Date: Tue, 23 Dec 2008 20:19:35 +0900 From: Norikatsu Shigemura <nork@FreeBSD.org> To: Maxim Sobolev <sobomax@FreeBSD.org> Cc: Ed Schouten <ed@80386.nl>, Roman Divacky <rdivacky@FreeBSD.org>, Current <freebsd-current@FreeBSD.org>, FreeBSD Subject: Re: Change select(2) to kevent(2) on script(1)... Message-ID: <20081223201935.b5948bb7.nork@FreeBSD.org> In-Reply-To: <494FFF42.7090102@FreeBSD.org> References: <20081221012752.cdc5cbfc.nork@FreeBSD.org> <20081221211949.GS1176@hoeg.nl> <20081222091203.GA28920@freebsd.org> <494F740E.3040502@FreeBSD.org> <20081223002901.9b71e60d.nork@FreeBSD.org> <494FFF42.7090102@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi sobomax! On Mon, 22 Dec 2008 12:57:38 -0800 Maxim Sobolev <sobomax@FreeBSD.org> wrote: > > I think that performance improvement is significant(I don't > > think performance improved by my patch). But my patch is the > And can you explain where that "significant improvement" comes from? Are > you saying that tty layer / pseudo-terminal driver is somehow much more > efficient with kqeue(2) compared to select(2)/poll(2)? There is > something broken about it if so. > In any case without any numbers this discussion is pretty much pointless. I'm sorry. My "significant" means is "important". I missed word choice. I consider that: 1. on select(2) v.s. kqueue(2) in this case, not performance improved. 2. both select(2) and kqueue(2) are not broken. I'm interesting in implementation of script(1) by kqueue(2).
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20081223201935.b5948bb7.nork>