RFR (S): 8136854: G1 ConcurrentG1RefineThread::stop delays JVM shutdown for >150ms
tom.benson at oracle.com
Wed Jan 27 15:22:10 UTC 2016
OK, thanks for the data.
On 1/27/2016 10:17 AM, Aleksey Shipilev wrote:
> On 01/27/2016 05:37 PM, Tom Benson wrote:
>> Was the change tried on a small system to see if startup is actually
>> slowed down there, by the much tighter loop consuming CPU? I guess one
>> possible answer is "we don't care that much about systems that small for
>> G1. "
> Another plausible answer would be: 1 ms delay in a polling loop is still
> large enough to knock off a thread from a CPU, and small enough to
> improve responsiveness.
> Anyhow, my lousy 1.7 GHz 2-core ultrabook improved the HelloWorld time
> quite significantly with this patch: 210 ms -> 90 ms. Even when I
> downclock it to 800 MHz, it still improves: 240 ms -> 200 ms.
More information about the hotspot-gc-dev