Answer to a little bit old question...

> I'm seeing strange behavior where requests are _much_ faster when routed 
through a proxy (in this case the Fiddler diagnostic tool). Note that this is 
not a caching proxy, and all the requests are POSTs anyway, so I don't think 
that is the explanation. If I run the app with an HTTP_PROXY environment 
variable defined it is much faster than without - the code is the same in both 
cases. I've instrumented the code as well to display the progression of 
requests, and it appears to be the same in both cases except the proxied 
requests return much faster.

> I'd love to have the same performance regardless of whether or not a proxy is 
used, so is there something I'm potentially missing that might speed up the 
non- proxied case as well?

Note that Fiddler is re-using old connections, so this might be an explanation for the speed-up.
You can see (by using curl debug function) if when using direct connection - each request creates its own connection or there is connection re-use.

Just my 2 cents.

Yehezkel

-------------------------------------------------------------------
List admin: http://cool.haxx.se/list/listinfo/curl-library
Etiquette: http://curl.haxx.se/mail/etiquette.html
Received on 2013-06-18