[Linux-cluster] GFS2 and fragmentation
rpeterso at redhat.com
Wed Aug 8 12:50:51 UTC 2012
----- Original Message -----
| Hi All,
| We have a RedHat 6.2 cluster with 4 nodes using GFS2 for shared
| filesystems. One of the filesystems we need to share is
| /var/spool/mail. In general, with recent upgrades and improvements
| GFS2, which has been working really, really well. We're starting to
| some significant fragmentation on files in the filesystem, though,
| after recreating the filesystem after the RHEL 6 upgrade. My
| understanding was that there were fixes in RHEL 6 that made
| defragmentation un-(or less?) necessary, but we're seeing a
| increase in the amount of fragmentation since the upgrade. By the
| we're seeing numbers in the range of 4,000-6,000 extents/GB for some
| these files, which seems a bit large.
| So, I've got two questions:
| 1. At what point should we be worried about the number of
| 2. Are there plans for a defragmentation tool?
| -- scooter
GFS2 has never really managed file fragmentation, so it's not a new problem.
Simultaneous writes to GFS2 will cause fragmentation.
There's nothing different in 6.2 regarding file fragmentation from any
other release of the kernel, so perhaps you can give us more details
about what you're seeing?
Having said that, Red Hat's GFS2 team HAS been actively developing code in
the GFS2 kernel code to reduce file fragmentation. Many of these patches
have already been sent upstream (to the kernel.org kernel), and we have
working prototypes for 6.4. Here's an upstream link to one of our major
defrag patches (there are others related to it scheduled for the next
We currently don't have any plans for defrag tool for GFS2. In theory, you
can always copy the data from an old file system to a new one using this
new kernel code, and it should be less fragmented.
Red Hat File Systems
More information about the Linux-cluster