On Fri, Feb 19, 2010 at 11:08:41AM -0800, Bernard Li wrote: > On Thu, Feb 18, 2010 at 7:41 PM, Scott Dworkis <[email protected]> wrote: > > > i tried the tmpfs thing (actually /dev/ramN), but decided syncing back and > > forth to disks to preserve data across reboots was suboptimal. never tried > > rrdcached. > > Yeah that's one of the downside of the tmpfs route. Definitely give > rrdcached a try and report back your experiences.
There is also the option to tell the fs to push writes out less frequently, which results to far less IO traffic. For ext3 mounting with something like "noatime,data=writeback,commit=60" is a good start. The likelihood of data/filesystem corruption after a power failure is most likely higher but on the other hand unlike rrdcached you still get access to the latest data when you read an rrd file. Cheers, Kostas Georgiou ------------------------------------------------------------------------------ Download Intel® Parallel Studio Eval Try the new software tools for yourself. Speed compiling, find bugs proactively, and fine-tune applications for parallel performance. See why Intel Parallel Studio got high marks during beta. http://p.sf.net/sfu/intel-sw-dev _______________________________________________ Ganglia-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/ganglia-general
