Re: [Ganglia-developers] hsflowd for Windows + Ganglia webfrontend
Hi Neil: On Thu, Feb 10, 2011 at 8:52 PM, Neil McKee neil.mc...@inmon.com wrote: OK, I cleared out everything under /var/lib/ganglia/rrds/. Now I see the problem. In the short term I guess gmond/sflow.c could just submit zeros for the missing metrics instead of leaving them out altogether(?) However in the long term it would seem more elegant to fix this in the place where the RRD is constructed. After all, for most of these metrics posting a value of 0 is just plain wrong. When the value is really dunno or not applicable or undefined then leaving it out seems more correct. I've changed my mind after hearing other people's thoughts on the matter. The correct fix should be in the frontend code. I'm already working on it for cpu_report and mem_report. However, it would be tricky for the load_* metrics. Hopefully we could reach a consensus on it soon and be able to report load metrics in hsflowd under Windows. I hope you didn't spend too much time on the patch for submitting zeros for missing metrics :) Thanks, Bernard -- The ultimate all-in-one performance toolkit: Intel(R) Parallel Studio XE: Pinpoint memory and threading errors before they happen. Find and fix more than 250 security defects in the development cycle. Locate bottlenecks in serial and parallel code that limit performance. http://p.sf.net/sfu/intel-dev2devfeb ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] hsflowd for Windows + Ganglia webfrontend
Hi Neil: On Fri, Feb 11, 2011 at 2:26 PM, Neil McKee neil.mc...@inmon.com wrote: It might be helpful to have commit privileges for minor bugfixes, yes. Although I wouldn't use it for bigger changes that require consensus. Yeah, that would be the idea. Bigger changes should be discussed prior to being checked-in. An alternative approach would be to create a separate branch to work on the code until it's stable enough to be merged back into trunk. I'm working on a bigger patch that will add an sflow { } configuration block so we can have options to control the following: - the sflow udp port - whether to submit 0s rather than leave undefined metrics out altogether (as a workaround for that issue with the CPU/mem charts for Windows) - whether to ignore the hostname that comes with with host-sflow so that gmond will do it's own reverse lookup (to get the FQDN instead) - whether to submit the extra metrics that host-sflow sends for physical servers - whether to submit the extra metrics that host-sflow sends for virtual servers Should have it ready for review later this afternoon. Once the sFlow HTTP and memcached counter-blocks are finalized then we could quickly add support for those metrics too. More input on those would be very welcome: http://blog.sflow.com/search/label/HTTP http://blog.sflow.com/search/label/Memcache I know we've talked briefly about this before, but do you consider this a major change in the code? I would really like to create a release 3.2 branch from trunk soon. We will then work on stabilizing the code for eventual release as 3.2.0. So I guess my question to you is is this material for 3.2.0 or a future release? Thanks, Bernard -- The ultimate all-in-one performance toolkit: Intel(R) Parallel Studio XE: Pinpoint memory and threading errors before they happen. Find and fix more than 250 security defects in the development cycle. Locate bottlenecks in serial and parallel code that limit performance. http://p.sf.net/sfu/intel-dev2devfeb ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] hsflowd for Windows + Ganglia webfrontend
Hi Neil: On Tue, Feb 15, 2011 at 11:43 AM, Bernard Li bern...@vanhpc.org wrote: I've changed my mind after hearing other people's thoughts on the matter. The correct fix should be in the frontend code. I'm already working on it for cpu_report and mem_report. However, it would be tricky for the load_* metrics. Hopefully we could reach a consensus on it soon and be able to report load metrics in hsflowd under Windows. Code committed: https://sourceforge.net/apps/trac/ganglia/changeset/2477 Now we just need the load_* metrics from hsflowd Windows and we're in business ;-) Thanks, Bernard -- The ultimate all-in-one performance toolkit: Intel(R) Parallel Studio XE: Pinpoint memory and threading errors before they happen. Find and fix more than 250 security defects in the development cycle. Locate bottlenecks in serial and parallel code that limit performance. http://p.sf.net/sfu/intel-dev2devfeb ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] Vertical label in metric.php
Hi Jesse: On Fri, Feb 11, 2011 at 7:30 PM, Jesse Becker becker...@mail.nih.gov wrote: As I recall, it forces the graphs within the images to align between images that include labels, and those that do not. One of Ganglia's strengths is allowing for easy data/time correlations. This is easy only if the graphs actually have the same timescale (generally true), and line up appropriately (which this patch tries to help with). At least, that how I remember it. As far as I can tell, if we revert the code back to: $rrdtool_graph['vertical-label'] = ' '; the alignment is the same as if there were a label. You can test this by adding 'vl=blah' at the end of the image URL and compare it with the graph having ' ' as vertical-label. Could you please confirm? Thanks! Cheers, Bernard -- The ultimate all-in-one performance toolkit: Intel(R) Parallel Studio XE: Pinpoint memory and threading errors before they happen. Find and fix more than 250 security defects in the development cycle. Locate bottlenecks in serial and parallel code that limit performance. http://p.sf.net/sfu/intel-dev2devfeb ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] gmond not connecting to gmetad
Hi Joseph: For future reference, this mailing-list is for developer discussions. For general questions, please use the ganglia-general mailing-list: https://lists.sourceforge.net/lists/listinfo/ganglia-general On Sat, Feb 12, 2011 at 11:46 PM, Joseph joseph@sc.com wrote: With this I have also installed gmond on 114 nodes separately. However, 92 of these nodes are able to establish connection with gmetad while the remaining 22 nodes have gone MIA. gmond is definitely running but these 22 nodes just simply refused to connects up with the gmetad. The gmond config setting are all the same default setting used across all nodes and the only thing I can guess of is perhaps the difference in the IP subnet? 92 nodes are on '10.192.64.XX' and '10.192.65.XX' whilst the others of the 22 nodes are on '10.192.84.XX' and '10.192.85.XX'. If that is the case, may I know what is the solution to this? Chances are you need to enable multicast routing between the two subnets in your router. Alternatively, you can configure Ganglia using unicast. Good luck. Cheers, Bernard -- The ultimate all-in-one performance toolkit: Intel(R) Parallel Studio XE: Pinpoint memory and threading errors before they happen. Find and fix more than 250 security defects in the development cycle. Locate bottlenecks in serial and parallel code that limit performance. http://p.sf.net/sfu/intel-dev2devfeb ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers