Shortage of the current implementation of Soft Updates
The current FreeBSD Soft Updates poses to a performance peanlity when there’re plenty of i-nodes and this is very common case in badly-designed systems, however, I think this should be solved.
共 105 篇文章。
The current FreeBSD Soft Updates poses to a performance peanlity when there’re plenty of i-nodes and this is very common case in badly-designed systems, however, I think this should be solved.
junsu has pointed out that gcc has the ablity to do profile, record the data and optimize the generated code according to the data. The nearest compiler guru I can visit is Prof. Husheng LIAO (sorry, the link here is not available to the Internet at the time writing, but this is hopefully to be changed soon) who recently concentrate his research in optimization for the Java Language Compiling process.
Further information will be available here soon.
das@ [David Schultz] has done some benchmark of the different PID allocators recently being discussed on hackers@, and the result is available here.
It’s important to have a scientific view when doing any benchmarks. Today, phk and Robert Watson has posted several hints to the -current list.
As planned, Jeff Roberson has made ULE scheduler the default for FreeBSD’s CVS -HEAD. This is an important step going forward to 5-STABLE.