RFR(s): 8150362: G1 base elapsed time prediction is wrong because rs_length prediction is wrong (original) (raw)

Thomas Schatzl thomas.schatzl at oracle.com
Wed Mar 9 09:23:08 UTC 2016


Hi Sangheon,

On Tue, 2016-03-08 at 10:08 -0800, sangheon wrote:

Hi all,

Could I have some reviews for this change? We predict remembered set length as follows from G1CollectorPolicy::predictbaseelapsedtimems(sizet pendingcards): sizet rslength = predictrslengthdiff(); This is incomplete and it is inconsistent when compare with the use case of the function from G1CollectorPolicy::calculateyounglisttargetlength(). 'adjrslengths = rslengths + predictrslengthdiff()' In this case, we use rslength + rslengthdiff. I am proposing to use the sum of rslength and rslengthdiff. i.e. 'rs length + rs length diff'. CR: https://bugs.openjdk.java.net/browse/JDK-8150362 Webrev: http://cr.openjdk.java.net/~sangheki/8150362/webrev.00 Testing: JPRT, some performance tests showed no big difference.

looks good.

Thanks, Thomas



More information about the hotspot-gc-dev mailing list