On Sat, 2008-08-02 at 19:13 -1000, Tim Newsham wrote:
My measurements show that a simple dummy server (accept, forkio, recv byte) handles roughly 7500 requests/connects per second, the server/client that do real messages do about 4500 req and connections per second. If all requests are on the same connection one after another it does about 13500 requests/second. For comparisons, a C ping-pong server does about 3600/second if it has to fork for each new connection/request, and about 35000/sec if its all on the same connection. So it seems at least competitive with a forking C server. I havent tested threaded C servers.
What kind of performance do you actually need? Can your network connection actually sustain the bandwidth of your synthetic benchmarks? For reference, I've got a demo HAppS-based server which handles reasonably high load pretty well I think: (tested using apache-bench, loopback interface, amd64 @ 2.2GHz) With cached content 450k: with 1 concurrent client: 760 requests per second ~1ms latency 34Mb/s with 100 concurrent clients: 1040 requests per second ~90ms latency 46Mb/s on a non-cached generated-on-demand 3k page: with 1 concurrent client: 280 requests per second ~4ms latency 900Kb/s bandwidth with 100 concurrent clients: 240 requests per second ~400ms latency 750Kb/s bandwidth Using http keep-alive boots requests per sec by ~20% Obviously this is testing with a loopback network. My point is, it's serving at a rather higher rate than most real network connections I could buy (except local ethernet networks). Duncan