|
|
Sponsored Content
Top Forums
UNIX for Dummies Questions & Answers
Dual CPU's and 'top'
Post 38510 by davidg on Thursday 17th of July 2003 01:15:40 PM
07-17-2003
Hi,
Sorry to hook in this late, I hope we are still in time.
This is something you never want to see !!
Especialy with internal disks. Please make sure you have the latest top-patch installed ! If so take a closer look as top is not realy a good advisor on systemload, but of cours should still be a bit more accurate.
WIO is Waiting for IO and means that your disks are so bussy that another request for IO had to be put into wait. Your system will take it of waiting after a while again and will retry in a moment.
WIO is slowing down your server a lot. This can be caused by swap as well (running out of memory).
Anyway, for a good check you should do the following :
sar -u 2 20 # This will tell you the actual cpu usage
sar -d 2 20 # If wio keeps high, check the disk and see which one it is
You'dd better check the disk if this is just a single disk. ES should replace the disk/fibre channel or whatever if it's realy staying at such a load.
Most of all a "format" --> specify the bussy disk --> analyze --> read , should come up with timout errors. keep a "tail -f /var/adm/messages" open !
I think this is more than enough food for you now
Let me know if I was in time, or if you need some extra help.
Regs David
Sorry to hook in this late, I hope we are still in time.
This is something you never want to see !!
Especialy with internal disks. Please make sure you have the latest top-patch installed ! If so take a closer look as top is not realy a good advisor on systemload, but of cours should still be a bit more accurate.
WIO is Waiting for IO and means that your disks are so bussy that another request for IO had to be put into wait. Your system will take it of waiting after a while again and will retry in a moment.
WIO is slowing down your server a lot. This can be caused by swap as well (running out of memory).
Anyway, for a good check you should do the following :
sar -u 2 20 # This will tell you the actual cpu usage
sar -d 2 20 # If wio keeps high, check the disk and see which one it is
You'dd better check the disk if this is just a single disk. ES should replace the disk/fibre channel or whatever if it's realy staying at such a load.
Most of all a "format" --> specify the bussy disk --> analyze --> read , should come up with timout errors. keep a "tail -f /var/adm/messages" open !
I think this is more than enough food for you now
Let me know if I was in time, or if you need some extra help.
Regs David
|
|
10 More Discussions You Might Find Interesting
1. UNIX for Dummies Questions & Answers
I have a process in my TOP output that is consistantly at 97% usage. I have 16 CPUs on my box. So is the 97% the cumalative usage of all the CPUs or just one? (3 Replies)
Discussion started by: kskywr
3 Replies
2. UNIX for Advanced & Expert Users
I am using the Red Hat Enterprise Linux AS release 3 (Taroon), 2.4.21-4.EL. When I see the output of the command 'top'. I am getting the following
************************************************************************************
2 processes: 227 sleeping, 5 running, 0 zombie, 0 stopped... (3 Replies)
Discussion started by: praveen_b744
3 Replies
3. UNIX for Dummies Questions & Answers
hi,
i want to know cpu utilizatiion per process per cpu..for single processor also if multicore in linux ..to use these values in shell script to kill processes exceeding cpu utilization.ps (pcpu) command does not give exact values..top does not give persistant values..psstat,vmstat..does njot... (3 Replies)
Discussion started by: pankajd
3 Replies
4. AIX
Okay, I am trying to come up with a multi-platform script to report top ten CPU and memory hog processes, which will be run by our enterprise monitoring application as an auto-action item when the CPU and Memory utilization gets reported as higher than a certain threshold
I use top on other... (5 Replies)
Discussion started by: thenomad
5 Replies
5. Shell Programming and Scripting
I am using Ubuntu 9.04. I want to write a shell script to get the information about cpu idle from top command at the real time when i call it, compare cpu idle with 20 (20%), if cpu idle > 20 exit 1, vice versa exit 0. Anybody can help me to resolve it ?
Thanks alot. (7 Replies)
Discussion started by: huyquocnguyen
7 Replies
6. Solaris
What should we do if we show a 0% cpu idl on top? (5 Replies)
Discussion started by: Pouchie1
5 Replies
7. UNIX Benchmarks
p520's prtconf ..two internal drives 10K RPMs 140G, 2 dual core 1.5 GHz processors, 8 Gig of RAM, running AIX 7.1, with the newest gcc compiler
The numbers don't make sense,
Can someone comment ??
BYTE UNIX Benchmarks (Version 3.11)
System -- AIX p520 1 7 00CD5D0C4C00
Start... (2 Replies)
Discussion started by: ppchu99
2 Replies
8. UNIX for Dummies Questions & Answers
Hi,
We have a Solaris server that has about 43 Oracle databases on it and we also have the Oracle Enterprise Manager - emagent that is used to monitor these databases
When running top, the emagent is showing as one of the top process. Excerpts from running top shows something as below:
... (3 Replies)
Discussion started by: newbie_01
3 Replies
9. Hardware
For dual CPU motherboards, of which there are a few on the market mainly targeting the server-oriented clientele, I was wondering how this works in practice. Will the two CPUs be detected automatically not only by the BIOS, but also by the operating system? In other words, will the user see one... (7 Replies)
Discussion started by: figaro
7 Replies
10. Red Hat
Hi
please see attached picture of the TOP command.
the "java" process seem to consume 700% of cpu
is that mean that he uses 100% of every 7 cpu cores?
thanks (2 Replies)
Discussion started by: guy3145
2 Replies
LEARN ABOUT ULTRIX
iostat
iostat(1) General Commands Manual iostat(1) Name iostat - report I/O statistics Syntax iostat [ -c ] [ -t ] [ disknames ] [ interval ] [ count ] Description The command reports I/O statistics for terminals, disks and cpus. For terminals the number of input and output characters are counted. For disks the number of 512 byte blocks per second and number of transfers per second are displayed. For cpus, it provides the percentage of time the system has spent in user mode, in user mode running low priority (niced) processes, in system mode, and idling. On multipro- cessor systems these cpu statistics represent a cumulative summary of all the cpus. The optional disknames argument causes disk statistics to be displayed for the specified disks. If this argument is not specified then disk statistics will be displayed for the first 3 disks only. The optional interval argument causes to report once each interval seconds. The first report is for all time since a reboot and each sub- sequent report is for the last interval only. The optional count argument restricts the number of reports. Options -c Displays the percentage of time each cpu spent in user mode, running low priority (nice'd) processes, in system mode, and idling. -t Displays the number of characters read from and written to terminals. Examples This example will cause cpu and disk statistics for the 5 disks ra0, ra1, ra2, ra3, and ra4. iostat ra0 ra1 ra2 ra3 ra4 This example will cause cpu, terminal, and disk statistics for ra0 to be displayed and updated every 2 seconds. iostat -t ra0 2 Files See Also vmstat(1), cpustat(1) iostat(1)