T10/14-275r8 question

Bill Martin-SSI bill.martin at ssi.samsung.com
Wed Apr 15 09:29:52 PDT 2015


Formatted message: <a href="http://www.t10.org/cgi-bin/ac.pl?t=r&f=r1504153_f.htm">HTML-formatted message</a>

This restriction could be expanded for future use by modification of this
model clause when those uses are documented. I have expanded this to include
thin provisioned logical units.
Bill Martin
SSD I/O Standards
Samsung Semiconductor, Inc.
Cell (408) 499-1839
From: owner-t10 at t10.org [mailto:owner-t10 at t10.org] On Behalf Of Gerry Houlder
Sent: Tuesday, April 14, 2015 12:08 PM
To: T10 Reflector
Subject: Re: T10/14-275r8 question
Kevin has noted this text in the Background Control model clause:
"A device server that supports Background Operation Control as described in
this subclause shall:
a) be a resource provisioned device as described in 4.7.3.2;
b) ..."
This restricts use of Background Control feature to resource provisioned
devices.
On Tue, Apr 14, 2015 at 1:52 PM, Joe Breher
<Joe.Breher at hgst.com> wrote:
Kevin -
Great observation. I certainly think that BACKGROUND CONTROL has far wider
applicability than that described in 14-275. While not at the proposal stage,
I have been pondering some possibilities in that regard. There are many QoS
improvement aspects of system behavior that can piggyback upon this
mechanism.
While the model clause material in 14-275r8 4.32 "Background Operation
Control" is written in terms of managing (over)provisioning, I see nothing
elsewhere (e.g. the command description "5.99 BACKGROUND CONTROL command"
preventing its use for other purposes. Have you found text within 14-275 that
prohibits the use of the BACKGROUND CONTROL command to anything other than
the explicitly listed use case?
Lacking any specific prohibition upon such, my position would be that other
uses can be described in the future that might control other forms of
background operations by means of this mechanism. Such may require additional
model text describing such usage of the BACKGROUND CONTROL command -- which
is likely out of scope for this particular proposal. Though it may suggest a
renaming of this particular model subclause to something more specific to the
use cases within the proposal. Is this something we should do at this time?
Though your comment has prompted me to consider that 14-275r8 does not
include all the necessary changes to SBC - such as the addition of the new
commands to the "Commands for direct block access devices" Table 33 in
sbc4r04.
Joe Breher
Storage Architecture Technologist
Standards Setting Organization
San Jose Research Center
HGST, a Western Digital company
(478) 2-Breher
(478) 227-3437<tel:%28478%29%20227-3437>
This e-mail may contain confidential or legally privileged information of
HGST. If you are not the intended recipient, please notify us immediately by
responding to this e-mail and then deleting it from your system.
On Apr 13, 2015, at 5:30 PM, Kevin D Butt
<kdbutt at us.ibm.com> wrote:
 Bill,
Why does the storage intelligence restrict the Background Operation Control
and Write Stream to only Resource Provisioned devices, when there could be
value if it was used for both Thin and Thick Provisioning?
Thanks,
Kevin D. Butt
SCSI Architect, Tape Firmware, CAMSS
T10 Standards
MS 6TYA, 9000 S. Rita Rd., Tucson, AZ 85744
Tel: 520-799-5280<tel:520-799-5280>
Fax: 520-799-2723<tel:520-799-2723> (T/L:321)
Email address: kdbutt at us.ibm.com
http://www-03.ibm.com/servers/storage/



More information about the T10 mailing list