Re: Speeding up INSERTs and UPDATEs to partitioned tables - Mailing list pgsql-hackers

On 11/4/18 5:07 AM, David Rowley wrote:
> I've attached v13 which hopefully addresses these.
> 

I ran a test against the INSERT case using a 64 hash partition.

Non-partitioned table: ~73k TPS
Master: ~25k TPS
0001: ~26k TPS
0001 + 0002: ~68k TPS

The profile of 0001 shows that almost all of 
ExecSetupPartitionTupleRouting() is find_all_inheritors(), hence the 
last test with a rebase of the original v1-0002 patch.

Best regards,
  Jesper