> > I had the flush params commented out = set to defaults.
> > Now trying with:
> > MaxUnflushedWrites = 1000
> > MaxUnflushedWriteTime = 300
> >
> > I assume that should imply that a delay of 300 seconds (5 min) after
> > NBACKUP -L should be sufficient. Will try with ten minutes.
> >
>
> Didn't work. I still got a modified file error on copy.
>
> Now trying with these settings
> MaxUnflushedWrites = 100
> MaxUnflushedWriteTime = 60
>
> And also 100 select transactions in an isql script between lock and
> copy. If this works as expected, I would assume that each transaction
> results in at least one disk write (header page?), which should force a
> flush. But perhaps the MaxUnflushesWrites param doesn't mean number of
> write operations to any page, but rather number of pages that have been
> written to? In that case I'm not sure my dummy SQL will have any effect.

MaxUnflushesWrites is not about every single page write. It is sooner about
"write process" as a whole. Every write (not read-only) transaction finishes
with such "write process": when all pages modified by this (and probably some
others) transaction is writen to disk.

> I'm reluctant to use a script/mode/setting that essentially ignores the
> flush and copies anyway. I assume this would imply a risk of a corrupt
> copy. If not, please explain why.

There is no writes to the souce file contents and copy can't be corrupted.

In any case - you asks for opinions and mine is above. This is just an opinion.
Decision is up to you ;)

Regards,
Vlad