Re: [reiserfs-list] Disk fragmentation and performance degradation caused by NFS/ preallocation code interaction

2001-10-26 Thread Eric Whiting
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*512M

Re: [reiserfs-list] Disk fragmentation and performance degradation caused by NFS/ preallocation code interaction

2001-10-25 Thread Chris Mason
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

Re: [reiserfs-list] Disk fragmentation and performance degradation caused by NFS/ preallocation code interaction

2001-10-25 Thread Anne Milicia
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 allocates

Re: [reiserfs-list] Disk fragmentation and performance degradation caused by NFS/ preallocation code interaction

2001-10-25 Thread Chris Mason
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).