03-02-2011 08:58 AM - edited 03-04-2019 11:37 AM
Hey all,
I have a router that is running at ~37% CPU utilization with ~37% interrupt utlization. I have verified that CEF is enabled on all interfaces and that it is running. In addition I have followed Ciscos troubleshooting guide http://www.cisco.com/en/US/products/hw/routers/ps359/products_tech_note09186a00801c2af0.shtml
After running some tests I am leaning towards a CEF problem. You will notice that there is a high number of cache misses, and processed packets. I am unsure if any of this matters though. I have read that a CPU utlization of 10% or higher due to interrupts is bad but is it really?
Also, is it possible for HSRP to cause high CPU interrupt levels? Here is some output from various commands. Any help is appreciated.
Thanks all,
CJ
show processes cpu sorted 5min
CPU utilization for five seconds: 36%/36%; one minute: 36%; five minutes: 35%
PID Runtime(ms) Invoked uSecs 5Sec 1Min 5Min TTY Process
45 276544 85958342 3 0.08% 0.08% 0.08% 0 Per-Second Jobs
73 51373292 410515501 125 0.08% 0.07% 0.08% 0 IP Input
57 200 322 621 0.16% 0.15% 0.04% 2 SSH Process
41 4582240 21976370 208 0.00% 0.03% 0.02% 0 Net Background
16 1656608881548211510 107 0.00% 0.01% 0.01% 0 EnvMon
5 24911736 8778295 2837 0.16% 0.03% 0.00% 0 Check heaps
2 29948 17191665 1 0.08% 0.01% 0.00% 0 Load Meter
95 33828 125805075 0 0.08% 0.01% 0.00% 0 CEF process
221 1178960 60383456 19 0.08% 0.00% 0.00% 0 HSRP IPv4
208 2112 85927351 0 0.08% 0.00% 0.00% 0 trunk conditioni
11 0 1 0 0.00% 0.00% 0.00% 0 IPC Zone Manager
10 12 1432634 0 0.00% 0.00% 0.00% 0 IPC Dynamic Cach
13 1328 85938723 0 0.00% 0.00% 0.00% 0 IPC Deferred Por
12 2316 85938725 0 0.00% 0.00% 0.00% 0 IPC Periodic Tim
14 0 1 0 0.00% 0.00% 0.00% 0 IPC Seat Manager
7 0 2 0 0.00% 0.00% 0.00% 0 Timers
17 0 1 0 0.00% 0.00% 0.00% 0 OIR Handler
18 0 1 0 0.00% 0.00% 0.00% 0 Crash writer
8 0 2 0 0.00% 0.00% 0.00% 0 ATM AutoVC Perio
20 0 2 0 0.00% 0.00% 0.00% 0 ATM Idle Timer
9 0 2 0 0.00% 0.00% 0.00% 0 ATM VC Auto Crea
----------------------------------------------------------------------------------------------------------------------
sho cef int
GigabitEthernet0/1 is up (if_number 3)
Corresponding hwidb fast_if_number 3
Corresponding hwidb firstsw->if_number 3
ICMP redirects are always sent
Per packet load-sharing is disabled
IP unicast RPF check is disabled
Inbound access list is 101
Outbound access list is protectout
Hardware idb is GigabitEthernet0/1
Fast switching type 1, interface type 27
IP CEF switching enabled
IP Flow switching turbo vector
IP Flow CEF switching turbo vector
IP MTU 1500
<---omitted---->
GigabitEthernet0/2 is up (if_number 4)
Corresponding hwidb fast_if_number 4
Corresponding hwidb firstsw->if_number 4
ICMP redirects are always sent
Per packet load-sharing is disabled
IP unicast RPF check is disabled
Inbound access list is not set
Outbound access list is not set
Hardware idb is GigabitEthernet0/2
Fast switching type 1, interface type 27
IP CEF switching enabled
IP Feature Fast switching turbo vector
IP Feature CEF switching turbo vector
Input fast flags 0x400000, Input fast flags2 0x0, Output fast flags 0x10000, Output fast flags2 0x0
ifindex 5(5)
Slot 0 Slot unit 2 Unit 1 VC -1
Transmit limit accumulator 0x0 (0x0)
IP MTU 1500
-----------------------------------------------------------------------------------------------------------------------------------------------------------
sho cef drop
CEF Drop Statistics
Slot Encap_fail Unresolved Unsupported No_route No_adj ChkSum_Err
RP 67456021 0 0 154587241 0 0
-----------------------------------------------------------------------------------------------------------------------------------------------------------
sho interfaces switching
GigabitEthernet0/1 description Primary Handoff-CentriLogic
Throttle count 0
Drops RP 3946 SP 0
SPD Flushes Fast 263432 SSE 0
SPD Aggress Fast 0
SPD Priority Inputs 2880114 Drops 0
Protocol IP
Switching path Pkts In Chars In Pkts Out Chars Out
Process 240646779 3075941537 179238873 4268814505
Cache misses 791867 - - -
Fast 2738878053 1533579307 1501157067 4275204374
Auton/SSE 0 0 0 0
Protocol DEC MOP
Switching path Pkts In Chars In Pkts Out Chars Out
Process 0 0 142983 11009691
Cache misses 0 - - -
Fast 0 0 0 0
Auton/SSE 0 0 0 0
Protocol ARP
Switching path Pkts In Chars In Pkts Out Chars Out
Process 6012 360720 6002 360120
Cache misses 0 - - -
Fast 0 0 0 0
Auton/SSE 0 0 0 0
Protocol Other
Switching path Pkts In Chars In Pkts Out Chars Out
Process 0 0 8595659 515739540
Cache misses 0 - - -
Fast 0 0 0 0
Auton/SSE 0 0 0 0
NOTE: all counts are cumulative and reset only after a reload.
GigabitEthernet0/2 To BTROC2-AS1 gi3/39
Throttle count 0
Drops RP 9 SP 0
SPD Flushes Fast 16 SSE 0
SPD Aggress Fast 0
SPD Priority Inputs 34362050 Drops 0
Protocol IP
Switching path Pkts In Chars In Pkts Out Chars Out
Process 175236306 2796785412 139274556 3033584364
Cache misses 204911663 - - -
Fast 1655007830 3856814651 2708496561 3523926699
Auton/SSE 0 0 0 0
Protocol DEC MOP
Switching path Pkts In Chars In Pkts Out Chars Out
Process 0 0 142981 11009537
Cache misses 0 - - -
Fast 0 0 0 0
Auton/SSE 0 0 0 0
Protocol ARP
Switching path Pkts In Chars In Pkts Out Chars Out
Process 2622647 157358820 58110943 3486656580
Cache misses 0 - - -
Fast 0 0 0 0
Auton/SSE 0 0 0 0
Protocol Other
Switching path Pkts In Chars In Pkts Out Chars Out
Process 5539 2309763 8595566 515733960
Cache misses 0 - - -
Fast 0 0 0 0
Auton/SSE 0 0 0 0
----------------------------------------------------------------------------------------------------------
show cef not-cef-switched
CEF Packets passed on to next switching layer
Slot No_adj No_encap Unsupp'ted Redirect Receive Options Access Frag
RP 45187360 0 0 0 41702189 6726 0 0
03-07-2011 02:36 AM
Hi
36% is interrupt, looks to me bad as some process raising interrupt constantly to the CPU.
do you see any abnormallty ?
if you suspect HSRP, is it your HSRP configured with aggresive timers?
what kind of the box is this?
do you see the input Q is is increasing on the interfaces?, if yes, you can see the punt packets of the interface using "show buffer input-in x/y"
if able to open a TAC case, they will do the CPU profiling to find what functions taking up your CPU.
May be can you post your config (remove any sensitve info)
Regards
03-08-2011 09:58 PM
If the CPU utilization due to interrupts was high for a long time, then it should be a concern.
The traffic across the network could play a role in this.
To determine which process is causing the high CPU, we could do the CPU profiling.
-Shyam.
Discover and save your favorite ideas. Come back to expert answers, step-by-step guides, recent topics, and more.
New here? Get started with these tips. How to use Community New member guide