We detect it when the website stops responding (as described on ganglia-developers list).
Then it is 'fixed' by indeed simply restarting gmetad. As of January 2013, SARA has a new name: SURFsara. ing. Ramon Bastiaans - Senior Systems Programmer - Cluster Computing | Operations, Support & Development | SURFsara | Science Park 140 | 1098 XG Amsterdam | T +31 (0)20 592 30 00 | ramon.bastia...@surfsara.nl | www.surfsara.nl | On 20 apr. 2013, at 17:22, Vladimir Vuksan <vli...@veus.hr> wrote: > There are reports of similar behavior. Do you simply restart gmetad when this > happens ? How do you detect hanging/crashing ? > > Vladimir > > On Fri, 19 Apr 2013, Ramon Bastiaans wrote: > >> The gaps in our ganglia graphs are caused by gmetad incidentally >> hanging/crashing due to a XML Parse error. >> >> We use a ramdisk which is working good for our setup. >> >> - Ramon >> >> As of January 2013, SARA has a new name: SURFsara. >> >> ing. Ramon Bastiaans - Senior Systems Programmer - Cluster Computing >> | Operations, Support & Development | SURFsara | Science Park 140 | 1098 XG >> Amsterdam | T +31 (0)20 592 30 00 | ramon.bastia...@surfsara.nl | >> www.surfsara.nl | >> >> >> >> >> On 19 apr. 2013, at 15:57, David Chin <chi...@wfu.edu> wrote: >> >>> Hello, all: >>> >>> I just got a ganglia installation installed on RHEL6 -- ganglia 3.5.0 with >>> ganglia-web 3.5.7. >>> >>> Things seem to be working fine, except that I get intermittent gaps in the >>> data. My installation is private, but you can see a similar thing here at >>> SURFsara's installation in the month view: >>> >>> >>> https://ganglia.surfsara.nl/?r=month&cs=&ce=&m=load_one&s=by+name&c=LISA+Cluster&h=&host_regex=&max_graphs=0&tab=m&vn=&sh=1&z=small&hc=4 >>> >>> In a previous installation, I was able to get around this by using a RAM >>> filesystem. However, the amount of data now precludes me from doing it. >>> (Previously, the RRD data only took up about 2GB, and it's now about 25GB.) >>> >>> I also get spurious spikes, where it looks like the data goes to MAX_FLOAT >>> or something like that. >>> >>> I was wondering if anyone has seen either of these behaviors, and if they >>> have suggestions for dealing with them. >>> >>> Thanks, >>> Dave >>> >>> >>> -- >>> David Chin, Ph.D. >>> chi...@wfu.edu High Performance Computing Systems Analyst >>> Office: +1.336.758.2964 Wake Forest University >>> Mobile: +1.336.608.0793 Winston-Salem, NC >>> Email-to-txt: 3366080...@mms.att.net Google Talk: chi...@wfu.edu >>> Web: http://users.wfu.edu/chindw/ http://linuxfollies.blogspot.com/ >>> https://plus.google.com/108169173177119739731/about >>> ------------------------------------------------------------------------------ >>> Precog is a next-generation analytics platform capable of advanced >>> analytics on semi-structured data. The platform includes APIs for building >>> apps and a phenomenal toolset for data science. Developers can use >>> our toolset for easy data analysis & visualization. Get a free account! >>> http://www2.precog.com/precogplatform/slashdotnewsletter_______________________________________________ >>> Ganglia-general mailing list >>> Ganglia-general@lists.sourceforge.net >>> https://lists.sourceforge.net/lists/listinfo/ganglia-general >> >>
smime.p7s
Description: S/MIME cryptographic signature
------------------------------------------------------------------------------ Try New Relic Now & We'll Send You this Cool Shirt New Relic is the only SaaS-based application performance monitoring service that delivers powerful full stack analytics. Optimize and monitor your browser, app, & servers with just a few lines of code. Try New Relic and get this awesome Nerd Life shirt! http://p.sf.net/sfu/newrelic_d2d_apr
_______________________________________________ Ganglia-general mailing list Ganglia-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-general