No -- bonnie doesn't need 1G ram -- bonnie needs to test using a file
much larger than available ram to ensure that bonnie actually writes
something to disk and not just to the VFS/buffercache layer.
eric
Bo Moon wrote:
>
> Hi,
>
> What does 2*RAM mean?
> His box has 512M RAM, so he need 2*512
Hi,
What does 2*RAM mean?
His box has 512M RAM, so he need 2*512M for Bonnie?
Why?
Thanks,
Bo
Chris Mason wrote:
>
> > Linux box is 512M RAM. The files fit in buffer cache. I run the bonnies
> > of size n+50. Results are fairly constant until I hit about 300M. Then
> > they seem to fall off
On Thursday, October 25, 2001 03:06:27 PM -0600 Eric Whiting <[EMAIL PROTECTED]> wrote:
> Here is some feedback of 2.4.13+the patch from Chris. Two tests: local
> fs and NFS. I still see odd things happening at files above 300G. This
> is reiserfs formatted -v2 (3.6) with a default mount (tail)
Here is some feedback of 2.4.13+the patch from Chris. Two tests: local
fs and NFS. I still see odd things happening at files above 300G. This
is reiserfs formatted -v2 (3.6) with a default mount (tail).
Linux box is 512M RAM. The files fit in buffer cache. I run the bonnies
of size n+50. Results
Chris Mason wrote:
>
> Anyway, Anne, could you please take a look and make sure this still
> improves your performance? I think the odd results you got for 2.4.12
> before were probably due to actual fragmentation against prellocated
> blocks from other files. With a single writer, 2.4.13 alloc
On Tuesday, October 23, 2001 02:19:57 PM -0400 Anne Milicia
<[EMAIL PROTECTED]> wrote:
[ great analysis of fragmentation problem + fix ]
>
> So, my question is can journal_mark_freed() be safely skipped when
> reiserfs_free_block() is called by __discard_prealloc()? Can you think
> of any pr