Re: GFS: GULM vs. DLM

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



I don't think anyone has ever compared DLM vs GULM with more than a handful of nodes. GULM has a history of servicing large clusters, but is being phased out.

In theory, the two should be comparable performance-wise - especially when GULM is set up in a redundant fashion. If, however, you will have nodes constantly joining and leaving the cluster - an unlikely scenario - that may imply that you should use GULM.

The suggestion to use GULM probably comes from historical knowledge that GULM performed well in HPC environments, while the DLM was largely unused in that regard (because it is relatively new).

 brassow

On Jan 24, 2006, at 3:00 PM, Eric Anderson wrote:

Wendy Cheng wrote:
Anthony Assi wrote:

Hi,

I would like to know which locking method you guys think is more preferable to implement on a 36 nodes Cluster (V20Z); The Distributed Lock Manager (dlm) or the Grand Unified Locking Manager (gulm) ?

DLM without doubts (since gulm is mostly in maintenance mode)


I recently talked with someone at RedHat (can't recall his name unfortunately) through a salesperson, and he claimed anything over about 20 nodes should use GULM instead. Is that not true? How about the max of 256 nodes?

Eric



-- ----------------------------------------------------------------------- - Eric Anderson Sr. Systems Administrator Centaur Technology
Anything that works is better than anything that doesn't.
----------------------------------------------------------------------- -

--

Linux-cluster@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/linux-cluster


--

Linux-cluster@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/linux-cluster

[Index of Archives]     [Corosync Cluster Engine]     [GFS]     [Linux Virtualization]     [Centos Virtualization]     [Centos]     [Linux RAID]     [Fedora Users]     [Fedora SELinux]     [Big List of Linux Books]     [Yosemite Camping]

  Powered by Linux