On Wed, Nov 23, 2011 at 7:57 PM, Robert Haas <robertmhaas@gmail.com> wrote:
> On Wed, Nov 23, 2011 at 1:30 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
>> What I think might make more sense is to keep two variables,
>> RecentGlobalXmin with its current meaning and RecentDatabaseWideXmin
>> which considers only xmins of transactions in the current database.
>> Then HOT cleanup could select the appropriate cutoff depending on
>> whether it's working on a shared or non-shared relation.
>
> Unfortunately, that would have the effect of lengthening the time for
> which ProcArrayLock is held, and as benchmark results from Pavan's
> patch in that area show, that makes a very big difference to total
> throughput on write-heavy workloads.
Agreed. The performance effect of doing that would be noticeable, and
I quickly ruled out that solution without even mentioning it at
version one.
> On a related note, Simon's
> proposed change here would also complicate things for that patch,
> because databaseId would have to become part of PGXACT rather than
> PGPROC, and that would make the PGXACT act array larger
That is correct.
> and thus
> slower to scan. I have deep respect for the perils of not doing HOT
> cleanup quickly enough, but ProcArrayLock contention is nothing to
> sneeze at either.
If you measure the difference we'll be able to see what difference
adding 4 bytes onto every pgtran makes. I think it will be small.
OTOH, the effect of database bloat is well documented and has a
seriously negative effect on performance that easily outweighs the
slight loss.
--
Simon Riggs http://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Training & Services