On Wed, 2005-03-09 at 21:43 -0500, Serge E. Hallyn wrote: > My plan is to use unixbench, dbench, stream, and hackbench. Webstone > requires two machines, but people seem to respect it's results, so maybe > I'll just have to give in and use it. I suppose I could try apachebench > as well, I'll just need to set apache back up... > > (I actually haven't found how to get meaningful results from dbench, > but I didn't try very hard) > > But I am still curious which of the above (or any not listed) are > considered more useful. Though I'm assuming it's mostly that those > numbers will be more meaningful because they've been used before for > selinux performance comparisons? Make sure you do dbench on ext2, not ext3. Benchmarks on SMP are also of particular interest, as we don't want to lose the gains in scalability achieved from the AVC RCU work by NEC, but hopefully that is a non-issue due to your current lockless approach. -- Stephen Smalley <sds@private> National Security Agency
This archive was generated by hypermail 2.1.3 : Thu Mar 10 2005 - 05:02:01 PST