Horton

RE: Speed up transaction completion faster after many relations are accessed in a transaction

Tsunakawa, Takayuki <tsunakawa.takay@jp.fujitsu.com>

View thread View on postgr.es
From: "Tsunakawa, Takayuki" <tsunakawa.takay@jp.fujitsu.com>
To: 'Peter Eisentraut' <peter.eisentraut@2ndquadrant.com>
Cc: "Imai, Yoshikazu" <imai.yoshikazu@jp.fujitsu.com>, Tom Lane <tgl@sss.pgh.pa.us>, Andres Freund <andres@anarazel.de>, 'Simon Riggs' <simon@2ndquadrant.com>, David Rowley <david.rowley@2ndquadrant.com>, "pgsql-hackers@lists.postgresql.org" <pgsql-hackers@lists.postgresql.org>
Date: 2019-04-04T04:37:59Z
Lists: pgsql-hackers 
Hi Peter,

From: Peter Eisentraut [mailto:peter.eisentraut@2ndquadrant.com]
> I did a bit of performance testing, both a plain pgbench and the
> suggested test case with 4096 partitions.  I can't detect any
> performance improvements.  In fact, within the noise, it tends to be
> just a bit on the slower side.
> 
> So I'd like to kick it back to the patch submitter now and ask for more
> justification and performance analysis.
> 
> Perhaps "speeding up planning with partitions" needs to be accepted first?

David kindly showed how to demonstrate the performance improvement on March 26, so I changed the status to needs review.  I'd appreciate it if you could continue the final check.


Regards
Takayuki Tsunakawa

Commits

  1. Reorder LOCALLOCK structure members to compact the size

  2. Be more careful to not lose sync in the FE/BE protocol.