Date: Tue, 19 Jun 2007 00:07:31 +0900 From: Takeharu KATO <takeharu1219@ybb.ne.jp> To: Poul-Henning Kamp <phk@phk.freebsd.dk> Cc: freebsd-current@freebsd.org Subject: Re: Evaluation of High Precision Event Timer Driver for userland timer facility Message-ID: <46769FB3.8060002@ybb.ne.jp> In-Reply-To: <6014.1179937161@critter.freebsd.dk> References: <6014.1179937161@critter.freebsd.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi Thank you for your comment. I'm sorry that the reply is late. > > Basing this facility on the HPET almost guarantees that we cannot > use it in FreeBSD, because the HPET is not available on more than > a couple of our architectures. > Certainly the facility is not available non-PC platform, it highly depends on board specs. How do you think about introducing this facility as a kernel option. As far as I think, this facility is a kind of device driver, this is not timer facility which is used in common. Certainly, it may have no dramatic effect as you said. Therefore, I did not mean to introduce this facility into FreeBSD by all means, certainly. > Without userland access to the timekeeping hardware, it is difficult > to avoid the system call overhead and once in the kernel anyway > it is doubtful that splitting the code between userland and > kernel really gives much of a payoff. > > I am aware that Linux has a userland timestamping facility, but > I am also aware of its numerous shortcomings. > Sorry, I can not figure out shortcomings of this, would you tell me shortcomings of mmaped HPET time stamp facility?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?46769FB3.8060002>