I'll outline some difference between your php and node implementation and share my results
1) Apache runs multiple workers / threads. You'll need to use cluster in your node script to match this. 2) mysql_connect in php does implicit connection pooling. Use "createPool()" in node script My results using cluster/pool and wrk as load generator ( "wrk -t 10 -c 100 -d 100s http://localhost:9615/"; ) - https://gist.github.com/sidorares/5f90ecb853c902786338 php ~500 resp/sec node ~3000 resp/sec On Sunday, 1 March 2015 09:24:17 UTC+11, Anirban Bhattacharya wrote: > > Tom, > Thanks for taking yourbtime going through the code. > I did add connection.createPool as you suggested when I startes this post. > But didn't see much difference so removed. > > You are right i mixed up my two thkughts in one i tried to test with > default of both, in other i was assuming they are having similar > configuration. > > So the failures in apache for 15 mins run is probably due to Apache > started rejecting new proccesses as anymore proceas could maxout runtime > memory. > > I didn't understand the point you said the query size is greater than 1 in > node. What is that? > > Yes I may do pool in both and see again. -- Job board: http://jobs.nodejs.org/ New group rules: https://gist.github.com/othiym23/9886289#file-moderation-policy-md Old group rules: 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 unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/nodejs/1acca32e-9ec8-4842-b419-e4fbf33dd2f5%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
