JITServer: Disaggregated Caching JIT Compiler for the JVM in the Cloud

Alexey Khrabrov, Marius Pirvu, Vijay Sundaresan, Eyal de Lara

USENIX Annual Technical Conference (USENIX ATC 22), Carlsbad, CA, July 2022



Managed runtimes such as the Java virtual machine (JVM) rely on just-in-time (JIT) compilers to improve application performance by converting bytecodes into optimized machine code. Unfortunately, JIT compilation introduces significant CPU and memory runtime overheads. JIT compiler disaggregation is a technique that decouples the JIT from the JVM and ships compilation to a separate remote process. JIT disaggregation reduces overall memory usage; however, its communication overheads result in higher system-wide CPU usage. JITServer is a disaggregated caching JIT compiler we implemented in the Eclipse OpenJ9 JVM. It improves system-wide resource utilization by enabling the caching of compiled native code and its reuse in JVMs running on different machines. JITServer is transparent to the application developer, and supports all the dynamic features in the JVM specification. In our experiments, JITServer reduced overall CPU cost by up to 77%, overall memory usage by up to 62%, application start time by up to 58% and warm-up time by up to 87%.