Re: Use generation context to speed up tuplesorts

On 8/8/21 9:02 AM, David Rowley wrote:
> On Sat, 7 Aug 2021 at 12:10, Tomas Vondra <tomas(dot)vondra(at)enterprisedb(dot)com> wrote:
>>
>> On 8/6/21 3:07 PM, David Rowley wrote:
>>> All of the tests show that the patches to improve the allocation
>>> efficiency of generation.c don't help to improve the results of the
>>> test cases. I wondered if it's maybe worth trying to see what happens
>>> if instead of doubling the allocations each time, quadruple them
>>> instead. I didn't try this.
>>>
>>
>> I doubt quadrupling the allocations won't help very much, but I suspect
>> the problem might be in the 0004 patch - at least that's what shows
>> regression in my results. Could you try with just 0001-0003 applied?
>
> But 0004 only changes the logic which controls the threshold of when
> we allocate an oversized chunk. It looks like the threshold is 512KB
> with the 0004 patch. My test is only doing a maximum allocation of
> 296 bytes so will never allocate an oversized chunk.
>
> Can you explain why you think 0004 would cause performance regressions?
>

It's based solely on results of my benchmarks, where this patch seems to
cause performance regression. I agree it's a bit bizzare, considering
what the patch does.

regards

--
Tomas Vondra
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company