IssueTracker

Context

When using the option -Xcheck:jni, deflate compression becomes orders of magnitude slower due to multiple native calls that are being interrupted.

To compress an 8MB array, 16,384 native calls are made that use the 8MB input array and the 512 byte output array. These arrays are accessed using GetPrimitiveArrayCritical that with -Xcheck:jni copies the array: http://hg.openjdk.java.net/jdk/jdk/file/c5eb27eed365/src/hotspot/share/prims/jniCheck.cpp#l1862 The copying of the arrays leads to 128GB of copying which dominates execution time.

Not sure how many users use this option, but we can potentially have a build analyzer warning when detecting this option.