Poor raid 1 performance?

F

Folkert Rienstra

Change odd and even sectors in odd and even strip(e)s and your story starts
to make some sense. Unfortunately strip(e)s are a hindrance in RAID1,
e.g. if a file is in 3 strips it is read in 3 chunks when it could have
been read faster in 2 (1+ strip by one drive, 1+ strip by the other).
 
F

Folkert Rienstra

Antoine Leca said:
In news:[email protected], Folkert Rienstra va escriure:

For my enlightment, how common are RAID controllers using (paired) IDE
devices?

Very.
There are more expensive ones that have restricted themselfs to using
only 1 device per channel and they come with single device cables only.
Instead of 2 channels they come with 4 or even 8.
I learned reading
http://www.storagereview.com/guide2000/ref/hdd/perf/raid/conf/ctrlMultiple.html,
but it seems a bit old (2000?), particularly when it comes to disk interfaces.

In a nutshell that says: ATA can't multitask so lets rant about SCSI.
Not very useful.
Where can I find present-day informations?

Nothing much changed except maybe Overlapped and Queued feature set
which should bring ATA upto speed with SCSI but that never caught on.

IDE (I prefer to speak of IDE here, because ATA actually can)
cannot start simultanious reads from 2 devices on the same channel or start
a read and write simultaniously unless the write goes before the read.

What this boils down to is that you can't in some circumstances average your
access times (no parallel seeks) and can't use the full bandwidth of the channel
(empty bursts) so that your accesses appear simultanious (parallel), instead they
are serial (one access after the other) and you get only half the thruput per drive.

This isn't so much of a problem for long sequential reads (to start with: no seeks)
and no real need to start commands simultaniously(*) because when one drive reads
the other caches ahead and buffers, the whole transfer is at 100% interface speed
from buffer when the command that requests that data comes. So it looses half
by being serial but gains 100% by being able to use the full bandwidth for itself.
(*) Only the first commands are in serial, every next one is virtually parallel as
long as the read commands are sequencial.
About "single channel" vs. "separate channel", right?

Yes, and how they appear on the PCI bus.
I am sorry, I did not (then) match the terminology, now I did better (read
the above article, for once.)



I was assuming this would allow two transfers to occur simultaneously,
wouldn't it?

And this question is about IDE or SCSI or both?
Or dual channel SCSI only?
 

Ask a Question

Want to reply to this thread or ask your own question?

You'll need to choose a username for the site, which only take a couple of moments. After that, you can post your question and our members will help you out.

Ask a Question

Top