[Dynamic buffer calc] Support dynamic buffer calculation

cfgmgr/Makefile.am

@@ -5,6 +5,16 @@ LIBNL_LIBS = -lnl-genl-3 -lnl-route-3 -lnl-3
 
 bin_PROGRAMS = vlanmgrd teammgrd portmgrd intfmgrd buffermgrd vrfmgrd nbrmgrd vxlanmgrd sflowmgrd natmgrd coppmgrd
 
+cfgmgrdir = $(datadir)/swss
+
+dist_cfgmgr_DATA = \
+		buffer_check_headroom_mellanox.lua \
+		buffer_headroom_mellanox.lua \
+		buffer_pool_mellanox.lua \
+		buffer_check_headroom_vs.lua \
+		buffer_headroom_vs.lua \
+		buffer_pool_vs.lua
+
 if DEBUG
 DBGFLAGS = -ggdb -DDEBUG
 else
@@ -31,7 +41,7 @@ intfmgrd_CFLAGS = $(DBGFLAGS) $(AM_CFLAGS) $(CFLAGS_COMMON) $(CFLAGS_SAI)
 intfmgrd_CPPFLAGS = $(DBGFLAGS) $(AM_CFLAGS) $(CFLAGS_COMMON) $(CFLAGS_SAI)
 intfmgrd_LDADD = -lswsscommon
 
-buffermgrd_SOURCES = buffermgrd.cpp buffermgr.cpp $(top_srcdir)/orchagent/orch.cpp $(top_srcdir)/orchagent/request_parser.cpp shellcmd.h
+buffermgrd_SOURCES = buffermgrd.cpp buffermgr.cpp buffermgrdyn.cpp $(top_srcdir)/orchagent/orch.cpp $(top_srcdir)/orchagent/request_parser.cpp shellcmd.h
 buffermgrd_CFLAGS = $(DBGFLAGS) $(AM_CFLAGS) $(CFLAGS_COMMON) $(CFLAGS_SAI)
 buffermgrd_CPPFLAGS = $(DBGFLAGS) $(AM_CFLAGS) $(CFLAGS_COMMON) $(CFLAGS_SAI)
 buffermgrd_LDADD = -lswsscommon

cfgmgr/buffer_check_headroom_mellanox.lua

@@ -0,0 +1,131 @@
+-- KEYS - port name
+-- ARGV[1] - profile name
+-- ARGV[2] - new size
+-- ARGV[3] - pg to add
+
+local port = KEYS[1]
+local input_profile_name = ARGV[1]
+local input_profile_size = ARGV[2]
+local new_pg = ARGV[3]
+local accumulative_size = 0
+
+local appl_db = "0"
+local config_db = "4"
+local state_db = "6"
+
+local ret_true = {}
+local ret_false = {}
+local ret = {}
+local default_ret = {}
+
+table.insert(ret_true, "result:true")
+table.insert(ret_false, "result:false")
+
+-- Fetch the cable length from CONFIG_DB
+redis.call('SELECT', config_db)
+local cable_length_keys = redis.call('KEYS', 'CABLE_LENGTH*')
+if #cable_length_keys == 0 then
+    return ret_true
+end
+
+-- Check whether cable length exceeds 300m (maximum value in the non-dynamic-buffer solution)
+local cable_length_str = redis.call('HGET', cable_length_keys[1], port)
+if cable_length_str == nil then
+    return ret_true
+end
+local cable_length = tonumber(string.sub(cable_length_str, 1, -2))
+if cable_length > 300 then
+    default_ret = ret_false
+else
+    default_ret = ret_true
+end
+table.insert(default_ret, 'debug:no max_headroom_size configured, check cable length instead')
+
+local speed = redis.call('HGET', 'PORT|' .. port, 'speed')
+
+-- Fetch the threshold from STATE_DB
+redis.call('SELECT', state_db)
+
+local max_headroom_size = tonumber(redis.call('HGET', 'BUFFER_MAX_PARAM_TABLE|' .. port, 'max_headroom_size'))
+if max_headroom_size == nil then
+    return default_ret
+end
+
+local asic_keys = redis.call('KEYS', 'ASIC_TABLE*')
+local pipeline_delay = tonumber(redis.call('HGET', asic_keys[1], 'pipeline_latency'))
+if speed == 400000 then
+    pipeline_delay = pipeline_delay * 2 - 1
+end
+accumulative_size = accumulative_size + 2 * pipeline_delay * 1024
+
+-- Fetch all keys in BUFFER_PG according to the port
+redis.call('SELECT', appl_db)
+
+local debuginfo = {}
+
+local function get_number_of_pgs(keyname)
+    local range = string.match(keyname, "Ethernet%d+:([^%s]+)$")
+    local size
+    if range == nil then
+        table.insert(debuginfo, "debug:invalid pg:" .. keyname)
+        return 0
+    end
+    if string.len(range) == 1 then
+        size = 1
+    else
+        size = 1 + tonumber(string.sub(range, -1)) - tonumber(string.sub(range, 1, 1))
+    end
+    return size
+end
+
+local no_input_pg = true
+if new_pg ~= nil then
+    if get_number_of_pgs(new_pg) ~= 0 then
+        no_input_pg = false
+        new_pg = 'BUFFER_PG_TABLE:' .. new_pg
+    end
+end
+
+-- Fetch all the PGs, accumulate the sizes
+-- Assume there is only one lossless profile configured among all PGs on each port
+table.insert(debuginfo, 'debug:other overhead:' .. accumulative_size)
+local pg_keys = redis.call('KEYS', 'BUFFER_PG_TABLE:' .. port .. ':*')
+for i = 1, #pg_keys do
+    local profile = string.sub(redis.call('HGET', pg_keys[i], 'profile'), 2, -2)
+    local current_profile_size
+    if profile ~= 'BUFFER_PROFILE_TABLE:ingress_lossy_profile' and (no_input_pg or new_pg ~= pg_keys[i]) then
+        if profile ~= input_profile_name and not no_input_pg then
+            local referenced_profile = redis.call('HGETALL', profile)
+            for j = 1, #referenced_profile, 2 do
+                if referenced_profile[j] == 'size' then
+                    current_profile_size = tonumber(referenced_profile[j+1])
+                end
+            end
+        else
+            current_profile_size = input_profile_size
+            profile = input_profile_name
+        end
+        accumulative_size = accumulative_size + current_profile_size * get_number_of_pgs(pg_keys[i])
+        table.insert(debuginfo, 'debug:' .. pg_keys[i] .. ':' .. profile .. ':' .. current_profile_size .. ':' .. get_number_of_pgs(pg_keys[i]) .. ':accu:' .. accumulative_size)
+    end
+end
+
+if not no_input_pg then
+    accumulative_size = accumulative_size + input_profile_size * get_number_of_pgs(new_pg)
+    table.insert(debuginfo, 'debug:' .. new_pg .. '*:' .. input_profile_name .. ':' .. input_profile_size .. ':' .. get_number_of_pgs(new_pg) .. ':accu:' .. accumulative_size)
+end
+
+if max_headroom_size > accumulative_size then
+    table.insert(ret, "result:true")
+else
+    table.insert(ret, "result:false")
+end
+
+table.insert(ret, "debug:max headroom:" .. max_headroom_size)
+table.insert(ret, "debug:accumulative headroom:" .. accumulative_size)
+
+for i = 1, #debuginfo do
+    table.insert(ret, debuginfo[i])
+end
+
+return ret

cfgmgr/buffer_check_headroom_vs.lua

@@ -0,0 +1 @@
+buffer_check_headroom_mellanox.lua

cfgmgr/buffer_headroom_mellanox.lua

@@ -0,0 +1,129 @@
+-- KEYS - profile name
+-- ARGV[1] - port speed
+-- ARGV[2] - cable length
+-- ARGV[3] - port mtu
+-- ARGV[4] - gearbox delay
+
+-- parameters retried from databases:
+-- From CONFIG_DB.LOSSLESS_TRAFFIC_PATTERN
+--      small packet percentage:    the parameter which is used to control worst case regarding the cell utilization
+--      mtu:                        the mtu of lossless packet
+-- From STATE_DB.ASIC_TABLE:
+--      cell size:                  cell_size of the ASIC
+--      pipeline_latency:           the latency 
+--      mac_phy_delay:
+--      peer_response_time:
+
+local lossless_mtu
+local small_packet_percentage
+local cell_size
+local pipeline_latency
+local mac_phy_delay
+local peer_response_time
+
+local port_speed = tonumber(ARGV[1])
+local cable_length = tonumber(string.sub(ARGV[2], 1, -2))
+local port_mtu = tonumber(ARGV[3])
+local gearbox_delay = tonumber(ARGV[4])
+
+local appl_db = "0"
+local config_db = "4"
+local state_db = "6"
+
+local ret = {}
+
+if gearbox_delay == nil then
+    gearbox_delay = 0
+end
+
+-- Fetch ASIC info from ASIC table in STATE_DB
+redis.call('SELECT', state_db)
+local asic_keys = redis.call('KEYS', 'ASIC_TABLE*')
+
+-- Only one key should exist
+local asic_table_content = redis.call('HGETALL', asic_keys[1])
+for i = 1, #asic_table_content, 2 do
+    if asic_table_content[i] == "cell_size" then
+        cell_size = tonumber(asic_table_content[i+1])
+    end
+    if asic_table_content[i] == "pipeline_latency" then
+        pipeline_latency = tonumber(asic_table_content[i+1]) * 1024
+    end
+    if asic_table_content[i] == "mac_phy_delay" then
+        mac_phy_delay = tonumber(asic_table_content[i+1]) * 1024
+    end
+    if asic_table_content[i] == "peer_response_time" then
+        peer_response_time = tonumber(asic_table_content[i+1]) * 1024
+    end
+end
+
+-- Fetch lossless traffic info from CONFIG_DB
+redis.call('SELECT', config_db)
+local lossless_traffic_keys = redis.call('KEYS', 'LOSSLESS_TRAFFIC_PATTERN*')
+
+-- Only one key should exist
+local lossless_traffic_table_content = redis.call('HGETALL', lossless_traffic_keys[1])
+for i = 1, #lossless_traffic_table_content, 2 do
+    if lossless_traffic_table_content[i] == "mtu" then
+        lossless_mtu = tonumber(lossless_traffic_table_content[i+1])
+    end
+    if lossless_traffic_table_content[i] == "small_packet_percentage" then
+        small_packet_percentage = tonumber(lossless_traffic_table_content[i+1])
+    end
+end
+
+-- Fetch DEFAULT_LOSSLESS_BUFFER_PARAMETER from CONFIG_DB
+local lossless_traffic_keys = redis.call('KEYS', 'DEFAULT_LOSSLESS_BUFFER_PARAMETER*')
+
+-- Calculate the headroom information
+local speed_of_light = 198000000
+local minimal_packet_size = 64
+local cell_occupancy
+local worst_case_factor
+local propagation_delay
+local bytes_on_cable
+local bytes_on_gearbox
+local xoff_value
+local xon_value
+local headroom_size
+local speed_overhead
+
+-- Adjustment for 400G
+if port_speed == 400000 then
+    pipeline_latency = 37 * 1024
+    speed_overhead = port_mtu
+else
+    speed_overhead = 0
+end
+
+if cell_size > 2 * minimal_packet_size then
+    worst_case_factor = cell_size / minimal_packet_size
+else
+    worst_case_factor = (2 * cell_size) / (1 + cell_size)
+end
+
+cell_occupancy = (100 - small_packet_percentage + small_packet_percentage * worst_case_factor) / 100
+
+if (gearbox_delay == 0) then
+    bytes_on_gearbox = 0
+else
+    bytes_on_gearbox = port_speed * gearbox_delay / (8 * 1024)
+end
+
+bytes_on_cable = 2 * cable_length * port_speed * 1000000000 / speed_of_light / (8 * 1024)
+propagation_delay = port_mtu + bytes_on_cable + 2 * bytes_on_gearbox + mac_phy_delay + peer_response_time
+
+-- Calculate the xoff and xon and then round up at 1024 bytes
+xoff_value = lossless_mtu + propagation_delay * cell_occupancy
+xoff_value = math.ceil(xoff_value / 1024) * 1024
+xon_value = pipeline_latency
+xon_value = math.ceil(xon_value / 1024) * 1024
+
+headroom_size = xoff_value + xon_value + speed_overhead
+headroom_size = math.ceil(headroom_size / 1024) * 1024
+
+table.insert(ret, "xon" .. ":" .. math.ceil(xon_value))
+table.insert(ret, "xoff" .. ":" .. math.ceil(xoff_value))
+table.insert(ret, "size" .. ":" .. math.ceil(headroom_size))
+
+return ret

cfgmgr/buffer_headroom_vs.lua

@@ -0,0 +1 @@
+buffer_headroom_mellanox.lua