Originally posted by: SystemAdmin
Hi guys,
I have some questions regarding the restriping of a GPFS file system (version 3.1.0.9). For the sake of simplicity the cluster is consisted from only 1 node and no customization to the FS, just default settings. The GPFS was created with 2 disks in it, I suspended the second disk, and moved some data to the GPFS FS. Look below:
bash-3.00# mmdf test_gpfs
disk disk size failure holds holds free KB free KB
name in KB group metadata data in full blocks in fragments
-------------
--------
--------------------
Disks in storage pool: system
nsd0 71687000 -1 yes yes 59282432 ( 83%) 9208 ( 0%)
nsd2 71687000 -1 yes yes 71619072 (100%) 336 ( 0%)
-------------------
(pool total) 143374000 130901504 ( 91%) 9544 ( 0%)
============= ==================== ===================
(total) 143374000 130901504 ( 91%) 9544 ( 0%)
Inode Information
Number of used inodes: 4041
Number of free inodes: 136247
Number of allocated inodes: 140288
Maximum number of inodes: 140288
After that i resumed the disk and tried mmrestripefs -b with the idea to rebalance the data blocks across the 2 disks so i will have even I/O to both disks and not just reads from the first disk.
bash-3.00# mmrestripefs test_gpfs -b
Scanning file system metadata, phase 1 ...
Scan completed successfully.
Scanning file system metadata, phase 2 ...
Scan completed successfully.
Scanning file system metadata, phase 3 ...
Scan completed successfully.
Scanning file system metadata, phase 4 ...
Scan completed successfully.
Scanning user file metadata ...
100 % complete on Fri Jun 8 11:31:43 2007
Scan completed successfully.
bash-3.00# mmdf test_gpfs
disk disk size failure holds holds free KB free KB
name in KB group metadata data in full blocks in fragments
-------------
--------
--------------------
Disks in storage pool: system
nsd0 71687000 -1 yes yes 59483648 ( 83%) 9440 ( 0%)
nsd2 71687000 -1 yes yes 71371520 (100%) 360 ( 0%)
-------------------
(pool total) 143374000 130855168 ( 91%) 9800 ( 0%)
============= ==================== ===================
(total) 143374000 130855168 ( 91%) 9800 ( 0%)
Inode Information
Number of used inodes: 4041
Number of free inodes: 136247
Number of allocated inodes: 140288
Maximum number of inodes: 140288
As you can notice the restripe didn't rebalance the FS at all, from the docs i read i thought -b will rebalance the blocks evenly to all disks in the FS? I have to note that the data in the FS is 2 big files and that's all (8G and 3G). Am i missing something? Thanks in advance.