09-10-2008 11:58 PM
Hello
We are experiencing very high memory issue (90-95%). Only the ethernet interface is configured. Firstly run on JUNOS 8.2 and i have upgrated it to JUNOS 9.0R3 and currently downgrade it on JUNOS 8.5 R 1, but not see any changes in memory utalization. The memory is 256MB and the router is J4350. Thanks
Solved! Go to Solution.
09-11-2008 12:22 AM
09-11-2008 12:25 AM
Hi
This is not an easy question to answer as there is really very little information to work on. One of the obvious things that can cause high CPU utilization is the volume of traffic going through the box and possible what services that have been enabled.
There is a less obvious one that might be relavant to you and that is if shaping is enabled. Please see KB11003 for more details on this topic.
Anton
09-11-2008 02:00 AM
09-11-2008 03:39 AM
Hi Norman
Sorry I did indeed read your question to quickly. As xuzhengwei mentioned a copy of "show system processes" would be useful. Could you also include "show chassis routing-engine.
If you look at the output below, I actullay have 59% utilization while my router is doing nothing. From the "show system processes" output however you can see the memory is defided between Active, In Active, Wired, Cache, Buffered and Free.
adelport@epsom> show chassis routing-engine Routing Engine status: Temperature 32 degrees C / 89 degrees F CPU temperature 37 degrees C / 98 degrees F DRAM 768 MB Memory utilization 59 percent CPU utilization: User 1 percent Real-time threads 11 percent Kernel 88 percent Idle 0 percent Model RE-J.3 Serial ID BTRD44400174 Start time 2008-08-13 15:06:50 CEST Uptime 28 days, 21 hours, 41 minutes, 11 seconds Load averages: 1 minute 5 minute 15 minute 0.15 0.07 0.01 adelport@epsom> show system processes summary last pid: 12256; load averages: 0.13, 0.07, 0.01 up 28+21:41:52 12:37:22 90 processes: 3 running, 69 sleeping, 18 waiting Mem: 47M Active, 78M Inact, 304M Wired, 62M Cache, 69M Buf, 250M Free Swap: PID USERNAME THR PRI NICE SIZE RES STATE TIME WCPU COMMAND 11 root 1 171 52 0K 12K RUN 624.0H 91.80% idle 4037 root 1 132 0 516M 276M RUN 67.9H 6.15% fwdd adelport@epsom>
09-11-2008 09:34 PM
Here are the outputs, kindly help and suggess what to do? Thanks
ubl@KCICORE9b> show chassis routing-engine
Routing Engine status:
Temperature 21 degrees C / 69 degrees F
CPU temperature 44 degrees C / 111 degrees F
DRAM 256 MB
Memory utilization 88 percent
CPU utilization:
User 161 percent
Real-time threads 214 percent
Kernel -179 percent
Idle -96 percent
Model RE-J4350-2540
Serial ID NR4759
Start time 2008-09-10 14:15:40 UTC
Uptime 1 day, 19 hours, 19 minutes, 23 seconds
Load averages: 1 minute 5 minute 15 minute
0.01 0.02 0.00
ubl@KCICORE9b> show system processes summary
last pid: 7616; load averages: 0.07, 0.04, 0.00 up 1+19:20:10 09:35:20
89 processes: 3 running, 68 sleeping, 18 waiting
Mem: 71M Active, 23M Inact, 115M Wired, 6696K Cache, 34M Buf, 23M Free
Swap:
PID USERNAME THR PRI NICE SIZE RES STATE TIME WCPU COMMAND
11 root 1 171 52 0K 12K RUN 40.2H 95.46% idle
4059 root 1 96 0 350M 96264K RUN 166:40 2.44% fwdd
09-11-2008 10:15 PM
ubl@KCICORE9b> show system processes extensive
last pid: 7617; load averages: 0.02, 0.03, 0.00 up 1+19:21:22 09:36:32
89 processes: 2 running, 69 sleeping, 18 waiting
Mem: 71M Active, 23M Inact, 115M Wired, 6696K Cache, 34M Buf, 23M Free
Swap:
PID USERNAME THR PRI NICE SIZE RES STATE TIME WCPU COMMAND
11 root 1 171 52 0K 12K RUN 40.3H 93.99% idle
4059 root 1 96 0 350M 96264K select 166:45 3.76% fwdd
4099 root 1 96 0 4584K 3404K select 0:48 0.15% dcd
4061 root 1 96 0 9312K 7908K select 7:41 0.00% isdnd
12 root 1 -20 -139 0K 12K WAIT 4:31 0.00% swi7: clock sio
4048 root 1 96 0 13428K 4304K select 0:34 0.00% chassisd
4004 root 1 20 0 0K 12K rtl_gp 0:33 0.00% rtl_alloc
4087 root 1 4 0 12000K 5156K kqread 0:32 0.00% rpd
4014 root 1 96 0 1576K 824K select 0:25 0.00% bslockd
4050 root 1 96 0 3336K 1360K select 0:20 0.00% craftd
4049 root 1 96 0 2572K 1652K select 0:11 0.00% alarmd
21 root 1 -68 -187 0K 12K WAIT 0:11 0.00% irq5: uhci0 uhci0*
4058 root 1 96 0 3732K 1848K select 0:10 0.00% bfdd
14 root 1 -40 -159 0K 12K WAIT 0:08 0.00% swi2: net
---(more)---
2 root 1 -8 0 0K 12K - 0:07 0.00% g_event
44 root 1 -16 0 0K 12K - 0:07 0.00% schedcpu
4003 root 1 -48 -167 0K 12K WAIT 0:07 0.00% swi0: +
39 root 1 -16 0 0K 12K psleep 0:06 0.00% vmkmemdaemon
5094 root 1 96 0 2740K 1952K select 0:05 0.00% dood
45 root 1 -8 0 0K 12K mdwait 0:05 0.00% md0
15 root 1 -16 0 0K 12K - 0:05 0.00% yarrow
4056 root 1 96 0 2852K 1668K select 0:05 0.00% ppmd
4 root 1 -8 0 0K 12K - 0:05 0.00% g_down
3 root 1 -8 0 0K 12K - 0:04 0.00% g_up
4098 root 1 96 0 5276K 2916K select 0:03 0.00% snmpd
31 root 1 20 0 0K 12K syncer 0:03 0.00% syncer
4088 root 1 111 15 4204K 2992K select 0:03 0.00% sampled
3944 root 1 96 0 2520K 1676K select 0:03 0.00% eventd
4086 root 1 96 0 4896K 2776K select 0:02 0.00% mib2d
8 root 1 171 52 0K 12K pgzero 0:02 0.00% pagezero
4090 root 1 96 0 2832K 1824K select 0:02 0.00% pppd
4097 root 1 96 0 3600K 1848K select 0:02 0.00% pfed
33 root 1 -16 0 0K 12K sdflus 0:02 0.00% softdepflush
4089 root 1 96 0 4288K 2540K select 0:02 0.00% cosd
4095 root 1 96 0 3780K 2380K select 0:02 0.00% dfwd
4096 root 1 96 0 6460K 2884K select 0:01 0.00% kmd
4094 root 1 4 0 0K 12K peer_s 0:01 0.00% peer proxy
---(more 45%)---
4046 root 1 96 0 1328K 532K select 0:01 0.00% watchdog
24 root 1 -64 -183 0K 12K WAIT 0:01 0.00% irq14: ata0
32 root 1 -4 0 0K 12K vlruwt 0:01 0.00% vnlru
37 root 1 -16 0 0K 12K psleep 0:01 0.00% vmuncachedaemon
9 root 1 -16 0 0K 12K psleep 0:00 0.00% bufdaemon
4092 root 1 96 0 4836K 2856K select 0:00 0.00% httpd
4051 root 1 96 0 16908K 13592K select 0:00 0.00% mgd
1 root 1 8 0 1092K 636K wait 0:00 0.00% init
4010 root 1 8 0 1452K 896K nanslp 0:00 0.00% cron
4102 root 1 4 0 0K 12K peer_s 0:00 0.00% peer proxy
92 root 1 -8 0 0K 12K mdwait 0:00 0.00% md1
4064 root 1 8 0 1428K 744K nanslp 0:00 0.00% getty
7 root 1 -16 0 0K 12K psleep 0:00 0.00% pagedaemon
3932 root 1 96 0 1396K 728K select 0:00 0.00% usbd
7614 ubl 1 96 0 11980K 7108K select 0:00 0.00% cli
36 root 1 4 0 0K 12K pfeacc 0:00 0.00% if_pfe_listen
4053 root 1 96 0 1820K 1004K select 0:00 0.00% inetd
4093 root 1 96 0 5652K 2492K select 0:00 0.00% authd
7615 root 1 96 0 16964K 13928K select 0:00 0.00% mgd
7613 root 1 8 0 1672K 1264K wait 0:00 0.00% login
7612 root 1 96 0 1712K 1264K select 0:00 0.00% telnetd
4091 root 1 104 0 2660K 1440K select 0:00 0.00% mplsoamd
3654 root 1 -8 0 0K 12K mdwait 0:00 0.00% md2
---(more 69%)---
22 root 1 8 0 0K 12K usbevt 0:00 0.00% usb0
7617 root 1 97 0 22052K 1428K RUN 0:00 0.00% top
3667 root 1 -8 0 0K 12K mdwait 0:00 0.00% md3
4065 root 1 5 0 1432K 768K ttyin 0:00 0.00% getty
3677 root 1 -8 0 0K 12K mdwait 0:00 0.00% md4
27 root 1 -48 -167 0K 12K WAIT 0:00 0.00% swi0: sio
0 root 1 -16 0 0K 0K WAIT 0:00 0.00% swapper
38 root 1 4 0 0K 12K picacc 0:00 0.00% if_pic_listen
6 root 1 8 0 0K 12K - 0:00 0.00% kqueue taskq
40 root 1 8 0 0K 12K - 0:00 0.00% nfsiod 0
35 root 1 4 0 0K 12K dump_r 0:00 0.00% kern_dump_proc
34 root 1 98 0 0K 12K sleep 0:00 0.00% netdaemon
41 root 1 8 0 0K 12K - 0:00 0.00% nfsiod 1
42 root 1 8 0 0K 12K - 0:00 0.00% nfsiod 2
43 root 1 8 0 0K 12K - 0:00 0.00% nfsiod 3
5 root 1 8 0 0K 12K - 0:00 0.00% thread taskq
23 root 1 8 0 0K 12K usbtsk 0:00 0.00% usbtask
10 root 1 -16 0 0K 12K ktrace 0:00 0.00% ktrace
16 root 1 -12 -131 0K 12K WAIT 0:00 0.00% swi9: task queue
17 root 1 -12 -131 0K 12K WAIT 0:00 0.00% swi9: +
18 root 1 -16 -135 0K 12K WAIT 0:00 0.00% swi8: +
13 root 1 -24 -143 0K 12K WAIT 0:00 0.00% swi6: vm
19 root 1 -28 -147 0K 12K WAIT 0:00 0.00% swi5: cambio
---(more 92%)---
29 root 1 -32 -151 0K 12K WAIT 0:00 0.00% swi4: ip6mismatch+
28 root 1 -36 -155 0K 12K WAIT 0:00 0.00% swi3: ip6opt ipopt
30 root 1 -44 -163 0K 12K WAIT 0:00 0.00% swi1: ipfwd
20 root 1 -52 -171 0K 12K WAIT 0:00 0.00% irq11: isab0
26 root 1 -60 -179 0K 12K WAIT 0:00 0.00% irq1: atkbd0
25 root 1 -64 -183 0K 12K WAIT 0:00 0.00% irq15: ata1
09-11-2008 10:57 PM - edited 09-11-2008 11:24 PM
09-11-2008 11:44 PM
Hi
In your scenario I don't think you have anything to be worried about. You have 71M of Active memory. The rest of the memory are all in difference stages of being cached or aged out. Have a look at this article.
http://www.freebsd.org/doc/en_US.ISO8859-1/books/f
09-14-2008 06:47 AM
AntonD, I also have a J-4350 and it arrived with JunOS 9.1 and the fwdd was using 7% of CPU all the time (router was idle, only I was connecting to it). I upgraded to JunOS 9.2R1 and now fwdd is using 14%-15% of CPU. I am just wondering, what does it do really? is this normal?