On Wed, Jan 25, 2012 at 10:34:54AM -0600, Eric Sandeen wrote:

On 1/24/12 11:19 PM, Amit Sahrawat wrote:

quoted

In XFS we can write parallel (i.,e we can make use of allocation
groups for writing process). If the files are kept in individual
directories, there is a possibility that first the blocks for that
files be used from individual allocation groups. If I start ‘4’
writing process(cp 100MB_file /<dirnum>/) – after writing is finished
– if I check the bmap – it does shows that initial allocation was from
individual allocation groups.
Even though in Ext4 also we do have groups – but I am not able to get
behavior similar to XFS.
If I check the file extents – the extents are in mixed form, the
allocation pattern is also very fragmented.

Please share more on this. Also, if there is a possible exact test
case to check for parallel writes support.

It seems that you are asking more about allocation policy than parallelism
in general?  With either filesystem, you could use preallocation to wind
up with more contiguous files when you write them in parallel, though
that requires some idea of the file size ahead of time.

ext4 doesn't have that exact dir::group heuristic that xfs uses,
but it does have other mechanisms and heuristics to try to get good
file and directory layout.

XFs has different allocation policies according to mount options
used.  inode32 (default for > 1TB), inode64 (default for <1TB) and
filestreams. Each will give you different layouts for the same test
depending on the size of your filesystem and the amount of free
space you have available in it.

If XFS does what you want, then use it. There is no good reason for
trying to make ext4 do everything XFS does because it simply can't.
Especially when it comes to allocation strategies and policies...

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs