RFR: 8221392: Reduce ConcurrentGCThreads spinning during start up

Claes Redestad claes.redestad at oracle.com
Mon Mar 25 09:53:32 UTC 2019


Hi,

just a comment: I ran this through a few OOTB startup tests on my laptop
(so G1 etc) and can see a statistically significant (8%) reduction in
context switches and small improvements on various other metrics. Great!

Thanks!

/Claes

On 2019-03-25 09:36, Per Liden wrote:
> During startup, ConcurrentGCThreads end up in a loop sleeping for 1ms 
> over and over (typically 30-50 times), until is_init_completed() is 
> true. This is not optimal, and we should instead have them wait until 
> they are signaled. This problem has been observed before, as comments in 
> JDK-8136854 suggests.
> 
> This patch introduces wait_init_completed(), which will block until 
> set_init_completed() is called. Note that the newly introduced 
> InitCompleted_lock is only used to control the interaction between 
> wait_init_completed() and set_init_completed(). is_init_completed() is 
> still lock-free and was just cleaned up to use proper atomic 
> load_acquire/release_store semantics.
> 
> Bug: https://bugs.openjdk.java.net/browse/JDK-8221392
> Webrev: http://cr.openjdk.java.net/~pliden/8221392/webrev.0
> 
> /Per


More information about the hotspot-gc-dev mailing list