| From: | Xuneng Zhou <xunengzhou(at)gmail(dot)com> |
|---|---|
| To: | Feike Steenbergen <feikesteenbergen(at)gmail(dot)com> |
| Cc: | Eduard Stepanov <crtxcz(at)gmail(dot)com>, Induja Sreekanthan <indujas(at)google(dot)com>, pgsql-hackers(at)postgresql(dot)org, Simhachala Sasikanth Gottapu <simhachala(at)google(dot)com>, Vishal Bagga <vishalbagga(at)google(dot)com>, Madhukar <madhukarprasad(at)google(dot)com>, Shihao Zhong <shihaozhong(at)google(dot)com>, Yi Ding <yidin(at)google(dot)com>, Hardik Singh Negi <hardiksnegi(at)google(dot)com> |
| Subject: | Re: BUG: ReadStream look-ahead exhausts local buffers when effective_io_concurrency>=64 |
| Date: | 2026-07-03 03:54:31 |
| Message-ID: | CABPTF7VV0H5DRZBsC3T-SOenVE5MkdwpsWSy9pEJ_sPOuCC5uQ@mail.gmail.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Hi Feike,
On Wed, May 6, 2026 at 8:48 PM Feike Steenbergen
<feikesteenbergen(at)gmail(dot)com> wrote:
>
>
>
> On Wed, 6 May 2026 at 14:24, Feike Steenbergen <feikesteenbergen(at)gmail(dot)com> wrote:
> > For now, the problem disappears again when switching to io_method='worker'
>
> I spoke too soon it seems. It happens less frequently, but we do still have the issue even with io_method='worker'.
> Reverting to io_method='sync' as I would expect that will solve the issue.
Interestingly, I wonder why this variance would occur in production.
This is the more interesting part of this thread. I did some
investigation & experiment, pg 19 passed the reproducer even if
da6874635db is removed. A series of improvements made in April may
contribute to this. Will return soon to share the findings..
--
Regards,
Xuneng Zhou
HighGo Software Co., Ltd.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | jian he | 2026-07-03 03:55:43 | Re: Row pattern recognition |
| Previous Message | Dilip Kumar | 2026-07-03 03:53:49 | Re: Proposal: Conflict log history table for Logical Replication |