Command Deadline Timeout Change

Paul Suhler Paul.Suhler at
Tue Aug 19 20:15:20 PDT 2014

Formatted message: <a href="">HTML-formatted message</a>

Thanks, Gerry.	That is indeed a severe limit.



From: Gerry Houlder [mailto:gerry.houlder at]

Sent: Tuesday, August 19, 2014 11:11 AM

To: Paul Suhler

Cc: T10 E-mail Reflector (t10 at

Subject: Re: Command Deadline Timeout Change

These commands are only valid for devices that implement type 2 Protection
Information. Those commands are illegal for type 0 and type 1 PI
configurations. This would severely limit the systems that could use the
feature. other than that, it is an interesting idea.

On Tue, Aug 19, 2014 at 12:18 PM, Paul Suhler
<Paul.Suhler at> wrote:

During an internal discussion yesterday, it was suggested that I simplify the
proposal by having deadlines only apply to the READ(32) and WRITE(32)
commands, because those have some reserved bytes, one of which could be used
to replicate the ICC field in the READ / WRITE FPDMA QUEUED commands.  This
would have advantages:

1)	Simplified by no longer piggybacking the timeout value on the
priority feature.

2)	Allows a different timeout per command (rather than per priority)

At least one other company had expressed an interest in this functionality;
is it acceptable to have this only for the two commands?



Paul A. Suhler, PhD

Research Staff Member

HGST Research

paul.suhler at

o: 949-476-1180 x275448

m: 949-241-6443

3001 Daimler St.

Santa Ana, CA 92705-5812<<a href="">;

More information about the T10 mailing list