RFR: 8298377: JfrVframeStream causes deadlocks in ZGC

Erik Österlund eosterlund at openjdk.org
Wed Dec 21 16:20:51 UTC 2022


On Thu, 8 Dec 2022 11:23:57 GMT, Stefan Karlsson <stefank at openjdk.org> wrote:

> The JfrVFrameStream is used while generating stack traces for events. One of the events are the ZPage allocation event. This event is sometimes sent when ZGC is relocating. The current implementation of JfrVFrameStream uses WalkContinuation::include, which causes JFR to walk the continuation and perform GC barriers. This is problematic, since ZGC has a requirement that we never perform load barriers while running the relocation code. If we do, we might end up performing other reloctions from the the relocation code, and in some cases that causes dead locks.
> 
> I propose that JFR doesn't walk the continuations when sending events. An alternative could be to limit this to ZGC, but I'd like to get some feedback around that from JFR / Loom devs.
> 
> We've been testing this patch in the Generational ZGC repository.

I have a branch here with a single commit for my proposed fix: https://github.com/fisk/jdk/tree/8298377_jfr_stack_trace
If you like it I can try to figure out how to hijack this PR. I basically create a new DisableStackTracingMark class, that does what deopt does today, and sprinkles it in our ZGC stack watermark processing, and make sure the JFR tracing thread starts processing on the threads it samples.

-------------

PR: https://git.openjdk.org/jdk/pull/11586


More information about the hotspot-dev mailing list