Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 06 Sep 1999 22:08:35 +0200
From:      "P.C. Uiterlinden" <puiterl@hacom.nl>
To:        Albert Max Lai <amlai@columbia.edu>
Cc:        aic7xxx@freebsd.org
Subject:   Re: Tagged queueing = lower write throughput?
Message-ID:  <37D41F43.FE1B754A@hacom.nl>
References:  <37CEE504.B84D6E75@hacom.nl> <14287.61853.465632.692046@konichiwa.cc.columbia.edu>

next in thread | previous in thread | raw e-mail | index | archive | help
Albert,

Thanks for replying to my mail. Now I at least know I'm not the only one
experiencing this kind of behavior.

Still I think it's strange that tagged queuing is able to slow things
down. I can't think of an obvious reason. Anyone cares to come up with
one?

Meanwhile, I'll download the manual of the hard disk to see if I can
discover something for my self.

Regards,

Paul.


Albert Max Lai wrote:
> 
> On Thursday, 2 September 1999, P.C. Uiterlinden wrote:
> 
> > While playing with RAID0, I found out that enabling tagged queueing
> > deteriorates write throughput considerably. The MD driver seems not
> 
> I have noticed that one has to play around with the queueing depth to
> get the highest throughput. With my IBM DGVSO9U (9ZX), the optimal
> queuing depth is between 12-14. With my Quantum Viking 4.5 NSE, having
> tagged queueing turned on slows it down.


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe aic7xxx" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?37D41F43.FE1B754A>