Re: [HACKERS] Clock with Adaptive Replacement - Mailing list pgsql-hackers

From Andrey Borodin
Subject Re: [HACKERS] Clock with Adaptive Replacement
Date
Msg-id FC949382-02EE-4AAA-8D76-9513EE2470BA@yandex-team.ru
Whole thread Raw
In response to Re: [HACKERS] Clock with Adaptive Replacement  (Andres Freund <andres@anarazel.de>)
Responses Re: [HACKERS] Clock with Adaptive Replacement  (Andres Freund <andres@anarazel.de>)
Re: [HACKERS] Clock with Adaptive Replacement  (Thomas Munro <thomas.munro@enterprisedb.com>)
List pgsql-hackers

> 24 апр. 2018 г., в 23:14, Andres Freund <andres@anarazel.de> написал(а):
>
> On 2018-04-24 17:16:47 +0500, Andrey Borodin wrote:
>> But, I think that cost of development of real page eviction strategy
>> itself is neglectable small compared to infrastructure changes needed
>> by any non-CS5 strategy.
>
> What problems are you seeing? This isn't a lot of code?
1. Teaching BgWriter to used data from eviction strategy to aggressively flush data to disk (instead of ++next_to_clean
)
2. Implementing strategies as lock-free algorithms for freelist
These parts seem most important for benchmarking.
Also:
3. Converting all rings to single buffer manager where possible
4. Using O_DIRECT while writing data files
5. Using aio and scheduling of writes
These parts are not necessary, but most challenging, while not impossible though.

Best regards, Andrey Borodin.

pgsql-hackers by date:

Previous
From: Thomas Munro
Date:
Subject: Re: Excessive PostmasterIsAlive calls slow down WAL redo
Next
From: Heikki Linnakangas
Date:
Subject: Re: Racing DEADLOCK on PostgreSQL 9.3