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

[Linux-cluster] Two node cluster benchmark



Hello,

I have a two node cluster configured like: 
  Ubuntu 10.04 + CMAN + DRBD + GFS2

In a benchmark, I run simultaneously on both nodes, a script that make
write operations in the filesystem until it fills.

But when I run the benchmark, foo-node remains almost the whole time
waiting for bar-node write to the file system. Is this normal? How could
I optimize this?

Cman config:
################################################################################
<?xml version="1.0"?>

<cluster name="MyCluster" config_version="1">
  <logging debug="on"/>
  <totem consensus="6000" token="3000"/>
  <cman two_node="1" expected_votes="1"/>
  <dlm plock_ownership="1" plock_rate_limit="0"/>
  <gfs_controld plock_rate_limit="0"/>
  
  <clusternodes>
    <clusternode name="192.168.0.1" nodeid="1">
      <fence>
        <method name="human"> 
          <device name="human" nodename="192.168.0.1"/> 
        </method>       
      </fence>
    </clusternode>

    <clusternode name="192.168.0.2" nodeid="2">
      <fence> 
        <method name="human"> 
          <device name="human" nodename="192.168.0.2"/> 
        </method>
      </fence>
    </clusternode>
  </clusternodes>

  <fencedevices>
    <fencedevice name="human" agent="fence_manual"/>
  </fencedevices>
</cluster>
################################################################################

GFS2 config:
################################################################################
mkfs.gfs2 -p lock_dlm -t MyCluster:MyFileSystem -j 2 /dev/drbd2
mount.gfs2 /dev/drbd2 /var/fs_tests/gfs2/ -o noatime
################################################################################

Thank you in advance
Best regards
--
Thiago Henrique


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