concurrent mode failure in minor gc/ -XX:CMSFullGCsBeforeCompaction=1

[Y.S.Ramakrishna at Sun.COM]

> One important thing we have learned about CMS is
> that the filtering of short-lived objects in the young gen is
> important both for relieving short-term pressure on the CMS collector
> and in the long-term for reducing fragmentation of the old
> gen, either or both of which might otherwise cause concurrent mode failure.

Rereading that, I see that it was too cryptic. What I meant was
that use of the survivor spaces (and at _last_ a tenuring threshold of
1, if not higher -- use PrintTenuringDistribution to tune an optimum)
is crucial to getting good performance out of CMS.

- ramki