[T10] 答复: Question: About the number of identify

Guojian (F) guojian111 at hisilicon.com
Thu Mar 3 01:20:40 PST 2016

Why does it need to tolerate the single bit error? If there is a bit error, I think it is more reasonable to start a link reset. Next training, the signal may be more quality.

发件人: Gerry Houlder [mailto:gerry.houlder at seagate.com]
发送时间: 2016年3月3日 1:11
收件人: Guojian (F)
抄送: t10 at t10.org
主题: Re: [T10] Question: About the number of identify

Yes, the reason for sending three IDENTIFY frames is so that a single bit error in an IDENTIFY frame can be tolerated. The connection is successful if at least one of the IDENTIFY frames is received without error by the other end of the link.

On Mon, Feb 29, 2016 at 6:53 PM, Guojian (F) <guojian111 at hisilicon.com<mailto:guojian111 at hisilicon.com>> wrote:

发件人: Guojian (F)
发送时间: 2016年2月26日 15:35
收件人: t10 at t10.org<mailto:t10 at t10.org>
抄送: Yangjunbin (Jim, HS); zhanggaochuan; Lilinhan (Linkin, Turing); Ningzuolin
主题: Question: About the number of identify

We know that identify frame can be sent one or three to the other side after speed negotiation completed.
What I want to know is what is the consideration? Just ensure the other side can receive identify?
Is there any chance that a SAS PHY will miss the first identify frame?
Now I met a issue. When the host send just one identify frame, the HDD will occur receiving identify expired with little probability. This issue will be fixed when the host send three identify frame.


Attached Picture:
[cid:image001.png at 01D17570.0E5F7960]

T10 mailing list
T10 at t10.org<mailto:T10 at t10.org>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.t10.org/pipermail/t10/attachments/20160303/69fa566d/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 29381 bytes
Desc: image001.png
URL: <http://www.t10.org/pipermail/t10/attachments/20160303/69fa566d/attachment.png>

More information about the T10 mailing list