From: Tom Lane <tgl@sss.pgh.pa.us>
To: Andrew Dunstan <andrew@dunslane.net>
cc: Kevin McKibbin <kevinmckibbin123@gmail.com>,
        pgsql-performance@lists.postgresql.org
Subject: Re: pgbench: could not connect to server: Resource temporarily
 unavailable
In-reply-to: <83134bb1-3a21-059f-1cd6-4997de2652b8@dunslane.net>
References: 
 <CADc_NKg2d+oZY9mg4DdQdoUcGzN2kOYXBu-3--RW_hEe0tUV=g@mail.gmail.com>
 <3909995.1661052002@sss.pgh.pa.us>
 <35d221aa-3da4-f744-3965-ceca7f71f4ea@dunslane.net>
 <8864.1661116501@sss.pgh.pa.us>
 <83134bb1-3a21-059f-1cd6-4997de2652b8@dunslane.net>
Comments: In-reply-to Andrew Dunstan <andrew@dunslane.net>
	message dated "Sun, 21 Aug 2022 17:26:55 -0400"
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <33897.1661118503.1@sss.pgh.pa.us>
Date: Sun, 21 Aug 2022 17:48:23 -0400
Message-ID: <33898.1661118503@sss.pgh.pa.us>
Archived-At: 
 <https://www.postgresql.org/message-id/33898.1661118503%40sss.pgh.pa.us>
Precedence: bulk

Andrew Dunstan <andrew@dunslane.net> writes:
> On 2022-08-21 Su 17:15, Tom Lane wrote:
>> On the whole this is smelling more like a Linux kernel bug than
>> anything else.

> *nod*

Conceivably we could work around this in libpq: on EAGAIN, just
retry the failed connect(), or maybe better to close the socket
and take it from the top with the same target server address.

On the one hand, reporting EAGAIN certainly sounds like an
invitation to do just that.  On the other hand, if the failure
is persistent then libpq is locked up in a tight loop --- and
"Insufficient entries in the routing cache" doesn't seem like a
condition that would clear immediately.

It's also pretty unclear why the kernel would want to return
EAGAIN instead of letting the nonblock connection path do the
waiting, which is why I'm suspecting a bug rather than designed
behavior.

I think I'm disinclined to install such a workaround unless we
get confirmation from some kernel hacker that it's operating
as designed and application-level retry is intended.

			regards, tom lane