Date: Sat, 19 Dec 2009 12:44:14 +0100 From: Hans Petter Selasky <hselasky@c2i.net> To: freebsd-arch@freebsd.org Cc: Ulrich =?iso-8859-1?q?Sp=F6rlein?= <uqs@spoerlein.net>, Harti Brandt <harti@freebsd.org> Subject: Re: network statistics in SMP Message-ID: <200912191244.17803.hselasky@c2i.net> In-Reply-To: <20091219112711.GR55913@acme.spoerlein.net> References: <20091215103759.P97203@beagle.kn.op.dlr.de> <200912151313.28326.jhb@freebsd.org> <20091219112711.GR55913@acme.spoerlein.net>
index | next in thread | previous in thread | raw e-mail
On Saturday 19 December 2009 12:27:12 Ulrich Spörlein wrote:
> On Tue, 15.12.2009 at 13:13:28 -0500, John Baldwin wrote:
> > On Tuesday 15 December 2009 12:45:13 pm Harti Brandt wrote:
> > > I see. I was also thinking along these lines, but was not sure whether
> > > it is worth the trouble. I suppose this does not help to implement
> > > 64-bit counters on 32-bit architectures, though, because you cannot
> > > read them reliably without locking to sum them up, right?
> >
> > Either that or you just accept that you have a small race since it is
> > only stats. :)
>
> This might be stupid, but can we not easily *read* 64bit counters
> on 32bit machines like this:
>
> do {
> h1 = read_upper_32bits;
> l1 = read_lower_32bits;
> h2 = read_upper_32bits;
> l2 = read_lower_32bits; /* not needed */
> } while (h1 != h2);
Hi,
Just a comment. You know you don't need a while loop to get a stable value?
Should be implemented like this, in my opinion:
h1 = read_upper_32bits;
l1 = read_lower_32bits;
h2 = read_upper_32bits;
if (h1 != h2)
l1 = 0xffffffffUL;
sum64 = (h1<<32) | l1;
--HPS
home |
help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200912191244.17803.hselasky>