| To: | pcp <pcp@xxxxxxxxxxx> |
|---|---|
| Subject: | pcp updates - patch to handle missing node-cpu mapping info on single CPU systems |
| From: | Mark Goodwin <mgoodwin@xxxxxxxxxx> |
| Date: | Thu, 22 Jan 2015 11:09:41 +1100 |
| Delivered-to: | pcp@xxxxxxxxxxx |
| User-agent: | Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.3.0 |
Debian verge 32bit systems (and possibly others) either don't fake a numa node on single CPU systems, or don't export the node-cpu mapping info in /sysfs. This was causing some buffer overrun issues found by valgrind when hinv.nnode is zero but it was assumed to be at least one on all systems. I haven't committed this because I don't have a debian/i686 system handy to test it on. I've only tested it on a fedora/4cpu/1node system.
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [pcp] pernode metrics still wrong on 1 CPU systems, Mark Goodwin |
|---|---|
| Next by Date: | ActiveMQ PMDA: Caching + some other fixes, Ryan Doyle |
| Previous by Thread: | pernode metrics still wrong on 1 CPU systems, Ken McDonell |
| Next by Thread: | Re: [pcp] pcp updates - patch to handle missing node-cpu mapping info on single CPU systems, Ken McDonell |
| Indexes: | [Date] [Thread] [Top] [All Lists] |
