Am Montag, 12. August 2013 19:03:27 UTC+2 schrieb Ben Noordhuis: > > On Mon, Aug 12, 2013 at 6:05 PM, Jens Himmelreich > <jens.him...@gmail.com <javascript:>> wrote: > > Hi, > > > > I have a node-server between an nginx-webserver (static content) and an > > varnish. > > Behind the varnish are two application-server for search and > cart-hosting. > > The > > node-machine has 4 cores. Every machine has load 0.1 except the > > node-machine. > > It has a load of 4.0. The node-application is an express-application > running > > in > > a node-cluster with 4 workers. http.globalAgent.maxSockets is set to > 400. > > Does anyone know why the load is high? > > Because it's doing a lot? Your post is too light on details to really > make informed suggestions. Try profiling your application to see > where it's spending its time. >
I see. I had to do a profiling. It's a little bit complecated, because we use coffeescript. The --nodejs --prof Parameters won't went to the workers. The global coffee is used, which I could instrument. I tried it without the cluster - to get a quick result for --prof - and I see that the load is going to 0.02. So it seems to be a problem of the cluster. (I know, I will do the profiling.) Are there experiences with a cluster- load which rise to 1 per cpu? best regards jens -- -- Job Board: http://jobs.nodejs.org/ Posting guidelines: https://github.com/joyent/node/wiki/Mailing-List-Posting-Guidelines You received this message because you are subscribed to the Google Groups "nodejs" group. To post to this group, send email to nodejs@googlegroups.com To unsubscribe from this group, send email to nodejs+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/nodejs?hl=en?hl=en --- You received this message because you are subscribed to the Google Groups "nodejs" group. To unsubscribe from this group and stop receiving emails from it, send an email to nodejs+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/groups/opt_out.