-errors encountered per second on
455 received packets.
456 ocarrier/s Number of carrier-errors encountered per second on trans‐
458 mitted packets.
459 The output for the flag -w provides information about the utilization
461 of the IPv4-layer (formal SNMP-names between brackets):
462 inrecv/s Number of IP datagrams received from interfaces per second,
464 including those received in error (ipInReceives).
465 outreq/s Number of IP datagrams that local higher-layer protocols
467 supplied to IP in requests for transmission per second
468 (ipOutRequests).
469 indeliver/s Number of received IP datagrams that have been successfully
471 delivered to higher protocol-layers per second (ipInDeliv‐
472 ers).
473 forward/s Number of received IP datagrams per second for which this
475 entity was not their final IP destination, as a result of
476 which an attempt was made to forward (ipForwDatagrams).
477 reasmok/s Number of IP datagrams successfully reassembled per second
479 (ipReasmOKs).
480 fragcreat/s Number of IP datagram fragments generated per second at
482 this entity (ipFragCreates).
483 The output for the flag -W provides information about the failures that
485 were detected in the IPv4-layer (formal SNMP-names between brackets):
486 in: dsc/s Number of input IP datagrams per second for which no prob‐
488 lems were encountered to prevent their continued processing
489 but that were discarded, e.g. for lack of buffer space
490 (ipInDiscards).
491 in: hder/s Number of input IP datagrams per second discarded due to
493 errors in the IP header (ipInHdrErrors).
494 in: ader/s Number of input IP datagrams per second discarded because
496 the IP address in the destination field was not valid to be
497 received by this entity (ipInAddrErrors).
498 in: unkp/s Number of inbound packets per second that were discarded
500 because of an unknown or unsupported protocol (ipInUnknown‐
501 Protos).
502 in: ratim/s Number of timeout-situations per second while other frag‐
504 ments were expected for successful reassembly (ipReasmTime‐
505 out).
506 in: rfail/s Number of failures detected per second by the IP reassembly
508 algorithm (ipReasmFails).
509 out: dsc/s Number of output IP datagrams per second for which no prob‐
511 lems were encountered to prevent their continued processing
512 but that were discarded, e.g. for lack of buffer space
513 (ipOutDiscards).
514 out: nrt/s Number of IP datagrams per second discarded because no
516 route could be found (ipOutNoRoutes).
517 The output for the flag -y provides information about the general uti‐
519 lization of the ICMPv4-layer and some information per type of ICMP-mes‐
520 sage (formal SNMP-names between brackets):
521 intot/s Number of ICMP messages (any type) received per second at
523 this entity (icmpInMsgs).
524 outtot/s Number of ICMP messages (any type) transmitted per second
526 from this entity (icmpOutMsgs).
527 inecho/s Number of ICMP Echo (request) messages received per second
529 (icmpInEchos).
530 inerep/s Number of ICMP Echo-Reply messages received per second
532 (icmpInEchoReps).
533 otecho/s Number of ICMP Echo (request) messages transmitted per sec‐
535 ond (icmpOutEchos).
536 oterep/s Number of ICMP Echo-Reply messages transmitted per second
538 (icmpOutEchoReps).
539 The output for the flag -Y provides information about other types of
541 ICMPv4-messages (formal SNMP-names between brackets):
542 ierr/s Number of ICMP messages received per second but determined
544 to have ICMP-specific errors (icmpInErrors).
545 isq/s Number of ICMP Source Quench messages received per second
547 (icmpInSrcQuenchs).
548 ird/s Number of ICMP Redirect messages received per second (icmp‐
550 InRedirects).
551 idu/s Number of ICMP Destination Unreachable messages received
553 per second (icmpInDestUnreachs).
554 ite/s Number of ICMP Time Exceeded messages received per second
556 (icmpOutTimeExcds).
557 oerr/s Number of ICMP messages transmitted per second but deter‐
559 mined to have ICMP-specific errors (icmpOutErrors).
560 osq/s Number of ICMP Source Quench messages transmitted per sec‐
562 ond (icmpOutSrcQuenchs).
563 ord/s Number of ICMP Redirect messages transmitted per second
565 (icmpOutRedirects).
566 odu/s Number of ICMP Destination Unreachable messages transmitted
568 per second (icmpOutDestUnreachs).
569 ote/s Number of ICMP Time Exceeded messages transmitted per sec‐
571 ond (icmpOutTimeExcds).
572 The output for the flag -u provides information about the utilization
574 of the UDPv4-layer (formal SNMP-names between brackets):
575 indgram/s Number of UDP datagrams per second delivered to UDP users
577 (udpInDatagrams).
578 outdgram/s Number of UDP datagrams transmitted per second from this
580 entity (udpOutDatagrams).
581 inerr/s Number of received UDP datagrams per second that could not
583 be delivered for reasons other than the lack of an applica‐
584 tion at the destination port (udpInErrors).
585 noport/s Number of received UDP datagrams per second for which there
587 was no application at the destination port (udpNoPorts).
588 The output for the flag -z provides information about the utilization
590 of the IPv6-layer (formal SNMP-names between brackets):
591 inrecv/s Number of input IPv6-datagrams received from interfaces per
593 second, including those received in error (ipv6IfStatsInRe‐
594 ceives).
595 outreq/s Number of IPv6-datagrams per second that local higher-layer
597 protocols supplied to IP in requests for transmission
598 (ipv6IfStatsOutRequests). This counter does not include
599 any forwarded datagrams.
600 inmc/s Number of multicast packets per second that have been
602 received by the interface (ipv6IfStatsInMcastPkts).
603 outmc/s Number of multicast packets per second that have been
605 transmitted to the interface (ipv6IfStatsOutMcastPkts).
606 indeliv/s Number of IP datagrams successfully delivered per second to
608 IPv6 user-protocols, including ICMP (ipv6IfStatsInDeliv‐
609 ers).
610 reasmok/s Number of IPv6 datagrams successfully reassembled per sec‐
612 ond (ipv6IfStatsReasmOKs).
613 fragcre/s Number of IPv6 datagram fragments generated per second at
615 this entity (ipv6IfStatsOutFragCreates).
616 The output for the flag -Z provides information about the failures that
618 were detected in the IPv6-layer (formal SNMP-names between brackets):
619 in: dsc/s Number of input IPv6 datagrams per second for which no
621 problems were encountered to prevent their continued pro‐
622 cessing but that were discarded, e.g. for lack of buffer
623 space (ipv6IfStatsInDiscards).
624 in: hder/s Number of input datagrams per second discarded due to
626 errors in the IPv6 header (ipv6IfStatsInHdrErrors).
627 in: ader/s Number of input datagrams per second discarded because the
629 IPv6 address in the destination field was not valid to be
630 received by this entity (ipv6IfStatsInAddrErrors).
631 in: unkp/s Number of locally-addressed datagrams per second that were
633 discarded because of an unknown or unsupported protocol
634 (ipv6IfStatsInUnknownProtos).
635 in: ratim/s Number of timeout-situations per second while other IPv6
637 fragments were expected for successful reassembly
638 (ipv6ReasmTimeout).
639 in: rfail/s Number of failures detected per second by the IPv6 reassem‐
641 bly-algorithm (ipv6IfStatsReasmFails).
642 out: dsc/s Number of output IPv6 datagrams per second for which no
644 problems were encountered to prevent their continued pro‐
645 cessing but that were discarded, e.g. for lack of buffer
646 space (ipv6IfStatsOutDiscards).
647 out: nrt/s Number of IPv6 datagrams per second discarded because no
649 route could be found (ipv6IfStatsInNoRoutes).
650 The output for the flag -k provides information about the general uti‐
652 lization of the ICMPv6-layer and some information per type of ICMP-mes‐
653 sage (formal SNMP-names between brackets):
654 intot/s Number of ICMPv6 messages (any type) received per second at
656 the interface (ipv6IfIcmpInMsgs).
657 outtot/s Number of ICMPv6 messages (any type) transmitted per second
659 from this entity (ipv6IfIcmpOutMsgs).
660 inerr/s Number of ICMPv6 messages received per second that had
662 ICMP-specific errors, such as bad ICMP checksums, bad
663 length, etc (ipv6IfIcmpInErrors).
664 innsol/s Number of ICMP Neighbor Solicit messages received per sec‐
666 ond (ipv6IfIcmpInNeighborSolicits).
667 innadv/s Number of ICMP Neighbor Advertisement messages received per
669 second (ipv6IfIcmpInNeighborAdvertisements).
670 otnsol/s Number of ICMP Neighbor Solicit messages transmitted per
672 second (ipv6IfIcmpOutNeighborSolicits).
673 otnadv/s Number of ICMP Neighbor Advertisement messages transmitted
675 per second (ipv6IfIcmpOutNeighborAdvertisements).
676 The output for the flag -K provides information about other types of
678 ICMPv6-messages (formal SNMP-names between brackets):
679 iecho/s Number of ICMP Echo (request) messages received per second
681 (ipv6IfIcmpInEchos).
682 ierep/s Number of ICMP Echo-Reply messages received per second
684 (ipv6IfIcmpInEchoReplies).
685 oerep/s Number of ICMP Echo-Reply messages transmitted per second
687 (ipv6IfIcmpOutEchoReplies).
688 idu/s Number of ICMP Destination Unreachable messages received
690 per second (ipv6IfIcmpInDestUnreachs).
691 odu/s Number of ICMP Destination Unreachable messages transmitted
693 per second (ipv6IfIcmpOutDestUnreachs).
694 ird/s Number of ICMP Redirect messages received per second
696 (ipv6IfIcmpInRedirects).
697 ord/s Number of ICMP Redirect messages transmitted per second
699 (ipv6IfIcmpOutRedirect).
700 ite/s Number of ICMP Time Exceeded messages received per second
702 (ipv6IfIcmpInTimeExcds).
703 ote/s Number of ICMP Time Exceeded messages transmitted per sec‐
705 ond (ipv6IfIcmpOutTimeExcds).
706 The output for the flag -U provides information about the utilization
708 of the UDPv6-layer (formal SNMP-names between brackets):
709 indgram/s Number of UDPv6 datagrams per second delivered to UDP users
711 (udpInDatagrams),
712 outdgram/s Number of UDPv6 datagrams transmitted per second from this
714 entity (udpOutDatagrams),
715 inerr/s Number of received UDPv6 datagrams per second that could
717 not be delivered for reasons other than the lack of an
718 application at the destination port (udpInErrors).
719 noport/s Number of received UDPv6 datagrams per second for which
721 there was no application at the destination port (udpNo‐
722 Ports).
723 The output for the flag -t provides information about the utilization
725 of the TCP-layer (formal SNMP-names between brackets):
726 insegs/s Number of received segments per second, including those
728 received in error (tcpInSegs).
729 outsegs/s Number of transmitted segments per second, excluding those
731 containing only retransmitted octets (tcpOutSegs).
732 actopen/s Number of active opens per second that have been supported
734 by this entity (tcpActiveOpens).
735 pasopen/s Number of passive opens per second that have been supported
737 by this entity (tcpPassiveOpens).
738 nowopen Number of connections currently open (snapshot), for which
740 the state is either ESTABLISHED or CLOSE-WAIT (tcpCur‐
741 rEstab).
742 The output for the flag -T provides information about the failures that
744 were detected in the TCP-layer (formal SNMP-names between brackets):
745 inerr/s Number of received segments per second received in error
747 (tcpInErrs).
748 retrans/s Number of retransmitted segments per second (tcpRe‐
750 transSegs).
751 attfail/s Number of failed connection attempts per second that have
753 occurred at this entity (tcpAttemptFails).
754 estabreset/s
756 Number of resets per second that have occurred at this
757 entity (tcpEstabResets).
758 outreset/s Number of transmitted segments per second containing the
760 RST flag (tcpOutRsts).
761 The output for the flag -h provides information about utilization of
763 Infiniband ports:
764 controller Name of controller.
766 port Controller port.
768 busy Busy percentage for this port.
770 ipack/s Number of packets received from this port per second.
772 opack/s Number of packets transmitted to this port per second.
774 igbps/s Effective number of gigabits received per second.
776 ogbps/s Effective number of gigabits transmitted per second.
778 maxgbps/s Maximum rate as number of gigabits per second.
780 lanes Number of lanes.
782 The output for the flag -O provides information about the top-3 of pro‐
784 cesses with the highest processor consumption:
785 pid Process-id (if zero, the process has exited while the pid
787 could not be determined).
788 command The name of the process.
790 cpu% The percentage of cpu-capacity being consumed. This value
792 can exceed 100% for a multithreaded process running on a
793 multiprocessor machine.
794 The output for the flag -G provides information about the top-3 of pro‐
796 cesses with the highest memory consumption:
797 pid Process-id (if zero, the process has exited while the pid
799 could not be determined).
800 command The name of the process.
802 mem% The percentage of resident memory-utilization by this
804 process.
805 The output for the flag -D provides information about the top-3 of pro‐
807 cesses that issue the most read and write accesses to disk:
808 pid Process-id (if zero, the process has exited while the pid
810 could not be determined).
811 command The name of the process.
813 dsk% The percentage of read and write accesses related to the
815 total number of read and write accesses issued on disk by
816 all processes, so a high percentage does not imply a high
817 disk load on system level.
818 The output for the flag -N provides information about the top-3 of pro‐
820 cesses that issue the most socket transfers for IPv4/IPv6:
821 pid Process-id (if zero, the process has exited while the pid
823 could not be determined).
824 command The name of the process.
826 net% The percentage of socket transfers related to the total
828 number of transfers issued by all processes, so a high per‐
829 centage does not imply a high network load on system level.
830
832 To see today's cpu-activity so far (supposed that atop is logging in
833 the background):
834 atopsar
836 To see the memory occupation for June 5, 2018 between 10:00 and 12:30
838 (supposed that atop has been logging daily in the background):
839 atopsar -m -r /var/log/atop_20180605 -b 10:00 -e 12:30
841 or
843 atopsar -m -r 20180605 -b 10:00 -e 12:30
845 or, suppose it is June 8, 2018 at this moment
847 atopsar -m -r yyy -b 10:00 -e 12:30
849 Write a logfile with atop to record the system behaviour for 30 minutes
851 (30 samples of one minute) and produce all available reports after‐
852 wards:
853 atop -w /tmp/atoplog 60 30
855 atopsar -A -r /tmp/atoplog
857 To watch TCP activity evolve for ten minutes (10 samples with sixty
859 seconds interval):
860 atopsar -t 60 10
862 To watch the header-lines ('_' as last character) of all reports with
864 only the detail-lines showing critical resource consumption (marker '*'
865 or '+' as last character):
866 atopsar -AM | grep '[_*+]$'
868
870 /etc/atoprc
871 Configuration file containing system-wide default values (mainly
872 flags). See related man-page.
873 ~/.atoprc
875 Configuration file containing personal default values (mainly
876 flags). See related man-page.
877 /var/log/atop/atop_YYYYMMDD
879 Daily data file, where YYYYMMDD are digits representing the date.
880
882 atop(1), atopconvert(1), atoprc(5), atopacctd(8), netatop(4),
883 netatopd(8)
884 https://www.atoptool.nl
885
887 Gerlof Langeveld (gerlof.langeveld@atoptool.nl)
888Linux January 2019 ATOPSAR(1)