NVIDIA UFM Telemetry Documentation v1.18.2
NVIDIA UFM Telemetry Documentation v1.18.2

Ports Counters Info

The table below lists the names of Registers/Pages supported by telemetry, along with their respective field lists.

Register / Page Name

Field List

SLRIP

ffe_tap[0-8]_ib[0-3]_lane[0-3]

ffe_tap_en_ib[0-3]_lane[0-3]

mixer_offset[0-1]_ib[0-3]_lane[0-3]

saved[0-1]_mixer_offset0_ib[0-3]_lane[0-3]

saved[0-1]_sel_enc0_ib[0-3]_lane[0-3]

sel_enc[0-2]_ib[0-3]_lane[0-3]

slrip_status_lane[0-3]

SLRP

crnt_bgn_offset_n[0-1]_lane[0-3]

crnt_bgn_offset_p[0-1]_lane[0-3]

dp_sel_lane[0-3]

gctrl_bin_bgn[0-1]_n_lane[0-3]

gctrl_bin_bgn[0-1]_p_lane[0-3]

mixer_offset_down_lane[0-3]

mixer_offset_eye_scan_lane[0-3]

mixer_offset_up_lane[0-3]

sel_amp_mixer_biasgen_down_lane[0-3]

sel_amp_mixer_biasgen_eo_lane[0-3]

sel_amp_mixer_biasgen_mid_lane[0-3]

sel_amp_mixer_biasgen_up_lane[0-3]

sel_bias2ctle_lane[0-3]

sel_bias_en_[0-6]_lane[0-3]

sel_digital_gctrl_lane[0-3]

sel_enc_lane[0-3]

sel_gctrln_en_[0-6]_lane[0-3]

sel_gctrlp_en_[0-6]_lane[0-3]

sel_ref_in_mixer_biasgen_down_lane[0-3]

sel_ref_in_mixer_biasgen_eo_lane[0-3]

sel_ref_in_mixer_biasgen_mid_lane[0-3]

sel_ref_in_mixer_biasgen_up_lane[0-3]

sel_ref_out_mixer_biasgen_down_lane[0-3]

sel_ref_out_mixer_biasgen_eo_lane[0-3]

sel_ref_out_mixer_biasgen_mid_lane[0-3]

sel_ref_out_mixer_biasgen_up_lane[0-3]

selgc_ref_op[0-1]_alev_ctle_lane[0-3]

SLRG

Lane[0-3]Grade

dn_eye_grade_lane[0-3]

fom_ext_conf_cap_lane[0-3]

fom_ext_conf_lane[0-3]

fom_measurment_lane[0-3]

fom_mode_lane[0-3]

grade_lane_speed_lane[0-3]

grade_version_lane[0-3]

height_eo_neg_low_lane[0-3]

height_eo_neg_mid_lane[0-3]

height_eo_neg_up_lane[0-3]

height_eo_pos_low_lane[0-3]

height_eo_pos_mid_lane[0-3]

height_eo_pos_up_lane[0-3]

initial_fom_lane[0-3]

last_fom_lane[0-3]

lower_eye_lane[0-3]

mid_eye_grade_lane[0-3]

mid_eye_lane[0-3]

nblks_max_lane[0-3]

nerrs_min_lane[0-3]

phase_eo_neg_low_lane[0-3]

phase_eo_neg_mid_lane[0-3]

phase_eo_neg_up_lane[0-3]

phase_eo_pos_low_lane[0-3]

phase_eo_pos_mid_lane[0-3]

phase_eo_pos_up_lane[0-3]

up_eye_grade_lane[0-3]

upper_eye_lane[0-3]

PTYS

data_rate_oper

PPHCR

active_hist_type

bin_range_[0-15]_high_val

bin_range_[0-15]_low_val

bin_range_write_mask

hist_max_measurement

hist_min_measurement

hist_type

num_of_bins

pphcr_local_port

pphcr_pnat

we

SLSIR

ae_state_lane[0-3]

cal_abort_cnt_lane[0-3]

cal_done_cnt_lane[0-3]

cdr_abort_cnt_lane[0-3]

cdr_done_cnt_lane[0-3]

cdr_error_lane[0-3]

eom_abort_cnt_lane[0-3]

eom_done_cnt_lane[0-3]

eq_abort_cnt_lane[0-3]

eq_done_cnt_lane[0-3]

feq_adc_overload_lane[0-3]

imem_chksm_error_lane[0-3]

nop_dsovf_error_lane[0-3]

nop_dsunf_error_lane[0-3]

nop_rsovf_error_lane[0-3]

nop_rsunf_error_lane[0-3]

peq_adc_overload_lane[0-3]

rd_iter_cnt_lane[0-3]

rx_cal_ugl_state_lane[0-3]

rx_eom_ugl_state_lane[0-3]

rx_eq_ugl_state_lane[0-3]

rx_init_abort_cnt_lane[0-3]

rx_init_done_cnt_lane[0-3]

rx_ugl_state_lane[0-3]

sd_hits_cnt_lane[0-3]

sd_iter_cnt_lane[0-3]

tx_ugl_state_lane[0-3]

SLTP

alev_minus_bfm2_lane[0-3]

alev_plus_bfm2_lane[0-3]

blev_lane[0-3]

drv_amp_lane[0-3]

main_tap_lane[0-3]

ob_alev_out_lane[0-3]

ob_amp_lane[0-3]

ob_bad_stat_lane[0-3]

ob_m2lp_lane[0-3]

obnlev_lane[0-3]

obplev_lane[0-3]

ph_pol_admin_lane[0-3]

post_tap_lane[0-3]

pre_2_tap_lane[0-3]

pre_tap_lane[0-3]

regn_bfm1p_lane[0-3]

regp_bfm1n_lane[0-3]

sltp_status_lane[0-3]

tap[0-11]_lane[0-3]

tx_alev_lane[0-3]

PMDR

clp_[1,4]x

cluster

gb_valid

gearbox_die_num

ib_port

label_port_query

local_port

local_port_query

lp_msb

mcm_tile_num

mcm_tile_valid

module

module_lane_mask

physical_rx_lane[0-3]

physical_tx_lane[0-3]

pll_index

pmdr_status

pnat

pport

sd_4x_rx

sd_4x_tx

sd_lane_mask_rx

sd_lane_mask_tx

slot_index

split

swid

tile_cluster

tile_pport

usr_sd_4x_rx

usr_sd_4x_tx

version

vl_num

PPLL

ae_pll[0-3]

analog_var_pll[0-3]

bg_trim

bg_trim_valid

cal_abort

cal_abort_sticky

cal_done

cal_en

cal_error_counter

cal_internal_state

cal_main_state

cal_valid_sticky

clear_cause_pll[0-3]

clock_valid_pll[0-3]

cvb_trim

cvb_trim_valid

dco_coarse

dco_coarse_bin

dlf2_phlock_det_status_sticky_pll[0-3]

fctrl_measure_pll[0-3]

high_var_pll[0-3]

lma_rcal_code

lma_rcal_tx_n_code

lma_rcal_tx_p_code

lock_clk_val_cause_pll[0-3]

lock_lost_counter_pll[0-3]

lock_pll[0-3]

lock_pulse_pll[0-3]

lock_status_pll[0-3]

lockdet_cnt_based_lock

lockdet_cnt_based_lock_pll[0-3]

lockdet_err_cnt_active_lock

lockdet_err_cnt_active_lock_pll[0-3]

lockdet_err_cnt_locked_sticky

lockdet_err_cnt_locked_sticky_pll[0-3]

lockdet_err_cnt_unlocked_sticky

lockdet_err_cnt_unlocked_sticky_pll[0-3]

lockdet_err_measure_done

lockdet_err_measure_done_pll[0-3]

lockdet_err_state

lockdet_err_state_pll[0-3]

lockdet_error_count_pll[0-3]

lockdet_mode_retimer_pll[0-3]

lokcdet_error_count

low_var_pll[0-3]

mid_var_pll[0-3]

num_plls_[5,7,16]nm

pll_lockdet_state

pll_pwrup_pll[0-3]

pll_speed_pll[0-3]

pll_ugl_state

plllock_clk_val_pll[0-3]

pwr_up_state

rcal_done_valid_sticky

rcal_fsm_done

rcal_tx_n_valid_sticky

rcal_tx_p_valid_sticky

speedo

speedo_valid

SLLM

ber_mon_exp_lane[0-3]

ber_mon_lane[0-3]

ber_mon_mantissa_lane[0-3]

ctle_peq_cnt_lane[0-3]

ctle_peq_en_lane[0-3]

dffe_peq_en_lane[0-3]

dffe_peq_scout_skip_lane[0-3]

ib[1,3]_max_lm_90_tries_lane[0-3]

lm_active_lane[0-3]

lm_clk90_fl_err_acc_lane[0-3]

lm_clk90_fl_err_max_lane[0-3]

lm_counter_dn_lane[0-3]

lm_counter_mid_lane[0-3]

lm_counter_up_lane[0-3]

lm_en_lane[0-3]

lm_was_active_lane[0-3]

peq_adc_vref_step_lane[0-3]

peq_dffe_delay_lane[0-3]

peq_dffe_iters_lane[0-3]

peq_f1_adapt_skip_lane[0-3]

peq_train_mode_lane[0-3]

peq_tsense_en_lane[0-3]

peq_vref_iters_lane[0-3]

pib_gw_lock_lane[0-3]

vref_peq_en_lane[0-3]

PHY BER Params

alarm_th_eff_ber

alarm_th_raw_ber

alarm_th_sym_ber

normal_th_eff_ber

normal_th_raw_ber

normal_th_sym_ber

port_type_eff_ber

port_type_raw_ber

port_type_sym_ber

rs_fec_group_eff_ber

rs_fec_group_raw_ber

rs_fec_group_sym_ber

sampling_rate_eff_ber

sampling_rate_raw_ber

sampling_rate_sym_ber

time_window_eff_ber

time_window_raw_ber

time_window_sym_ber

warning_th_eff_ber

warning_th_raw_ber

warning_th_sym_ber

MRCS

max_delta_freq_[0-1]

max_freq_[0-1]

measured_freq_[0-1]

min_freq_[0-1]

PEMI Module Samples

pemi_dp_st_lane[0-7]

pemi_module_st

pemi_rx_power_lane[0-7]

pemi_temperature

pemi_tx_bias_lane[0-7]

pemi_tx_power_lane[0-7]

pemi_voltage

PEMI SNR Samples

snr_host_lane[0-7]

snr_media_lane[0-7]

PEMI Laser Samples

laser_age

laser_frequency_error_lane[0-7]

laser_temperature_lane[0-7]

tec_current

PEMI Pam4 Samples

pam4_level_transition_host_lane[0-7]

pam4_level_transition_media_lane[0-7]

PEMI Pre FEC BER Samples

pre_fec_ber_avg_host

pre_fec_ber_avg_media

pre_fec_ber_max_host

pre_fec_ber_max_media

pre_fec_ber_min_host

pre_fec_ber_min_media

pre_fec_ber_val_host

pre_fec_ber_val_media

PEMI Pre FEC BER Properties

pre_fec_ber_avg_high_host_alarm

pre_fec_ber_avg_high_host_warning

pre_fec_ber_avg_high_media_alarm

pre_fec_ber_avg_high_media_warning

pre_fec_ber_cap

pre_fec_ber_max_high_host_alarm

pre_fec_ber_max_high_host_warning

pre_fec_ber_max_high_media_alarm

pre_fec_ber_max_high_media_warning

pre_fec_ber_min_high_host_alarm

pre_fec_ber_min_high_host_warning

pre_fec_ber_min_high_media_alarm

pre_fec_ber_min_high_media_warning

PEMI Ferc Samples

ferc_avg_host

ferc_avg_media

ferc_max_host

ferc_max_media

ferc_min_host

ferc_min_media

ferc_val_host

ferc_val_media

PHY Counters

link_down_events

PHY Statistics

conf_level_raw_ber

eff_ber

effective_ber_coef

effective_ber_magnitude

phy_corrected_bits

phy_effective_errors

phy_raw_errors_lane[0-3]

phy_received_bits

phy_symbol_errors

raw_ber

raw_ber_coef

raw_ber_coef_lane[0-3]

raw_ber_lane[0-3]

raw_ber_magnitude

raw_ber_magnitude_lane[0-3]

symbol_ber

symbol_ber_coef

symbol_ber_magnitude

time_since_last_clear

PHY InfiniBand General Counters

dqs2llu_xmit_wait_arb_global

general_receive_discard_external_contain

general_transmit_discard_external_contain

grxb_fecn_mark

port_rcv_data_qword

port_receive_poison

port_sw_hoq_lifetime_limit_discards

port_xmit_data_qword

port_xmit_ebp

rq_general_error

Histograms

fc_zero_hist

hist[0-15]

Troubleshoot

group_opcode

status_message

status_opcode

Operation Info

cable_proto_cap

cable_proto_cap_ext

core_to_phy_link_enabled

core_to_phy_link_proto_enabled

core_to_phy_link_width_enabled

eth_100g_fec_support

eth_25g_50g_fec_support

eth_an_fsm_state

eth_an_link_enabled

fec_mode_request

ib_phy_fsm_state

loopback_mode

neg_mode_active

pd_fsm_state

pd_link_enabled

pddr_fec_mode_active

pddr_link_speed_active

pddr_link_width_active

phy_hst_fsm_state

phy_hst_link_enabled

phy_manager_link_enabled

phy_manager_link_proto_enabled

phy_manager_link_width_enabled

phy_mngr_fsm_state

profile_fec_in_use

proto_active

psi_fsm_state

retran_mode_active

retran_mode_request

Link Down Info

ber_exp

ber_mantissa

down_blame

e2e_reason_opcode

last_ber_exp

last_ber_mantissa

local_reason_opcode

max_ber_exp

max_ber_mantissa

min_ber_exp

min_ber_mantissa

num_of_ber_alarams

remote_reason_opcode

Link Up Info

fast_link_up_status

time_to_link_up

time_to_link_up_disable_to_pd

time_to_link_up_disable_to_sd

time_to_link_up_phy_up_to_active

time_to_link_up_sd_to_phy_up

up_reason_drv

up_reason_mng

up_reason_pwr

PLR

hi_retransmission_rate

plr_rcv_code_err

plr_rcv_codes

plr_rcv_uncorrectable_code

plr_sync_events

plr_xmit_codes

plr_xmit_retry_codes

plr_xmit_retry_codes_within_t_sec_max

plr_xmit_retry_events

Port VL

PortRcvDataSLExt[0-15]

PortRcvDataVLExt[0-15]

PortRcvPktVLExt[0-15]

PortVLXmitFlowCtlUpdateErrors[0-15]

PortVLXmitTimeCongExt[0-15]

PortXmitDataSLExt[0-15]

PortXmitDataVLExt[0-15]

PortXmitPktVLExt[0-15]

PortXmitWaitVLExt[0-15]

MLNX Counters Page0

rq_num_dup

rq_num_lae

rq_num_leeoe

rq_num_lle

rq_num_lpe

rq_num_lqpoe

rq_num_mce

rq_num_oos

rq_num_rae

rq_num_retrans_rsync

rq_num_rire

rq_num_roe

rq_num_wrfe

sq_num_bre

sq_num_ldb_drops

sq_num_leeoe

sq_num_lle

sq_num_lpe

sq_num_lqpoe

sq_num_mwbe

sq_num_oos

sq_num_rabrte

sq_num_rae

sq_num_retrans_rsync

sq_num_rire

sq_num_rnr

sq_num_roe

sq_num_rree

sq_num_to

sq_num_tree

sq_num_wrfe

MLNX Counters Page1

max_cnak_fifo_size

maximum_dcrs

minimum_dcrs

rq_close_non_gb_gc

rq_curr_gb_connect

rq_curr_gb_reconnect

rq_dcr_inhale_events

rq_gb_trap_cnak

rq_not_gb_connect

rq_not_gb_reconnect

rq_num_cnak_sent

rq_num_dc_cacks

rq_num_no_dcrs

rq_num_sig_err

rq_open_gb

rq_open_gb_cnak

rq_state_active_gb

rq_state_avail_dcrs

rq_state_dcr_lifo_size

sq_cnak_drop

sq_num_cnak

sq_num_dc_cacks

sq_num_sig_err

sq_reconnect

sq_reconnect_ack

sq_reconnect_ack_bad

MLNX Counters Page255

dc_has_max_used_entries_in_line

dc_hash_curr_used_lines

num_cqovf

num_eqovf

rq_close_gb_gc

rq_cwc_ghost_discard_connect

rq_cwc_ghost_discard_reconnect

rq_cwc_reconnect_probable_current_connection

rq_cwc_reconnect_stale_connection

rq_cwc_uncertainty_discard

rq_next_gb_connect

rq_next_gb_reconnect

rq_num_dc_cacks_collision

rq_num_dc_cacks_full_hash

rq_psn_close_gb

rq_psn_close_gb_cwc

sq_num_ds_ex_pi_retry

Sharp PM Counters

ack_packet_sent

aeth_syndrome_ack_packet

hba_multi_packet_message_dropped_bytes

hba_multi_packet_message_dropped_pkts

hba_received_bytes

hba_received_pkts

hba_sent_ack_bytes

hba_sent_ack_packets

hba_sharp_lookup

oos_nack_rcv

packet_discard_sharp

packet_discard_transport

packet_sent

rcds_send_bytes

rcds_sent_packets

retry_packet_sent

rnr_event

rnr_nack_rcv

timeout_event

General Info

build_id

device_hw_rev

device_id

device_technology

fw_date_dmy

fw_hour

fw_ini_ver

fw_version

hw_uptime

psid

sw_version

Device Temperature

dev_temperature

Port Counters

excessive_buffer_errors

link_down_counter

link_error_recovery_counter

local_link_integrity_errors

port_rcv_constraint_errors

port_rcv_data

port_rcv_errors

port_rcv_pkts

port_rcv_remote_physical_errors

port_rcv_switch_relay_errors

port_xmit_constraint_errors

port_xmit_data

port_xmit_discard

port_xmit_pkts

port_xmit_wait

symbol_error_counter

vl15_dropped

Port Counters Extended

ExcessiveBufferOverrunErrorsExtended

LinkDownedCounterExtended

LinkErrorRecoveryCounterExtended

LocalLinkIntegrityErrorsExtended

PortMultiCastRcvPktsExtended

PortMultiCastXmitPktsExtended

PortRcvConstraintErrorsExtended

PortRcvDataExtended

PortRcvErrorsExtended

PortRcvPktsExtended

PortRcvRemotePhysicalErrorsExtended

PortRcvSwitchRelayErrorsExtended

PortUniCastRcvPktsExtended

PortUniCastXmitPktsExtended

PortXmitConstraintErrorsExtended

PortXmitDataExtended

PortXmitDiscardsExtended

PortXmitPktsExtended

PortXmitWaitExtended

QP1DroppedExtended

SymbolErrorCounterExtended

VL15DroppedExtended

Extended Speeds Counters

ErrorDetectionCounterLane.[0-11]

FECCorrectableBlockCountrLane.[0-11]

FECCorrectedSymbolCounterLane.[0-11]

FECUncorrectableBlockCounterLane.[0-11]

PortFECCorrectableBlockCounter

PortFECCorrectedSymbolCounter

PortFECUncorrectableBlockCounter

RetransmissionPerSec

SyncHeaderErrorCounter

UnknownBlockCounter

LLR Statistics

MaxRetransmissionRate

Port Rcv Error Details

PortBufferOverrunErrors

PortDLIDMappingErrors

PortLocalPhysicalErrors

PortLoopingErrors

PortMalformedPacketErrors

PortVLMappingErrors

Port Xmit Discard Details

PortInactiveDiscards

PortNeighborMTUDiscards

PortSwHOQLifetimeLimitDiscards

PortSwLifetimeLimitDiscards

Port RN Counters

pfrn_received_error

pfrn_received_packet

pfrn_start_packet

pfrn_xmit_packet

port_ar_trials

port_rcv_rn_error

port_rcv_rn_pkt

port_rcv_switch_relay_rn_error

port_xmit_rn_pkt

Port HBF Counters

rx_pkt_forwarding_ar

rx_pkt_forwarding_ar_sg[0-2]

rx_pkt_forwarding_hbf

rx_pkt_forwarding_hbf_sg[0-2]

rx_pkt_forwarding_static

rx_pkt_hbf_fallback_local

rx_pkt_hbf_fallback_remote

Fast Recovery Counters

consecutive_normal_credit_watchdog

consecutive_normal_eff_ber

consecutive_normal_raw_ber

consecutive_normal_sym_ber

counter_overflow_credit_watchdog

counter_overflow_eff_ber

counter_overflow_raw_ber

counter_overflow_sym_ber

last_value_[0-2]_credit_watchdog

last_value_[0-2]_eff_ber

last_value_[0-2]_raw_ber

last_value_[0-2]_sym_ber

max_value_credit_watchdog

max_value_eff_ber

max_value_raw_ber

max_value_sym_ber

min_value_credit_watchdog

min_value_eff_ber

min_value_raw_ber

min_value_sym_ber

num_errors_credit_watchdog

num_errors_eff_ber

num_errors_raw_ber

num_errors_sym_ber

num_normals_credit_watchdog

num_normals_eff_ber

num_normals_raw_ber

num_normals_sym_ber

num_warnings_credit_watchdog

num_warnings_eff_ber

num_warnings_raw_ber

num_warnings_sym_ber

Port Hierarchy

bus

device

function

m_asic

m_cage

m_label

m_port

m_slot_type

m_slot_value

m_split

m_type

Link Partner

link_partner_description

link_partner_lid

link_partner_node_guid

link_partner_port_num

Ports

fec_mode_active

link_speed_active

link_width_active

logical_state

phy_state

pi_fec_mode_active

pi_link_speed_active

pi_link_width_active

Performance Histogram Info

cap_cell_size

cap_hist_bin_size

cap_max_port_hist_id

cap_max_sample_time

Performance Histogram Buffer Control

performance_histogram_buffer_control_bin_size_egress[0-15]

performance_histogram_buffer_control_bin_size_ingress[0-15]

performance_histogram_buffer_control_hist_min_value_egress[0-15]

performance_histogram_buffer_control_hist_min_value_ingress[0-15]

performance_histogram_buffer_control_histogram_type_egress[0-15]

performance_histogram_buffer_control_histogram_type_ingress[0-15]

performance_histogram_buffer_control_mode_egress[0-15]

performance_histogram_buffer_control_mode_ingress[0-15]

performance_histogram_buffer_control_sample_time_egress[0-15]

performance_histogram_buffer_control_sample_time_ingress[0-15]

Performance Histogram Buffer Data

performance_histogram_buffer_data_bin_high[0-9]_egress[0-15]

performance_histogram_buffer_data_bin_high[0-9]_ingress[0-15]

performance_histogram_buffer_data_bin_low[0-9]_egress[0-15]

performance_histogram_buffer_data_bin_low[0-9]_ingress[0-15]

performance_histogram_buffer_data_histogram_type_egress[0-15]

performance_histogram_buffer_data_histogram_type_ingress[0-15]

performance_histogram_buffer_data_max_sampled_egress[0-15]

performance_histogram_buffer_data_max_sampled_ingress[0-15]

performance_histogram_buffer_data_min_sampled_egress[0-15]

performance_histogram_buffer_data_min_sampled_ingress[0-15]

Calculated Info

NormalizedXW

Normalized_CBW

Normalized_XmitData

infiniband_CBW

© Copyright 2024, NVIDIA. Last updated on Aug 15, 2024.