Date: Mon, 06 Sep 2010 14:10:13 +0300 From: Andriy Gapon <avg@icyb.net.ua> To: Kostik Belousov <kostikbel@gmail.com> Cc: freebsd-fs@freebsd.org Subject: Re: zfs very poor performance compared to ufs due to lack of cache? Message-ID: <4C84CC15.5000907@icyb.net.ua> In-Reply-To: <20100906110406.GC2396@deviant.kiev.zoral.com.ua> References: <7EA7AD058C0143B2BF2471CC121C1687@multiplay.co.uk> <1F64110BFBD5468B8B26879A9D8C94EF@multiplay.co.uk> <4C83A214.1080204@DataIX.net> <06B9D23F202D4DB88D69B7C4507986B7@multiplay.co.uk> <4C842905.2080602@DataIX.net> <330B5DB2215F43899ABAEC2CF71C2EE0@multiplay.co.uk> <4C84C857.1070306@icyb.net.ua> <20100906110406.GC2396@deviant.kiev.zoral.com.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
on 06/09/2010 14:04 Kostik Belousov said the following: > On Mon, Sep 06, 2010 at 01:54:15PM +0300, Andriy Gapon wrote: >> on 06/09/2010 02:57 Steven Hartland said the following: >>> Based on Jeremy's comments I'm updating the box the stable. Its building now >>> but will be the morning before I can reboot to activate changes as I need to >>> deactivate the stream instance and wait for all active connections to finish. >>> >>> That said the problem doesn't seem to be cache + free but more cache + free >>> + inactive with inactive being the large chunk, so not sure this change >>> would make any difference? >>> >>> How does ufs deal with this, does it take inactive into account? Seems a bit >>> silly for inactive pages to prevent reuse for extended periods when the >>> memory could be better used as cache. >> >> Inactive pages are also a cache, just a different kind. > Not quite. Inactive pages may be dirty. Such pages cannot be freed or reused > without pageout. Yes, they can be dirty, but I didn't say that inactive was a "clean-only" cache. ARC entries can also be dirty and it's still a cache. -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4C84CC15.5000907>