linux-ide.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Linda Walsh <lkml@tlinx.org>
To: linux-ide@vger.kernel.org
Subject: Port Multiplier access with Sil 3124
Date: Sun, 08 Feb 2009 12:38:14 -0800	[thread overview]
Message-ID: <498F42B6.8030607@tlinx.org> (raw)

Is there something different, from normal disk-access, that I need to do
to access hard disks beyond '1', on a port-multiplier?

I thought I remembered reading the port multiplier support was
working for many SATA and SATA RAID controller capable chipsets,
including the Sil 3124.

I picked up a 2-Bay external SATA enclosure that I'm trying to access in
(what I thought) was the simplest mode: "JBOD".  However, when I boot,
I am only seeing the first hard disk.

Experimenting, I tried a single hard disk in both positions -- one
position let me see the disk directly (as though it was a direct,
str8-thru connection), the other position showed up detected by
the boot BIOS as a 7MB HD by some unrecognized vendor.   In
linux, I'm able to access and use the hard disk when it appears
'str8-thru', but linux sees nothing concerning the 7MB pseudo HD.

Is my expectation that the driver would simply recognize the
external enclosure by whatever I had the external enclosure set to,
too optimistic?  Do I need to run some special util to setup the disks in
JBOD mode?  I guess I thought I only needed to worry about
'special utils' if I was using the disk-pair in a RAID config (0/1)...

It seems there should be a linux util to manage the "container",
'sil57xx'  --  I take it is not used for RAID-only config?

My ultimate aim is to use it in a RAID-0, mirror config (my luck
with SATA disk drives has been abysmal, of late (*sigh*)).

Anyone with any real-world experience about when the 3Gb SAS
starts to become a bottleneck?  I know that theoretically, it could
support a hair over 350MB/s if there was no overhead, which would
reliably only support 2 hard disks at full speed (assuming ~120MB/s
max linear read speed/disk).  Does that jive with people's real-world 
experience?  I.e. port-multipliers can provide full throughput for
2-HD's but not likely 3? 

Should I be looking for an sil57xx program somewhere (the box contained
a mini-CD, but it looks like a driver for an older kernel (2.6.9).  Not 
so sure about it's usefulness in my setup.

Thanks,
-linda


             reply	other threads:[~2009-02-08 21:08 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-02-08 20:38 Linda Walsh [this message]
2009-02-09  9:26 ` Port Multiplier access with Sil 3124 Grant Grundler
2009-02-09 22:01   ` Linda Walsh
2009-02-09 14:35 ` Greg Freemyer
2009-02-09 20:09   ` Mark Lord
2009-02-09 22:22   ` Linda Walsh
2009-02-09 23:01     ` Greg Freemyer
2009-02-10  0:15       ` Jeff Garzik
2009-02-10  1:07         ` Linda Walsh
2009-02-10  3:48           ` Jeff Garzik
2009-02-11  2:09           ` Tejun Heo
2009-02-12  4:16             ` Robert Hancock
2009-02-10  3:25         ` Greg Freemyer
2009-02-11  2:12 ` Tejun Heo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=498F42B6.8030607@tlinx.org \
    --to=lkml@tlinx.org \
    --cc=linux-ide@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).