Re: Question of Parallel Hash Join on TPC-H Benchmark

From: Zhang Mingli <zmlpostgres(at)gmail(dot)com>
To: Ba Jinsheng <bajinsheng(at)u(dot)nus(dot)edu>, pgsql-bugs(at)lists(dot)postgresql(dot)org <pgsql-bugs(at)lists(dot)postgresql(dot)org>, Tomas Vondra <tomas(at)vondra(dot)me>
Subject: Re: Question of Parallel Hash Join on TPC-H Benchmark
Date: 2024-10-10 14:47:00
Message-ID: 3c7df680-97e6-4f20-ab27-65fb8282f95e@Spark
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-bugs

Hi,

Zhang Mingli
www.hashdata.xyz
On Oct 10, 2024 at 22:41 +0800, Tomas Vondra <tomas(at)vondra(dot)me>, wrote:
>
> You can try setting parallel_setup_cost and parallel_tuple_cost to 0,
> and reducing min_parallel_{table,index}_scan_size. That should force a
> parallel plan, and you'll see if parallelism is helpful.
In addition to this, it seems you’r eager a parallel-aware HashJoin.
Check if  enable_parallel_hash = on, an explain(verbose) will show related GUCs.

In response to

Responses

Browse pgsql-bugs by date

  From Date Subject
Next Message Ba Jinsheng 2024-10-10 16:52:27 Re: Question of Parallel Hash Join on TPC-H Benchmark
Previous Message Tomas Vondra 2024-10-10 14:40:43 Re: Question of Parallel Hash Join on TPC-H Benchmark