Enhance stream telemetry

Signed-off-by: Ze Gan <ganze718@gmail.com>

Author: Pterosaur

doc/TAM/SAI-Proposal-TAM-stream-telemetry.md

@@ -77,10 +77,12 @@ The existing telemetry solution relies on a process to proactively query stats a
 - The vendor SDK should support querying the minimal polling interval for each counter.
 - When reconfiguring any stream settings, whether it is the polling interval or the stats list, the existing stream will be interrupted and regenerated.
 - If any of monitored objects is deleted, the existing stream will be interrupted and regenerated.
+- The collector is designed to handle single-cycle counter rollovers; however, vendors must ensure that the data does not roll over twice between two collection intervals.
 
 ### Phase 2
 
 - Supports updating configuration without interrupting the telemetry stream
+- Support stats of tam telemetry for debugging purpose
 
 ## Architecture Design
 
@@ -971,6 +973,13 @@ typedef struct _sai_stat_st_capability_t
      */
     uint64_t minimal_polling_interval;
 
+/**
+     * @brief Maximal polling interval in nanoseconds
+     *
+     * If polling interval is more than this value, it will be unacceptable.
+     */
+    uint64_t maximal_polling_interval;
+
 } sai_stat_st_capability_t;
 
 typedef struct _sai_stat_st_capability_list_t
@@ -1007,3 +1016,60 @@ sai_s32_list_t tel_type_mode[2] = {-1, -1};
 sai_query_attribute_enum_values_capability(switch_id, SAI_OBJECT_TYPE_TAM_TEL_TYPE, SAI_TAM_TEL_TYPE_ATTR_MODE, tel_type_mode)
 
 ```
+
+#### Stats for TAM telemetry
+
+```c++
+
+/**
+ * @brief TAM telemetry counter IDs in sai_get_tam_telemetry_stats_ext() call
+ */
+typedef enum _sai_tam_telemetry_stat_t
+{
+    /** Tam telemetry stat range start */
+    SAI_TAM_TELEMETRY_STAT_START,
+
+    /**
+     * @brief Total number of telemetry records successfully ingested
+     *
+     * Indicates the cumulative count of telemetry messages received and accepted
+     * into the telemetry system.
+     * Unit: Count [uint64_t]
+     */
+    SAI_TAM_TELEMETRY_STAT_INGESTED_RECORDS = SAI_TAM_TELEMETRY_STAT_START,
+
+    /**
+     * @brief Number of telemetry records pending read or processing
+     *
+     * Represents current backlog or pending messages awaiting processing.
+     * This is a gauge-type value rather than a monotonically increasing counter.
+     * Unit: Count [uint64_t]
+     */
+    SAI_TAM_TELEMETRY_STAT_PENDING_READ_RECORDS,
+
+    /**
+     * @brief Total number of telemetry records successfully consumed
+     *
+     * Indicates the cumulative count of telemetry records that have been processed
+     * by the consumer.
+     * Unit: Count [uint64_t]
+     */
+    SAI_TAM_TELEMETRY_STAT_CONSUMED_RECORDS,
+
+    /**
+     * @brief Total number of telemetry records dropped
+     *
+     * Represents the cumulative number of telemetry messages discarded due to
+     * buffer overflow, timeout, or internal error.
+     * Unit: Count [uint64_t]
+     */
+    SAI_TAM_TELEMETRY_STAT_DROPPED_RECORDS,
+
+    /** Tam telemetry stat range end */
+    SAI_TAM_TELEMETRY_STAT_END,
+
+    SAI_TAM_TELEMETRY_STAT_CUSTOM_RANGE_BASE = 0x10000000,
+
+} sai_tam_telemetry_stat_t;
+
+```

inc/saitam.h

@@ -1716,6 +1716,57 @@ typedef enum _sai_tam_telemetry_attr_t
 
 } sai_tam_telemetry_attr_t;
 
+/**
+ * @brief TAM telemetry counter IDs in sai_get_tam_telemetry_stats_ext() call
+ */
+typedef enum _sai_tam_telemetry_stat_t
+{
+    /** Tam telemetry stat range start */
+    SAI_TAM_TELEMETRY_STAT_START,
+
+    /**
+     * @brief Total number of telemetry records successfully ingested
+     *
+     * Indicates the cumulative count of telemetry messages received and accepted
+     * into the telemetry system.
+     * Unit: Count [uint64_t]
+     */
+    SAI_TAM_TELEMETRY_STAT_INGESTED_RECORDS = SAI_TAM_TELEMETRY_STAT_START,
+
+    /**
+     * @brief Number of telemetry records pending read or processing
+     *
+     * Represents current backlog or pending messages awaiting processing.
+     * This is a gauge-type value rather than a monotonically increasing counter.
+     * Unit: Count [uint64_t]
+     */
+    SAI_TAM_TELEMETRY_STAT_PENDING_READ_RECORDS,
+
+    /**
+     * @brief Total number of telemetry records successfully consumed
+     *
+     * Indicates the cumulative count of telemetry records that have been processed
+     * by the consumer.
+     * Unit: Count [uint64_t]
+     */
+    SAI_TAM_TELEMETRY_STAT_CONSUMED_RECORDS,
+
+    /**
+     * @brief Total number of telemetry records dropped
+     *
+     * Represents the cumulative number of telemetry messages discarded due to
+     * buffer overflow, timeout, or internal error.
+     * Unit: Count [uint64_t]
+     */
+    SAI_TAM_TELEMETRY_STAT_DROPPED_RECORDS,
+
+    /** Tam telemetry stat range end */
+    SAI_TAM_TELEMETRY_STAT_END,
+
+    SAI_TAM_TELEMETRY_STAT_CUSTOM_RANGE_BASE = 0x10000000,
+
+} sai_tam_telemetry_stat_t;
+
 /**
  * @brief Create and return a telemetry object
  *
@@ -2593,6 +2644,54 @@ sai_status_t sai_tam_telemetry_get_data(
         _Inout_ sai_size_t *buffer_size,
         _Out_ void *buffer);
 
+/**
+ * @brief Get TAM telemetry statistics counters. Deprecated for backward compatibility.
+ *
+ * @param[in] tam_telemetry_id TAM telemetry id
+ * @param[in] number_of_counters Number of counters in the array
+ * @param[in] counter_ids Specifies the array of counter ids
+ * @param[out] counters Array of resulting counter values.
+ *
+ * @return #SAI_STATUS_SUCCESS on success, failure status code on error
+ */
+typedef sai_status_t (*sai_get_tam_telemetry_stats_fn)(
+        _In_ sai_object_id_t tam_telemetry_id,
+        _In_ uint32_t number_of_counters,
+        _In_ const sai_stat_id_t *counter_ids,
+        _Out_ uint64_t *counters);
+
+/**
+ * @brief Get TAM telemetry statistics counters extended.
+ *
+ * @param[in] tam_telemetry_id TAM telemetry id
+ * @param[in] number_of_counters Number of counters in the array
+ * @param[in] counter_ids Specifies the array of counter ids
+ * @param[in] mode Statistics mode
+ * @param[out] counters Array of resulting counter values.
+ *
+ * @return #SAI_STATUS_SUCCESS on success, failure status code on error
+ */
+typedef sai_status_t (*sai_get_tam_telemetry_stats_ext_fn)(
+        _In_ sai_object_id_t tam_telemetry_id,
+        _In_ uint32_t number_of_counters,
+        _In_ const sai_stat_id_t *counter_ids,
+        _In_ sai_stats_mode_t mode,
+        _Out_ uint64_t *counters);
+
+/**
+ * @brief Clear tam_telemetry statistics counters.
+ *
+ * @param[in] tam_telemetry_id TAM telemetry id
+ * @param[in] number_of_counters Number of counters in the array
+ * @param[in] counter_ids Specifies the array of counter ids
+ *
+ * @return #SAI_STATUS_SUCCESS on success, failure status code on error
+ */
+typedef sai_status_t (*sai_clear_tam_telemetry_stats_fn)(
+        _In_ sai_object_id_t tam_telemetry_id,
+        _In_ uint32_t number_of_counters,
+        _In_ const sai_stat_id_t *counter_ids);
+
 /**
  * @brief SAI TAM API set
  */
@@ -2662,6 +2761,10 @@ typedef struct _sai_tam_api_t
     sai_get_tam_counter_subscription_attribute_fn  get_tam_counter_subscription_attribute;
     sai_bulk_object_create_fn                      create_tam_counter_subscriptions;
     sai_bulk_object_remove_fn                      remove_tam_counter_subscriptions;
+
+    sai_get_tam_telemetry_stats_fn                 get_tam_telemetry_stats;
+    sai_get_tam_telemetry_stats_ext_fn             get_tam_telemetry_stats_ext;
+    sai_clear_tam_telemetry_stats_fn               clear_tam_telemetry_stats;
 } sai_tam_api_t;
 
 /**

inc/saitypes.h

@@ -1992,6 +1992,12 @@ typedef struct _sai_stat_st_capability_t
      */
     uint64_t minimal_polling_interval;
 
+    /**
+     * @brief Maximal polling interval in nanoseconds
+     *
+     * If polling interval is more than this value, it will be unacceptable.
+     */
+    uint64_t maximal_polling_interval;
 } sai_stat_st_capability_t;
 
 typedef struct _sai_stat_st_capability_list_t

meta/structs.pl

@@ -164,18 +164,27 @@ sub BuildCommitHistory
         # of union may not increase by adding members, and actual union size
         # check is performed by sai sanity check
 
+        # Structs that are allowed to append new members at the end (ABI extension).
+        # api_t structs are always allowed. Add other structs here as needed.
+        my @extensible_structs = (
+            "sai_switch_health_data_t",
+            "sai_port_oper_status_notification_t",
+            "sai_stat_st_capability_t",
+        );
+
+        my %extensible = map { $_ => 1 } @extensible_structs;
+
         if ($currCount != $histCount and not $structTypeName =~ /^sai_\w+_api_t$/
-                and $structTypeName ne "sai_switch_health_data_t"
-                and $structTypeName ne "sai_port_oper_status_notification_t")
+                and not $extensible{$structTypeName})
         {
             LogError "FATAL: struct $structTypeName member count differs, was $histCount but is $currCount on commit $commit" if $type eq "struct";
         }
 
         if ($histCount > $currCount)
         {
-            if ($structTypeName eq "sai_port_oper_status_notification_t")
+            if ($extensible{$structTypeName})
             {
-                # we allow this to change back backward compatibility
+                # we allow extensible structs to change for backward compatibility
             }
             else
             {

meta/test.pm

@@ -646,7 +646,14 @@ sub CreateStructUnionSizeCheckTest
             $STRUCTS{$name} = $name;
 
             next if $name =~ /^sai_\w+_api_t$/; # skip api structs
-            next if $name eq "sai_switch_health_data_t";
+
+            # Skip extensible structs that are allowed to grow (see also structs.pl)
+            my %extensible_structs = map { $_ => 1 } (
+                "sai_switch_health_data_t",
+                "sai_port_oper_status_notification_t",
+                "sai_stat_st_capability_t",
+            );
+            next if $extensible_structs{$name};
 
             my $upname = uc($name);