I have a reproducible hang with kswapd in the run queue, everything else =
is
in an i/o wait. The load average is climbing.

Using either a highpoint RR2340 or an LSI8888ELP PCIe-8 lane controller,
I max out the write rate at between 900MB/Sec to 1.1GB/Sec into
16 seagate 500GB ES series drives. Eventually the system locks up
with kswapd0 getting 100% of one CPU. kswapd1 is not running.

The system is a SuperMicro H8DM3-2 (or an H8DMi-2) with 2222SE or 2216=20
opterons,
16GB of RAM. 2.6.22-5, 2.6.21 and 2.6.23-rc7 and 2.6.23-rc9 all lock up.
2.6.20 does not, but it also runs 200MB/Sec slower in write rates.
The base O/S is Centos 5.0
I can patch in KDB and look around (did this for 2.6.22-5) but I'm
not sure what to look for in kswapd to see what got lost to keep
the system locked up. With eralier kernels, the system needs a reset
button to recover. With 2.6.23-rc9 I was left with enough to get the=20
following
ps, top, and /proc/meminfo data

Hints anyone (please) as to how to slay this dragon?

Berkley


--=20

// E. F. Berkley Shands, MSc//

** Exegy Inc.**

349 Marshall Road, Suite 100

St. Louis , MO  63119

Direct:  (314) 218-3600 X450

Cell:  (314) 303-2546

Office:  (314) 218-3600

Fax:  (314) 218-3601

=20

The Usual Disclaimer follows...
=20
This e-mail and any documents accompanying it may contain legally =
privileged and/or confidential information belonging to Exegy, Inc. Such =
information may be protected from disclosure by law. The information is =
intended for use by only the addressee. If you are not the intended =
recipient, you are hereby notified that any disclosure or use of the =
information is strictly prohibited. If you have received this e-mail in =
error, please immediately contact the sender by e-mail or phone =
regarding instructions for return or destruction and do not use or =
disclose the content to others.