From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ira Weiny Subject: Re: [PATCH] infiniband-diags: Add SMP/QP0 usage explanation to general man page Date: Thu, 31 May 2012 18:13:30 -0700 Message-ID: <20120531181330.e79a903f.weiny2@llnl.gov> References: <20120531160249.f23247ea.weiny2@llnl.gov> <4FC80044.8010508@dev.mellanox.co.il> <20120531165831.7282b711.weiny2@llnl.gov> <4FC8157B.7040107@dev.mellanox.co.il> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <4FC8157B.7040107-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Hal Rosenstock Cc: "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" List-Id: linux-rdma@vger.kernel.org On Thu, 31 May 2012 21:06:03 -0400 Hal Rosenstock wrote: > On 5/31/2012 7:58 PM, Ira Weiny wrote: > > On Thu, 31 May 2012 19:35:32 -0400 > > Hal Rosenstock wrote: > > > >> On 5/31/2012 7:02 PM, Ira Weiny wrote: > >>> > >>> > >>> Signed-off-by: Ira Weiny > >>> --- > >>> doc/rst/infiniband-diags.8.in.rst | 12 ++++++++++++ > >>> 1 files changed, 12 insertions(+), 0 deletions(-) > >>> > >>> diff --git a/doc/rst/infiniband-diags.8.in.rst b/doc/rst/infiniband-diags.8.in.rst > >>> index 6a86ae2..9cd4524 100644 > >>> --- a/doc/rst/infiniband-diags.8.in.rst > >>> +++ b/doc/rst/infiniband-diags.8.in.rst > >>> @@ -23,6 +23,18 @@ may therefore work even in unconfigured subnets. Other, higher level > >>> utilities, require LID routed MAD's and to some extent SA/SM access. > >>> > >>> > >>> +THE USE OF SMP's (QP0) > >>> +====================== > >>> + > >>> +Many of the tools in this package rely on the use of SMP's via QP0 to acquire > >> > >> SMPs > > > > done > > > >> > >>> +data directly from hardware. > >> > >> SMA rather than hardware > > > > done. > > > >> > >>> While this mode of operation is not technically > >>> +in compliance with the InfiniBand specification, > >> > >> I think this is a grey area. > > > > I agree. However, I thought with SRIOV support and MKey support it was worth > mentioning this. > > For SRIOV (guests), the only diags are ibstat and ibstatus right now. > Should there be a separate guest package with just those and their man > pages ? I don't think so. Some other tools will work saquery, perfquery, etc. I know that it can be difficult for users to understand where the use of SMPs might hang them up, but at least this may give them a clue. Going forward it would be nice to have less dependencies on SMPs. But I think we agree it will always be nice to query the hardware (SMA) directly. Ira > > -- Hal > > > > > Ira > > > >> > >> -- Hal > >> > >>> practical experience has found > >>> +that this level of diagnostics is valuable when working with a fabric which is > >>> +broken or only partially configured. For this reason many of these tools may > >>> +require the use of an MKey or operation from Virtual Machines may be restricted > >>> +for security reasons. > >>> + > >>> + > >>> COMMON OPTIONS > >>> ============== > >>> > >> > > > > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-rdma" in > the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org > More majordomo info at http://vger.kernel.org/majordomo-info.html -- Ira Weiny Member of Technical Staff Lawrence Livermore National Lab 925-423-8008 weiny2-i2BcT+NCU+M@public.gmane.org -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html