Matthew Dillon wrote:
:If there is a reasonable expectation that Preview will perform
:differently then I am happy to test it, but the way I read Matt's
:email is that there has been no recent progress on SMP development
:that might improve performance here.
:
:Kris
I think they're gonna be
On 2007-05-19, Erik Wikström [EMAIL PROTECTED] wrote:
On 2007-05-19 01:58, Kris Kennaway wrote:
On Fri, May 18, 2007 at 04:46:27PM -0700, Matthew Dillon wrote:
A large chunk of the kernel still runs under the big giant
lock, including the light weight processes that libthread_xu
:I was hoping that Matt would reply to my questions above so I could
:try to find a more level playing field on which to compare Dragonfly
:and FreeBSD, but I'm afraid that the answer is that there currently
:are *no* kernel subsystems that are not Giant-locked, so all workloads
:will perform
On 2007-05-19 01:58, Kris Kennaway wrote:
On Fri, May 18, 2007 at 04:46:27PM -0700, Matthew Dillon wrote:
A large chunk of the kernel still runs under the big giant
lock, including the light weight processes that libthread_xu
uses, so something like mysql is going to hit a lot of
On 2007-05-19, Gergo Szakal [EMAIL PROTECTED] wrote:
On Fri, 18 May 2007 16:46:27 -0700 (PDT)
Matthew Dillon [EMAIL PROTECTED] wrote:
A large chunk of the kernel still runs under the big giant
lock, including the light weight processes that libthread_xu
uses, so something like
On 2007-05-19, Gergo Szakal [EMAIL PROTECTED] wrote:
On Fri, 18 May 2007 19:58:24 -0400
Kris Kennaway [EMAIL PROTECTED] wrote:
You may be able to get DragonFly to run on the machines you
were having problems with by compiling it with SMP but
without APIC_IO. With that
:If there is a reasonable expectation that Preview will perform
:differently then I am happy to test it, but the way I read Matt's
:email is that there has been no recent progress on SMP development
:that might improve performance here.
:
:Kris
I think they're gonna be about the same.
A large chunk of the kernel still runs under the big giant
lock, including the light weight processes that libthread_xu
uses, so something like mysql is going to hit a lot of BGL
contention.
You may be able to get DragonFly to run on the machines you
were having problems
On Fri, 18 May 2007 16:46:27 -0700 (PDT)
Matthew Dillon [EMAIL PROTECTED] wrote:
A large chunk of the kernel still runs under the big giant
lock, including the light weight processes that libthread_xu
uses, so something like mysql is going to hit a lot of BGL
contention.