On Mon, 1 Mar 2010 12:00:56 -0700 Mark Post <mp...@novell.com> wrote:
> >>> On 2/25/2010 at 12:07 PM, Ron Foster at Baldor-IS <rfos...@baldor.com> > >>> wrote: > > Everyone, > > > > The following explains why I might want to know this. > > Ron, > > The delay between the application issuing the write, and the I/O being issued > by the kernel is more on the order of seconds. Certainly not hours or days. > If some change that had been made a week ago suddenly disappeared after a > crash and reboot, that wasn't due to the kernel caching the write. Something > else was definitely happening there. There is one exception in some kernels - that is dirty mmap data may escape for days due to bugs. I couldn't tell you offhand if the enterprise vendor kernels have that bug (or bug + fix) but certainly there have been problems like that. Usual dirty caching is about 5-60 seconds. Alan ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to lists...@vm.marist.edu with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390