Re: Read-ahead and parallelism in redo recovery - Mailing list pgsql-hackers

From Decibel!
Subject Re: Read-ahead and parallelism in redo recovery
Date
Msg-id 3AAB6457-A03A-4DAA-8457-743F712F7289@decibel.org
Whole thread Raw
In response to Re: Read-ahead and parallelism in redo recovery  (Florian Weimer <fweimer@bfk.de>)
Responses Re: Read-ahead and parallelism in redo recovery  ("Heikki Linnakangas" <heikki@enterprisedb.com>)
Re: Read-ahead and parallelism in redo recovery  (Tom Lane <tgl@sss.pgh.pa.us>)
List pgsql-hackers
On Feb 29, 2008, at 8:10 AM, Florian Weimer wrote:
> In the end, I wouldn't be surprised if for most loads, cache warming
> effects dominated recovery times, at least when the machine is not
> starved on RAM.


Uh... that's exactly what all the synchronous reads are doing...  
warming the cache. And synchronous reads are only fast if the system  
understands what's going on and reads a good chunk of data in at  
once. I don't know that that happens.

Perhaps a good short-term measure would be to have recovery allocate  
a 16M buffer and read in entire xlog files at once.
-- 
Decibel!, aka Jim C. Nasby, Database Architect  decibel@decibel.org
Give your computer some brain candy! www.distributed.net Team #1828



pgsql-hackers by date:

Previous
From: Tom Lane
Date:
Subject: Re: [BUGS] bug or not bug, xmlvalidate(xml, text) can read and show one line from file
Next
From: "Heikki Linnakangas"
Date:
Subject: Re: Read-ahead and parallelism in redo recovery