Your ioc is probably either out of memory or mbufs. Use memShow to check on
memory usage and mbufShow to check on mbuf usage. As far as mbufs go, on our
iocs the max is 1500. If "number of mbufs:" = 1500 and/or "number of times
drained protocols for space:" is greater than 0 you're probably out of mbufs.
This happens to us on an ioc. We believe that workstation processes post
monitors on PVs but then never service them. Buffers on the workstation fill to
a system maximum, then mbufs on the ioc are allocated and filled to the
1500 max. We can identify the workstations involved, have not been able to
associate a socket with a process to figure out what process(es) are involved
(on the workstation). The only way arround the out of mbufs problem is to
either reboot the workstation(s) or the ioc. We reboot the ioc.
Frank
- Navigate by Date:
- Prev:
TCP s_errno_ENOBUFS error in CAS Noboru Yamamoto
- Next:
database race condition? Till Straumann
- Index:
1994
1995
1996
1997
1998
<1999>
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
- Navigate by Thread:
- Prev:
TCP s_errno_ENOBUFS error in CAS Noboru Yamamoto
- Next:
RE: TCP s_errno_ENOBUFS error in CAS Jeff Hill
- Index:
1994
1995
1996
1997
1998
<1999>
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
|