| To: | Alberto Nava <beto@xxxxxxxxxxx> |
|---|---|
| Subject: | Re: direct-IO writes strange behavior |
| From: | Steve Lord <lord@xxxxxxxx> |
| Date: | 24 Nov 2003 14:36:24 -0600 |
| Cc: | linux-xfs@xxxxxxxxxxx |
| In-reply-to: | <3FC25E14.80001@xxxxxxxx> |
| Organization: | |
| References: | <3FBECF7E.6010509@xxxxxxxx> <3FBFEF6A.3000609@xxxxxxxxxxx> <3FC0EFEA.5070108@xxxxxxx> <3FC24602.5010904@xxxxxxxxxxx> <3FC25E14.80001@xxxxxxxxxxx> |
| Reply-to: | lord@xxxxxxxx |
| Sender: | linux-xfs-bounce@xxxxxxxxxxx |
On Mon, 2003-11-24 at 13:37, Alberto Nava wrote: > Alberto Nava wrote: > > > > >> This may be an interaction with the unwritten extent handling code. > >> Try this on a file system made with the mkfs option -d unwritten=0. > >> > > Thanks. > > > > I tried it but made not difference. We got an unmapped bh and reverted > > to buffered-IO. > opps.... It does work. I didn't preallocate enough space for the > file as I was testing it. It works great now :-). > > Are there any concerns when setting unwritten=0? unwritten = 0 was the only supported mode on linux (and originally irix) for a long time. The issue was that using preallocation meant you could go read old data off the disk. On linux now an unwritten=0 filesystem should restrict the preallocation calls to root. Steve -- Steve Lord <lord@xxxxxxx> |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: direct-IO writes strange behavior, Alberto Nava |
|---|---|
| Next by Date: | XFS and LBD patch on 2.4.20 or 2.4.22, Gustavo Rincon |
| Previous by Thread: | Re: direct-IO writes strange behavior, Alberto Nava |
| Next by Thread: | Re: direct-IO writes strange behavior, Nathan Scott |
| Indexes: | [Date] [Thread] [Top] [All Lists] |