[ofa-general] Re: [PATCH] opensm: fix race in main OpenSM flow.

Hal Rosenstock hal.rosenstock at gmail.com
Mon Dec 8 11:32:04 PST 2008


Sasha,

On Sat, Dec 6, 2008 at 10:40 PM, Sasha Khapyorsky <sashak at voltaire.com> wrote:
> Hi Hal,
>
> On 16:03 Thu 04 Dec     , Hal Rosenstock wrote:
>>
>> Looks to me like this has been there from around the following commit
>> or some related changes shortly thereafter:
>>
>> commit 1b2eb3daddbfa9fc555488cddbea12b01f6635a3
>> Date:   Mon Jan 28 03:10:18 2008 +0200
>>
>>     opensm: wait_for_pending_transaction() generalization
>>
>>     Function wait_for_pending_transaction() is global now and moved from
>>     PerfMgr to StateMgr, all related objects are generalized.
>>
>> If so, this is applicable to 3.1 and maybe also 3.0 based OpenSMs.
>
> No, it doesn't really affect main flow of 3.1 (and 3.0) - it was used
> only in discovery phase of PerfMgr (and when it is running in standby SM
> mode) which has experimental status in 3.1. But it does affect almost
> all OpenSM-3.2.x versions.

What's the difference between 3.2 and 3.1 in this regard ? Is it just
the experimental status of PerfMgr ?

As PerfMgr is part of 3.1, isn't this an important issue for 3.1 when
perf mgr enabled ?

-- Hal

>
> Sasha
>



More information about the general mailing list