Process are blocked for several seconds in a cluster

From: Carlos Rodriguez (crodriguez@eliop.es)
Date: Thu Jan 22 2004 - 04:55:39 EST

• Next message: Maaskant Gert: "SUMMARY: Sys_check question."
• Previous message: n. federov: "Swap mirroring with LSM"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]

Hello Managers.

I have installed a Tru64 Unix TruCluster V5.1A Patch Kit 3 Operating
System with two members.
I have an application running on one member as a cluster service.
This application communicates over TCP/IP with a remote host and
sends to this host one message per second.
Under some actions on the cluster, like booting the other member,
copying large files to a shared disk or using cfsmgr to change the
node which is serving the /usr fileset, I have seen that the process
is blocked between 3 and 5 seconds. This makes my process not to
comply with the requirement of sending a message every second.

I wonder why the process is blocked in this cases. It seems to be
related with cluster_lockd service. In other words, it seems that the
user level is blocked while the system is doing some actions that
affect to the cluster. But I do not know and I do not Know how I can
solve the problem.

Thanks in advance.

Carlos Rodriguez del Castillo <crodriguez@eliop.es>
ELIOP, S.A.
Madrid-Spain

• Next message: Maaskant Gert: "SUMMARY: Sys_check question."
• Previous message: n. federov: "Swap mirroring with LSM"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]

This archive was generated by hypermail 2.1.7 : Sat Apr 12 2008 - 10:49:49 EDT