On 09/27/2017 10:50 PM, Andres Freund wrote:
This'll allow the later patches to allow the compiler to perform the
relevant optimizations. It also allows to optimize e.g. pq_sendint64()
to avoid having to do multiple byteswaps.
After applying all the required patches, able to see some performance gain
Virtual Machine configuration - Centos 6.5 x64 / 16 GB RAM / 8 VCPU core
processor
./pgbench -M prepared -j 10 -c 10 -f /tmp/pgbench-many-cols.sql postgres
-T TIME
After taking Median of 3 run -
Case 1 – TIME=300
PG HEAD =>41285.089261 (excluding connections establishing)
PG HEAD+patch =>tps= 42446.626947(2.81+% vs. head)
Case 2- TIME=500
PG HEAD =>tps = 41252.897670 (excluding connections establishing)
PG HEAD+patch =>tps= 42257.439550(2.43+% vs. head)
Case 3- TIME=1000
PG HEAD =>tps = 1061.031463 (excluding connections establishing)
PG HEAD+patch => tps= 8011.784839(3.30+% vs. head)
Case 4-TIME=1500
PG HEAD =>tps = 40365.099628 (excluding connections establishing)
PG HEAD+patch =>tps= 42385.372848(5.00+% vs. head)
--
regards,tushar
EnterpriseDB https://www.enterprisedb.com/
The Enterprise PostgreSQL Company
