Subject: Re: [boost] ACID transactions/flushing/MySQL InnoDB
From: Stefan Strasser (strasser_at_[hidden])
Date: 2009-12-11 03:41:36
Am Friday 11 December 2009 00:04:31 schrieb Phil Endecott:
> Hi Stefan,
> Stefan Strasser wrote:
> > writing 512 bytes, aligned to 512 bytes, without O_CREAT, when the file
> > already exists, brings the desired results
> > 2 seconds with much less disk usage.
> > that's some set of conditions.
> I would be interested to know how this compares to mmapping the file
> and then writing to memory and calling msync().
for sequential writing?
there is no real difference, with mapping a little slower in my tests, but not
the advantage of mapping from the performance viewpoint is random access,
since you're avoiding all the lseek() system calls.
with mapping you have to meet the same criteria as mentioned above to get
physical sequential writing. aligned sequential sector writes.
Boost list run by bdawes at acm.org, gregod at cs.rpi.edu, cpdaniel at pacbell.net, john at johnmaddock.co.uk