10-03-2012
That's kind of the question -- does it really need to move? Why?
The usual problem is forcing a process to not move, because doing so costs time and cache bandwidth. Pinning a long-running intensive process to one CPU can be a good improvement in performance to not just itself but other things on the system.
This User Gave Thanks to Corona688 For This Post:
10 More Discussions You Might Find Interesting
1. UNIX for Advanced & Expert Users
hi,
is there any tool that i can use to update my scripts (SH scripts)
form Unix to linux.
please mention any useful websites.
thanx in advance (2 Replies)
Discussion started by: omran
2 Replies
2. UNIX for Advanced & Expert Users
Using binary translators, would it be possible capture the runtime image (instructions and data) of processes and translate these so that the process can run from where it left on a machine with a different architecture? This will be useful for migrating applications to heterogenous systems for... (3 Replies)
Discussion started by: sumona
3 Replies
3. UNIX for Advanced & Expert Users
Hi all,
Would appreciate advise on my situation.
Currently server A is in production. Server A takes in data from Server X, does some processing and send to server Y. We are going to develop a different system in server B, something like an enhanced version of A. Server A will be retired once... (2 Replies)
Discussion started by: new2ss
2 Replies
4. UNIX for Dummies Questions & Answers
how can i migrate a running process in unix to another node for load balancing? (3 Replies)
Discussion started by: aisalihu
3 Replies
5. UNIX for Advanced & Expert Users
how can i migrate a running process in unix to another node? (1 Reply)
Discussion started by: aisalihu
1 Replies
6. Shell Programming and Scripting
Hi,
We are doing migration from DB2 to Teradata.
There are couple of things involving in the project.
Please see below following order
Autosys-Jil script
Profile script
Category1
Teradata script
Data stage job script
Tera data script
Export files script..
Like that we have 10000... (1 Reply)
Discussion started by: onesuri
1 Replies
7. UNIX for Dummies Questions & Answers
fork() system is used to create a child a process.lets consider fork() echo krace will print krace twice .if i give it in loop it will print krace 2 power n time..in this case all child and parent process executes same process ...but i want to create a four different child process to execute four... (4 Replies)
Discussion started by: kracekumar
4 Replies
8. Solaris
Is there any ways to check the process usage for specific time interval. I tried with prstat but am not able to obtain the expected result and even with /var/adm/messages also. (12 Replies)
Discussion started by: rogerben
12 Replies
9. Solaris
Hi Experts,
Our servers running Solaris 10 with SAP Application. The memory utilization always >90%, but the process on SAP is too less even nothing.
Why memory utilization on solaris always looks high?
I have statement about memory on solaris, is this true:
Memory in solaris is used for... (4 Replies)
Discussion started by: edydsuranta
4 Replies
10. AIX
I'm New to AIX / VIOS
We're doing a FC switch cutover on an ibm device, connected via SAN.
How do I tell if one path to my remote disk is lost? (aix lvm)
How do I tell when my link is down on my HBA port?
Appreciate your help, very much! (4 Replies)
Discussion started by: BG_JrAdmin
4 Replies
LEARN ABOUT HPUX
serialize
serialize(2) System Calls Manual serialize(2)
NAME
serialize() - force target process to run serially with other processes
SYNOPSIS
DESCRIPTION
The system call is used to force the target process referenced by the pid value passed in to run serially with other processes also marked
for serialization. If the value of pid is zero, then the currently running process is marked for serialization. Once a process has been
marked by the process stays marked until process completion, unless is reissued on the serialized process with timeshare set to 1. If
timeshare is set to 1, the process specified in pid will be returned to normal timeshare scheduling algorithms.
This call is used to improve process throughput since process throughput usually increases for large processes when they are executed seri-
ally instead of allowing each program to run for only a short period of time. By running large processes one at a time, the system makes
more efficient use of the CPU as well as system memory, since each process does not end up constantly faulting in its working set, to only
have the pages stolen when another process starts running. As long as there is enough memory in the system, processes marked by behave no
differently from other processes in the system. However, once memory becomes tight, processes marked by are run one at a time with the
highest priority processes being run first. Each process runs for a finite interval of time before another serialized process is allowed
to run.
RETURN VALUE
returns zero upon successful completion, or nonzero if the system call failed.
ERRORS
If fails, it sets (see errno(2)) to the following value:
The pid passed in does not exist.
WARNINGS
The user has no way of forcing an execution order on serialized processes.
AUTHOR
was developed by HP.
SEE ALSO
serialize(1), privileges(5).
serialize(2)