| To: | Ralf Hildebrandt <Ralf.Hildebrandt@xxxxxxxxxx> |
|---|---|
| Subject: | Re: Could not allocate buf during xfs_fsr? |
| From: | Nathan Scott <nathans@xxxxxxx> |
| Date: | Mon, 27 Mar 2006 16:28:03 +1100 |
| Cc: | Justin Piszcz <jpiszcz@xxxxxxxxxxxxxxx>, linux-xfs@xxxxxxxxxxx |
| In-reply-to: | <20060326225754.GF4776@xxxxxxxxxx> |
| References: | <Pine.LNX.4.64.0603260919080.17017@p34> <20060327075716.C753448@xxxxxxxxxxxxxxxxxxxxxxxx> <Pine.LNX.4.64.0603261730040.13535@p34> <20060327085501.A838564@xxxxxxxxxxxxxxxxxxxxxxxx> <20060326225754.GF4776@xxxxxxxxxx> |
| Sender: | linux-xfs-bounce@xxxxxxxxxxx |
| User-agent: | Mutt/1.5.3i |
On Mon, Mar 27, 2006 at 12:57:55AM +0200, Ralf Hildebrandt wrote: > * Nathan Scott <nathans@xxxxxxx>: > > > Hmm, odd. Its trying to allocate 16MG - 4KB, which looks like > > the BUFFERMAX sizing case in xfs_fsr.c... which shouldn't really > > pose a problem. Unless there's a leak or something like that - > > is the resident set size (RSS) column in top(1) for fsr growing > > unbounded? > > Yes it is. > Holy shit, it's growing 16-32 MB per second. UgH! Well, I can't reproduce this locally, it sits at ~16MB resident for me constantly. I'll need you to look into this some more.. valgrind may help. cheers. -- Nathan |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: How many people regularly defrag their XFS filesystems?, Federico Sevilla III |
|---|---|
| Next by Date: | fchown permission check bug, Jakob Østergaard |
| Previous by Thread: | Re: Could not allocate buf during xfs_fsr?, Ralf Hildebrandt |
| Next by Thread: | Re: kernel BUG at fs/direct-io.c:916!, Nathan Scott |
| Indexes: | [Date] [Thread] [Top] [All Lists] |