RFR (XS): 8188877: Improper synchronization in offer_termination

Andrew Haley aph at redhat.com
Mon Nov 27 11:55:32 UTC 2017


On 27/11/17 09:30, Thomas Schatzl wrote:
>   so, summing up this discussion, the change is good to go? I think we
> can always add any implementation dependent optimizations later.
> 
> If everybody agrees, I will push it.

OK from me.  I'm still a bit nervous about the possible performance
implications of interpreted code taking an extremely long time to get
to a safepoint.  However, I did some experiments and it looks like the
worst case we're likely to encounter is about a couple of hundred
microseconds.

-- 
Andrew Haley
Java Platform Lead Engineer
Red Hat UK Ltd. <https://www.redhat.com>
EAC8 43EB D3EF DB98 CC77 2FAD A5CD 6035 332F A671



More information about the hotspot-gc-dev mailing list