12-03-2009
Why CPU time is longer than Elasped time?
I thought a program's elapsed time, some program language call it real time, should be the time of a program from start to finish. And it should be equal or longer than CPU time. This is true for the most of the cases. However, I do see some of my programs CPU time is longer than Elapsed time.
This is from Syncsort run log (ran on solaries):
Elapsed time: 0:09:27.35 CPU time: 0:17:13.85
I saw the same happened on one of my SAS programs (also ran on solaries).
Can anyone explain to me why? Is elapsed time really reflacts program time from start to end? If yes, how can a program still consumes CPU after it completed?
9 More Discussions You Might Find Interesting
1. HP-UX
Hi,
I am loking for a c++ function that calculate CPU time under HP-UX
Thank you (1 Reply)
Discussion started by: limame
1 Replies
2. IP Networking
If i fire followin command on unix (linux/solaris) and windows
ftp serverX where serverX is not in the network,
it takes more time to get reply on unix(3-4 mins) rather windows(1 min),
can anybody tell me why this happens? and how to reduce this time span? (1 Reply)
Discussion started by: amolwar
1 Replies
3. UNIX for Advanced & Expert Users
Hello all,
I'm using clock() function (from ctime) to realize how long it takes my threaded application to complete an algorithm. I would like to know how this function behaves in multicore boxes, that is: does it return the sum of the clock ticks of each processor the program was runned on ?... (0 Replies)
Discussion started by: clalfa
0 Replies
4. UNIX for Advanced & Expert Users
Hi,
I have problem like everyday i have to check which process consuming more cpu time. I have done it manually using top command..
Is there any script which will tell the exact process name which will consuming more time. I am using hpux. (1 Reply)
Discussion started by: rajesh08
1 Replies
5. UNIX Desktop Questions & Answers
Hi i am a newbie thanks in advance
i have a process which keeps on running but doesn't use any CPU time and doesn't do the functionality which it is suppose to do .
If i kill the process and start the process again then the process kicks in and starts using CPU time and continues to do its... (3 Replies)
Discussion started by: nick1982
3 Replies
6. Solaris
We are using JAVA program and strange thing is it takes 100% CPU when not in use.
The program function is to stream a file on output port (one direction). It checks one directory and when there is a file in it, starts.
While it is streaming the CPU usage is normal, about 20%.
But, if... (9 Replies)
Discussion started by: orange47
9 Replies
7. Shell Programming and Scripting
Hi ,
I am trying to :wall: my head while scripting ..I am really new to this stuff , never did it before :( .
how to find cpu's system high time and user time high in a script??
thanks , help would be appreciated !
:) (9 Replies)
Discussion started by: sushwey
9 Replies
8. UNIX for Advanced & Expert Users
Hi Experts,
If a thread running on CPU needs some data from RAM (from near or far RAM) it requests the data (this moment of time is t0) and gets it in moment of time in t1, and continues his work.
Between t0 and t1, while data is transferring from RAM, the thread is goes out from CPU? Is the... (2 Replies)
Discussion started by: sant
2 Replies
9. AIX
Hi,
i am seeing some strange things on a lpar which we have at this moment.
With nmon i see a process aix_timeout_thread which is using lots of cpu (70-80%, all cpu which is "free" is used). This is a kernel process (for as far i can find out) but i am wondering what is causing this to happen... (5 Replies)
Discussion started by: aixvinnie
5 Replies
LEARN ABOUT LINUX
s390_runtime_instr
S390_RUNTIME_INSTR(2) System Calls Manual S390_RUNTIME_INSTR(2)
NAME
s390_runtime_instr - enable/disable s390 CPU run-time instrumentation
SYNOPSIS
#include <asm/runtime_instr.h>
int s390_runtime_instr(int command, int signum);
DESCRIPTION
The s390_runtime_instr() system call starts or stops CPU run-time instrumentation for the calling thread.
The command argument controls whether run-time instrumentation is started (S390_RUNTIME_INSTR_START, 1) or stopped (S390_RUN-
TIME_INSTR_STOP, 2) for the calling thread.
The signum argument specifies the number of a real-time signal. The real-time signal is sent to the thread if the run-time instrumentation
buffer is full or if the run-time-instrumentation-halted interrupt occurred.
RETURN VALUE
On success, s390_runtime_instr() returns 0 and enables the thread for run-time instrumentation by assigning the thread a default run-time
instrumentation control block. The caller can then read and modify the control block and start the run-time instrumentation. On error, -1
is returned and errno is set to one of the error codes listed below.
ERRORS
EINVAL The value specified in command is not a valid command or the value specified in signum is not a real-time signal number.
ENOMEM Allocating memory for the run-time instrumentation control block failed.
EOPNOTSUPP
The run-time instrumentation facility is not available.
VERSIONS
This system call is available since Linux 3.7.
CONFORMING TO
This Linux-specific system call is available only on the s390 architecture. The run-time instrumentation facility is available beginning
with System z EC12.
NOTES
Glibc does not provide a wrapper for this system call, use syscall(2) to call it.
SEE ALSO
syscall(2), signal(7)
Linux Programmer's Manual 2012-12-17 S390_RUNTIME_INSTR(2)