I have seen about 30% performance regression for TreeTest
in swingMark benchmark.

And it seems the regression was introduced in the last few builds. There was
no such regression in earlier builds like b60-b65.

(compared to jdk 1.3.0).

To reproduce:

% uname -a
SunOS vispro 5.7 Generic_106541-16 sun4u sparc SUNW,Ultra-30

% jdk1.4/bin/java -version
java version "1.4.0-beta_refresh"
Java(TM) 2 Runtime Environment, Standard Edition (build 1.4.0-beta_refresh-b70)
Java HotSpot(TM) Client VM (build 1.4.0-beta_refresh-b70, mixed mode)


% jdk1.4/bin/java -client -ms256m -mx256m -cp /home/zzhang/bugs perfteam.swingmark.SwingMark -r 5 -q -testfile defaulttests.txt

JMTest_04 1152 1102 1131 1092 1052
TextAreaTest 6190 4311 4211 4312 4010
SliderTest 3504 2680 2771 2631 2650
ListTest 2671 2400 2140 2150 2120
TableRowTest 9670 8665 8568 8432 8472
TreeTest 23536 22058 21297 21467 21237


% jdk1.3/bin/java -version
java version "1.3.0"
Java(TM) 2 Runtime Environment, Standard Edition (build 1.3.0)
Java HotSpot(TM) Client VM (build 1.3.0, mixed mode)

% jdk1.3/bin/java -client -ms256m -mx256m -cp /home/zzhang/bugs perfteam.swingmark.SwingMark -r 5 -q -testfile defaulttests.txt

JMTest_04 8267 5013 4722 4848 4693
TextAreaTest 4972 4049 3861 3880 3939
SliderTest 4102 3480 3650 3580 3660
ListTest 2888 2787 2688 2697 2686
TableRowTest 8669 8142 8024 8014 8403
TreeTest 17391 16377 16288 16307 16376

As you would see from above, TreeTest has about 30% regression in average,
and TextAreaTest also has some.

similiar regressions also would be seen when run with -server flag.

I am not sure if this bug is related to 4478833.