Re: optimize lookups in snapshot [sub]xip arrays - Mailing list pgsql-hackers

From Nathan Bossart
Subject Re: optimize lookups in snapshot [sub]xip arrays
Date
Msg-id 20220808223254.GA1393216@nathanxps13
Whole thread Raw
In response to Re: optimize lookups in snapshot [sub]xip arrays  (John Naylor <john.naylor@enterprisedb.com>)
Responses Re: optimize lookups in snapshot [sub]xip arrays
List pgsql-hackers
On Mon, Aug 08, 2022 at 01:46:48PM +0700, John Naylor wrote:
> Okay, I think it's basically in good shape. Since it should be a bit
> faster than a couple versions ago, would you be up for retesting with
> the original test having 8 to 512 writers?

Sure thing.  The results are similar.  As before, the improvements are most
visible when the arrays are large.

    writers  head  patch
    8        672   680
    16       639   664
    32       701   689
    64       705   703
    128      628   653
    256      576   627
    512      530   584
    768      450   536
    1024     350   494

> And also add the const
> markers we discussed upthread?

Oops, sorry about that.  This is done in v9.

> Aside from that, I plan to commit this
> week unless there is further bikeshedding.

Great, thanks.

-- 
Nathan Bossart
Amazon Web Services: https://aws.amazon.com

Attachment

pgsql-hackers by date:

Previous
From: "Euler Taveira"
Date:
Subject: Re: logical replication restrictions
Next
From: Thomas Munro
Date:
Subject: Re: Checking pgwin32_is_junction() errors