- From: Mike Cowlishaw <mfc@vnet.ibm.com>
- Date: Sun, 12 Nov 95 19:04:17 GMT
- To: http-wg%cuckoo.hpl.hp.com@hplb.hpl.hp.com
Well, it looks as though enough clients are around for this to get interesting. For example, my server is now showing around 1% more requests than transactions; all of the excess must be requests on persistent connections. I've also noticed a measureable increase in throughput and an average response time drop. It's interesting to note that the number of packets transmitted has increased slightly (per request) from before; doubtless because persistent connections require that TCPIP_NODELAY be set. Has anyone done any simulation of this side-effect? (For live statistics on some of the above, try http://www2.hursley.ibm.com/!statistics) Mike Cowlishaw IBM Fellow
Received on Sunday, 12 November 1995 11:12:01 UTC