On Sun, Jan 16, 2011 at 8:41 PM, Kevin Grittner
<Kevin.Grittner@wicourts.gov> wrote:
> Robert Haas wrote:
\>> I think you may be confused about what the patch does - currently,
>> pages with hint bit changes are considered dirty, period.
>> Therefore, they are written whenever any other dirty page would be
>> written: by the background writer cleaning scan, at checkpoints,
>> and when a backend must write a dirty buffer before reallocating it
>> to hold a different page. The patch keeps the first of these and
>> changes the second two
>
> No, I understood that. I'm just concerned that if you eliminate the
> other two, we may be recomputing visibility based on clog often
> enough to kill performance.
>
> In other words, I'm asking that you show that the other two methods
> aren't really needed for decent overall performance.
Admittedly I've only done one test, but on the basis of that test I'd
say the other two methods ARE really needed for decent overall
performance. I think it'd be interesting to see this tested on a
machine with large shared buffers, where the background writer might
succeed in cleaning a higher fraction of the pages before the bulk
read buffer access strategy starts recycling buffers. But I'm not
very optimistic.
--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company
