CPU load difference CPVIEW vs TOP on R80.30 kernel 3.1

[TomShanti]

Hi Checkmates,

can someone explain to me why I can see different CPU loads between CPVIEW and TOP since our upgrade to R80.30 kernel 3.1 (UMFW) on our 16core OpenServer ?

This is the affinity setting:

eth7: CPU 0
fw_0: CPU 15
fw_1: CPU 7
fw_2: CPU 14
fw_3: CPU 6
fw_4: CPU 13
fw_5: CPU 5
fw_6: CPU 12
fw_7: CPU 4
mpdaemon: CPU 4 5 6 7 12 13 14 15
fwd: CPU 4 5 6 7 12 13 14 15
dtlsd: CPU 4 5 6 7 12 13 14 15
vpnd: CPU 4 5 6 7 12 13 14 15
in.asessiond: CPU 4 5 6 7 12 13 14 15
pepd: CPU 4 5 6 7 12 13 14 15
lpd: CPU 4 5 6 7 12 13 14 15
dtpsd: CPU 4 5 6 7 12 13 14 15
rtmd: CPU 4 5 6 7 12 13 14 15
pdpd: CPU 4 5 6 7 12 13 14 15
in.acapd: CPU 4 5 6 7 12 13 14 15
cprid: CPU 4 5 6 7 12 13 14 15
cpd: CPU 4 5 6 7 12 13 14 15
Interface eth4: has multi queue enabled
Interface eth5: has multi queue enabled
Interface eth6: has multi queue enabled
Interface eth10: has multi queue enabled
Interface eth11: has multi queue enabled
Interface eth12: has multi queue enabled
Interface eth13: has multi queue enabled
Interface eth8: has multi queue enabled
Interface eth9: has multi queue enabled

Thanks and regards

Thomas

[Danny]

How many CPU cores are licensed?

What's this command showing?

sqlite3 -header CPViewDB.dat \
'select name_of_cpu, cpu_usage from UM_STAT_UM_CPU_UM_CPU_ORDERED_TABLE order by cpu_usage desc limit 10;'

[TomShanti]

Hi Danny,

license is for 16 cores:

[Expert@xxxxxx:0]# cplic print
Host Expiration Features
192.168.xxx.xxx never CPSG-C-8-U CPSG-C-8-U CPSB-FW CPSB-VPN CPSB-ADN CPSB-ACCL CPSB-IA CPSB-IPS CPSB-APCL CPSB-CTNT CK-xxxxxxxxxxxxx

The output of your command is:

[Expert@xxxxxx:0]# sqlite3 -header CPViewDB.dat 'select name_of_cpu, cpu_usage from UM_STAT_UM_CPU_UM_CPU_ORDERED_TABLE order by cpu_usage desc limit 10;'
Error: no such table: UM_STAT_UM_CPU_UM_CPU_ORDERED_TABLE

ccc

-------------------------------------------------- ccc v4.7 -
xxxxx
-------------------------------------------------------------
System Firewall Cluster Node (HA) > Standby
Type Open Server
OS R80.30 GAiA 3.10 JHF (Take 155) @ 64-bit
CPUSE Build 1889 | Host access: Any
CPU 16 Cores | SMT: - | Load 0.12
RAM 252 GB (Free: 237 GB) | Swapping 0 GB
SecureXL On | Multi-Queue Interfaces -
CoreXL On ( Cores) | Dynamic Dispatcher: On
Core dumps Present | Crash dumps: -
Disk use / 14% | /var/log/ 1%
Uptime 1 days, 12 hours | NTP: Synced
-------------------------------------------------------------
Managed by xxxxx (IP: 192.168.xxx.xxx)
Policy xxxxx - Apr 25 2020 `20:46
Inspection Stateful | Address Spoofing: None
Blades FW, VPN, IPS, IA, MON
-------------------------------------------------------------
IPS Apr 18 2020 `13:10 | xxx

AppC Apr 18 2020 `13:10 | xxx

URLF Apr 18 2020 `13:10 | xxx

ABot Apr 18 2020 `13:10 | xxx

AV Apr 18 2020 `13:10 | xxx
-------------------------------------------------------------
Interfaces 802.1Q VLAN Support, bnx2x, igb, ixgbe, tg3
SYNC Ifs 1
VLANs Defined
SNMP v3 Only
RAID -

I ran ccc on the passive member. btw very nice script !

Seems it does not pickup the MQ interfaces correctly ....

Dumps in  /var/log/dump/usermode/ are only from cpview

Thanks and regards

Thomas

[TomShanti · Accepted solution]

I just got sudden enlightment 😁

TOP shows the cumulative value of CPVIEWs "User" and "System" column of a CPU.

Regards Thomas

[HristoGrigorov]

If you are trying to compare CPU usage to system load average than these are two different things. Btw, do you have any excess RX-DRP on interfaces ?

You mention USMFW but just for info, it is not enabled on this system according what top displays.

[TomShanti]

Hi,

currently no excessive RS-DRPs.

Why would you say UMFW is not enabled ?

[Expert@xxxxx:0]# cpprod_util FwIsUsermode
1

Regards Thomas

[HristoGrigorov]

You have many fwk0_* processes which should not be the case when UMFW is enabled ?

[TomShanti]

If you press Shift+H in top the fwk0_dev_0 will resolve to the fwk... processes.

[HristoGrigorov]

Right you are 🙂 Sorry for false alarm 😉