On Fri, 11 Mar 2005, Nick Lewycky wrote:
is a branch called "collapsed forwarding"[4], but it currently only applies to accelerator setups. It could perhaps be adapted.
It appliest equal to all setups. It was designed for accelerator setups as there is where this is most needed, but is not limited to acceleration.
That's good news.
The drawback is that latency is increased significantly on frequently used non-cacheable content as the second client needs to wait for the first reply to arrive before Squid knows the reply can not be cached.
That's an interesting problem. So for a non-cacheable resource, n hits from the client must correspond to n hits to the server? Otherwise you could send the result to both clients, yes?
What's keeping it from being landed on the Squid trunk, perhaps with a configuration option? I've been considering rebasing my own branch off of it, I just haven't gotten around to trying it out. I was assuming it was unfinished.
Nick
