Hi, I'm stress testing a simple GAE-Java application that serves static images: nothing is generated dynamically. The test client has multiple threads (up to 100) that request randomly-selected images. As the number of threads in the client gets to 50 and above I can achieve hundreds of requests per second - but many of the requests fail with 503 (service not available) errors. The errors come in blocks: a whole bunch of requests will fail with 503, then I'll get a lot of successes, then another batch of failures.
Is this likely to be because I'm hitting the 500 requests per second limit (http://code.google.com/appengine/docs/quotas.html#Requests)? If so is there any way to change this behaviour so that, as the limit is approached, clients see higher latency rather than errors? Also, I've noticed that if I run the test client on a different machine I don't see the errors. Could GAE be blocking my original test client, having noticed a large number of requests from the same IP address? Does GAE have this sort of per-client filter? Thanks for any help, Jon -- You received this message because you are subscribed to the Google Groups "Google App Engine for Java" group. To post to this group, send email to google-appengine-j...@googlegroups.com. To unsubscribe from this group, send email to google-appengine-java+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/google-appengine-java?hl=en.
