Comments on: AOT and JVM http://blog.juma.me.uk/2008/10/08/aot-for-java/ Thu, 14 Jul 2011 17:33:59 +0000 hourly 1 http://wordpress.com/ By: ArtemGr http://blog.juma.me.uk/2008/10/08/aot-for-java/#comment-47 Wed, 15 Oct 2008 10:04:46 +0000 http://ijuma.wordpress.com/?p=27#comment-47 “If you do find your self restarting it on a regular basis, something is wrong with your app, your config, your hardware, or whatever.” – true, for example, I might need to restart it because the JVM run out of perm space or because there is a security hole in the JVM which must be fixed ASAP or because I need to update one of the libraries or for million other reasons. Welcome to real world.

]]> By: Dmitry Leskov http://blog.juma.me.uk/2008/10/08/aot-for-java/#comment-38 Mon, 13 Oct 2008 08:12:58 +0000 http://ijuma.wordpress.com/?p=27#comment-38 Well, I agree that the convenience of developers should be considered, but once your app is in production environment, you should not need to restart the server. If you do find your self restarting it on a regular basis, something is wrong with your app, your config, your hardware, or whatever.

]]> By: ArtemGr http://blog.juma.me.uk/2008/10/08/aot-for-java/#comment-34 Thu, 09 Oct 2008 11:54:20 +0000 http://ijuma.wordpress.com/?p=27#comment-34 And Tomcat isn’t the best representative for this restart hit, it is merely a layer. If it is a layer over a C++ database, then okay, but if it is a layer over some heavy Java things, like Velocity template parsers and Berkley DB-JE, then the hit is quite large.

]]> By: ArtemGr http://blog.juma.me.uk/2008/10/08/aot-for-java/#comment-33 Thu, 09 Oct 2008 11:47:56 +0000 http://ijuma.wordpress.com/?p=27#comment-33 “Tomcat startup time is irrelevant for web app users and, to a large extent, web app developers,” – not true. Any restart gives a load hit: if you have a 200 request/second server, then the longer it restarts, the more the chance it won’t start it all, instead crumbling under the load. There is a noticable difference between how easy it is to restart for an AOT C++ server and a similar Java server.

]]> By: Ismael Juma http://blog.juma.me.uk/2008/10/08/aot-for-java/#comment-32 Thu, 09 Oct 2008 10:35:38 +0000 http://ijuma.wordpress.com/?p=27#comment-32 I agree that the main benefit is for desktop applications, but I think you’re mistaken when you say that web app developers do not restart Tomcat itself on a regular basis. Products like JavaRebel have improved the situation, but for all web developers that still don’t use it, restarting Tomcat is very common given the brittleness of hot deployment and hotswap.

]]> By: Dmitry Leskov http://blog.juma.me.uk/2008/10/08/aot-for-java/#comment-31 Thu, 09 Oct 2008 08:59:59 +0000 http://ijuma.wordpress.com/?p=27#comment-31 Regarding IBM results: Tomcat startup time is irrelevant for web app users and, to a large extent, web app developers, because they normally do not need to restart Tomcat itself on a regular basis.

That said, startup time can indeed make a difference for users of desktop apps, e.g. Eclipse RCP. You may find Eclipse Classic compiled with the latest Excelsior JET 6.5 beta 2 at the URL under my name. Though we have not worked specifically on the RCP startup time yet, it seems to launch reasonably fast on our systems.

]]>