Date: Sat, 12 Apr 2003 15:48:56 -0400 From: Chris BeHanna <cbehanna@panasas.com> To: stable@freebsd.org Subject: Re: PATCH: Forcible delaying of UFS (soft)updates Message-ID: <200304121548.56524.cbehanna@panasas.com> In-Reply-To: <C1398952884B984C8AB1519CEAC66F940A18DF@OLYMPIC.AD.HartBrothers.Com> References: <C1398952884B984C8AB1519CEAC66F940A18DF@OLYMPIC.AD.HartBrothers.Com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Saturday 12 April 2003 12:58, Dave Hart wrote:
> Marko Zec said:
> > Alfred Perlstein wrote:
> > > * Marko Zec <zec@tel.fer.hr> [030411 19:01] wrote:
> > > > When enabled, the extended delaying policy introduces
> > > > some additional changes:
> > > >
> > > > - fsync() no longer flushes the buffers to disk, but
> > > > returns immediately instead;
>
> [...]
>
> > > Making fsync() not work is a good way to make any sort
> > > of userland based transactional system break badly.
>
> [...]
>
> > If the disk would start spinning every now and than,
> > the whole patch would than become pointless...
>
> As I feared.
>
> > [...] the fact that the modified fsync() just returns
> > without doing anything useful doesn't mean the data will be
> > lost - it will simply be delayed until the next coalesced
> > updating occurs.
>
> Unless, of course, your system or power happens to fail.
> Imagine you have a database program keeping track of banking
> transactions. [...]
Then you won't be running that program on a *laptop*, now, will
you? It'll be in a NOC with hefty power-failover hardware already in
place.
Can we pretty please keep criticisms of this patch in their proper
context? Power-saving features for a *laptop* have little or no
bearing on the behavior of mission-critical back office applications.
--
Chris BeHanna
Software Engineer (Remove "bogus" before responding.)
behanna@bogus.zbzoom.net
Turning coffee into software since 1990.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200304121548.56524.cbehanna>