fsck_ufs out of swapspace

[Paul Mather]

On Dec 17, 2011, at 3:36 PM, Michiel Boland wrote:

> FreeBSD 9.0-PRERELEASE locked up while into some heavy I/O and failed to shut down properly, so I had to power-cycle. After it came back up it said
> 
> Starting file system checks:
> ** SU+J Recovering /dev/ada0a
> ** Reading 33554432 byte journal from inode 4.
> swap_pager: out of swap space
> swap_pager_getswapspace(16): failed
> pid 67 (fsck_ufs), uid 0, was killed: out of swap space
> fsck: /dev/ada0a: Killed: 9
> Script /etc/rc.d/fsck running
> Unknown error; help!
> ERROR: ABORTING BOOT (sending SIGTERM to parent)!
> 
> The only way to continue was to do a full fsck (with no journal)
> 
> This is a Sun Blade 100 (sparc64) with 768M of RAM.
> So the fsck is taking up all of this? That can't be right.
> 
> What can I do to troubleshoot this further?


FWIW, I had this happen to me several weeks ago on FreeBSD/powerpc64 9-CURRENT.  I had to get the machine up and running so I simply abandoned use of SU+J and went back to using just UFS+SU.  (Not very helpful, I know, but there you go.)  I figure it is likely to be some kind of endianness problem in the SU+J code, given the lack of complaints on FreeBSD/i386 and FreeBSD/amd64.

Cheers,

Paul.

PS: The system I was using is an Apple Xserve G5 with 4 GB of RAM and 5 GB of swap space.  As you say, surely fsck can't be using that much memory...