On 12/16/2011 2:51 PM, Ira Weiny wrote: > On Fri, 16 Dec 2011 11:24:54 -0800 > Hal Rosenstock <[email protected]> wrote: > >> >> Also, make log_send_error into a routine and also call when MAD is cancelled. >> >> This patch is an alternative to Ira's v4 patch entitled >> "opensm: Move Error printing to MAD error call back functions" >> which pushes this functionality up into the send error callbacks. >> >> This patch is currently compile tested only. >> >> Signed-off-by: Hal Rosenstock <[email protected]> > > I think this is acceptable as well.
Guess it's up to Alex to decide which way to go... > My main need was to report which request MAD did not get a response. I'll update to v2 eliminating the hop pointer as you indicated in a previous email and maybe look for any send error callback logging redundancy and remove that too but I'd prefer to wait to here Alex's comments. > I will test when I get back on the system which was having the issues. Thanks. That will be most helpful (and save me some time)! -- Hal > Acked-by: Ira Weiny <[email protected]> > >> --- >> diff --git a/libvendor/osm_vendor_ibumad.c b/libvendor/osm_vendor_ibumad.c >> index e2ebd8e..3781792 100644 >> --- a/libvendor/osm_vendor_ibumad.c >> +++ b/libvendor/osm_vendor_ibumad.c >> @@ -98,6 +98,37 @@ typedef struct _umad_receiver { >> >> static void osm_vendor_close_port(osm_vendor_t * const p_vend); >> >> +static void log_send_error(osm_vendor_t * const p_vend, osm_madw_t *p_madw) >> +{ >> + if (p_madw->p_mad->mgmt_class != IB_MCLASS_SUBN_DIR) { >> + /* LID routed */ >> + OSM_LOG(p_vend->p_log, OSM_LOG_ERROR, "ERR 5410: " >> + "Send completed with error (%s) -- dropping\n" >> + "\t\t\tClass 0x%x, Method 0x%X, Attr 0x%X, " >> + "TID 0x%" PRIx64 ", LID %u\n", >> + ib_get_err_str(p_madw->status), >> + p_madw->p_mad->mgmt_class, p_madw->p_mad->method, >> + cl_ntoh16(p_madw->p_mad->attr_id), >> + cl_ntoh64(p_madw->p_mad->trans_id), >> + cl_ntoh16(p_madw->mad_addr.dest_lid)); >> + } else { >> + ib_smp_t *p_smp; >> + >> + /* Direct routed SMP */ >> + p_smp = osm_madw_get_smp_ptr(p_madw); >> + OSM_LOG(p_vend->p_log, OSM_LOG_ERROR, "ERR 5411: " >> + "DR SMP Send completed with error (%s) -- dropping\n" >> + "\t\t\tMethod 0x%X, Attr 0x%X, TID 0x%" PRIx64 >> + ", Hop Ptr: 0x%X\n", >> + ib_get_err_str(p_madw->status), >> + p_madw->p_mad->method, >> + cl_ntoh16(p_madw->p_mad->attr_id), >> + cl_ntoh64(p_madw->p_mad->trans_id), >> + p_smp->hop_ptr); >> + osm_dump_smp_dr_path(p_vend->p_log, p_smp, OSM_LOG_ERROR); >> + } >> +} >> + >> static void clear_madw(osm_vendor_t * p_vend) >> { >> umad_match_t *m, *e, *old_m; >> @@ -185,6 +216,7 @@ put_madw(osm_vendor_t * p_vend, osm_madw_t * p_madw, >> ib_net64_t tid) >> p_req_madw = old_lru->v; >> p_bind = p_req_madw->h_bind; >> p_req_madw->status = IB_CANCELED; >> + log_send_error(p_vend, p_req_madw); >> pthread_mutex_lock(&p_vend->cb_mutex); >> (*p_bind->send_err_callback) (p_bind->client_context, p_req_madw); >> pthread_mutex_unlock(&p_vend->cb_mutex); >> @@ -326,32 +358,6 @@ static void *umad_receiver(void *p_ptr) >> >> /* if status != 0 then we are handling recv timeout on send */ >> if (umad_status(p_madw->vend_wrap.umad)) { >> - >> - if (mad->mgmt_class != IB_MCLASS_SUBN_DIR) { >> - /* LID routed */ >> - OSM_LOG(p_vend->p_log, OSM_LOG_ERROR, "ERR >> 5410: " >> - "Send completed with error -- >> dropping\n" >> - "\t\t\tClass 0x%x, Method 0x%X, Attr >> 0x%X, " >> - "TID 0x%" PRIx64 ", LID %u\n", >> - mad->mgmt_class, mad->method, >> - cl_ntoh16(mad->attr_id), >> - cl_ntoh64(mad->trans_id), >> - cl_ntoh16(ib_mad_addr->lid)); >> - } 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); >> - osm_dump_smp_dr_path(p_vend->p_log, smp, >> - OSM_LOG_ERROR); >> - } >> - >> if (!(p_req_madw = get_madw(p_vend, &mad->trans_id))) { >> OSM_LOG(p_vend->p_log, OSM_LOG_ERROR, >> "ERR 5412: " >> @@ -361,6 +367,7 @@ static void *umad_receiver(void *p_ptr) >> cl_ntoh64(mad->trans_id)); >> } else { >> p_req_madw->status = IB_TIMEOUT; >> + log_send_error(p_vend, p_req_madw); >> /* cb frees req_madw */ >> pthread_mutex_lock(&p_vend->cb_mutex); >> pthread_cleanup_push(unlock_mutex, > > -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
