250 likes | 356 Views
A New Transpant JAVA Thread Migration System Using Just-in-Time Recompilation. Wenzhang Zhu, Cho-Li Wang, Weijian Fang, and Francis C.M. Lau The University of Hong Kong. Java Thread. Lightweight computation unit Supports concurrency Supported by Java at language level
E N D
A New Transpant JAVA Thread Migration System Using Just-in-Time Recompilation Wenzhang Zhu, Cho-Li Wang, Weijian Fang, and Francis C.M. Lau The University of Hong Kong
Java Thread • Lightweight computation unit • Supports concurrency • Supported by Java at language level • Shared memory paradigm • Multithreading used in large Java programs – e.g. Tomcat, JBoss 16th IASTED PDCS 2004, Cambridge, USA
True Parallelism for Threads • Multiple threads of a program spreading over multiple compute nodes in a cluster • A “global object space” to support data sharing • JESSICA2 [8] threads Heap objects CPU1 CPU2 CPU3 16th IASTED PDCS 2004, Cambridge, USA
Dynamic Thread Migration • To achieve load balancing and best performance for applications underloaded overloaded balancedworkload 16th IASTED PDCS 2004, Cambridge, USA
Example of Thread Migration • Program: • 1: i=1; • 2: j=2; • 3: k=i+j; • We need to carry the code and its execution state to remote node • What is in the execution state? At least • the program counter • the intermediate values of variables Node 1 i=1; j=2; Node 2 k=i+j; 16th IASTED PDCS 2004, Cambridge, USA
Previous Approaches • User level • Bytecode level [6][7] • JVM level [4][5], with JIT [9] • Normal thread execution suffers • time: checking flags and flushing registers to memory • space: code size expanded • A multithreaded Java application will have >95% normal execution, <5% migration • What we present will help optimize the 95% 16th IASTED PDCS 2004, Cambridge, USA
JIT Compilation • Can we migrate native code? • No, machines are not the same Javabytecodeinexecution Native code Migrate? JITC 16th IASTED PDCS 2004, Cambridge, USA
New Approach • Derive portable bytecode-oriented thread context (BTC) from native (raw) thread context (RTC) • Restore BTC to RTC • Re-run JIT compilation in both phases to transform the thread context Source node Target node 16th IASTED PDCS 2004, Cambridge, USA
The Detailed Steps • Very quickly … 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (source node) Stack walk compute() main() JVM-kernel function() 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (source node) Stack walk Frame segmentation Java frames to migrate compute() main() JVM-kernel function() 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (source node) Stack walk Frame segmentation compute() Bytecode PC positioning iinc 1, 1 iload_1 bipush 30 if_icmplt 5 incl %ebx cmpl $0x1e, %ebx jl 0x82512432 Mapping main() 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (source node) Stack walk Frame segmentation compute() Bytecode PC positioning iinc 1, 1 iload_1 bipush 30 if_icmplt 5 incl %ebx cmpl $0x1e, %ebx jl 0x82512432 Breakpoint selection breakpoint getstatic #2 return 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (source node) Stack walk compute() Frame segmentation local 0: java.lang.thread local 1: int stack 0: float stack 1: int Bytecode PC positioning Breakpoint selection Type derivation main() local 0: java.lang.thread stack 0: double stack 2: double 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (source node) Stack walk re-generate native code with breakpoints Frame segmentation compute() Bytecode PC positioning inc %ebx cmpl $1e, %ebx jl 0x82512432 0x82512432: … capture frames… --- save local var’s and their type return getstatic #2 Iload_1 Breakpoint selection Type derivation Translation main() ...other native code... jmp start_migration 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (source node) Stack walk replace saved return address with the newly generated code Frame segmentation compute() Bytecode PC positioning inc %ebx cmpl $1e, %ebx jl 0x82512432 0x82512432: … capture frames… --- save local var’s and their type return saved return address Breakpoint selection activation record of compute() Type derivation main() Translation Native code patching ...other native code... jmp start_migration 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (target node) Thread creation Frame PC 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (target node) • use JIT compiler to derive register • mapping at restoration point generate code stub Thread creation compute() Dynamic register patching Register recovering stub: movl %0x1234, %eax movl %0x5678, %ebx ... main() Register recovering stub: movl %0x1111, %eax ... 16th IASTED PDCS 2004, Cambridge, USA
Just-in-Time Recompilation (target node) Compiled methods: reg1 <- value1 jmp restore_point1 Stack growth Thread creation compute(){ ... retore_point1: } frame 1 %ebp Dynamic register patching Ret addr reg1 <- value1 reg2 <- value2 jmp restore_point0 Stack rebuilding main(){ ... retore_point10: } frame 0 %ebp Ret addr Linking code stub and native frames trampoline frame trampoline bootstrap frame bootstrap(){ trampoline(); closing handler(); } %ebp 16th IASTED PDCS 2004, Cambridge, USA
Experimentation • Cluster of 2GHz P4 PCs, running Linux kernel 2.4.22 • Normal runtime overhead = 0 • Migration latency hiding • Pre-loading classes needed at target node when the frames have been segmented • Overlapping class loading with stack transform at source node 16th IASTED PDCS 2004, Cambridge, USA
Migration Overhead DNIC: Dynamic Native Code Instrumentation approach JITR: Just-in-Time recompilation approach JITR+Preload: Just-in-Time recompilation with class preloading enabled 16th IASTED PDCS 2004, Cambridge, USA
Multithreaded Java Application Server Simulation 16th IASTED PDCS 2004, Cambridge, USA
Parallel Mesh Refinement Simulation 16th IASTED PDCS 2004, Cambridge, USA
Conclusion • This paper presents an efficient transparent Java thread migration system using the technique of JIT recompilation without code instrumentation • The idea of using JIT recompilation demonstrates a new use of the JIT compiler to gather runtime information 16th IASTED PDCS 2004, Cambridge, USA
JESSICA2 Website www.csis.hku.hk/~clwang/projects/JESSICA2.html 16th IASTED PDCS 2004, Cambridge, USA