From: tsh@mrc-lmb.cam.ac.uk
Date: Wed May 14 2003 - 08:10:22 EDT
Hi managers,
TU5.1/PK5
We have a shared-memory problem. Some jobs are refusing to
run because of insufficient shared memory, and when I look
at the situation with ipcs, I see what appears to be a large
number of shared-mem segments which I cant attribute to any
running process. Any ideas? Can I restore order without
a reboot?
e.g. ipcs-a | grep aml2
m 18 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 80904 80904 5:22:00 5:22:00 5:22:00
m 19 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 150504 150504 5:24:03 5:24:03 5:24:03
m 20 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 137895 137895 5:25:01 5:25:01 5:25:01
m 21 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 159606 159606 5:25:20 5:25:20 5:25:20
m 22 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 148030 148030 5:25:53 5:25:53 5:25:53
m 23 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 161370 161370 5:26:27 5:26:27 5:26:27
m 24 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 159741 159741 5:39:50 5:39:50 5:39:50
m 451 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 307200 469549 469549 6:20:43 6:20:43 6:20:43
m 1093 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 138904 138904 4:20:35 4:20:35 4:20:35
m 70 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 309547 309547 4:21:12 4:21:12 4:21:12
m 71 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 174171 174171 4:22:41 4:22:41 4:22:41
m 72 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 130901 130901 4:23:16 4:23:16 4:23:16
m 73 0 --rw-rw-rw- aml2 aml2 aml2 aml2 0 1228800 241020 241020 4:23:51 4:23:51 4:23:51
But aml2 has no processes in the system.
Cheers,
Terry.
Terry Horsnell (tsh@mrc-lmb.cam.ac.uk)
I.T. Manager
Medical Research Council
Lab of Molecular Biology
Hills Road
CAMBRIDGE CB2 2QH
U.K.
Phone: +44 (0)1223 248011
Fax: +44 (0)1223 213556
This archive was generated by hypermail 2.1.7 : Sat Apr 12 2008 - 10:49:18 EDT