Re: Anyone tried Flashcache with PostgreSQL?

From: Cédric Villemain <cedric(dot)villemain(dot)debian(at)gmail(dot)com>
To: Arjen van der Meijden <acmmailing(at)tweakers(dot)net>
Cc: pgsql-performance(at)postgresql(dot)org
Subject: Re: Anyone tried Flashcache with PostgreSQL?
Date: 2011-03-07 15:48:07
Message-ID: AANLkTimiTFh20uo5gS7r0uA=ap42sX5Ta+8edDaOjTng@mail.gmail.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-performance

2011/3/3 Arjen van der Meijden <acmmailing(at)tweakers(dot)net>:
> On 2-3-2011 16:29 Robert Haas wrote:
>>
>> On Mon, Feb 28, 2011 at 2:09 PM, Josh Berkus<josh(at)agliodbs(dot)com>  wrote:
>>>
>>> Does anyone have the hardware to test FlashCache with PostgreSQL?
>>>
>>> http://perspectives.mvdirona.com/2010/04/29/FacebookFlashcache.aspx
>>>
>>> I'd be interested to hear how it performs ...
>>
>> It'd be a lot more interesting if it were a write-through cache rather
>> than a write-back cache, wouldn't it?
>
> That's what bcache tries to accomplish, both read and write cache.
> It also appears to aim to be more widely usable, rather than the relatively
> specific requirements the facebook variant is designed for.
>
> http://bcache.evilpiepirate.org/
>
> They seem to try and combine both the dedicated ZIL and L2ARC functionality
> from ZFS in one block device based caching layer.

Bcache looks more interesting, yes. Still it is not production ready
and get some dangerous caveeat with administration tasks (for example
remounting devices without their caches open the door of all evils).

--
Cédric Villemain               2ndQuadrant
http://2ndQuadrant.fr/     PostgreSQL : Expertise, Formation et Support

In response to

Browse pgsql-performance by date

  From Date Subject
Next Message Jon Nelson 2011-03-07 19:07:35 plan variations: join vs. exists vs. row comparison
Previous Message Oleg Bartunov 2011-03-07 15:34:35 Re: Performance issues