[Linux-cluster] How to test GFS-6.0.2.20-1 on RHELAS3.0 ?

["Aydin SASMAZ" <sasmaz itu edu tr>]

Hi

 

I would like to be sure which method to test GFS-6.0.2.20-1installed 3 node file cluster doesn't corrupt data while multiple nodes writing on the same file. At the same time how LOCK_GULM manage filesystem ? Is there any known test? or benchmark other than bonnie++ . I would like to deploy 3 filesystem, each one on one gfs server and export these file systems with smb to other smb clients. I plan to use 3 smb instance for all 3 filesystem on every server node and load balancer in front of them.

 

Platform            : 3x HP-DL380 G4

OP                   : RedHat Enterprise Linux Advanced Server 3.0 Update 4

Cluster Suite     : 3.0, clumanager-1.2.22-2

                            redhat-config-cluster-1.0.3-1.noarch.rpm

GFS                 :    GFS-devel-6.0.2.20-1
                            GFS-modules-smp-6.0.2.20-1
                            GFS-6.0.2.20-1

Fencing Dev      : fence_ilo

 

 

Any advice would be appreciated.

 

Some notes about system :

------------------------------------------

 

[root gfs-test2 root]# gfs_tool df
/users/lnxsrv1:
  SB lock proto = "lock_gulm"
  SB lock table = "gfs-test:lnxsrv1"
  SB ondisk format = 1308
  SB multihost format = 1401
  Block size = 4096
  Journals = 8
  Resource Groups = 1596
  Mounted lock proto = "lock_gulm"
  Mounted lock table = "gfs-test:lnxsrv1"
  Mounted host data = ""
  Journal number = 1
  Lock module flags = async
  Local flocks = FALSE
  Local caching = FALSE

 

  Type           Total          Used           Free           use%          
  ------------------------------------------------------------------------
  inodes         8              8              0              100%
  metadata       92131          60723          31408          66%
  data           104492113      30341120       74150993       29%

 

/users/lnxsrv2:
  SB lock proto = "lock_gulm"
  SB lock table = "gfs-test:lnxsrv2"
  SB ondisk format = 1308
  SB multihost format = 1401
  Block size = 4096
  Journals = 8
  Resource Groups = 1596
  Mounted lock proto = "lock_gulm"
  Mounted lock table = "gfs-test:lnxsrv2"
  Mounted host data = ""
  Journal number = 1
  Lock module flags = async
  Local flocks = FALSE
  Local caching = FALSE

 

  Type           Total          Used           Free           use%          
  ------------------------------------------------------------------------
  inodes         5              5              0              100%
  metadata       38             38             0              100%
  data           104584209      0              104584209      0%

 

/users/lnxsrv3:
  SB lock proto = "lock_gulm"
  SB lock table = "gfs-test:lnxsrv3"
  SB ondisk format = 1308
  SB multihost format = 1401
  Block size = 4096
  Journals = 8
  Resource Groups = 396
  Mounted lock proto = "lock_gulm"
  Mounted lock table = "gfs-test:lnxsrv3"
  Mounted host data = ""
  Journal number = 1
  Lock module flags = async
  Local flocks = FALSE
  Local caching = FALSE

 

  Type           Total          Used           Free           use%          
  ------------------------------------------------------------------------
  inodes         5              5              0              100%
  metadata       10             10             0              100%
  data           25949437       0              25949437       0%

[root gfs-test1 root]# gulm_tool nodeinfo gfs-test{3,1}.-----
 Name: gfs-test1.-----
  ip    = 160.75.100.22
  state = Logged in
  mode = Slave
  missed beats = 0
  last beat = 1120235791271378
  delay avg = 6672475
  max delay = 9459850

 

[root gfs-test1 root]# gulm_tool nodeinfo gfs-test{3,2}.------
 Name: gfs-test2.------
  ip    = 160.75.100.23
  state = Logged in
  mode = Slave
  missed beats = 0
  last beat = 1120235802888768
  delay avg = 6678723
  max delay = 6880217

 

Aydin SASMAZ

System Support Engineer

ITU BIDB

Phone: +90 212 2853930

Fax    : +90 212 2856936