linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: John Robinson <john.robinson@anonymous.org.uk>
To: Linux RAID <linux-raid@vger.kernel.org>
Subject: Re: [Slightly OT] Cheap 4-port PCI-E SATA card?
Date: Tue, 04 Jan 2011 14:03:36 +0000	[thread overview]
Message-ID: <4D2328B8.4070608@anonymous.org.uk> (raw)
In-Reply-To: <4D224B22.6070007@hardwarefreak.com>

On 03/01/2011 22:18, Stan Hoeppner wrote:
> John Robinson put forth on 1/3/2011 10:00 AM:
>> On 03/01/2011 06:41, Stan Hoeppner wrote:
[...]
> When using PMPs one will always have less theoretical b/w per drive than
> what that drive can push on paper with a streaming read.  Considering
> that over 90% of real world workloads are random IO heavy, not
> streaming, it's unlikely you'll ever run out of b/w using a PMP based
> setup.  I haven't.

That's probably true but I don't like making compromises if I can 
possibly avoid it :-)

>> I doubt my motherboard supports FIS PMPs. It's an Asus P5Q Pro, Intel
>> P45+ICH10R, and I'm pretty sure the ICH10R doesn't support PMPs even if
>> the original spec said it would.
>
> I just looked it up, and the ICH10R does _NOT_ support PMP.  Neither
> does the onboard Silicon Image 5723 chip, which actually connects to the
> southbridge via a SATA II port (stupid).

Must be connected to the Marvell 88SE6111's SATA port. Well, the spec 
says 88SE6111 but my lspci shows an 88SE6121. The 88SE6121 ought to have 
two SATA ports, but I've found odd behaviour with the two non-ICH10R 
ports on the board when testing - basically if I use the second port but 
not the first port, nothing appears, even with Asus' Drive Xpert 
disabled. This is presumably the SilI 5723's contribution, hanging off 
the Marvell chip's SATA port, and clearly no use for RAID where a drive 
might die but we want to carry on, so I'll be ignoring the on-board 
Marvell/SilI stuff.

> BTW, the P5Q Pro has 3 PCIe x1 slots and 2 PCIe x16/x8 slots, plus 2 PCI
> slots.  You told us the only slot you have available is 1 PCIe x16/x8.
> What is consuming the 3 PCIe x1 slots?  The PCIe x1 slot just North of
> the top x16 slot should be free.  I'm guessing the other 2 are blocked
> by your GPU cooler, correct?

Ah, I'm sorry, no I didn't say I only the PCIe x16/x8 slot available, or 
at least that's not what I meant. I do need PCIe because both PCI slots 
are taken, but I do have all three PCIe x1 slots and one PCIe x8/x16 
slot available. The graphics card is only single thickness and could 
indeed be moved.

I know I could easily put two $30 2-port cards in, but for neatness I'd 
prefer one card with 4 ports, which is what I started this thread to 
look for. One 2-port card and a PMP is a reasonable solution that I 
might yet go for.

NB My PCI slots are occupied by a TV tuner card and a SCSI card which 
serves my tape library, and in any case I want to avoid the limitation 
of the PCI bus which would have half the bandwidth of one PCIe x1 v1 
slot even if it wasn't sharing with two other highish-bandwidth devices.

[...]
> I recommended the Marvell based card strictly because it does PCIe x1
> rev 2 for 500MB/s.  I only use the Silicon Image based cards, but I use
> more than one if I have more than 4 drives in an array.  The cost comes
> out the same at $40 as the Marvell card, but the SI route requires 2
> PCIe slots, and you only have one.

As noted I do have more PCIe slots, and I've just found a Lycom PE-115 
PCIe x1 2-port SATA-III card for £20, which some third-party sites say 
has a Marvell 88SE912x chip, and is PCIe v2.0, so that'd be my 
multi-card solution - two of them would give me the 4 ports I need to add.

[...]
> Well, you've given us conflicting requirements that are impossible to
> meet with any solution:
>
> 1.  Low cost
> 2.  Full b/w per drive
> 3.  Only one PCIe slot availiable
>
> There is not a solution available to meet all of your criteria.

My own research had got me that far, that's why I was asking here. If 
this is unreasonable, please excuse the noise...

>> Nevertheless, thank you very much for taking the time for such a
>> considered reply.
>
> You're welcome.  I think you're finding yourself in that "I want to have
> my cake, but eat it too" situation.  You can't get what you want at the
> price point you want.

Don't we all want to have our cake and eat it sometimes? ;-)

Thanks again for your thoughts.

Cheers,

John.

--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

      reply	other threads:[~2011-01-04 14:03 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-01-02 21:11 [Slightly OT] Cheap 4-port PCI-E SATA card? John Robinson
2011-01-02 22:31 ` Roman Mamedov
2011-01-03 15:11   ` John Robinson
2011-01-03 16:08     ` Roman Mamedov
2011-01-03 17:02     ` Sven Eschenberg
2011-01-02 22:41 ` Mark Knecht
2011-01-03 15:13   ` John Robinson
2011-01-03 17:57     ` Mark Knecht
2011-01-02 23:04 ` Matt Garman
2011-01-03 15:29   ` John Robinson
2011-01-03 15:35     ` Justin Piszcz
2011-01-03  6:41 ` Stan Hoeppner
2011-01-03 16:00   ` John Robinson
2011-01-03 22:18     ` Stan Hoeppner
2011-01-04 14:03       ` John Robinson [this message]

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=4D2328B8.4070608@anonymous.org.uk \
    --to=john.robinson@anonymous.org.uk \
    --cc=linux-raid@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).