From: Tom Lane <tgl@sss.pgh.pa.us>
To: Andres Freund <andres@anarazel.de>
cc: pgsql-hackers@postgresql.org, Thomas Munro <thomas.munro@enterprisedb.com>
Subject: Re: Large writable variables
In-reply-to: <20181015200754.7y7zfuzsoux2c4ya@alap3.anarazel.de>
References: <20181015200754.7y7zfuzsoux2c4ya@alap3.anarazel.de>
Comments: In-reply-to Andres Freund <andres@anarazel.de>
	message dated "Mon, 15 Oct 2018 13:07:54 -0700"
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <18429.1539635786.1@sss.pgh.pa.us>
Date: Mon, 15 Oct 2018 16:36:26 -0400
Message-ID: <18430.1539635786@sss.pgh.pa.us>
Precedence: bulk

Andres Freund <andres@anarazel.de> writes:
> So we have 500kb of not-initialized memory mapped into every
> process. That's, uh, not nothing.

Bleah.

> 0000000008585088 0000000000131104 b hist_entries
> 0000000008716192 0000000000016384 b hist_start

I'm unsure what fraction of processes would have use for these.

> 0000000008435040 0000000000085280 b DCHCache
> 0000000008391168 0000000000043840 b NUMCache

We could surely allocate these on first use.

> 0000000008560224 0000000000023440 b tzdefrules_s
> 0000000008536704 0000000000023440 b gmtmem.7009

I think that tzdefrules_s is not used in common cases (though I could be
wrong about that), so we could win by alloc-on-first-use.  The same might
be true for gmtmem, but there's a sticking point: there is no provision
for failure there, so I'm unsure how we avoid crashing on OOM.

> 0000000008238336 0000000000008192 b PqRecvBuffer
> 0000000008734208 0000000000005136 B BackendWritebackContext
> 0000000008386368 0000000000003200 b held_lwlocks

These are below my personal threshold of pain.

> fmgr_builtins isn't readonly even though declared a const - I assume
> because it's full of addresses that will be mapped differently from
> execution to execution.

Check.

> I'm unclear as to why ScanKeywords, DCH_keywords aren't in a readonly
> section.

I think it's the same problem: pointers can't be truly const because
they have to be changed if one relocates the executable.

We could possibly fix these by changing the data structure so that
what's in a ScanKeywords entry is an offset into some giant string
constant somewhere.  No idea how that would affect performance, but
I do notice that we could reduce the sizeof(ScanKeyword), which can't
hurt.

			regards, tom lane