Re: Benchmarking gcj-built Tomcat
Gary Benson wrote: > Costin Manolache wrote: >> My benchmarks ( > 1 yr ago ) showed GCJ-based tomcat to be as fast >> as the IBM JDK1.3 ( the fastest VM at that time ). There were small >> differences under different loads - but the garbage collector seemed >> like the biggest factor ( GCJ performed worse on JSP pages where >> more objects were created if I remember correctly ). > > Do you still have the benchmark code around? I'd love to see it... No special code - I used the same tests as for regular tomcat. The tricky part was getting tomcat ( and all its depedents ) compiled with GCJ, then figure out how to deal with resources. Dynamic class loading turned out to just work, but I think I had to do few tweaks in the class loader ( basically hack it to use a flat loader - probably now it won't be needed ). After tomcat was working - "ab" with servlets and jsps. >> The amazing thing was the startup time - almost 0 ( it felt more >> like apache :-). > > It does start up fast :) The compiler we're using has a funky > experimental optimiser (the same as used in the fast free eclipse > project), and the startup became perhaps twice as fast when I switched > from gcj 3.3. It compiles JSPs pretty fast too. That's one reason > why I'd like to benchmark it. Startup time is probably more important for ant or javac or other things that are run frequently. But it is cool to see tomcat start in the same time as apache. ( or ant as fast as make ) > >> BTW - GCJ is not a virtual machine and doesn't have a JIT - it is a >> ahead-of-time compiler, just like C and C++ compilers. > > This may have been true a while back, but it isn't now -- gcj can > interpret bytecode just like any other JVM. In my Tomcat package this > is exactly what it does when executing servlets (everything else is > built to native code). You're right in that doesn't have a JIT > though. I did compile the servlets as well to native. >> The biggest problem at that time was dynamic class loading. GCJ has >> a small interpretor and could load servlets - but the difference in >> performance between precompiled code and interpretor was >> significant. > > It probably still is, though not as bad. But it's not such a big > problem as it seems, as most of the calls that a given servlet makes > will be to native-compiled methods. JSPs tend to have a lot of code inside. The interesting part is that class loading works ( or it used to work ) by using .so files. So it should be possible to hack the webapp deployer to invoke gcj on all the jar files in lib/ and generate the .so. I don't know how easy it is to get the .so files loaded, but I'm sure gcj uses dl* to work with the .so files. The only major problem I see is the sandbox - but unfortunately most people don't use it anyway ( even if they should ). From a security point of view - compiling all the servlets to native or running in JDK without sandbox is equivalent - a bad serlvet can do as much damage as it wants. But if you want security - I'm not sure if GCJ implements the sandbox and all the code verifications that are needed - last time I looked it didn't seem to. Costin - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
Re: Benchmarking gcj-built Tomcat
Costin Manolache wrote: > My benchmarks ( > 1 yr ago ) showed GCJ-based tomcat to be as fast > as the IBM JDK1.3 ( the fastest VM at that time ). There were small > differences under different loads - but the garbage collector seemed > like the biggest factor ( GCJ performed worse on JSP pages where > more objects were created if I remember correctly ). Do you still have the benchmark code around? I'd love to see it... > The amazing thing was the startup time - almost 0 ( it felt more > like apache :-). It does start up fast :) The compiler we're using has a funky experimental optimiser (the same as used in the fast free eclipse project), and the startup became perhaps twice as fast when I switched from gcj 3.3. It compiles JSPs pretty fast too. That's one reason why I'd like to benchmark it. > BTW - GCJ is not a virtual machine and doesn't have a JIT - it is a > ahead-of-time compiler, just like C and C++ compilers. This may have been true a while back, but it isn't now -- gcj can interpret bytecode just like any other JVM. In my Tomcat package this is exactly what it does when executing servlets (everything else is built to native code). You're right in that doesn't have a JIT though. > The biggest problem at that time was dynamic class loading. GCJ has > a small interpretor and could load servlets - but the difference in > performance between precompiled code and interpretor was > significant. It probably still is, though not as bad. But it's not such a big problem as it seems, as most of the calls that a given servlet makes will be to native-compiled methods. Gary [ [EMAIL PROTECTED] ][ GnuPG 85A8F78B ][ http://inauspicious.org/ ] - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
Re: Benchmarking gcj-built Tomcat
Gary Benson wrote: > Hi all, > > I've been working on building Tomcat and its dependencies to native > code with gcj, and I'm interested to see how it compares against > Tomcat running under a 'normal' JVM. Now, I'm well aware that > benchmarks are not a real-world indicator of performance, but I don't > have any particular web application to test and I was wondering if > anyone has a benchmarking suite that they can point me at. My benchmarks ( > 1 yr ago ) showed GCJ-based tomcat to be as fast as the IBM JDK1.3 ( the fastest VM at that time ). There were small differences under different loads - but the garbage collector seemed like the biggest factor ( GCJ performed worse on JSP pages where more objects were created if I remember correctly ). The amazing thing was the startup time - almost 0 ( it felt more like apache :-). BTW - GCJ is not a virtual machine and doesn't have a JIT - it is a ahead-of-time compiler, just like C and C++ compilers. My understanding is that it compiles Java code to the same intermediary-code as C++ - so you shouldn't see any major difference between C++ code and Java code compiled with GCJ. Except that GCJ programs use garbage collection and java libraries - with the good and the bads. The biggest problem at that time was dynamic class loading. GCJ has a small interpretor and could load servlets - but the difference in performance between precompiled code and interpretor was significant. Another problem was that not everything compiled, I had to do some tricks ( now it shouldn't be a problem ). Also the tests were made with tomcat 3.3 - I tried to compile 4.0 but there were more compile problems. Costin > > In case you are interested in the gcj-built packages, they are > available at http://people.redhat.com/gbenson/naoko/ as source rpms > and as binary rpms compiled for Red Hat Linux 9. Everything except > the webapps is compiled to native code; the webapps are basically > unmodified and are interpreted just as they would be with a normal JVM. > > Thanks, > Gary > > [ [EMAIL PROTECTED] ][ GnuPG 85A8F78B ][ http://inauspicious.org/ ] - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
Re: Benchmarking gcj-built Tomcat
Sadly it doesn't do any JITting. I recommend writing a custom classloader that Runtime.exec()'s gcj to compile the webapp into a .so, and then dlopen() that. - a Gary Benson <[EMAIL PROTECTED]> writes: > Chad Johnson wrote: > > I can't help with the benchmark software but I've got a question for > > you. Generally speaking, how well does the gcj bytecode interpreter > > perform? Is it purely and interpreter or does it do some jit'ing? > > As far as I know, it's just an interpreter, but I may be wrong. > However, any calls to native-code stuff will execute as native code so > it's perhaps not quite as bad as it may seem. > > Gary > > - > To unsubscribe, e-mail: [EMAIL PROTECTED] > For additional commands, e-mail: [EMAIL PROTECTED] > > -- "Education is not filling a bucket but lighting a fire." -- WB Yeats - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
RE: Benchmarking gcj-built Tomcat
Gary, Hmm, interesting. The benchmarks found at: http://www.webperformanceinc.com/library/ServletReport/ Should be reproduceable by scripts included in that article. Chad Johnson -Original Message- From: Gary Benson [mailto:[EMAIL PROTECTED] Sent: Tuesday, October 14, 2003 10:14 AM To: Tomcat Developers List Subject: Re: Benchmarking gcj-built Tomcat As far as I know, it's just an interpreter, but I may be wrong. However, any calls to native-code stuff will execute as native code so it's perhaps not quite as bad as it may seem. Gary - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
Re: Benchmarking gcj-built Tomcat
Chad Johnson wrote: > I can't help with the benchmark software but I've got a question for > you. Generally speaking, how well does the gcj bytecode interpreter > perform? Is it purely and interpreter or does it do some jit'ing? As far as I know, it's just an interpreter, but I may be wrong. However, any calls to native-code stuff will execute as native code so it's perhaps not quite as bad as it may seem. Gary - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
RE: Benchmarking gcj-built Tomcat
Gary, I can't help with the benchmark software but I've got a question for you. Generally speaking, how well does the gcj bytecode interpreter perform? Is it purely and interpreter or does it do some jit'ing? Chad Johnson -Original Message- From: Gary Benson [mailto:[EMAIL PROTECTED] Sent: Tuesday, October 14, 2003 9:22 AM To: [EMAIL PROTECTED] Subject: Benchmarking gcj-built Tomcat Hi all, I've been working on building Tomcat and its dependencies to native code with gcj, and I'm interested to see how it compares against Tomcat running under a 'normal' JVM. Now, I'm well aware that benchmarks are not a real-world indicator of performance, but I don't have any particular web application to test and I was wondering if anyone has a benchmarking suite that they can point me at. In case you are interested in the gcj-built packages, they are available at http://people.redhat.com/gbenson/naoko/ as source rpms and as binary rpms compiled for Red Hat Linux 9. Everything except the webapps is compiled to native code; the webapps are basically unmodified and are interpreted just as they would be with a normal JVM. Thanks, Gary [ [EMAIL PROTECTED] ][ GnuPG 85A8F78B ][ http://inauspicious.org/ ] - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED] - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
Benchmarking gcj-built Tomcat
Hi all, I've been working on building Tomcat and its dependencies to native code with gcj, and I'm interested to see how it compares against Tomcat running under a 'normal' JVM. Now, I'm well aware that benchmarks are not a real-world indicator of performance, but I don't have any particular web application to test and I was wondering if anyone has a benchmarking suite that they can point me at. In case you are interested in the gcj-built packages, they are available at http://people.redhat.com/gbenson/naoko/ as source rpms and as binary rpms compiled for Red Hat Linux 9. Everything except the webapps is compiled to native code; the webapps are basically unmodified and are interpreted just as they would be with a normal JVM. Thanks, Gary [ [EMAIL PROTECTED] ][ GnuPG 85A8F78B ][ http://inauspicious.org/ ] - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
