Re: Delay locking partitions during INSERT and UPDATE

From: Tomas Vondra <tomas(dot)vondra(at)2ndquadrant(dot)com>
To: John Naylor <john(dot)naylor(at)2ndquadrant(dot)com>
Cc: John Naylor <jcnaylor(at)gmail(dot)com>, David Rowley <david(dot)rowley(at)2ndquadrant(dot)com>, PostgreSQL Hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org>
Subject: Re: Delay locking partitions during INSERT and UPDATE
Date: 2019-01-20 14:42:35
Message-ID: 070a66d3-0826-4093-e939-9bf68d4554ba@2ndquadrant.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On 1/20/19 5:45 AM, John Naylor wrote:
> On Sat, Jan 19, 2019 at 10:59 AM Tomas Vondra
> <tomas(dot)vondra(at)2ndquadrant(dot)com> wrote:
>>
>> On 1/19/19 12:05 AM, John Naylor wrote:
>>> I used a similar test, but with unlogged tables, and "-c 2", and got:
>>>
>>> normal table: 32000tps
>>> 10k partitions / master: 82tps
>>> 10k partitions / patch: 7000tps
>>>
>>> So far I haven't gotten quite as good performance as you and Tomas,
>>> although it's still a ~85x improvement.
>>
>> What hardware are you running the tests on? I wouldn't be surprised if
>> you were hitting some CPU or I/O bottleneck, which we're not hitting.
>
> 9 year-old laptop, Core i3. Side note, I miswrote my test parameters
> above -- should be "-c4 -j2".
>

Hmmm, I wouldn't be surprised if it was getting throttled for some
reasons (e.g. temperature).

regards

--
Tomas Vondra http://www.2ndQuadrant.com
PostgreSQL Development, 24x7 Support, Remote DBA, Training & Services

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Fabien COELHO 2019-01-20 14:48:14 Re: Alternative to \copy in psql modelled after \g
Previous Message Fabien COELHO 2019-01-20 11:35:20 Re: Alternative to \copy in psql modelled after \g