| From: | Simon Riggs <simon(at)2ndquadrant(dot)com> |
|---|---|
| To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
| Cc: | Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>, Greg Stark <gsstark(at)mit(dot)edu>, Russell Smith <mr-russ(at)pws(dot)com(dot)au>, josh(at)agliodbs(dot)com, Postgres Hackers <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: Checkpoint cost, looks like it is WAL/CRC |
| Date: | 2005-07-08 18:35:15 |
| Message-ID: | 1120847715.3940.344.camel@localhost.localdomain |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Fri, 2005-07-08 at 09:47 -0400, Tom Lane wrote:
> Simon Riggs <simon(at)2ndquadrant(dot)com> writes:
> > Having raised that objection, ISTM that checking for torn pages can be
> > accomplished reasonably well using a few rules...
>
> I have zero confidence in this; the fact that you can think of
> (incomplete, inaccurate) heuristics for heap-page operations doesn't
> mean you can make it work for indexes.
If we can find heuristics that cover some common cases, then I would be
happy. Anything that allows us to prove that we don't need to recover is
good. If we reduce the unknown state to an acceptable risk, then we are
more likely to make use of the performance gain in the real world.
Of course, they need to be accurate. Let's not get hung up on my error
rate.
I don't think we should care too much about indexes. We can rebuild
them...but losing heap sectors means *data loss*.
Best Regards, Simon Riggs
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Tom Lane | 2005-07-08 18:45:43 | Re: Checkpoint cost, looks like it is WAL/CRC |
| Previous Message | Josh Berkus | 2005-07-08 16:27:28 | Re: Checkpoint cost, looks like it is WAL/CRC |