Re: Does TupleQueueReaderNext() really need to copy its result?

Hi Thomas,

+1 to the idea! I ran some experiments on both of your patches.

I could reproduce the speed gain that you saw for a plan with a simple
parallel sequential scan. However, I got no gain at all for a parallel
hash join and parallel agg query.

-----------------------------------------------------------------------

select pg_prewarm('lineitem');
-- lineitem is 17G. (TPCH scale = 20). shared_buffers = 30G
explain analyze select * from lineitem;

[w/o any patch] 99s
[w/ first patch] 89s
[w/ last minimal tuple patch] 79s

-----------------------------------------------------------------------

select pg_prewarm('lineitem');
-- lineitem is 17G. (TPCH scale = 20). shared_buffers = 30G
explain analyze select count(*) from lineitem;

[w/o any patch] 10s
[w/ first patch] 10s
[w/ last minimal tuple patch] 10s

-----------------------------------------------------------------------

select pg_prewarm('lineitem');
select pg_prewarm('orders');
-- lineitem is 17G, orders is 4G. (TPCH scale = 20). shared_buffers = 30G

explain analyze select count(*)
from lineitem
join orders on l_orderkey = o_orderkey
where o_totalprice > 5.00;

[w/o any patch] 54s
[w/ first patch] 53s
[w/ last minimal tuple patch] 56s

-----------------------------------------------------------------------

Maybe I'm missing something, since there should be improvements with
anything that has a gather?

As for gather merge, is it possible to have a situation where the slot
input to tqueueReceiveSlot() is a heap slot (as would be the case for a
simple select *)? If yes, in those scenarios, we would be incurring an
extra call to minimal_tuple_from_heap_tuple() because of the extra call
to ExecFetchSlotMinimalTuple() inside tqueueReceiveSlot() in your patch.
And since, in a gather merge, we can't avoid the copy on the leader side
(heap_copy_minimal_tuple() inside gm_readnext_tuple()), we would be
doing extra work in that scenario. I couldn't come up with a plan that
creates a scenario like this however.

Regards,
Soumyadeep (VMware)