Horton
Menu

Re: increasing the default WAL segment size

Robert Haas <robertmhaas@gmail.com>

View thread
From: Robert Haas <robertmhaas@gmail.com>
To: Andres Freund <andres@anarazel.de>
Cc: Beena Emerson <memissemerson@gmail.com>, Peter Eisentraut <peter.eisentraut@2ndquadrant.com>, "pgsql-hackers@postgresql.org" <pgsql-hackers@postgresql.org>
Date: 2016-12-20T13:10:29Z
Lists: pgsql-hackers 
On Tue, Dec 20, 2016 at 3:28 AM, Andres Freund <andres@anarazel.de> wrote:
> I do think this has the potential for negative performance
> implications. Consider code like
>                         /* skip over the page header */
>                         if (CurrPos % XLogSegSize == 0)
>                         {
>                                 CurrPos += SizeOfXLogLongPHD;
>                                 currpos += SizeOfXLogLongPHD;
>                         }
>                         else
> right now that's doable in an efficient manner, because XLogSegSize is
> constant. If it's a variable and the compiler doesn't even know it's a
> power-of-two, it'll have to do a full "div" - and that's quite easily
> noticeable in a lot of cases.
>
> Now it could entirely be that the costs of this will be swamped by
> everything else, but I'd not want to rely on it.

We could use the GUC assign hook to compute a mask and a shift, so
that this could be written as (CurrPos & mask_variable) == 0.  That
would avoid the division instruction, though not the memory access.  I
hope this is all in the noise, though.  I know this is code is hot but
I think it'll be hard to construct a test case where the bottleneck is
anything other than the speed at which the disk can absorb bytes.  I
suppose we could set fsync=off and put the whole cluster on a RAMDISK
to avoid those bottlenecks, but of course no real storage system
behaves like that.

-- 
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company

Commits

Same data as JSON: GET /api/v1/messages/:b64id/commits the thread's linked commits as JSON, with link sources. API reference →

  1. Make WAL segment size configurable at initdb time.

  2. Perform only one ReadControlFile() during startup.

  3. Introduce BYTES unit for GUCs.

  4. Remove useless duplicate inclusions of system header files.

  5. Refactor other replication commands to use DestRemoteSimple.

  6. Add a SHOW command to the replication command language.

  7. Add a new DestReceiver for printing tuples without catalog access.

  8. Support fls().

  9. Extend yesterday's patch making BLCKSZ and RELSEG_SIZE configurable to also

  10. Commit the reasonably uncontroversial parts of J.R. Nield's PITR patch, to

  11. XLOG (also known as WAL -:)) Bootstrap/Startup/Shutdown.

  12. Transaction log manager core code.