Re: Append with naive multiplexing of FDWs

>It is "asynchronous append on async-capable'd postgres-fdw scans". It

>could be called as such in the sense that it is intended to be used

>with sharding.

 Yes that's it.

 

>Did you looked at my benchmarking result upthread?  Even it gives

>significant gain even when gathering large number of tuples from

>multiple servers or even from a single server.  It is because of its

>asynchronous nature.

I mean it gain performance at first, but it mets bottleneck while

increase the number of the nodes.

For example:

   It has 2 nodes, it will gain 200% performance.

   It has 3 nodes, it will gain 300% performance.

   However,

   It has 4 nodes, it gain 300% performance.

   It has 5 nodes, it gain 300% performance.

   ...

    

 

----

Highgo Software (Canada/China/Pakistan)
URL : www.highgo.ca
EMAIL: mailto:movead(dot)li(at)highgo(dot)ca