What are you clustering with? Yes, we have seen clusters have problems (kill nodes) when CPU is way over taxed. (like after a hyperswap or when a system with a lot of servers is beat up with scans or backups hitting many servers at once).
You may have to adjust timeouts of things if you expect them not to be dispatched in a "reasonable" time (generally 5 seconds is the default on things that use /dev/watchdog - SLES HAE and TSAMP). We see this on our dev/test systems which run very close to 100% 24x7. We don't see it in prod where we leave reasonable white space. -----Original Message----- From: Linux on 390 Port [mailto:[email protected]] On Behalf Of Victor Echavarry Diaz Sent: Wednesday, February 17, 2016 2:30 PM To: [email protected] Subject: [LINUX-390] Cluster down with high cpu utilization We have a couple of servers in a cluster mode under z/Linux. The clustered servers are on different z/VM LPAR's. To prevent excessive resource usage we have capped many of these servers. The z/VM is 6.3 with 3 IFL's and SLES 11SP4. For some reason some of these clusters shutdown. The Unix group said at the time this happened, one of the LPAR cpu usage is at 300%. My questions are: 1. Could this be possible? Are there any known scenarios that could cause this? 2. If this is true, how can we avoid it? Any specifics steps we should take? Regards, Victor Echavarry System Programmer, EVERTEC LLC WARNING: This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this email in error please delete it immediately. Please note that any views or opinions presented in this email are solely those of the author and do not necessarily represent those of EVERTEC, Inc. or its affiliates. Finally, the integrity and security of this message cannot be guaranteed on the Internet, and as such EVERTEC, Inc. and its affiliates accept no liability for any damage caused by any virus transmitted by this email. ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 ---------------------------------------------------------------------- For more information on Linux on System z, visit http://wiki.linuxvm.org/ ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 ---------------------------------------------------------------------- For more information on Linux on System z, visit http://wiki.linuxvm.org/
