Unexpected CPU utilization on LTM
Hello I am testing 2 different LTMs(VE) and would like to compere the CPU performance to select CPUs for our customer enviroment. BIG-IP 12.1.1 Build 0.0.184 Final 8core BIG-IP 13.1.1 Build 0.0.4 Final 12core During that load testing(1000TPS for SSL), I noticed that the CPU usage of Lower version LTM(8cores) is at 40%, but higher version LTM(12cores) is at 50%. I expected that 12 cores LTM had lower consumption of CPU than 8cores, these results were completely the opposit. Could someone tell me why did that turn out like this ? Thanks in advance for the help.
Which CPU is the Analysis plane on F5 chassis ?
Based on this article https://support.f5.com/csp/article/K15468, All even CPUs are TMM, All odd CPUs are other process except the last one(analysis plane). Is the article valid for F5 chassis. I would like to know which blade's CPU on a chassis handle analysis plane ? Example My F5 CPUs F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".1 = Gauge32: 6 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".2 = Gauge32: 8 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".3 = Gauge32: 3 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".4 = Gauge32: 3 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".5 = Gauge32: 11 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".6 = Gauge32: 3 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".7 = Gauge32: 15 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".8 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".9 = Gauge32: 10 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".10 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".11 = Gauge32: 10 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".12 = Gauge32: 5 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".13 = Gauge32: 8 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".14 = Gauge32: 2 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".15 = Gauge32: 14 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".16 = Gauge32: 4 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".17 = Gauge32: 13 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".18 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".19 = Gauge32: 13 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".20 = Gauge32: 0 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".21 = Gauge32: 10 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".22 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".23 = Gauge32: 8 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."1".24 = Gauge32: 0 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".1 = Gauge32: 4 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".2 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".3 = Gauge32: 3 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".4 = Gauge32: 7 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".5 = Gauge32: 14 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".6 = Gauge32: 2 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".7 = Gauge32: 11 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".8 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".9 = Gauge32: 8 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".10 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".11 = Gauge32: 10 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".12 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".13 = Gauge32: 15 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".14 = Gauge32: 3 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".15 = Gauge32: 14 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".16 = Gauge32: 2 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".17 = Gauge32: 8 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".18 = Gauge32: 3 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".19 = Gauge32: 11 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".20 = Gauge32: 8 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".21 = Gauge32: 10 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".22 = Gauge32: 1 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".23 = Gauge32: 10 F5-BIGIP-SYSTEM-MIB::sysMultiHostCpuUser5s."3".24 = Gauge32: 0 Thanks,
High CPU utilization : tmm.0 118.0%
Hi All , Is there any option to find which process is using the more cpu , as we can see for tmm.0 it shows 118% , can we find out what causing the tmm.0 to go up ? Swap: 5242876k total, 0k used, 5242876k free, 2956952k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 18298 root 1 -19 8549m 82m 61m R 118.8 0.5 79279:13 tmm.0 21723 root 39 19 195m 128m 8720 S 74.3 0.8 1:30.87 java 19329 root 20 0 2342m 277m 24m S 53.9 1.7 3389:31 bd 13582 root 20 0 48936 29m 15m S 36.5 0.2 67574:52 bigd 19346 root 20 0 115m 46m 31m S 29.7 0.3 421:18.84 pabnagd 6989 root 20 0 177m 117m 25m S 3.6 0.7 6823:17 mcpd 17797 root 20 0 175m 151m 20m S 3.6 0.9 4175:09 asm_start 5672 root 25 5 113m 27m 22m S 1.6 0.2 3715:39 merged cpu_id five_sec_avg.ratio ------ ------------------ 0 72 1 96 2 71 3 84 -------------------------- Sys::TMM: 0.0 -------------------------- Global TMM Process Id 18298 Running TMM Id 0 TMM Count 1 CPU Id 0 Memory (bytes) Total 6.5G Used 3.3G CPU Usage Ratio (%) Last 5 Seconds 61 Last 1 Minute 59 Last 5 Minutes 57 -------------------------- Sys::TMM: 0.2 -------------------------- Global TMM Process Id 18298 Running TMM Id 2 TMM Count 1 CPU Id 2 Memory (bytes) Total 0 Used 0 CPU Usage Ratio (%) Last 5 Seconds 53 Last 1 Minute 51 Last 5 Minutes 50
High CPU utilisation for process 'kwolker' of even cores
Top output top - 10:47:36 up 16 days, 14:56, 1 user, load average: 6.61, 6.60, 6.55 Tasks: 348 total, 1 running, 344 sleeping, 0 stopped, 3 zombie %Cpu0 : 98.3 us, 1.7 sy, 0.0 ni, 0.0 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st %Cpu1 : 4.6 us, 2.6 sy, 0.0 ni, 78.4 id, 0.3 wa, 0.0 hi, 14.1 si, 0.0 st %Cpu2 : 98.3 us, 1.7 sy, 0.0 ni, 0.0 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st %Cpu3 : 2.7 us, 2.7 sy, 0.0 ni, 94.6 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st KiB Mem : 21515168 total, 136644 free, 19177572 used, 2200952 buff/cache KiB Swap: 1048572 total, 636212 free, 412360 used. 279056 avail Mem PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 12795 root 10 -10 2965172 2.0g 1112 S 63.5 9.9 10305:47 kwolker 29071 root 10 -10 2965172 2.0g 1184 S 63.1 9.9 16356:45 kwolker 20101 root 10 -10 827056 264176 1308 S 62.8 1.2 8902:54 kwolker 21192 root 1 -19 13.0g 1.6g 1.6g S 10.3 7.9 795:25.12 tmm.0
Virtual BIG-IQ uses a lot of cpu
Hi Is it normal that a virtual BIG-IQ uses almost 7ghz from a esxi host. Also the cpu is always at around 80-85 % if I check the cpu under monitor on the server itself. Its only used to manage licenses and not BIG-IP systems so it should idle most of the time. Best regards Daniel
CPU 100% System Crash
Hi my big ip system crash any time CPU reach 100% is there any way to debug this and find what cause the hight utilization? my system is using irules, HTTP Compression (with CPU Saver), stream profile, web acceleration it always happen when the connection & throughput is Hight my system is 11.3
iRule to log all HTTP_REQUEST and insert a cookie
Hello, I wrote an iRule that uses HSL for sending syslog level data to remote servers. The iRule sends all HTTP_REQUESTs to HSL pool. There are three pools defined - each for specific purposes. I find that the iRule causes an issue of running on one CPU probably because the way the variables are defined and accessed. I have attached the iRule for your reference. Can somebody tell me if I am doing anything inefficient? Much appreciated. when RULE_INIT { array set ::active_clients { } } when CLIENT_ACCEPTED { set hsl [HSL::open -proto UDP -pool syslog_server_pool] set hsl1 [HSL::open -proto UDP -pool syslog_server_pool_1] set hsl2 [HSL::open -proto UDP -pool syslog_server_pool_2] Send the data using local7 facility <190> HSL::send $hsl "<190> [IP::client_addr] [[clock format [clock seconds] -format "%d/%b/%Y:%H:%M:%S %z"]] --[IP::local_addr]--NY--80--CLIENT_ACCEPTED" } when HTTP_REQUEST { if { [info exists ::active_clients([IP::client_addr])] } { incr ::active_clients([IP::client_addr]) } else { set ::active_clients([IP::client_addr]) 1 } if { not ([HTTP::cookie exists SITESERVER] ) } { set F2C "[string range [AES::key 128] 15 end][string range [AES::key 128] 15 end]" HTTP::cookie insert name "F2C" value $F2C } HSL::send $hsl1 "<190> [IP::client_addr] \[[clock format [clock seconds] -format "%d/%b/%Y:%H:%M:%S %z"]\] --[IP::local_addr]--NY--80--[URI::path [HTTP::uri]][URI::basename [HTTP::uri]]--UA=[HTTP::header User-Agent]--CT=[HTTP::header "Content-type"]" HSL::send $hsl2 "<190> [IP::client_addr] \[[clock format [clock seconds] -format "%d/%b/%Y:%H:%M:%S %z"]\] --[IP::local_addr]--NY--80--P2--[URI::path [HTTP::uri]][URI::basename [HTTP::uri]]--QS=[HTTP::query]--C=[HTTP::header cookie]--UA=[HTTP::header User-Agent]--CT=[HTTP::header "Content-type"]" } when HTTP_REQUEST_DATA { set refid "unknown" foreach x [split [string tolower [HTTP::payload]] "&"] { if { $x starts_with "refid=" } { set refid [lindex [split $x "="] 1] } } HSL::send $hsl2 "<190> [IP::client_addr] [[clock format [clock seconds] -format "%d/%b/%Y:%H:%M:%S %z"]] --[IP::local_addr]--NY--80--P2--refid=$refid--F2C=$F2C" } when HTTP_RESPONSE { if { [info exists F2C] and $F2C ne ""} { HTTP::cookie insert name "F2C" value $F2C unset -nocomplain F2C } } when CLIENT_CLOSED { if { [info exists ::active_clients([IP::client_addr])] } { HSL::send $hsl "<190> [IP::client_addr] [[clock format [clock seconds] -format "%d/%b/%Y:%H:%M:%S %z"]] --[IP::local_addr]--NY--80--CLIENT_CLOSED--$::active_clients([IP::client_addr])" unset ::active_clients([IP::client_addr]) } }
