HPE GreenLake Administration
- Community Home
- >
- Servers and Operating Systems
- >
- Operating Systems
- >
- Operating System - OpenVMS
- >
- Re: MON CLUS query
Operating System - OpenVMS
1827897
Members
1870
Online
109970
Solutions
Forums
Categories
Company
Local Language
back
Forums
Discussions
Forums
- Data Protection and Retention
- Entry Storage Systems
- Legacy
- Midrange and Enterprise Storage
- Storage Networking
- HPE Nimble Storage
Discussions
Forums
Discussions
Discussions
Discussions
Forums
Discussions
back
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
- BladeSystem Infrastructure and Application Solutions
- Appliance Servers
- Alpha Servers
- BackOffice Products
- Internet Products
- HPE 9000 and HPE e3000 Servers
- Networking
- Netservers
- Secure OS Software for Linux
- Server Management (Insight Manager 7)
- Windows Server 2003
- Operating System - Tru64 Unix
- ProLiant Deployment and Provisioning
- Linux-Based Community / Regional
- Microsoft System Center Integration
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Blogs
Information
Community
Resources
Community Language
Language
Forums
Blogs
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
04-05-2006 10:22 PM
04-05-2006 10:22 PM
MON CLUS query
Running a 3 node cluster under VMS7.2.
2 primary nodes have exactly same sysgen settings and values. Each of 2 nodes have disk arrays mirrored to the 'paired' node.
Nodes seem reasonably well balanced, but when issuing MON CLUS command, the results reported in the 'LOCK' quadrant are severely imbalanced; 1 node reporting tot ENQ/DEQ rates that are at times 10x higher than its partner node. Could anyone please shed light on how these stats should be interpreted?
What value(s) can be considered good/bad?
What sysgen parameter - if any - affects this?
Is it expected to have such relative differences in a cluster that we're attempting to balance.
Would appreciate any advice at all please.
2 primary nodes have exactly same sysgen settings and values. Each of 2 nodes have disk arrays mirrored to the 'paired' node.
Nodes seem reasonably well balanced, but when issuing MON CLUS command, the results reported in the 'LOCK' quadrant are severely imbalanced; 1 node reporting tot ENQ/DEQ rates that are at times 10x higher than its partner node. Could anyone please shed light on how these stats should be interpreted?
What value(s) can be considered good/bad?
What sysgen parameter - if any - affects this?
Is it expected to have such relative differences in a cluster that we're attempting to balance.
Would appreciate any advice at all please.
3 REPLIES 3
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
04-05-2006 10:41 PM
04-05-2006 10:41 PM
Re: MON CLUS query
Paul,
lock ENQs (and DEQs) are done by 'the applications'. If the applications are making sensibly use of locking, higher rates would indicate higher application load, which would be 'good'.
You could use MONI LOCK and MONI DLOCK to try to find out, what kind of lock operations are happening and whether there is a lot of 'remote' locking instead of local locking.
There could also be lock re-mastering, but the MONI RLOCK command is not available in V7.2, should would have to look at the RM counters with SDA> SHOW SYMB/ALL PMS$GL_RM
Local locking will just consume kernel mode CPU time, remote locking will also add interrupt mode time and use cluster interconnect bandwidth.
Volker.
lock ENQs (and DEQs) are done by 'the applications'. If the applications are making sensibly use of locking, higher rates would indicate higher application load, which would be 'good'.
You could use MONI LOCK and MONI DLOCK to try to find out, what kind of lock operations are happening and whether there is a lot of 'remote' locking instead of local locking.
There could also be lock re-mastering, but the MONI RLOCK command is not available in V7.2, should would have to look at the RM counters with SDA> SHOW SYMB/ALL PMS$GL_RM
Local locking will just consume kernel mode CPU time, remote locking will also add interrupt mode time and use cluster interconnect bandwidth.
Volker.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
04-06-2006 01:45 PM
04-06-2006 01:45 PM
Re: MON CLUS query
If your system has files that are opened on more than one node, then the first node that opens a file becomes the "lock mastering node" for that file, and has to handle both local lock processing and locks taken out by the "other" node.
If your system has mostly "local" file processing then the lock rates are probably just an indication of RMS file activity.
Setting up RMS statistics and monitoring on "hot" files can be used to check this.
The RMS_DEFAULT settings can have an effect on the number of locks, more buffers=more concurrent locks.
I wouldn't worry about enq/deq rates until they are > many thousand per second.
Phil
If your system has mostly "local" file processing then the lock rates are probably just an indication of RMS file activity.
Setting up RMS statistics and monitoring on "hot" files can be used to check this.
The RMS_DEFAULT settings can have an effect on the number of locks, more buffers=more concurrent locks.
I wouldn't worry about enq/deq rates until they are > many thousand per second.
Phil
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
04-06-2006 10:34 PM
04-06-2006 10:34 PM
Re: MON CLUS query
As you are before Vms 7.3, you should use the program available at
http://h18000.www1.hp.com/support/asktima/operating_systems/009F6DF1-BC7EC4E1-1C02A1.html
[OpenVMS] Example-C How to Monitor
the Dynamic Lock Remastering Activity
This is the monitor rlock for before Vms 7.3 (which has seen monitor rlock appear)
The opinions expressed above are the personal opinions of the authors, not of Hewlett Packard Enterprise. By using this site, you accept the Terms of Use and Rules of Participation.
Company
Support
Events and news
Customer resources
© Copyright 2025 Hewlett Packard Enterprise Development LP