i'm seeing fairly consistent panics in pool_get with a -current kernel
(not from the snapshot, but roughly same source) running on a slab.

panic: pool_get(mclpl): free list modified: magic=f00; page 0x3592000;
item addr 0x3592000

the trace is 
_Debugger
_panic
_pool_get
_mb8795_rxdmamap_load
_mb8795_rint
_xi_rint
_isrdispatch_autovec
_intrhand_autovec
_mi_switch
_tsleep
_sbwait
_soreceive
_nfs_receive
_nfs_reply
_nfs_request
_nfs_getattr
_nfs_lookup
_lookup
_namei
_sys___stat13
...

anyone else running into this?  it doesn't seem to happen any more
frequently under heavy load, and typical uptime is somewhere around 1 or
2 days when this happens.  nfs server is runing 1.4P/i386.

matt
-- 
matt debergalis <deberg@mit.edu> KB1CTH
finger deberg@ai.mit.edu for PGP key