RFR: 8061254: SPECjvm2008-XML performance regressions in 9-b33 (original) (raw)
Alan Bateman Alan.Bateman at oracle.com
Fri May 15 13:23:27 UTC 2015
- Previous message: RFR: 8061254: SPECjvm2008-XML performance regressions in 9-b33
- Next message: RFR: 8061254: SPECjvm2008-XML performance regressions in 9-b33
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On 13/05/2015 12:51, Claes Redestad wrote:
Hi,
9-b33 introduced a sustained regression in SPECjvm2008 xml.transform on a number of our test setups. JDK-8058643 removed the check on value.length > 0, which means repeated calls to "".hashCode() now do a store of the calculated value (0) to the hash field. This has potential to cause excessive cache coherence traffic in xml.transform[1] I remember the original change but of course didn't spot that empty String would result in a write of 0. I like Shipilev's First Law.
The patch looks good to me.
-Alan.
- Previous message: RFR: 8061254: SPECjvm2008-XML performance regressions in 9-b33
- Next message: RFR: 8061254: SPECjvm2008-XML performance regressions in 9-b33
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]