Re: [RFC][PATCH] linux-2.5.34_vsyscall_A0

[george anzinger <george@mvista.com>]

Stephen Hemminger wrote:
> 
> One reason gettimeofday ends up being important is that several
> databases call it a lot. They use it to build up a transaction id. Under
> big transaction loads, even the fast linux syscall path ends up being a
> bottleneck. Also, on NUMA machines the data used for time of day (xtime)
> ends up being a significant portion of the cache traffic.
> 
> It would be great to rework the whole TSC time of day stuff to work with
> per cpu data and allow unsychronized TSC's like NUMA. The problem is
> that for fast user level access, there would need to be some way to find
> out the current CPU and avoid preemption/migration for a short period.
> It seems like the LDT stuff for per-thread data could provide the
> current cpu (and maybe current pid) somehow.  And it would be possible
> to avoid  preemption while in a vsyscall text page, some other Unix
> variants do this to implement portions of the thread library in kernel
> provided user text pages.
> 
Now there is an idea!  Lock preemption in user space if and
only if the user is executing in a text page shared with the
kernel.  I have seen the need for such locking, but have
always thought they were too dangerous.  This convention
would introduce a much higher level of security.  What is
left is to devise a way to let the kernel know that the
preemption targeted task has left such a page so that the
preemption may proceed.  Possibly the kernel could plant a
hint on the page that each function would check for on exit.
-- 
George Anzinger   george@mvista.com
High-res-timers: 
http://sourceforge.net/projects/high-res-timers/
Preemption patch:
http://www.kernel.org/pub/linux/kernel/people/rml