[ofa-general] [PATCH] OpenSM: Add a Node Description check on light sweep to ensure that the ND has been found for each node.

[Hal Rosenstock]

On Wed, Jul 30, 2008 at 8:40 PM, Ira Weiny <weiny2 at llnl.gov> wrote:
> >From d2e52a8b9de02521b01de3414562f45e476cafbf Mon Sep 17 00:00:00 2001
> From: Ira K. Weiny <weiny2 at llnl.gov>
> Date: Wed, 30 Jul 2008 17:28:30 -0700
> Subject: [PATCH] Add a Node Description check on light sweep to ensure that the ND has been
>  found for each node.  This case covers the condition where a ND message is
>  dropped/lost for some reason and OpenSM is left with a valid configured node
>  which is not named correctly.

A couple of nits below.

> This is not the same as a node which has changed it's Node Descriptioin.  In
> this case the node needs to send a trap.

Is that case currently handled ?

> Signed-off-by: Ira K. Weiny <weiny2 at llnl.gov>
> ---
>  opensm/opensm/osm_state_mgr.c |   54 +++++++++++++++++++++++++++++++++++++++++
>  1 files changed, 54 insertions(+), 0 deletions(-)
>
> diff --git a/opensm/opensm/osm_state_mgr.c b/opensm/opensm/osm_state_mgr.c
> index b599582..15124c9 100644
> --- a/opensm/opensm/osm_state_mgr.c
> +++ b/opensm/opensm/osm_state_mgr.c
> @@ -506,6 +506,54 @@ Exit:
>  }
>
>  /**********************************************************************
> + During a light sweep check each node to see if the node descriptor is valid
> + if not issue a ND query.
> +**********************************************************************/
> +static void __osm_state_mgr_get_node_desc(IN cl_map_item_t * const p_object,
> +                                       IN void *context)
> +{
> +       osm_physp_t *p_physp = NULL;
> +       osm_node_t *const p_node = (osm_node_t *) p_object;
> +       ib_api_status_t status = IB_SUCCESS;
> +       osm_madw_context_t mad_context;
> +       osm_sm_t *sm = (osm_sm_t *)context;
> +
> +       OSM_LOG_ENTER(sm->p_log);
> +
> +       CL_ASSERT(p_node);
> +
> +       if (p_node->print_desc && strcmp(p_node->print_desc, "<unknown>"))
> +               /* if ND is valid, do nothing */
> +               goto exit;
> +
> +       OSM_LOG(sm->p_log, OSM_LOG_ERROR,
> +               "__osm_state_mgr_get_node_desc: "
> +               "Unknown node description \"%s\" for node 0x%016" PRIx64
> +               ".  Reissuing ND query\n",
> +               p_node->print_desc ? p_node->print_desc : "<unknown>",
> +               cl_ntoh64(osm_node_get_node_guid (p_node)));

Needs ERR code.

> +
> +       /* get a physp to request from. */
> +       p_physp = osm_node_get_any_physp_ptr(p_node);
> +
> +       mad_context.nd_context.node_guid = osm_node_get_node_guid(p_node);
> +
> +       status = osm_req_get(sm,
> +                            osm_physp_get_dr_path_ptr(p_physp),
> +                            IB_MAD_ATTR_NODE_DESC,
> +                            0, CL_DISP_MSGID_NONE, &mad_context);
> +       if (status != IB_SUCCESS)
> +               OSM_LOG(sm->p_log, OSM_LOG_ERROR,
> +                       "__osm_ni_rcv_get_node_desc: ERR 0D03: "

Shouldn't routine name be __osm_state_mgr_get_node_desc here ? Is ERR
code right ?

-- Hal

> +                       "Failure initiating NodeDescription request (%s)\n",
> +                       ib_get_err_str(status));
> +
> +exit:
> +       OSM_LOG_EXIT(sm->p_log);
> +}
> +
> +
> +/**********************************************************************
>  Initiates a lightweight sweep of the subnet.
>  Used during normal sweeps after the subnet is up.
>  **********************************************************************/
> @@ -514,6 +562,7 @@ static ib_api_status_t __osm_state_mgr_light_sweep_start(IN osm_sm_t * sm)
>        ib_api_status_t status = IB_SUCCESS;
>        osm_bind_handle_t h_bind;
>        cl_qmap_t *p_sw_tbl;
> +       cl_qmap_t *p_node_tbl;
>        cl_map_item_t *p_next;
>        osm_node_t *p_node;
>        osm_physp_t *p_physp;
> @@ -522,6 +571,7 @@ static ib_api_status_t __osm_state_mgr_light_sweep_start(IN osm_sm_t * sm)
>        OSM_LOG_ENTER(sm->p_log);
>
>        p_sw_tbl = &sm->p_subn->sw_guid_tbl;
> +       p_node_tbl = &sm->p_subn->node_guid_tbl;
>
>        /*
>         * First, get the bind handle.
> @@ -540,6 +590,10 @@ static ib_api_status_t __osm_state_mgr_light_sweep_start(IN osm_sm_t * sm)
>        cl_qmap_apply_func(p_sw_tbl, __osm_state_mgr_get_sw_info, sm);
>        CL_PLOCK_RELEASE(sm->p_lock);
>
> +       CL_PLOCK_ACQUIRE(sm->p_lock);
> +       cl_qmap_apply_func(p_node_tbl, __osm_state_mgr_get_node_desc, sm);
> +       CL_PLOCK_RELEASE(sm->p_lock);
> +
>        /* now scan the list of physical ports that were not down but have no remote port */
>        CL_PLOCK_ACQUIRE(sm->p_lock);
>        p_next = cl_qmap_head(&sm->p_subn->node_guid_tbl);
> --
> 1.5.4.5
>
> _______________________________________________
> general mailing list
> general at lists.openfabrics.org
> http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
>
> To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
>