|
From: Steve B. <st...@te...> - 2007-10-08 17:36:37
|
Have you disabled the Nagle Algorithm at the TCP level (using TCP_NO_DELAY)? > I'm building an arbitrage system, so responding to FIX messages quickly is > essential. I don't need to process hundreds of messages a second, but I > need to respond to the messages that arrive very quickly. > > > > I'm new to QuickFix, so my first test was to write a QFJ application that > just logs into the exchange with my credentials and lets QFJ handle the > heartbeat messages. Once heartbeats are established, I used WireShark to > capture the network traffic so I could see how long it takes to respond to > a > heartbeat from the exchange. The network capture data shows that QFJ's > best > time to respond to a heartbeat is about 1.5 ms, and some of the times are > much higher (seconds). > > > > I need to respond to all messages in sub-millisecond times, so I'm curious > how to improve these times. I've done the following: > > + Log level is WARN, so nothing is being logged > > + Using the MemoryStore for messages > > + Using the SocketInitiator > > > > Any suggestions on improving these times would be appreciated. Or if QFJ > is > not designed to handle these requirements, I'd be interested in knowing > that > as well. > > > > Thanks, > > Ted > > ------------------------------------------------------------------------- > This SF.net email is sponsored by: Splunk Inc. > Still grepping through log files to find problems? Stop. > Now Search log events and configuration files using AJAX and a browser. > Download your FREE copy of Splunk now >> > http://get.splunk.com/_______________________________________________ > Quickfixj-users mailing list > Qui...@li... > https://lists.sourceforge.net/lists/listinfo/quickfixj-users > |