... I came up with some pretty disturbing numbers: > http://devloop.org ... out what the hell you're doing and gone through quite ... stuff will not be hot. >* java threads are created first and ... force suboptimal scheduling when you're trying to benchmark a scheduler ...

linux-kernel - David Schwartz - Sep 13 2007 - 03:18

... > and I came up with some pretty disturbing numbers: > > http://devloop.org.uk/ ... > database stuff will not be hot. > > >* java threads are created first and the data ... reason to force suboptimal scheduling when you're trying to > benchmark a scheduler? Are ...

linux-kernel - Nick Piggin - Sep 12 2007 - 19:33

... >>> and I came up with some pretty disturbing numbers: >>> http://devloop.org.uk/ ... results (for both kernels and rdbms) >>> * java threads are created first and the data ... to force suboptimal scheduling when you're trying to >> benchmark a scheduler? Are ...

linux-kernel - Antoine Martin - Sep 13 2007 - 15:02

... to force suboptimal scheduling when > >> you're trying to > >> benchmark a scheduler? Are ... uncover some very noticeable differences in JVM > performance when stress-tested with a ... variable. The problem is that the number of times the math problem is ...

linux-kernel - David Schwartz - Sep 13 2007 - 17:47