Re: DB logging (was: Problem with the numbers I reported yesterday) - Mailing list pgsql-hackers

From ocie@paracel.com
Subject Re: DB logging (was: Problem with the numbers I reported yesterday)
Date
Msg-id 9802170144.AA00326@dolomite.paracel.com
Whole thread Raw
In response to Re: DB logging (was: Problem with the numbers I reported yesterday)  ("Kent S. Gordon" <kgor@inetspace.com>)
Responses Re: DB logging (was: Problem with the numbers I reported yesterday)  (Bruce Momjian <maillist@candle.pha.pa.us>)
List pgsql-hackers
Kent S. Gordon wrote:

[SNIP]

> Log files do get very big with image logging.  I would not expect a
> huge win in performance unless the log device is a raw device.  On a
> cooked device (file system) buffer cache effects are very large (all
> disk data is being buffered both by postgresql and the OS buffer
> cache.  The buffer cache is actual harmfully in this case, since data
> is not reused, and the writes are synced.  The number of writes to the
> log also flush out other buffer from the cache leading to even more
> io.).  If a system does not have raw devices (linux, NT), it would be
                                                ^^^^^
What exactly do you mean by "raw devices" that it is not offered by
Linux?  If I take a partition of one of my hard drives and I don't
make a filesystem on it, I can perform reads and writes on the "raw
device" /dev/hd?? or /dev/sd??  I didn't think these writes were
buffered (if that's what you're referring to), but I could be wrong.

Ocie Mitchell.

pgsql-hackers by date:

Previous
From: The Hermit Hacker
Date:
Subject: Re: [HACKERS] configure doesn't handle --with-compiler correctly
Next
From: Bruce Momjian
Date:
Subject: Re: DB logging (was: Problem with the numbers I reported yesterday)