[Auto Techsupport] Event driven Techsupport Changes (#8670)

#### Why I did it

Changes required for feature "Event Driven TechSupport Invocation & CoreDump Mgmt". [HLD](https://github.com/Azure/SONiC/pull/818 )

Requires: https://github.com/Azure/sonic-utilities/pull/1796.
Merging in any order would be fine.

Summary of the changes:

- Added the YANG Models for the new tables introduces as a part of this feature.
- Enhanced init_cfg.json with the default config required
- Added a compile Time flag which enables/disables the config required for this feature inside the init_cfg.json
- Enhanced the supervisor-proc-exit-listener script to populate `<feature>:<critical_proc> = <comm>:<pid>` info in the STATE_DB when it observes an proc exit notification for the critical processes running inside the docker.

Makefile.work

@@ -40,6 +40,9 @@
 #  * SONIC_DPKG_CACHE_SOURCE: Debian package cache location when cache enabled for debian packages
 #  * BUILD_LOG_TIMESTAMP: Set timestamp in the build log (simple/none)
 #  * DOCKER_EXTRA_OPTS: Extra command line arguments for dockerd running in slave container.
+#  * ENABLE_AUTO_TECH_SUPPORT: Enable the configuration for event-driven techsupport & coredump mgmt feature
+#  *                 Default: y
+#  *                 Values: y,n
 #
 ###############################################################################
 
@@ -282,6 +285,7 @@ SONIC_BUILD_INSTRUCTION :=  make \
                            SONIC_ENABLE_IMAGE_SIGNATURE=$(ENABLE_IMAGE_SIGNATURE) \
                            ENABLE_HOST_SERVICE_ON_START=$(ENABLE_HOST_SERVICE_ON_START) \
                            SLAVE_DIR=$(SLAVE_DIR) \
+                           ENABLE_AUTO_TECH_SUPPORT=$(ENABLE_AUTO_TECH_SUPPORT) \
                            BUILD_MULTIASIC_KVM=$(BUILD_MULTIASIC_KVM) \
                            $(SONIC_OVERRIDE_BUILD_VARS)
 

files/build_templates/init_cfg.json.j2

@@ -61,5 +61,26 @@
             "high_mem_alert": "disabled"
         }{% if not loop.last %},{% endif -%}
 {% endfor %}
+    },
+    "AUTO_TECHSUPPORT": {
+        "GLOBAL": {
+{%- if enable_auto_tech_support == "y" %}
+            "state" : "enabled", {% else %}
+            "state" : "disabled", {% endif %}
+            "rate_limit_interval" : "180",
+            "max_techsupport_limit" : "10.0",
+            "max_core_limit" : "5.0",
+            "since" : "2 days ago"
+        }
+    },
+    "AUTO_TECHSUPPORT_FEATURE": {
+{%- for feature, _, _, _ in features %}
+        "{{feature}}": {
+{%- if enable_auto_tech_support == "y" %}
+            "state" : "enabled", {% else %}
+            "state" : "disabled", {% endif %}
+            "rate_limit_interval" : "600"
+        }{%if not loop.last %},{% endif -%}
+{% endfor %} 
     }
 }

rules/config

@@ -144,6 +144,9 @@ INCLUDE_NAT = y
 # INCLUDE_DHCP_RELAY - build and install dhcp-relay package
 INCLUDE_DHCP_RELAY = y
 
+# ENABLE_AUTO_TECH_SUPPORT - Enable the configuration for event-driven techsupport & coredump mgmt feature
+ENABLE_AUTO_TECH_SUPPORT = y
+
 # TELEMETRY_WRITABLE - Enable write/config operations via the gNMI interface.
 # Uncomment to enable:
 # TELEMETRY_WRITABLE = y

slave.mk

@@ -163,6 +163,10 @@ ifeq ($(SONIC_INCLUDE_MACSEC),y)
 INCLUDE_MACSEC = y
 endif
 
+ifeq ($(ENABLE_AUTO_TECH_SUPPORT),y)
+ENABLE_AUTO_TECH_SUPPORT = y
+endif
+
 ifeq ($(SONIC_INCLUDE_MUX),y)
 INCLUDE_MUX = y
 endif
@@ -290,6 +294,7 @@ $(info "INCLUDE_KUBERNETES"              : "$(INCLUDE_KUBERNETES)")
 $(info "INCLUDE_MACSEC"                  : "$(INCLUDE_MACSEC)")
 $(info "INCLUDE_MUX"                     : "$(INCLUDE_MUX)")
 $(info "TELEMETRY_WRITABLE"              : "$(TELEMETRY_WRITABLE)")
+$(info "ENABLE_AUTO_TECH_SUPPORT"        : "$(ENABLE_AUTO_TECH_SUPPORT)")
 $(info "PDDF_SUPPORT"                    : "$(PDDF_SUPPORT)")
 $(info "MULTIARCH_QEMU_ENVIRON"          : "$(MULTIARCH_QEMU_ENVIRON)")
 $(info "SONIC_VERSION_CONTROL_COMPONENTS": "$(SONIC_VERSION_CONTROL_COMPONENTS)")
@@ -987,6 +992,7 @@ $(addprefix $(TARGET_PATH)/, $(SONIC_INSTALLERS)) : $(TARGET_PATH)/% : \
 	export include_restapi="$(INCLUDE_RESTAPI)"
 	export include_nat="$(INCLUDE_NAT)"
 	export include_sflow="$(INCLUDE_SFLOW)"
+	export enable_auto_tech_support="$(ENABLE_AUTO_TECH_SUPPORT)"
 	export include_macsec="$(INCLUDE_MACSEC)"
 	export include_mgmt_framework="$(INCLUDE_MGMT_FRAMEWORK)"
 	export include_iccpd="$(INCLUDE_ICCPD)"

src/sonic-yang-models/setup.py

@@ -78,6 +78,7 @@ setup(
     cmdclass={'build_py': my_build_py},
     data_files=[
         ('yang-models', ['./yang-models/sonic-acl.yang',
+                         './yang-models/sonic-auto_techsupport.yang',
                          './yang-models/sonic-bgp-common.yang',
                          './yang-models/sonic-bgp-global.yang',
                          './yang-models/sonic-bgp-neighbor.yang',

src/sonic-yang-models/tests/files/sample_config_db.json

@@ -1152,6 +1152,33 @@
                 "trap_group": "queue1_group1"
             }
         },
+        "AUTO_TECHSUPPORT": {
+            "GLOBAL": {
+                "state" : "enabled",
+                "rate_limit_interval" : "180",
+                "max_techsupport_limit" : "10.0",
+                "max_core_limit" : "0.0",
+                "since" : "2 days ago"
+            }
+        },
+        "AUTO_TECHSUPPORT_FEATURE": {
+            "bgp" :{
+                "state" : "disabled",
+                "rate_limit_interval" : "600"
+            },
+            "swss" : {
+                "state" : "enabled",
+                "rate_limit_interval" : "600"
+            },
+            "snmp" : {
+                "state" : "enabled",
+                "rate_limit_interval" : "500"
+            },
+            "dhcp_relay" : {
+                "state" : "disabled",
+                "rate_limit_interval" : "1000"
+            }
+        },
         "LLDP": {
             "GLOBAL": {
                 "mode": "TRANSMIT",
@@ -1371,7 +1398,6 @@
             }
         }
     },
-
     "SAMPLE_CONFIG_DB_UNKNOWN": {
         "UNKNOWN_TABLE": {
             "Error": "This Table is for testing, This Table does not have YANG models."

src/sonic-yang-models/tests/yang_model_tests/tests/auto_techsupport.json

@@ -0,0 +1,27 @@
+{
+    "AUTO_TECHSUPPORT_TEST":{
+	       "desc": "Configure auto techsupport params in AUTO_TECHSUPPORT Table"
+    },
+    "AUTO_TECHSUPPORT_WRONG_STATE_VALUE": {
+           "desc": "Configure state key with invalid value",
+           "eStrKey": "InvalidValue"
+    },
+    "AUTO_TECHSUPPORT_INVALID_RATE_LIMIT_FORMAT": {
+            "desc" : "Configure cooloff with a value of invalid format",
+            "eStrKey": "InvalidValue" 
+    },
+    "AUTO_TECHSUPPORT_OUT_OF_RANGE_DECIMAL": {
+            "desc" : "Configure a value for core-uage outside the range [0, 100)",
+            "eStr": "Value \"100.00\" does not satisfy the constraint \"0..99.99\" (range, length, or pattern)."
+    },
+    "AUTO_TECHSUPPORT_VALID_DECIMAL_VALUE": {
+            "desc" : "Configure a value for max_techsupport_size inside the range [0, 100)"
+    },
+    "AUTO_TECHSUPPORT_INVALID_FRACTION_DIGITS": {
+            "desc" : "Configure a value for max_techsupport_size inside the range [0, 100) but with 3 fractional digits",
+            "eStrKey": "InvalidValue" 
+    },
+    "AUTO_TECHSUPPORT_RATE_LIMIT_INTERVAL_TEST": {
+            "desc" : "Configure and test the valid configuration"
+    }
+}

src/sonic-yang-models/tests/yang_model_tests/tests_config/auto_techsupport.json

@@ -0,0 +1,85 @@
+{
+    "AUTO_TECHSUPPORT_TEST": {
+        "sonic-auto_techsupport:sonic-auto_techsupport": {
+            "sonic-auto_techsupport:AUTO_TECHSUPPORT": {
+                "sonic-auto_techsupport:GLOBAL": {
+                    "state" : "enabled",
+                    "rate_limit_interval" : "180",
+                    "max_techsupport_limit" : "10.0",
+                    "max_core_limit" : "5.0",
+                    "since" : "2 days ago"
+                } 
+            }
+        }
+    },
+    "AUTO_TECHSUPPORT_WRONG_STATE_VALUE": {
+        "sonic-auto_techsupport:sonic-auto_techsupport": {
+            "sonic-auto_techsupport:AUTO_TECHSUPPORT": {
+                "sonic-auto_techsupport:GLOBAL": {
+                    "state" : "start",
+                    "rate_limit_interval" : "180",
+                    "max_techsupport_limit" : "10.0",
+                    "max_core_limit" : "5.0",
+                    "since" : "2 days ago"                
+                } 
+            }
+        }
+    },
+    "AUTO_TECHSUPPORT_INVALID_RATE_LIMIT_FORMAT": {
+        "sonic-auto_techsupport:sonic-auto_techsupport": {
+            "sonic-auto_techsupport:AUTO_TECHSUPPORT": {
+                "sonic-auto_techsupport:GLOBAL": {
+                    "rate_limit_interval" : "whatever"
+                } 
+            }
+        }
+    },
+    "AUTO_TECHSUPPORT_OUT_OF_RANGE_DECIMAL": {
+        "sonic-auto_techsupport:sonic-auto_techsupport": {
+            "sonic-auto_techsupport:AUTO_TECHSUPPORT": {
+                "sonic-auto_techsupport:GLOBAL": {
+                    "max_core_limit" : "100.00",
+                    "rate_limit_interval" : "180"
+                } 
+            }
+        }
+    },
+    "AUTO_TECHSUPPORT_VALID_DECIMAL_VALUE": {
+        "sonic-auto_techsupport:sonic-auto_techsupport": {
+            "sonic-auto_techsupport:AUTO_TECHSUPPORT": {
+                "sonic-auto_techsupport:GLOBAL": {
+                    "max_techsupport_limit" : "11.23",
+                    "max_core_limit" : "99.99"
+                } 
+            }
+        }
+    },
+    "AUTO_TECHSUPPORT_INVALID_FRACTION_DIGITS": {
+        "sonic-auto_techsupport:sonic-auto_techsupport": {
+            "sonic-auto_techsupport:AUTO_TECHSUPPORT": {
+                "sonic-auto_techsupport:GLOBAL": {
+                    "max_techsupport_limit" : "11.111",
+                    "max_core_limit" : "99.99"
+                } 
+            }
+        }
+    },
+    "AUTO_TECHSUPPORT_RATE_LIMIT_INTERVAL_TEST": {
+        "sonic-auto_techsupport:sonic-auto_techsupport": {
+            "sonic-auto_techsupport:AUTO_TECHSUPPORT_FEATURE": {
+                "AUTO_TECHSUPPORT_FEATURE_LIST": [
+                    {
+                        "feature_name" : "bgp",
+                        "state" : "enabled",
+                        "rate_limit_interval" : "600"
+                    },
+                    {
+                        "feature_name" : "swss",
+                        "state" : "disabled",
+                        "rate_limit_interval" : "400"
+                    }
+                ]
+            }
+        }
+    }
+}

src/sonic-yang-models/yang-models/sonic-auto_techsupport.yang

@@ -0,0 +1,111 @@
+module sonic-auto_techsupport {
+
+    yang-version 1.1;
+
+    namespace "http://github.com/Azure/sonic-auto_techsupport";
+    prefix auto_techsupport;
+
+    import sonic-types {
+        prefix stypes;
+    }
+
+    description "Event Driven Techsupport & CoreDump Mgmt Capability in SONiC OS";
+
+    revision 2021-08-09 {
+        description "First Revision";
+    }
+
+    typedef decimal-repr {
+        type decimal64 {
+            fraction-digits 2;
+            range 0.0..99.99; 
+        }
+    }
+
+    container sonic-auto_techsupport {
+
+        container AUTO_TECHSUPPORT {
+
+                description "AUTO_TECHSUPPORT part of config_db.json";
+                
+                container GLOBAL {
+               
+                    leaf state {
+                        description "Knob to make techsupport invocation event-driven based on core-dump generation";
+                        type stypes:admin_mode;
+                    }
+
+                    leaf rate_limit_interval  {
+                        description "Minimum time in seconds between two successive techsupport invocations. Configure 0 to explicitly disable";
+                        type uint16;
+                    }
+
+                    leaf max_techsupport_limit {
+                        /*
+                        A value between 0.0-99.99 should be specified.
+                        The actual value in bytes is calculate based on the available space in the filesystem hosting /var/dump
+                        When the limit is crossed, the older dump files are incrementally deleted
+                        */
+                        description "Max Limit in percentage for the cummulative size of ts dumps. No cleanup is performed if the value isn't configured or is 0.0";
+                        type decimal-repr;
+                    }
+
+                    leaf max_core_limit {
+                        /*
+                        A value between 0.0-99.99 should be specified.
+                        The actual value in bytes is calculated based on the available space in the filesystem hosting /var/core
+                        When the limit is crossed, the older core files are incrementally deleted
+                        */
+                        description "Max Limit in percentage for the cummulative size of core dumps. No cleanup is performed if the value isn't congiured or is 0.0";
+                        type decimal-repr;
+                    }
+                    
+                    leaf since {
+                        /*
+                        Any valid date string of the formats specified here (https://www.gnu.org/software/coreutils/manual/html_node/Date-input-formats.html) 
+                        can be used. 
+                        */
+                        description "Only collect the logs & core-dumps generated since the time provided. A default value of '2 days ago' is used if this value is not set explicitly or a non-valid string is provided";
+                        type string {
+                            length 1..255;
+                        }
+                    }
+            }
+            /* end of container GLOBAL */
+        }
+        /* end of container AUTO_TECHSUPPORT */
+            
+        container AUTO_TECHSUPPORT_FEATURE {
+
+            description "AUTO_TECHSUPPORT_FEATURE part of config_db.json";
+
+            list AUTO_TECHSUPPORT_FEATURE_LIST {
+
+                key "feature_name";
+
+                leaf feature_name {
+                    description "The name of this feature";
+                    /* TODO: Leafref once the FEATURE YANG is added*/
+                    type string {
+                        length 1..255;
+                    }
+                }
+
+                leaf state {
+                    description "Enable auto techsupport invocation on the processes running inside this feature";
+                    type stypes:admin_mode;
+                }
+
+                leaf rate_limit_interval {
+                    description "Rate limit interval for the corresponding feature. Configure 0 to explicitly disable";
+                    type uint16;
+                }
+
+            }
+            /* end of AUTO_TECHSUPPORT_FEATURE_LIST */
+        }
+        /* end of container AUTO_TECHSUPPORT_FEATURE */
+    }
+    /* end of top level container */
+}
+