Re: [perf-discuss] Can we get the free memory number right again? (w/ ZFS)

2009-06-25 Thread johansen
On Thu, Jun 25, 2009 at 04:55:14PM -0400, David Collier-Brown wrote: > johan...@sun.com replied > > I disagree with the premise that the free memory calculation isn't > > useful because it doesn't count ZFS caches as free space. > [big snip] > > The space that's consumed by ZFS is in use and can't

Re: [perf-discuss] how to measure zfs performance

2009-06-25 Thread David Collier-Brown
kenny wrote: > > i was wondering what is the recommended way to measure the > > performance of zfs. > > i think my performance isn't as good as it should be, but with > > no measurement, i don't even know is my assumption is correct > > or wrong. > > > > so what do people around here use to measure

Re: [perf-discuss] Can we get the free memory number right again? (w/ ZFS)

2009-06-25 Thread David Collier-Brown
On Thu, Jun 25, 2009 at 11:16:50AM -0700, Sean Liu wrote: > > Now that ZFS cache will eat up all the free mem for cache, again > > that's all fine. But vmstat doesn't report meaningful free memory > > again. Yes memstat can tell you the ZFS file data size but who wants > > to run mdb every now and

Re: [perf-discuss] Can we get the free memory number right again? (w/ ZFS)

2009-06-25 Thread johansen
On Thu, Jun 25, 2009 at 12:18:04PM -0700, Sean Liu wrote: > Correct me if I am wrong. If the applications request memory from O/S, > the kernel will cut back ZFS cache - so in this sense the cache is > free, right? Nope. It doesn't work this way. ZFS has a thread that runs periodically, and is i

Re: [perf-discuss] Can we get the free memory number right again? (w/ ZFS)

2009-06-25 Thread Sean Liu
Johansen, Correct me if I am wrong. If the applications request memory from O/S, the kernel will cut back ZFS cache - so in this sense the cache is free, right? Yes ZFS cache is considered kernel memory, but as long as kenel will cut back its size and give back to applications, it'll be conside

Re: [perf-discuss] Can we get the free memory number right again? (w/ ZFS)

2009-06-25 Thread Mike Gerdts
On Thu, Jun 25, 2009 at 1:27 PM, wrote: > > On Thu, Jun 25, 2009 at 11:16:50AM -0700, Sean Liu wrote: > > Now that ZFS cache will  eat up all the free mem for cache, again > > that's all fine. But vmstat doesn't report meaningful free memory > > again. Yes memstat can tell you the ZFS file data si

Re: [perf-discuss] Can we get the free memory number right again? (w/ ZFS)

2009-06-25 Thread johansen
On Thu, Jun 25, 2009 at 11:16:50AM -0700, Sean Liu wrote: > Now that ZFS cache will eat up all the free mem for cache, again > that's all fine. But vmstat doesn't report meaningful free memory > again. Yes memstat can tell you the ZFS file data size but who wants > to run mdb every now and then? >

[perf-discuss] Can we get the free memory number right again? (w/ ZFS)

2009-06-25 Thread Sean Liu
Hi there, Before Solaris 8, vmstat will always report in the free column the "minfree" after a prolonged time, because the filesystem cache simply eats all available RAM. It was all fine but makes it difficult to find out the memory utilization on the boxes. The only ways to find out is to chec

[perf-discuss] Latest release of Filebench.

2009-06-25 Thread Andrew Wilson
FileBenchers, I uploaded version 1.4.8 of FileBench to sourceforge a couple of weeks ago, but I forgot to send out a notice. So, here it is. Sadly, this is the last work I will be doing on FileBench, at least for quite a while, as it is my last day at Sun. Hopefully others will carry on

Re: [perf-discuss] how to measure zfs performance

2009-06-25 Thread Bob Sneed
Kenny: Performance is all about your application; it's response time, throughput, and variance in those metrics. I suggest that all your problem-solving start and end from that perspective. If your application performance is not what you need and you suspect ZFS is the reason, there are tool

[perf-discuss] Openvpn stress testing under opensolaris question.

2009-06-25 Thread Andrreas Moschos
Hello there i would like to use opensolaris as an openvpn server with a maximum number of clients of 2000 - 3000. Opensolaris is my choise over linux for its advanced network stack and the multithreading capabilities - although openvpn is not the ideal multithreaded application (but can run mul