ZFS repeatable reboot 8.0-RC1

[grarpamp]

Hi.

I'm running i386 on i386, single P4 cpu, 1GiB RAM.
SiI 3114 -> SATA [single disk] -> GELI [AES-128] -> ZFS [sha256]
Straight RELENG_8 as of cvsup Oct 12 14:49:00 aka 8.0-RC1 plus.
ZFS pool is at v13, ZFS fs is at v3.
Hardware seems stable.
The only modification to config defaults is:
 loader.conf.local: vfs.zfs.arc_max=100663296

After boot -v, geli, zpool import, xf86, browser, etc my mem looks like:
 Mem: 33M Active, 22M Inact, 105M Wired, 676K Cache, 37M Buf, 827M Free
When putting load on ZFS it usually grows to about:
 Mem: 95M Active, 22M Inact, 302M Wired, 468K Cache, 37M Buf, 569M Free
Ls -l in one of the dirs takes 10min plus and I get:
  PID USERNAME PRI NICE   SIZE    RES STATE    TIME   WCPU COMMAND
   11 root     171 ki31     0K     8K RUN     21:24 47.27% idle
 1092 user      76    0 77328K 76116K zio->i   3:25 37.89% ls
  802 root      -8    -     0K     8K geli:w   1:42  8.98% g_eli[0] ad6
    9 root      -8    -     0K   128K arc_re   0:23  4.88% {arc_reclaim_thre}
I did not watch these during rm.

I have 1 parent dir holding 4 subdirs. The file count in each subdir
is respectively: 256363, 254086, 256017, 178054
Two thirds of files are about 14KiB in size, not many are more than
a few MiB nor less than 1KiB though a third are 1 byte.

I issue rm -r <parent_dir> and after maybe 30 seconds the machine
reboots. No syslog, panic or console messages. Dmesg from the prior
boot is still present in ram to prove kernel didn't emit any message.
memtest86 passes. There are maybe 10 seconds of complete GUI hangup
before the reboot occurs.

I also see it when make release'ing. Usually during what I _think_
is distributeworld or rolling up the tarballs under /R.

This is a big repeatable problem. How can I debug or fix it? Can
someone else create some mega sized dirs as above and replicate?

Thanks.