Re: PAPI in the ports

2007/6/22, Stanislav Sedov <stas@xxxxxxxxxxx>:

On Thu, 14 Jun 2007 13:27:01 +0200
Thomas Vogt <thomas@xxxxxxxxxx> mentioned:

>
> Yes you're right. But to have a such feature on a production system is
> nice if you have to debug issues. If I get a problem I can easily debug
> it without to simulate everything in the lab. It's not that I want to
> run such features 24/7.
>
> But perhaps "options HWPMC_HOOKS" in the kernel enables some hooks which
> could cause performance penalties even if I don't actively use such
> feature very often. Like many other debug options in the kernel. I don't
> know.
>

I'm using "options HWPMC_HOOKS" on heavily loaded web server almost
constantly, no visible penalty at all. Just my 2 cents.


Those are good news! :)


--
Stanislav Sedov
ST4096-RIPE




--
_________________________________________________________________
Empty your memory,
with a free()...
like a pointer!

If you cast a pointer to an integer,
it becomes an integer,
if you cast a pointer to a struct,
it becomes a struct.

The pointer can crash...,
and can overflow.

Be a pointer my friend...
_______________________________________________
freebsd-performance@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "freebsd-performance-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • [PATCH 04/15] mm: update split ptlock Kconfig
    ... while pte_alloc_one returns just a struct page pointer, ... a struct page pointer, ... +# PA-RISC 7xxx's debug spinlock_t is too large for 32-bit struct page. ... send the line "unsubscribe linux-kernel" in ...
    (Linux-Kernel)
  • Re: Release version crashes - again
    ... DWORD *pointer = NULL; ... are not usually equal in retail, but they usually are in debug. ... but my code is crashing in the CONSTRUCTOR area (long ...
    (microsoft.public.windowsce.embedded.vc)
  • Re: I think this is a bug...
    ... Doesn't this feature violate that concept? ... But Test_Method is passed a pointer, so it can validly be written ... AT THE VERY LEAST THIS SHOULD GENERATE A LOW-LEVEL WARNING. ... > a boxing conversion from every V to V^ to support ...
    (microsoft.public.dotnet.languages.vc)
  • Re: Dealing with HANDLEs
    ... On every new process event this program creates a new Process object and ... pointer and assigns the pointer from the to it. ... This worked in debug. ... Strange, I thought if I pass a pointer, it's like by ref, I can change its ...
    (microsoft.public.win32.programmer.kernel)
  • Re: PAPI in the ports
    ... any performance measuring does or must stress ... performance tests on a production server is not the very best idea. ... But to have a such feature on a production system is ... If I get a problem I can easily debug ...
    (freebsd-performance)