rpaul@crow.UUCP (Rodian Paul) (01/17/91)
Hi, I wonder if anyone can help with this quirk. One of our machines, a
4D/240GTX is being used as a front-end to a HDTV RAM recorder, a Grpahica.
The images are passed to the Graphica via the VME board of the 240. I don't
particularly think that tying up a 240 to dump images to a device is a prudent
way to go, but the designers of the Graphica didn't want to consider ethernet.
So according to the Graphica designers (who wrote the driver) we have to use
one of our PowerSeries machines to do the recording.
Another drawback to the situation is that for some reason (I can't get a
decent enough English translation), we have to continue using IRIX 3.2.1 on
that machine.
On to the problem...
Apparently, while a recording is being performed (usually in the backgroud),
if another user is also trying to use the 240, the machine (remotely or
from the console) will practially come to a standstill (except for the
recording process I presume) and several error messages will be logged
(see /usr/adm/SYSLOG excerpt below). Nobody has been able to confim however
if the standstill occurs when the recording process is not running. Due to
time constraints I haven't been able to check this out.
Anyway, am I looking at a probable hardware error or an inferior software
package? Perhaps someone can help point me on the right track.
-------------------------------------------------------------------------------
Here's the output of 'hinv':
4 25 MHZ IP7 Processors
FPU: MIPS R2010A/R3010 VLSI Floating Point Chip Revision: 2.0
CPU: MIPS R2000A/R3000 Processor Chip Revision: 2.0
Data cache size: 64 Kbytes
Instruction cache size: 64 Kbytes
Main memory size: 64 Mbytes
Genlock option installed
GT Graphics option installed
Integral Ethernet controller
Xylogics 754 4-drive SMD disk controller 0: Firmware version 2.7.0
SMD Disk drive: unit 1 on Xylogics controller 0
SMD Disk drive: unit 0 on Xylogics controller 0
Integral SCSI controller WD33C93
Tape drive: unit 7 on SCSI controller 0: QIC 150
Tape drive: unit 6 on SCSI controller 0: 8mm cartridge
-------------------------------------------------------------------------------
Here's the excerpt from /usr/adm/SYSLOG. I've included all messages that were
output at the same time, so some may not be relevant, this pattern is pretty
much the same for most sequences in the SYSLOG file, except that the recovered
drive message isn't repeated too often and each reference is to a different
c/h/s, I assume that the machine practically stalling generates that message.
Jan 14 21:10:44 rabbit grcond[25902]: CIO: 570, VME vector=0x0
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: NOTICE: xyl: time out on iopb
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: WARNING: stray VME interrupt on level 1 at PC=0x8006F570, VME vector=0x0
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: NOTICE: xyl: time out on iopb
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: WARNING: stray VME interrupt on level 1 at PC=0x8006F570, VME vector=0x0
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: NOTICE: xyl: time out on iopb
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: WARNING: stray VME interrupt on level 1 at PC=0x8006F570, VME vector=0xA0
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: NOTICE: xyl: time out on iopb
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: WARNING: stray VME interrupt on level 1 at PC=0x8006F570, VME vector=0xA0
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: NOTICE: xyl: time out on iopb
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: WARNING: stray VME interrupt on level 1 at PC=0x8006F570, VME vector=0x24
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: NOTICE: xyl: time out on iopb
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: WARNING: stray VME interrupt on level 1 at PC=0x8006F550, VME vector=0x24
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: NOTICE: xyl: time out on iopb
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: WARNING: stray VME interrupt on level 1 at PC=0x8006F570, VME vector=0x0
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: NOTICE: xyl: time out on iopb
Jan 14 21:10:44 rabbit grcond[25902]: CIO: xyl0d0: soft ECC corrected. c/h/s = 740/1/65 (recovered)
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: gm-2 (configured for IP7) 1.14+
Jan 14 21:10:44 rabbit grcond[25902]: CIO:
Jan 14 21:10:44 rabbit grcond[25902]: CIO: DEBUG_NOISE at 0x98066498
Jan 14 21:10:44 rabbit grcond[25902]: CIO: Loading PP ucode Version: @(#) PEAPOD 1.2 pp microcode assembler - 6/20/87
Jan 14 21:10:44 rabbit grcond[25902]: CIO: Sat Aug 19 19:28:49 1989 user unknown revision(1.123CLOVER2IP7GT)
Thanks.
-------------------------------------------------------------------------------
phone: +81 (3) 5706-8357
FAX: +81 (3) 5706-8437
email: crow!rpaul@ccut.cc.u-tokyo.ac.jp
ccut.cc.u-tokyo.ac.jp!crow!rpaul