Add new collector for InfiniBand statistics

Add new metrics for the InfiniBand network protocol including the amount of packets sent and received, the number of times the link has been downed and how many times the link has recovered from an error state.

Signed-Off-By: Robert Clark <robert.d.clark@hpe.com>
This commit is contained in:
Robert Clark 2017-02-07 10:46:51 -06:00
commit 4866adcb71
19 changed files with 226 additions and 0 deletions

View file

@ -654,6 +654,38 @@ node_hwmon_temp_max_celsius{chip="platform_coretemp_1",sensor="temp2"} 84
node_hwmon_temp_max_celsius{chip="platform_coretemp_1",sensor="temp3"} 84
node_hwmon_temp_max_celsius{chip="platform_coretemp_1",sensor="temp4"} 84
node_hwmon_temp_max_celsius{chip="platform_coretemp_1",sensor="temp5"} 84
# HELP node_infiniband_link_downed_total Number of times the link failed to recover from an error state and went down
# TYPE node_infiniband_link_downed_total counter
node_infiniband_link_downed_total{device="mlx4_0",port="1"} 0
node_infiniband_link_downed_total{device="mlx4_0",port="2"} 0
# HELP node_infiniband_link_error_recovery_total Number of times the link successfully recovered from an error state
# TYPE node_infiniband_link_error_recovery_total counter
node_infiniband_link_error_recovery_total{device="mlx4_0",port="1"} 0
node_infiniband_link_error_recovery_total{device="mlx4_0",port="2"} 0
# HELP node_infiniband_multicast_packets_received_total Number of multicast packets received (including errors)
# TYPE node_infiniband_multicast_packets_received_total counter
node_infiniband_multicast_packets_received_total{device="mlx4_0",port="1"} 93
node_infiniband_multicast_packets_received_total{device="mlx4_0",port="2"} 0
# HELP node_infiniband_multicast_packets_transmitted_total Number of multicast packets transmitted (including errors)
# TYPE node_infiniband_multicast_packets_transmitted_total counter
node_infiniband_multicast_packets_transmitted_total{device="mlx4_0",port="1"} 16
node_infiniband_multicast_packets_transmitted_total{device="mlx4_0",port="2"} 0
# HELP node_infiniband_port_data_received_bytes Number of data octets received on all links
# TYPE node_infiniband_port_data_received_bytes counter
node_infiniband_port_data_received_bytes{device="mlx4_0",port="1"} 4.631917e+06
node_infiniband_port_data_received_bytes{device="mlx4_0",port="2"} 0
# HELP node_infiniband_port_data_transmitted_bytes Number of data octets transmitted on all links
# TYPE node_infiniband_port_data_transmitted_bytes counter
node_infiniband_port_data_transmitted_bytes{device="mlx4_0",port="1"} 3.73344e+06
node_infiniband_port_data_transmitted_bytes{device="mlx4_0",port="2"} 0
# HELP node_infiniband_unicast_packets_received_total Number of unicast packets received (including errors)
# TYPE node_infiniband_unicast_packets_received_total counter
node_infiniband_unicast_packets_received_total{device="mlx4_0",port="1"} 61148
node_infiniband_unicast_packets_received_total{device="mlx4_0",port="2"} 0
# HELP node_infiniband_unicast_packets_transmitted_total Number of unicast packets transmitted (including errors)
# TYPE node_infiniband_unicast_packets_transmitted_total counter
node_infiniband_unicast_packets_transmitted_total{device="mlx4_0",port="1"} 61239
node_infiniband_unicast_packets_transmitted_total{device="mlx4_0",port="2"} 0
# HELP node_intr Total number of interrupts serviced.
# TYPE node_intr counter
node_intr 8.885917e+06