Date: Mon, 24 Jan 2011 15:47:37 +0000 From: Bruce Cran <bruce@cran.org.uk> To: Jeremy Chadwick <freebsd@jdc.parodius.com> Cc: freebsd-fs@freebsd.org Subject: Re: Write cache, is write cache, is write cache? Message-ID: <20110124154737.000025c1@unknown> In-Reply-To: <20110124144236.GA19500@icarus.home.lan> References: <1ABA88EDF84B6472579216FE@Octa64> <20110122111045.GA59117@icarus.home.lan> <AANLkTik_rii-F_QWTP3OdyTS0gx1tDxv6--2LGGF6Ear@mail.gmail.com> <20110124144236.GA19500@icarus.home.lan>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 24 Jan 2011 06:42:36 -0800 Jeremy Chadwick <freebsd@jdc.parodius.com> wrote: > In the case of ZFS, why would all data be written to the disk every > single time there's a write(2) operation? Performance-wise that makes > absolutely no sense. So there is absolutely going to be a "window of > failure" that can happen, and mirroring/raidz can recover from that, > as a result of the checksum "stuff". Very few people would expect data to be on disk after every write(2), but they should expect it to be on disk after every fsync(2) - my understanding is that databases depend on that for correct operation. -- Bruce Cran
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20110124154737.000025c1>