Date: Wed, 07 Nov 2007 14:23:30 +0100 From: Ivan Voras <ivoras@freebsd.org> To: freebsd-current@freebsd.org Subject: Re: geom_raid5 inclusion in HEAD? Message-ID: <fgse36$lbe$1@ger.gmane.org> In-Reply-To: <4731B8DA.8010201@conducive.net> References: <fgs516$mj8$1@ger.gmane.org> <487375.1457.qm@web30309.mail.mud.yahoo.com> <9bbcef730711070450x308129b4rb18577c317eee197@mail.gmail.com> <4731B8DA.8010201@conducive.net>
next in thread | previous in thread | raw e-mail | index | archive | help
韓家標 Bill Hacker wrote: > Ivan Voras wrote: >> On 07/11/2007, Arne Wörner <arne_woerner@yahoo.com> wrote: >>> Maybe gjournal could help, because graid5 honors the BIO_FLUSH, but >>> that is >>> untested... >> >> Yes, AFAIK this would work. >> > > A RAID5 is one of the harder ones to do both fast and well in > software-only. > > The better hardware ($$$) controllers have fast hardware XOR engines as > well as CPU-as-state-machines and battery-backed cache, and THEY have to > work hard. I agree. But regarding the immediate topic of gjournal on graid5: gjournal has hooks in the UFS code to do full sync before journal switch (commit), which it then propagates to the devices and issues BIO_FLUSH, so it can offer both speed and reliability in this particular case. > Given decent hardware & any UPS that costs less than the hardware > controller, these are 'choices' - not really show-stoppers. In theory this is correct, in practice still many people don't know the choices they are implicitly making.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?fgse36$lbe$1>