Faster Serialization and Faster RMI for Java Michael

Faster Serialization and Faster RMI for Java Michael Philippsen and the Java. Party Team Universität Karlsruhe and FZI Forschungszentrum Informatik Germany Forschungszentrum Informatik, Karlsruhe

Motivation • Serialization and RMI are too slow for Grande Applications: • Improvements are needed in three areas: – Faster serialization for Java – Faster RMI for Java – Use of non-TCP/IP networks with RMI • Java. Party project works on all three areas Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 2

Faster Serialization: UKA-Serialization • Drop-in replacement (plus class file retrofitter) • Save 76%-96% of the time needed for serialization • Minor (? ) incompatibilities: – targeted towards fast communication, not made for persistent objects (store objects now and reload them in x years with some future release of Java) – not yet: remote loading of byte code • Some impact on Sun Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 3

UKA Serialization: 5 key ideas 1 Explicit marshalling is faster than automatic marshalling by means of reflection 2 Slim type encoding is faster (no reflection needed) – Sun will include hook-method for it with next JDK – It is unlikely that Sun's RMI will use this hook 3 Two types of reset (avoid repetition) – Sun will work on the efficiency of the internal impl. 4 Better buffering and better buffer accessibility – Sun will not do that because they feel that making the buffer array visible is not very object-oriented 5 float[] and double[] with one JNI entry – Hotspot guys promise to do it Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 4

UKA Serialization: benchmarks Steps of improvement: Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 5

Faster RMI: Ka. RMI • Drop-in replacement with almost the same API • Can exploit non-TCP/IP networks • Saves up to 96% of the time needed for a remote method invocation (including UKA serialization): 80 ms on Digital Alphas connected by Myrinet • Minor (? ) incompatibilities: – no sockets & ports at user-level – no support of undocumented RMI classes • Some impact on Sun Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 6

Ka. RMI: Grande problems of Sun's RMI • RMI's transport layer cannot be replaced • • although high speed networks are available RMI's layers are badly documented sockets and ports at user-level API prevent use of non-TCP/IP transport RMI's implementation not optimized for speed (many temporary objects, many JNI calls, many hash tables. . . ) RMI's distributed garbage collector cannot be replaced although there are more efficient collectors for clusters Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 7

Ka. RMI: design Clean Interfaces between Design Layers Technology objects hide hardware Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 8

Benchmark Results Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 9

Conclusion & Future • With UKA Serialization and Ka. RMI, high-performance networks can be used for Grande Applications • More information and download: http: //wwwipd. ira. uka. de/Java. Party/ • Jini uses RMI as ist basic mechanism. With the current Jini hype, the Java Grande Forum needs your support to make a stonger impact on Sun to work on performance aspects. Michael Philippsen Universität Karlsruhe Faster Serialization and faster RMI 10