Re: Proposal: scan key push down to heap [WIP]

On Sat, Nov 19, 2016 at 6:48 PM, Dilip Kumar <dilipbalaut@gmail.com> wrote:
> patch1: Original patch (heap_scankey_pushdown_v1.patch), only
> supported for fixed length datatype and use heap_getattr.
>
> patch2: Switches memory context in HeapKeyTest + Store tuple in slot
> and use slot_getattr instead of heap_getattr.
>
> patch3: call HeapKeyTest in SeqNext after storing slot, and also
> switch memory context before calling HeapKeyTest.
>
> I haven't yet tested patch3 with TPCH, I will do that once machine is available.

As promised, I have taken the performance with TPCH benchmark and
still result are quite good. However this are less compared to older
version (which was exposing expr ctx and slot to heap).

Query       Head             [1] Patch3               Improvement
Q3           36122.425      32285.608         10%
Q4           6797               5763.871           15%
Q10        17996.104      15878.505          11%
Q12        12399.651        9969.489          19%

 [1] heap_scankey_pushdown_POC_V3.patch : attached with the mail.

--
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com