Date: Sat, 2 Jun 2007 17:31:46 -0400 From: Kris Kennaway <kris@obsecurity.org> To: Poul-Henning Kamp <phk@phk.freebsd.dk> Cc: takawata@freeBSD.org, Dag-Erling Sm??rgrav <des@des.no>, Nate Lawson <nate@root.org>, current@freeBSD.org, Kris Kennaway <kris@obsecurity.org> Subject: Re: HPET vs other timers Message-ID: <20070602213146.GA1302@rot13.obsecurity.org> In-Reply-To: <47223.1180818913@critter.freebsd.dk> References: <20070602194151.GA1604@rot13.obsecurity.org> <47223.1180818913@critter.freebsd.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, Jun 02, 2007 at 09:15:13PM +0000, Poul-Henning Kamp wrote: > In message <20070602194151.GA1604@rot13.obsecurity.org>, Kris Kennaway writes: ^^^ JFYI, I didn't :-) > > >> Anyone able to speculate why though? HPET only reads 32 bits from a > >> memory mapped region. No locking or other requirements. ACPI_timer > >> does multiple IO ops, which according to bde@ are much slower than > >> memory reads. > > HPET needs to do metastability mitigation and is not "just a read > from a memory mapped region". > > -- > Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 > phk@FreeBSD.ORG | TCP/IP since RFC 956 > FreeBSD committer | BSD since 4.3-tahoe > Never attribute to malice what can adequately be explained by incompetence. >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070602213146.GA1302>