[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <F766E4F80769BD478052FB6533FA745D19FAE66CAE@SC-VEXCH4.marvell.com>
Date: Wed, 15 Jun 2011 18:57:05 -0700
From: Xiangliang Yu <yuxiangl@...vell.com>
To: Jack Wang <jack_wang@...sh.com>,
'James Bottomley' <James.Bottomley@...senPartnership.com>
CC: "yxlraid@...il.com" <yxlraid@...il.com>,
"lucas.demarchi@...fusion.mobi" <lucas.demarchi@...fusion.mobi>,
"maciej.trela@...el.com" <maciej.trela@...el.com>,
"dan.j.williams@...el.com" <dan.j.williams@...el.com>,
"linux-scsi@...r.kernel.org" <linux-scsi@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Jacky Feng <jfeng@...vell.com>
Subject: RE: [PATCH] [SCSI] LIBSAS: fix libsas link error issue
>> I get the issue like this:
>> 1. HBA support 3Gbps, level 1 expander support 6Gbps, and level 2 expander
>> support 6Gbps;
>> 2. level 1 is fine, and find that level 2 link rate is 6Gbps in DISCOVER
command
>> response.
>> 3. LIBSAS think level 2 is 6Gbps by sas_ex_get_linkrate function, and send
>> command to level 2 expander
>> 4. LIBSAS link error.
>>
>[Jack Wang]
>What do you mean by "LIBSAS link error", OPEN_REJECT(CONNECTION RATE NOT
>SUPPORTED)? LIBSAS only get the error event through LLDD.
>According to SAS2r15 7.8.3
I mean that HBA get link error. Sorry.
>A SAS initiator port shall set the initial CONNECTION RATE field to:
>a) the highest supported connection rate supported by a potential pathway as
determined during the
>discover process (e.g., based on the logical link rates of each logical link
reported in the SMP
>DISCOVER responses); or
Sas_ex_get_linkrate function
>b) the logical link rate of the logical phy used to transmit the OPEN
address frame.
MVSAS get value of linkrate from sas_ex_get_linkrate function(child->linkrate)
>If a SAS initiator port selected a connection rate based on discover process
information but the connection
>request results in OPEN_REJECT (CONNECTION RATE NOT SUPPORTED), then the
discover process
>information is no longer current and the discover process should be run
again.
Fail again.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists