From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hal Rosenstock Subject: Re: [PATCH V4] opensm: Move Error printing to MAD error call back functions. Date: Fri, 16 Dec 2011 15:19:44 -0500 Message-ID: <4EEBA7E0.1090502@dev.mellanox.co.il> References: <20111216094934.0f7bd2ee.weiny2@llnl.gov> <4EEB9BAC.5040104@dev.mellanox.co.il> <20111216114557.27cef81e.weiny2@llnl.gov> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20111216114557.27cef81e.weiny2-i2BcT+NCU+M@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Ira Weiny Cc: Alex Netes , "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" List-Id: linux-rdma@vger.kernel.org On 12/16/2011 2:45 PM, Ira Weiny wrote: > On Fri, 16 Dec 2011 11:27:40 -0800 > Hal Rosenstock wrote: > >> On 12/16/2011 12:49 PM, Ira Weiny wrote: >>> >>> Only print the transaction ID of timed out MAD's on VERBOSE. >>> >>> Signed-off-by: Ira Weiny >>> --- > > [snip] > >>> - } else { >>> - ib_smp_t *smp; >>> - >>> - /* Direct routed SMP */ >>> - smp = (ib_smp_t *) mad; >>> - OSM_LOG(p_vend->p_log, OSM_LOG_ERROR, "ERR 5411: " >>> - "DR SMP Send completed with error -- dropping\n" >>> - "\t\t\tMethod 0x%X, Attr 0x%X, TID 0x%" PRIx64 >>> - ", Hop Ptr: 0x%X\n", >>> - mad->method, cl_ntoh16(mad->attr_id), >>> - cl_ntoh64(mad->trans_id), smp->hop_ptr); >> >> One thing I just noticed in cobbling up the other approach for >> comparison purposes is that the logging of the hop pointer was removed. >> Should that be preserved ? > > Since we are printing the request MAD wouldn't the hop pointer always be 0? Yes, that should be the case but I don't recall whether the original print always showed 0 when working off the returned umad rather than the request MAD. So I guess that should be eliminated in the vendor umad approach this... > And while we are at it we should print the DLID/SLID since it could be combined routing. AFAIK OpenSM doesn't currently support combined routing (only the diags do). This is a bigger change and that change should include any changes needed for logging. -- Hal > Ira > >> >> -- Hal >> >>> - osm_dump_smp_dr_path(p_vend->p_log, smp, >>> - OSM_LOG_ERROR); >>> - } >>> + OSM_LOG(p_vend->p_log, OSM_LOG_VERBOSE, "ERR 5410: " >>> + "Receive Timeout on Send -- dropping " >>> + "TID 0x%" PRIx64 "\n", cl_ntoh64(mad->trans_id)); >>> >>> if (!(p_req_madw = get_madw(p_vend, &mad->trans_id))) { >>> OSM_LOG(p_vend->p_log, OSM_LOG_ERROR, >>> diff --git a/opensm/osm_helper.c b/opensm/osm_helper.c >>> index f9f3d9d..b968679 100644 >>> --- a/opensm/osm_helper.c >>> +++ b/opensm/osm_helper.c >>> @@ -2059,8 +2059,9 @@ void osm_dump_smp_dr_path(IN osm_log_t * p_log, IN const ib_smp_t * p_smp, >>> char buf[BUF_SIZE]; >>> unsigned n; >>> >>> - n = sprintf(buf, "Received SMP on a %u hop path: " >>> - "Initial path = ", p_smp->hop_count); >>> + n = sprintf(buf, " DR SMP (TID 0x%" PRIx64 ") on a %u hop path: " >>> + "Initial path = ", >>> + cl_ntoh64(p_smp->trans_id), p_smp->hop_count); >>> n += sprint_uint8_arr(buf + n, sizeof(buf) - n, >>> p_smp->initial_path, >>> p_smp->hop_count + 1); >>> diff --git a/opensm/osm_perfmgr.c b/opensm/osm_perfmgr.c >>> index ded5a5e..fc3f74b 100644 >>> --- a/opensm/osm_perfmgr.c >>> +++ b/opensm/osm_perfmgr.c >>> @@ -212,7 +212,9 @@ static void perfmgr_mad_send_err_callback(void *bind_context, >>> p_mon_node = (monitored_node_t *) p_node; >>> >>> OSM_LOG(pm->log, OSM_LOG_ERROR, "ERR 4C02: %s (0x%" PRIx64 >>> - ") port %u\n", p_mon_node->name, p_mon_node->guid, port); >>> + ") port %u; DLID %u, TID 0x%" PRIx64 "\n", p_mon_node->name, >>> + p_mon_node->guid, port, cl_ntoh16(p_madw->mad_addr.dest_lid), >>> + cl_ntoh64(p_madw->p_mad->trans_id)); >>> >>> if (pm->subn->opt.perfmgr_redir && p_madw->status == IB_TIMEOUT) { >>> /* First, find the node in the monitored map */ >>> diff --git a/opensm/osm_sa_mad_ctrl.c b/opensm/osm_sa_mad_ctrl.c >>> index bde88fa..4caead1 100644 >>> --- a/opensm/osm_sa_mad_ctrl.c >>> +++ b/opensm/osm_sa_mad_ctrl.c >>> @@ -413,8 +413,18 @@ static void sa_mad_ctrl_send_err_callback(IN void *context, >>> Retire the original request MAD. >>> */ >>> >>> + OSM_LOG(p_ctrl->p_log, OSM_LOG_ERROR, "ERR 1A0A: " >>> + "SA MAD completed in error (%s): " >>> + "%s(%s), attr_mod 0x%x, TID 0x%" PRIx64 ", DLID %u\n", >>> + ib_get_err_str(p_madw->status), >>> + ib_get_sa_method_str(p_madw->p_mad->method), >>> + ib_get_sa_attr_str(p_madw->p_mad->attr_id), >>> + cl_ntoh32(p_madw->p_mad->attr_mod), >>> + cl_ntoh64(p_madw->p_mad->trans_id), >>> + cl_ntoh16(p_madw->mad_addr.dest_lid)); >>> + >>> osm_dump_sa_mad(p_ctrl->p_log, osm_madw_get_sa_mad_ptr(p_madw), >>> - OSM_LOG_ERROR); >>> + OSM_LOG_VERBOSE); >>> >>> /* sm_mad_ctrl_update_wire_stats( p_ctrl ); */ >>> >>> diff --git a/opensm/osm_sm_mad_ctrl.c b/opensm/osm_sm_mad_ctrl.c >>> index ee92c66..a3b444a 100644 >>> --- a/opensm/osm_sm_mad_ctrl.c >>> +++ b/opensm/osm_sm_mad_ctrl.c >>> @@ -704,6 +704,7 @@ Exit: >>> */ >>> static void sm_mad_ctrl_send_err_cb(IN void *context, IN osm_madw_t * p_madw) >>> { >>> + char lidstr[8]; >>> osm_sm_mad_ctrl_t *p_ctrl = context; >>> ib_api_status_t status; >>> ib_smp_t *p_smp; >>> @@ -713,13 +714,24 @@ static void sm_mad_ctrl_send_err_cb(IN void *context, IN osm_madw_t * p_madw) >>> CL_ASSERT(p_madw); >>> >>> p_smp = osm_madw_get_smp_ptr(p_madw); >>> + >>> + if (p_smp->mgmt_class == IB_MCLASS_SUBN_DIR) >>> + lidstr[0] = '\0'; >>> + else >>> + snprintf(lidstr, 8, " DLID %u", >>> + cl_ntoh16(p_madw->mad_addr.dest_lid)); >>> + >>> OSM_LOG(p_ctrl->p_log, OSM_LOG_ERROR, "ERR 3113: " >>> "MAD completed in error (%s): " >>> - "%s(%s), attr_mod 0x%x, TID 0x%" PRIx64 "\n", >>> + "%s(%s), attr_mod 0x%x, TID 0x%" PRIx64 " %s\n", >>> ib_get_err_str(p_madw->status), >>> ib_get_sm_method_str(p_smp->method), >>> ib_get_sm_attr_str(p_smp->attr_id), cl_ntoh32(p_smp->attr_mod), >>> - cl_ntoh64(p_smp->trans_id)); >>> + cl_ntoh64(p_smp->trans_id), >>> + lidstr); >>> + >>> + if (p_smp->mgmt_class == IB_MCLASS_SUBN_DIR) >>> + osm_dump_smp_dr_path(p_ctrl->p_log, p_smp, OSM_LOG_ERROR); >>> >>> /* >>> If this was a SubnSet MAD, then this error might indicate a problem >> > > -- 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