Hi Eric,
thanks for your quick reply...
You're right: I failed to mention that I use the Adaptec 2940 (aic7xxx)
driver. Sorry! Probably he's resetting the TCQ queue depth...
Is anybody using a different SCSI-driver (**NOT** aic7xxx) experiencing
this, too? All machines I have access to have Adaptec (aic7xxx)
controllers...
- Michael
"Eric Youngdale" <[EMAIL PROTECTED]> on 24.03.2000 15:32:08
To: Michael Kwasigroch/INTERCOPE/DE, [EMAIL PROTECTED]
cc:
Subject: Re: inducing SCSI bus scan
Received: from hercules.fairfax.datafocus.com ([204.255.0.2]) by
NS.INTERCOPE.COM (Lotus SMTP MTA Internal build v4.6.2 (651.2 6-10-1998))
with SMTP id C12568AC.00500E5A; Fri, 24 Mar 2000 15:34:26 +0100
Received: from halibut (halibut.fairfax.datafocus.com [172.16.3.77]) by
hercules.fairfax.datafocus.com with SMTP (Microsoft Exchange Internet Mail
Service Version 5.5.2448.0)
id G6WQSYT6; Fri, 24 Mar 2000 09:32:15 -0500
Message-ID: <000a01bf959d$bc21a970$[EMAIL PROTECTED]>
From: "Eric Youngdale" <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>,
<[EMAIL PROTECTED]>
References: <[EMAIL PROTECTED]>
Subject: Re: inducing SCSI bus scan
Date: Fri, 24 Mar 2000 09:32:08 -0500
MIME-Version: 1.0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
X-Priority: 3
X-MSMail-Priority: Normal
X-Mailer: Microsoft Outlook Express 5.00.2314.1300
X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2314.1300
----- Original Message -----
From: <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Cc: <[EMAIL PROTECTED]>
Sent: Friday, March 24, 2000 5:43 AM
Subject: inducing SCSI bus scan
> Hi all,
>
> issuing an
>
> echo "scsi add-single-device 0 1 2 3" >/proc/scsi/scsi
>
> works fine but you'll lose any tagged command queueing (TCQ) depths > 1.
> They'll be reset to one with (I'm sure) some performance penalty for the
> devices supporting it. This is why I don't use it anymore, my IBM scsi
> disks appear to be faster with a queue depth of eight.
>
> -> I could not find the reason for this by looking at the source code,
but
> I must admit I didn't tried too hard...
The way the interface to the low-level is currently designed, it isn't
possible to select queue depths on a single device. You do it for an
entire
bus. My guess is that the low-level driver you are using is resetting the
queue depth for all devices on the bus - I don't *think* it is the bus scan
code itself that is resetting the queue depth.
-Eric
-
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to [EMAIL PROTECTED]
