Run collectl command with no arguments
Simply run collectl command with no arguments before going deeper. By default it shows cpu, network and disk stats in brief format. Data has been logged every second and keeps growing until you exit.
# collectl waiting for 1 second sample... #<--------CPU--------><----------Disks-----------><----------Network----------> #cpu sys inter ctxsw KBRead Reads KBWrit Writes KBIn PktIn KBOut PktOut 5 0 507 616 1 1 141 8 128 214 116 199 12 0 1211 1064 0 0 0 0 758 671 72 350 11 1 1306 1277 1 1 1 1 922 849 109 486 15 1 1324 1727 0 0 0 0 385 557 256 514 5 0 1015 713 1 1 1 1 918 769 69 355 13 0 843 1046 0 0 0 0 145 286 189 303
Default with verbose mode
In this mode you give up one line per interval with hostname, date, time & much more details.
# collectl --verbose
waiting for 1 second sample...
### RECORD 1 >>> 2daygeek <<< (1483576392.001) (Wed Jan 4 17:33:12 2017) ###
# CPU SUMMARY (INTR, CTXSW & PROC /sec)
# User Nice Sys Wait IRQ Soft Steal Idle CPUs Intr Ctxsw Proc RunQ Run Avg1 Avg5 Avg15
10 0 0 0 0 0 0 89 6 1260 1199 2 401 2 0.32 0.84 1.02
# DISK SUMMARY (/sec)
#KBRead RMerged Reads SizeKB KBWrite WMerged Writes SizeKB
1 0 1 1 80 10 11 7
# NETWORK SUMMARY (/sec)
# KBIn PktIn SizeIn MultI CmpI ErrsI KBOut PktOut SizeO CmpO ErrsO
842 807 1069 0 0 0 163 467 359 0 0
Default with Detailed mode
By default mode, it uses summary output. If you want to see more details on specific instances, use the uppercase subsystem names -sCDN instead of lowercase.
# collectl -sCDN
waiting for 1 second sample...
### RECORD 1 >>> 2daygeek <<< (1483576773.001) (Wed Jan 4 17:39:33 2017) ###
# SINGLE CPU STATISTICS
# Cpu User Nice Sys Wait IRQ Soft Steal Idle
0 33 0 2 0 0 0 0 65
1 54 0 4 0 0 0 0 39
2 1 0 0 0 0 0 0 99
3 0 0 0 0 0 0 0 100
4 0 0 0 0 0 0 0 100
5 0 0 0 0 0 0 0 100
# DISK STATISTICS (/sec)
# <---------reads---------><---------writes---------><--------averages--------> Pct
#Name KBytes Merged IOs Size KBytes Merged IOs Size RWSize QLen Wait SvcTim Util
sda 0 0 0 0 16 0 4 4 4 0 0 0 0
sdb 1 0 1 1 0 0 1 1 0 0 0 0 0
# NETWORK STATISTICS (/sec)
#Num Name KBIn PktIn SizeIn MultI CmpI ErrsI KBOut PktOut SizeO CmpO ErrsO
0 eth0: 410 593 709 0 0 0 252 534 483 0 0
1 lo: 0 0 0 0 0 0 0 0 0 0 0
Collectl With Timestamps
To display collectl output with timestamps in each line, just add o switch with T option.
# collectl -oT waiting for 1 second sample... # <--------CPU--------><----------Disks-----------><----------Network----------> #Time cpu sys inter ctxsw KBRead Reads KBWrit Writes KBIn PktIn KBOut PktOut 14:42:25 0 0 151 228 1 1 57 9 5 50 5 44 14:42:26 4 0 471 746 64 2 0 0 127 206 117 197 14:42:27 11 1 1028 842 1 1 1 1 752 640 38 310 14:42:28 22 2 1882 2042 0 0 0 0 972 976 237 666 14:42:29 9 1 961 1265 1 1 1 1 340 454 181 410 14:42:30 1 0 238 322 0 0 56 7 30 82 8 67 14:42:31 21 1 2114 2077 1 1 1 1 1564 1394 243 803 14:42:32 19 1 1494 1461 0 0 0 0 802 741 119 467
Monitor CPU usage
To print summary of CPU usage, just add -sc with collectl command.
# collectl -sc waiting for 1 second sample... #<--------CPU--------> #cpu sys inter ctxsw 2 0 222 301 13 1 1295 1203 16 1 1225 1229 23 2 2016 2061 35 3 2944 3199 2 0 262 320 4 0 449 595
To print detailed CPU usage (individual CPU usage), just add -sC with collectl command.
# collectl -sC
waiting for 1 second sample...
# SINGLE CPU STATISTICS
# Cpu User Nice Sys Wait IRQ Soft Steal Idle
0 48 0 5 0 0 1 0 44
1 92 0 2 0 0 2 0 3
2 10 0 2 0 0 0 0 88
3 3 0 0 0 0 0 0 94
4 0 0 0 0 0 0 0 100
5 1 0 1 0 0 0 0 97
0 7 0 2 0 0 0 0 91
1 33 0 5 0 0 1 0 61
2 0 0 0 0 0 0 0 100
3 0 0 0 0 0 0 0 100
4 2 0 1 0 0 0 0 96
5 0 0 0 0 0 0 0 100
Monitor Memory usage
To print summary of Memory usage, just add -sm with collectl command.
# collectl -sm waiting for 1 second sample... #<-----------Memory-----------> #Free Buff Cach Inac Slab Map 615M 320M 1G 1G 596M 485M 636M 320M 1G 1G 596M 464M 645M 320M 1G 1G 596M 456M 679M 320M 1G 1G 596M 423M 679M 320M 1G 1G 596M 423M 678M 320M 1G 1G 596M 424M 644M 320M 1G 1G 596M 458M 630M 320M 1G 1G 596M 471M
To print detailed Memory usage, just add -sM with collectl command.
# collectl -sM
waiting for 1 second sample...
# MEMORY STATISTICS
# Node Total Used Free Slab Mapped Anon Locked Inact HitPct
0 16356M 11099M 5257M 350772K 5720K 10064K 0 3943M 100.00
1 16384M 2000M 14383M 61888K 6880K 28248K 0 1350M 100.00
0 16356M 11099M 5257M 350772K 5728K 10064K 0 3943M 100.00
1 16384M 2000M 14383M 61888K 6880K 28248K 0 1350M 100.00
0 16356M 11099M 5257M 350772K 5728K 10064K 0 3943M 100.00
1 16384M 1999M 14384M 61908K 6880K 28248K 0 1350M 100.00
0 16356M 11099M 5257M 350772K 5728K 10064K 0 3943M 100.00
1 16384M 1999M 14384M 61908K 6880K 28248K 0 1350M 100.00
Monitor Network usage
To print summary of Network usage, just add -sn with collectl command.
# collectl -sn
waiting for 1 second sample...
#<----------Network---------->
# KBIn PktIn KBOut PktOut
952 955 234 637
361 478 185 426
3 34 5 31
128 213 116 202
747 615 35 277
1695 1582 274 992
To print detailed Network usage, just add -sN with collectl command.
# collectl -sN waiting for 1 second sample... # NETWORK STATISTICS (/sec) #Num Name KBIn PktIn SizeIn MultI CmpI ErrsI KBOut PktOut SizeO CmpO ErrsO 0 eth0: 318 469 694 0 0 0 244 462 542 0 0 1 lo: 0 0 0 0 0 0 0 0 0 0 0 0 eth0: 20 89 233 0 0 0 9 77 129 0 0 1 lo: 0 0 0 0 0 0 0 0 0 0 0 0 eth0: 122 263 475 0 0 0 122 261 479 0 0 1 lo: 0 0 0 0 0 0 0 0 0 0 0 0 eth0: 748 637 1203 0 0 0 35 287 128 0 0 1 lo: 0 0 0 0 0 0 0 0 0 0 0 0 eth0: 1000 1020 1004 0 0 0 254 737 353 0 0 1 lo: 0 0 0 0 0 0 0 0 0 0 0
