Re: testing HS/SR - 1 vs 2 performance

On Fri, 2010-04-16 at 13:00 +0100, Simon Riggs wrote:
> Almost done

Here's the finished patch.

Internal changes only, no functional or user visible changes, so no
docs, just detailed explanatory comments.

Expectation is
* performance no longer depends upon max_connections
* recovery will be about same or slightly faster
* snapshots should be about equivalent primary/standby

Main changes are
* lock free add to sorted array (equivalent to GetNewTransactionId)
* bsearch for xid removal at commit/abort/TransactionIdIsInProgress
* faster, more compact approach to snapshots, with self-trimming
* some minor API changes to facilitate above
* new code to ignore deletion failures only when !consistent

Erik,

Could you retest please? 

-- 
 Simon Riggs           www.2ndQuadrant.com