Dell-Omnia-Clusters-HPC-AI/control_plane/input_params/opensm.conf

#
# DEVICE ATTRIBUTES OPTIONS
#
# The port GUID on which the OpenSM is running
guid 0x0000000000000000

# M_Key value sent to all ports qualifying all Set(PortInfo)
m_key 0x0000000000000000

# The lease period used for the M_Key on this subnet in [sec]
m_key_lease_period 0

# The protection level used for the M_Key on this subnet
m_key_protection_level 0

# If TRUE, SM tries to determine the m_key of unknown ports from guid2mkey file
# If FALSE, SM won't try to determine the m_key of unknown ports.
# Preconfigured m_key will be used instead
m_key_lookup TRUE

# SM_Key value of the SM used for SM authentication
sm_key 0x0000000000000001

# SM_Key value to qualify rcv SA queries as 'trusted'
sa_key 0x0000000000000001

# Note that for both values above (sm_key and sa_key)
# OpenSM version 3.2.1 and below used the default value '1'
# in a host byte order, it is fixed now but you may need to
# change the values to interoperate with old OpenSM running
# on a little endian machine.

# Subnet prefix used on this subnet
subnet_prefix 0xfe80000000000000

# The LMC value used on this subnet
lmc 0

# lmc_esp0 determines whether LMC value used on subnet is used for
# enhanced switch port 0. If TRUE, LMC value for subnet is used for
# ESP0. Otherwise, LMC value for ESP0s is 0.
lmc_esp0 FALSE

# sm_sl determines SMSL used for SM/SA communication
sm_sl 0

# The code of maximal time a packet can live in a switch
# The actual time is 4.096usec * 2^<packet_life_time>
# The value 0x14 disables this mechanism
packet_life_time 0x12

# The number of sequential packets dropped that cause the port
# to enter the VLStalled state. The result of setting this value to
# zero is undefined.
vl_stall_count 0x07

# The number of sequential packets dropped that cause the port
# to enter the VLStalled state. This value is for switch ports
# driving a CA or router port. The result of setting this value
# to zero is undefined.
leaf_vl_stall_count 0x07

# The code of maximal time a packet can wait at the head of
# transmission queue.
# The actual time is 4.096usec * 2^<head_of_queue_lifetime>
# The value 0x14 disables this mechanism
head_of_queue_lifetime 0x12

# The maximal time a packet can wait at the head of queue on
# switch port connected to a CA or router port
leaf_head_of_queue_lifetime 0x10

# Limit the maximal operational VLs
max_op_vls 5

# Force PortInfo:LinkSpeedEnabled on switch ports
# If 0, don't modify PortInfo:LinkSpeedEnabled on switch port
# Otherwise, use value for PortInfo:LinkSpeedEnabled on switch port
# Values are (IB Spec 1.2.1, 14.2.5.6 Table 146 "PortInfo")
#    1: 2.5 Gbps
#    3: 2.5 or 5.0 Gbps
#    5: 2.5 or 10.0 Gbps
#    7: 2.5 or 5.0 or 10.0 Gbps
#    2,4,6,8-14 Reserved
#    Default 15: set to PortInfo:LinkSpeedSupported
force_link_speed 15

# Force PortInfo:LinkSpeedExtEnabled on ports
# If 0, don't modify PortInfo:LinkSpeedExtEnabled on port
# Otherwise, use value for PortInfo:LinkSpeedExtEnabled on port
# Values are (MgtWG RefIDs #4722 and #9366)
#    1: 14.0625 Gbps
#    2: 25.78125 Gbps
#    3: 14.0625 Gbps or 25.78125 Gbps
#    4: 53.125 Gbps
#    5: 14.0625 Gbps or 53.125 Gbps
#    6: 25.78125 Gbps or 53.125 Gbps
#    7: 14.0625 Gbps, 25.78125 Gbps or 53.125 Gbps
#    30: Disable extended link speeds
#    Default 31: set to PortInfo:LinkSpeedExtSupported
force_link_speed_ext 31

# Force PortInfo:LinkWidthEnabled on switch ports
# If 0, don't modify PortInfo:LinkWidthEnabled on switch port
# Otherwise, use value for PortInfo:LinkWidthEnabled on switch port
# Values are (IB Spec 1.2.1, 14.2.5.6 Table 146 "PortInfo"
# augmented by MgtWG RefIDs #9306-9309)
#    1: 1x
#    2: 4x
#    3: 1x or 4x
#    4: 8x
#    5: 1x or 8x
#    6: 4x or 8x
#    7: 1x or 4x or 8x
#    8: 12x
#    9: 1x or 12x
#    10: 4x or 12x
#    11: 1x or 4x or 12x
#    12: 8x or 12x
#    13: 1x or 8x or 12x
#    14: 4x or 8x or 12x
#    15: 1x or 4x or 8x or 12x
#    16: 2x
#    17: 1x or 2x
#    18: 2x or 4x
#    19: 1x or 2x or 4x
#    20: 2x or 8x
#    21: 1x or 2x or 8x
#    22: 2x or 4x or 8x
#    23: 1x or 2x or 4x or 8x
#    24: 2x or 12x
#    25: 1x or 2x or 12x
#    26: 2x or 4x or 12x
#    27: 1x or 2x or 4x or 12x
#    28: 2x or 8x or 12x
#    29: 1x or 2x or 8x or 12x
#    30: 2x or 4x or 8x or 12x
#    31: 1x or 2x or 4x or 8x or 12x
#    32-254 Reserved
#    Default 255: set to PortInfo:LinkWidthSupported
force_link_width 255

# FDR10 on ports on devices that support FDR10
# Values are:
#    0: don't use fdr10 (no MLNX ExtendedPortInfo MADs)
#    Default 1: enable fdr10 when supported
#    2: disable fdr10 when supported
fdr10 1

# The subnet_timeout code that will be set for all the ports
# The actual timeout is 4.096usec * 2^<subnet_timeout>
subnet_timeout 18

# Threshold of local phy errors for sending Trap 129
local_phy_errors_threshold 0x08

# Threshold of credit overrun errors for sending Trap 130
overrun_errors_threshold 0x08

# Use SwitchInfo:MulticastFDBTop if advertised in PortInfo:CapabilityMask
use_mfttop TRUE

#
# PARTITIONING OPTIONS
#
# Partition configuration file to be used
partition_config_file /etc/rdma/partitions.conf

# Disable partition enforcement by switches (DEPRECATED)
# This option is DEPRECATED. Please use part_enforce instead
no_partition_enforcement FALSE

# Partition enforcement type (for switches)
# Values are both, out, in and off
# Default is both (outbound and inbound enforcement)
part_enforce both

# Allow both full and limited membership on the same partition
allow_both_pkeys FALSE

# Keep current and take into account old pkey indexes
# during calculation of physical ports pkey tables
keep_pkey_indexes TRUE

# SM assigned GUID byte where GUID is formed from OpenFabrics OUI
# followed by 40 bits xy 00 ab cd ef where xy is the SM assigned GUID byte
# and ab cd ef is an SM autogenerated 24 bits
# SM assigned GUID byte should be configured as subnet unique
sm_assigned_guid 0x00

#
# SWEEP OPTIONS
#
# The number of seconds between subnet sweeps (0 disables it)
sweep_interval 10

# If TRUE cause all lids to be reassigned
reassign_lids FALSE

# If TRUE forces every sweep to be a heavy sweep
force_heavy_sweep FALSE

# If TRUE every trap 128 and 144 will cause a heavy sweep.
# NOTE: successive identical traps (>10) are suppressed
sweep_on_trap TRUE

#
# ROUTING OPTIONS
#
# If TRUE count switches as link subscriptions
port_profile_switch_nodes FALSE

# Name of file with port guids to be ignored by port profiling
port_prof_ignore_file (null)

# The file holding routing weighting factors per output port
hop_weights_file (null)

# The file holding non-default port order per switch for routing
port_search_ordering_file (null)

# Routing engine
# Multiple routing engines can be specified separated by
# commas so that specific ordering of routing algorithms will
# be tried if earlier routing engines fail.
# Supported engines: minhop, updn, dnup, file, ftree, lash,
#    dor, torus-2QoS, nue, dfsssp, sssp
routing_engine (null)

# Routing engines will avoid throttled switch-to-switch links
# (supported by: nue, dfsssp, sssp; use FALSE if unsure)
avoid_throttled_links FALSE

# Connect roots (use FALSE if unsure)
connect_roots FALSE

# Use unicast routing cache (use FALSE if unsure)
use_ucast_cache FALSE

# Lid matrix dump file name
lid_matrix_dump_file (null)

# LFTs file name
lfts_file (null)

# The file holding the root node guids (for fat-tree or Up/Down)
# One guid in each line
root_guid_file (null)

# The file holding the fat-tree compute node guids
# One guid in each line
cn_guid_file (null)

# The file holding the fat-tree I/O node guids
# One guid in each line.
# If only io_guid file is provided, the rest of nodes
# are considered as compute nodes.
io_guid_file (null)

# If TRUE enables alternative indexing policy for ftree routing
# in quasi-ftree topologies that can improve shift-pattern support.
# The switch indexing starts from root switch and leaf switches
# are termination points of BFS algorithm
# If FALSE, the indexing starts from leaf switch (default)
quasi_ftree_indexing FALSE

# Number of reverse hops allowed for I/O nodes
# Used for connectivity between I/O nodes connected to Top Switches
max_reverse_hops 0

# The file holding the node ids which will be used by Up/Down algorithm instead
# of GUIDs (one guid and id in each line)
ids_guid_file (null)

# The file holding guid routing order guids (for MinHop and Up/Down)
guid_routing_order_file (null)

# Do mesh topology analysis (for LASH algorithm)
do_mesh_analysis FALSE

# Starting VL for LASH algorithm
lash_start_vl 0

# Maximum number of VLs for Nue routing algorithm (default: 1; to enforce
# deadlock-freedom even if QoS is not enabled). Set to 0 if Nue should
# automatically determine and choose maximum supported by the fabric, or
# any integer >= 1 (then Nue uses min(max_supported,nue_max_num_vls)
nue_max_num_vls 1

# If TRUE, then Nue assumes that switches will send/receive
# data traffic, too, and hence their paths are included in
# the deadlock-avoidance calculation (use FALSE if unsure)
nue_include_switches FALSE

# Port Shifting (use FALSE if unsure)
port_shifting FALSE

# Assign ports in a random order instead of round-robin
# If zero disable (default), otherwise use the value as a random seed
scatter_ports 0

# Don't use scatter for ports defined in
# guid_routing_order file
guid_routing_order_no_scatter FALSE

# SA database file name
sa_db_file (null)

# If TRUE causes OpenSM to dump SA database at the end of
# every light sweep, regardless of the verbosity level
sa_db_dump FALSE

# Torus-2QoS configuration file name
torus_config /etc/rdma/torus-2QoS.conf

#
# HANDOVER - MULTIPLE SMs OPTIONS
#
# SM priority used for deciding who is the master
# Range goes from 0 (lowest priority) to 15 (highest).
sm_priority 0

# If TRUE other SMs on the subnet should be ignored
ignore_other_sm FALSE

# Timeout in [msec] between two polls of active master SM
sminfo_polling_timeout 10000

# Number of failing polls of remote SM that declares it dead
polling_retry_number 4

# If TRUE honor the guid2lid file when coming out of standby
# state, if such file exists and is valid
honor_guid2lid_file FALSE

#
# TIMING AND THREADING OPTIONS
#
# Maximum number of SMPs sent in parallel
max_wire_smps 4

# Maximum number of timeout based SMPs allowed to be outstanding
# A value less than or equal to max_wire_smps disables this mechanism
max_wire_smps2 4

# The timeout in [usec] used for sending SMPs above max_wire_smps limit
# and below max_wire_smps2 limit
max_smps_timeout 600000

# The maximum time in [msec] allowed for a transaction to complete
transaction_timeout 200

# The maximum number of retries allowed for a transaction to complete
transaction_retries 3

# The maximum time in [msec] allowed for a "long" transacrion to complete
# Currently, long transaction is only set of optimized SL2VLMappingTable
long_transaction_timeout 500

# Maximal time in [msec] a message can stay in the incoming message queue.
# If there is more than one message in the queue and the last message
# stayed in the queue more than this value, any SA request will be
# immediately be dropped but BUSY status is not currently returned.
max_msg_fifo_timeout 10000

# Use a single thread for handling SA queries
single_thread FALSE

#
# MISC OPTIONS
#
# Daemon mode
daemon FALSE

# SM Inactive
sm_inactive FALSE

# Babbling Port Policy
babbling_port_policy FALSE

# Drop event subscriptions (InformInfo and ServiceRecord) on port removal and SM coming out of STANDBY
drop_event_subscriptions FALSE

# Validate IPoIB non-broadcast group creation parameters against
# broadcast group parameters per IETF RFC 4391 (default TRUE)
ipoib_mcgroup_creation_validation TRUE

# Validate multicast join parameters against multicast group
# parameters when MC group already exists
mcgroup_join_validation TRUE

# Use original extended SA rates only
# The original extended SA rates are up through 300 Gbps (12x EDR)
# Set to TRUE for subnets with old kernels/drivers that don't understand
# the new SA rates for 2x link width and/or HDR link speed (19-22)
# default is FALSE
use_original_extended_sa_rates_only FALSE

# Use Optimized SLtoVLMapping programming if supported by device
use_optimized_slvl FALSE

# Sync in memory files used for high availability with storage
fsync_high_avail_files TRUE

#
# Performance Manager Options
#
# perfmgr enable
# PerfMgr is enabled if TRUE and disabled if FALSE (default FALSE)
perfmgr FALSE

# redirection enable
# Redirection supported if TRUE and not supported if FALSE (default TRUE)
perfmgr_redir TRUE

# sweep time in seconds (default 180 seconds)
perfmgr_sweep_time_s 180

# Max outstanding queries (default 500)
perfmgr_max_outstanding_queries 500

# Ignore CAs on sweep (default FALSE)
perfmgr_ignore_cas FALSE

# Remove missing nodes from DB (default TRUE)
perfmgr_rm_nodes TRUE

# Log error counters to opensm.log (default TRUE)
perfmgr_log_errors TRUE

# Query PerfMgt Get(ClassPortInfo) for extended capabilities
# Extended capabilities include 64 bit extended counters
# and transmit wait support (default TRUE)
perfmgr_query_cpi TRUE

# Log xmit_wait errors (default FALSE)
perfmgr_xmit_wait_log FALSE

# If logging xmit_wait's; set threshold (default 65535)
perfmgr_xmit_wait_threshold 65535

#
# Event DB Options
#
# Dump file to dump the events to
event_db_dump_file (null)

#
# Event Plugin Options
#
# Event plugin name(s)
event_plugin_name (null)

# Options string that would be passed to the plugin(s)
event_plugin_options (null)

#
# Node name map for mapping node's to more descriptive node descriptions
# (man ibnetdiscover for more information)
#
node_name_map_name (null)

#
# DEBUG FEATURES
#
# The log flags used
log_flags 0x03

# Force flush of the log file after each log message
force_log_flush FALSE

# Log file to be used
log_file /var/log/opensm.log

# Limit the size of the log file in MB. If overrun, log is restarted
log_max_size 0

# If TRUE will accumulate the log over multiple OpenSM sessions
accum_log_file TRUE

# Per module logging configuration file
# Each line in config file contains <module_name><separator><log_flags>
# where module_name is file name including .c
# separator is either = , space, or tab
# log_flags is the same flags as used in the coarse/overall logging
per_module_logging_file /etc/rdma/per-module-logging.conf

# The directory to hold the file OpenSM dumps
dump_files_dir /var/log/

# If TRUE enables new high risk options and hardware specific quirks
enable_quirks FALSE

# If TRUE disables client reregistration
no_clients_rereg FALSE

# If TRUE OpenSM should disable multicast support and
# no multicast routing is performed if TRUE
disable_multicast FALSE

# If TRUE opensm will exit on fatal initialization issues
exit_on_fatal TRUE

# console [off|local]
console off

# Telnet port for console (default 10000)
console_port 10000

#
# QoS OPTIONS
#
# Enable QoS setup
qos FALSE

# QoS policy file to be used
qos_policy_file /etc/rdma/qos-policy.conf

# Suppress QoS MAD status errors
suppress_sl2vl_mad_status_errors FALSE

# QoS default options
qos_max_vls 0
qos_high_limit -1
qos_vlarb_high (null)
qos_vlarb_low (null)
qos_sl2vl (null)

# QoS CA options
qos_ca_max_vls 0
qos_ca_high_limit -1
qos_ca_vlarb_high (null)
qos_ca_vlarb_low (null)
qos_ca_sl2vl (null)

# QoS Switch Port 0 options
qos_sw0_max_vls 0
qos_sw0_high_limit -1
qos_sw0_vlarb_high (null)
qos_sw0_vlarb_low (null)
qos_sw0_sl2vl (null)

# QoS Switch external ports options
qos_swe_max_vls 0
qos_swe_high_limit -1
qos_swe_vlarb_high (null)
qos_swe_vlarb_low (null)
qos_swe_sl2vl (null)

# QoS Router ports options
qos_rtr_max_vls 0
qos_rtr_high_limit -1
qos_rtr_vlarb_high (null)
qos_rtr_vlarb_low (null)
qos_rtr_sl2vl (null)

#
# Congestion Control OPTIONS (EXPERIMENTAL)
#

# Enable Congestion Control Configuration
congestion_control FALSE

# CCKey to use when configuring congestion control
# note that this does not configure a new CCkey, only the CCkey to use
cc_key 0x0000000000000000

# Congestion Control Max outstanding MAD
cc_max_outstanding_mads 500

#
# Congestion Control SwitchCongestionSetting options
#
# Control Map - bitmask indicating which of the following are to be used
# bit 0 - victim mask
# bit 1 - credit mask
# bit 2 - threshold + packet size
# bit 3 - credit starvation threshold + return delay valid
# bit 4 - marking rate valid
cc_sw_cong_setting_control_map 0x0

# Victim Mask - 256 bit mask representing switch ports, mark packets with FECN
# whether they are the source or victim of congestion
# bit 0 - port 0 (enhanced port)
# bit 1 - port 1
# ...
# bit 254 - port 254
# bit 255 - reserved
cc_sw_cong_setting_victim_mask 0x0000000000000000000000000000000000000000000000000000000000000000

# Credit Mask - 256 bit mask representing switch ports to apply credit starvation
# bit 0 - port 0 (enhanced port)
# bit 1 - port 1
# ...
# bit 254 - port 254
# bit 255 - reserved
cc_sw_cong_setting_credit_mask 0x0000000000000000000000000000000000000000000000000000000000000000

# Threshold - value indicating aggressiveness of congestion marking
# 0x0 - none, 0x1 - loose, ..., 0xF - aggressive
cc_sw_cong_setting_threshold 0x00

# Packet Size - any packet less than this size will not be marked with a FECN
# units are in credits
cc_sw_cong_setting_packet_size 0

# Credit Starvation Threshold - value indicating aggressiveness of credit starvation
# 0x0 - none, 0x1 - loose, ..., 0xF - aggressive
cc_sw_cong_setting_credit_starvation_threshold 0x00

# Credit Starvation Return Delay - in CCT entry shift:multiplier format, see IB spec
cc_sw_cong_setting_credit_starvation_return_delay 0:0

# Marking Rate - mean number of packets between markings
cc_sw_cong_setting_marking_rate 0

#
# Congestion Control CA Congestion Setting options
#
# Port Control
# bit 0 = 0, QP based congestion control
# bit 0 = 1, SL/port based congestion control
cc_ca_cong_setting_port_control 0x0000

# Control Map - 16 bit bitmask indicating which SLs should be configured
cc_ca_cong_setting_control_map 0x0000

#
# CA Congestion Setting Entries
#
# Each of congestion control settings below configures the CA Congestion
# Settings for an individual SL.  The SL must be specified before the value.
# These options may be specified multiple times to configure different values
# for different SLs.
#
# ccti timer - when expires decrements 1 from the CCTI
# ccti increase - number to be added to the table index on receipt of a BECN
# trigger threshold - when the ccti is equal to this, an event is logged
# ccti min - the minimum value for the ccti.  This imposes a minimum rate
#            on the injection rate

# SL = 0
cc_ca_cong_setting_ccti_timer 0 0
cc_ca_cong_setting_ccti_increase 0 0
cc_ca_cong_setting_trigger_threshold 0 0
cc_ca_cong_setting_ccti_min 0 0

#
# Congestion Control Table
#
# Comma separated list of CCT entries representing CCT.
# Format is shift:multipler,shift_multiplier,shift:multiplier,...
cc_cct (null)

# Prefix routes file name
prefix_routes_file /etc/rdma/prefix-routes.conf

#
# IPv6 Solicited Node Multicast (SNM) Options
#
consolidate_ipv6_snm_req FALSE

# Log prefix
log_prefix (null)