chore: standardize count metric descriptions on "Number of"

crates/agent/src/instrumentation.rs

@@ -73,7 +73,7 @@ impl AgentMetricsState {
 pub fn create_metrics(meter: Meter) -> Arc<AgentMetricsState> {
     let http_counter = meter
         .u64_counter("http_requests")
-        .with_description("Total number of HTTP requests made.")
+        .with_description("Number of HTTP requests made.")
         .build();
     let http_req_latency_histogram: Histogram<f64> = meter
         .f64_histogram("request_latency")

crates/api-core/src/handlers/machine_scout.rs

@@ -441,7 +441,7 @@ fn record_reboot_duration_metric(
     log = warn,
     metric = counter,
     message = "Failed to wake up state handler for machine",
-    describe = "The amount of times a machine's state handler could not be woken after a \
+    describe = "Number of times a machine's state handler could not be woken after a \
                 scout-reported event"
 )]
 struct StateHandlerWakeupFailed {

crates/api-core/src/listener.rs

@@ -306,7 +306,7 @@ pub async fn start(
         .build();
     let connection_failed_counter = meter
         .u64_counter("carbide-api.tls.connection_fail")
-        .with_description("The amount of tcp connections that were failures")
+        .with_description("Number of inbound connections that failed")
         .build();
 
     let mut tls_acceptor_created = Instant::now();

crates/api-core/src/logging/service_health_metrics.rs

@@ -71,7 +71,7 @@ pub fn start_export_service_health_metrics(health_context: ServiceHealthContext)
         health_context
             .meter
             .u64_observable_gauge("carbide_db_pool_idle_conns")
-            .with_description("The amount of idle connections in the carbide database pool")
+            .with_description("Number of idle connections in the carbide database pool")
             .with_callback(move |observer| {
                 observer.observe(database_pool.num_idle() as u64, &[]);
             })
@@ -84,7 +84,7 @@ pub fn start_export_service_health_metrics(health_context: ServiceHealthContext)
             .meter
             .u64_observable_gauge("carbide_db_pool_total_conns")
             .with_description(
-                "The amount of total (active + idle) connections in the carbide database pool",
+                "Number of total (active + idle) connections in the carbide database pool",
             )
             .with_callback(move |observer| {
                 observer.observe(database_pool.size() as u64, &[]);
@@ -97,7 +97,7 @@ pub fn start_export_service_health_metrics(health_context: ServiceHealthContext)
         health_context
             .meter
             .u64_observable_gauge("carbide_resourcepool_used_count")
-            .with_description("Count of values in the pool currently allocated")
+            .with_description("Number of values in the pool currently allocated")
             .with_callback(move |observer| {
                 for (name, stats) in rp_stats.lock().unwrap().iter() {
                     observer.observe(
@@ -114,7 +114,7 @@ pub fn start_export_service_health_metrics(health_context: ServiceHealthContext)
         health_context
             .meter
             .u64_observable_gauge("carbide_resourcepool_free_count")
-            .with_description("Count of values in the pool currently available for allocation")
+            .with_description("Number of values in the pool currently available for allocation")
             .with_callback(move |observer| {
                 for (name, stats) in rp_stats.lock().unwrap().iter() {
                     let name_attr = KeyValue::new("pool", name.to_string());

crates/api-core/src/machine_update_manager/dpu_nic_firmware_metrics.rs

@@ -47,7 +47,7 @@ impl DpuNicFirmwareUpdateMetrics {
         let running_dpu_updates = self.running_dpu_updates.clone();
         meter
             .u64_observable_gauge("carbide_pending_dpu_nic_firmware_update_count")
-            .with_description("The number of machines in the system that need a firmware update.")
+            .with_description("Number of machines in the system that need a firmware update.")
             .with_callback(move |observer| {
                 observer.observe(pending_firmware_updates.load(Relaxed), &[]);
             })
@@ -56,7 +56,7 @@ impl DpuNicFirmwareUpdateMetrics {
         meter
             .u64_observable_gauge("carbide_unavailable_dpu_nic_firmware_update_count")
             .with_description(
-                "The number of machines in the system that need a firmware update but are unavailable for update.",
+                "Number of machines in the system that need a firmware update but are unavailable for update.",
             )
             .with_callback(move |observer| {
                 observer.observe(unavailable_dpu_updates.load(Relaxed), &[]);
@@ -66,7 +66,7 @@ impl DpuNicFirmwareUpdateMetrics {
         meter
             .u64_observable_gauge("carbide_running_dpu_updates_count")
             .with_description(
-                "The number of machines in the system that are running a firmware update.",
+                "Number of machines in the system that are running a firmware update.",
             )
             .with_callback(move |observer| {
                 observer.observe(running_dpu_updates.load(Relaxed), &[]);

crates/api-core/src/machine_update_manager/host_firmware.rs

@@ -258,17 +258,15 @@ impl HostFirmwareUpdateMetrics {
         let active_firmware_updates = self.active_firmware_updates.clone();
         meter
             .u64_observable_gauge("carbide_pending_host_firmware_update_count")
-            .with_description(
-                "The number of host machines in the system that need a firmware update.",
-            )
+            .with_description("Number of host machines in the system that need a firmware update.")
             .with_callback(move |observer| {
                 observer.observe(pending_firmware_updates.load(Ordering::Relaxed), &[])
             })
             .build();
         meter
             .u64_observable_gauge("carbide_active_host_firmware_update_count")
             .with_description(
-                "The number of host machines in the system currently working on updating their firmware.",
+                "Number of host machines in the system currently working on updating their firmware.",
             )
             .with_callback(move |observer|
                 observer.observe(active_firmware_updates.load(Ordering::Relaxed), &[]))

crates/api-core/src/machine_update_manager/metrics.rs

@@ -41,25 +41,23 @@ impl MachineUpdateManagerMetrics {
             self.concurrent_machine_updates_available.clone();
         meter
             .u64_observable_gauge("carbide_machines_in_maintenance_count")
-            .with_description("The total number of machines in the system that are in maintenance.")
+            .with_description("Number of machines in the system that are in maintenance.")
             .with_callback(move |observer| {
                 observer.observe(machines_in_maintenance.load(Ordering::Relaxed), &[])
             })
             .build();
         meter
             .u64_observable_gauge("carbide_machine_updates_started_count")
             .with_description(
-                "The number of machines in the system that are in the process of updating.",
+                "Number of machines in the system that are in the process of updating.",
             )
             .with_callback(move |observer| {
                 observer.observe(machine_updates_started.load(Ordering::Relaxed), &[])
             })
             .build();
         meter
             .u64_observable_gauge("carbide_concurrent_machine_updates_available")
-            .with_description(
-                "The number of machines in the system that we will update concurrently.",
-            )
+            .with_description("Number of machines in the system that we will update concurrently.")
             .with_callback(move |observer| {
                 observer.observe(
                     concurrent_machine_updates_available.load(Ordering::Relaxed),

crates/api-core/src/machine_validation/fixtures/test_metrics_collector.txt

@@ -1,16 +1,16 @@
-# HELP carbide_machine_validation_completed Count of machine validation that have completed successfully
+# HELP carbide_machine_validation_completed Number of machine validation runs that have completed successfully
 # TYPE carbide_machine_validation_completed gauge
 carbide_machine_validation_completed 10
-# HELP carbide_machine_validation_failed Count of machine validation that have failed
+# HELP carbide_machine_validation_failed Number of machine validation runs that have failed
 # TYPE carbide_machine_validation_failed gauge
 carbide_machine_validation_failed 15
-# HELP carbide_machine_validation_in_progress Count of machine validation that are in progress
+# HELP carbide_machine_validation_in_progress Number of machine validation runs that are in progress
 # TYPE carbide_machine_validation_in_progress gauge
 carbide_machine_validation_in_progress 20
 # HELP carbide_machine_validation_oldest_active_age_seconds Age in seconds of the oldest active machine validation run
 # TYPE carbide_machine_validation_oldest_active_age_seconds gauge
 carbide_machine_validation_oldest_active_age_seconds 0
-# HELP carbide_machine_validation_stale_runs_count Count of active machine validation runs considered stale
+# HELP carbide_machine_validation_stale_runs_count Number of active machine validation runs considered stale
 # TYPE carbide_machine_validation_stale_runs_count gauge
 carbide_machine_validation_stale_runs_count 0
 # HELP carbide_machine_validation_tests The details of machine validation tests

crates/api-core/src/machine_validation/metrics.rs

@@ -47,7 +47,7 @@ fn hydrate_meter(meter: Meter, shared_metrics: SharedMetricsHolder<MachineValida
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_machine_validation_completed")
-            .with_description("Count of machine validation that have completed successfully")
+            .with_description("Number of machine validation runs that have completed successfully")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     observer.observe(metrics.completed_validation as u64, attrs);
@@ -60,7 +60,7 @@ fn hydrate_meter(meter: Meter, shared_metrics: SharedMetricsHolder<MachineValida
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_machine_validation_failed")
-            .with_description("Count of machine validation that have failed")
+            .with_description("Number of machine validation runs that have failed")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     observer.observe(metrics.failed_validation as u64, attrs);
@@ -73,7 +73,7 @@ fn hydrate_meter(meter: Meter, shared_metrics: SharedMetricsHolder<MachineValida
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_machine_validation_in_progress")
-            .with_description("Count of machine validation that are in progress")
+            .with_description("Number of machine validation runs that are in progress")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     observer.observe(metrics.in_progress_validation as u64, attrs);
@@ -97,7 +97,7 @@ fn hydrate_meter(meter: Meter, shared_metrics: SharedMetricsHolder<MachineValida
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_machine_validation_stale_runs_count")
-            .with_description("Count of active machine validation runs considered stale")
+            .with_description("Number of active machine validation runs considered stale")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     observer.observe(metrics.stale_validation as u64, attrs);

crates/api-core/src/measured_boot/metrics_collector/metrics.rs

@@ -82,7 +82,7 @@ fn hydrate_meter(
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_measured_boot_profiles_total")
-            .with_description("The total number of measured boot profiles.")
+            .with_description("Number of measured boot profiles.")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     observer.observe(metrics.num_profiles as u64, attrs);
@@ -95,7 +95,7 @@ fn hydrate_meter(
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_measured_boot_bundles_total")
-            .with_description("The total number of measured boot bundles.")
+            .with_description("Number of measured boot bundles.")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     observer.observe(metrics.num_bundles as u64, attrs);
@@ -108,7 +108,7 @@ fn hydrate_meter(
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_measured_boot_machines_total")
-            .with_description("The total number of machines reporting measurements.")
+            .with_description("Number of machines reporting measurements.")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     observer.observe(metrics.num_machines as u64, attrs);
@@ -121,7 +121,7 @@ fn hydrate_meter(
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_measured_boot_machines_per_profile_total")
-            .with_description("The total number of machines per measured boot system profile.")
+            .with_description("Number of machines per measured boot system profile.")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     for (profile_id, total) in metrics.num_machines_per_profile.iter() {
@@ -143,7 +143,7 @@ fn hydrate_meter(
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_measured_boot_machines_per_bundle_total")
-            .with_description("The total number of machines per measured boot bundle.")
+            .with_description("Number of machines per measured boot bundle.")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     for (bundle_id, total) in metrics.num_machines_per_bundle.iter() {
@@ -161,9 +161,7 @@ fn hydrate_meter(
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_measured_boot_machines_per_bundle_state_total")
-            .with_description(
-                "The total number of machines per a given measured boot bundle state.",
-            )
+            .with_description("Number of machines in each measured boot bundle state.")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     for (bundle_state, total) in metrics.num_machines_per_bundle_state.iter() {
@@ -185,9 +183,7 @@ fn hydrate_meter(
         let metrics = shared_metrics.clone();
         meter
             .u64_observable_gauge("carbide_measured_boot_machines_per_machine_state_total")
-            .with_description(
-                "The total number of machines per a given measured boot machine state.",
-            )
+            .with_description("Number of machines in each measured boot machine state.")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     for (machine_state, total) in metrics.num_machines_per_machine_state.iter() {
@@ -209,9 +205,7 @@ fn hydrate_meter(
         let metrics = shared_metrics;
         meter
             .u64_observable_gauge("carbide_measured_boot_machines_per_pcr_value_total")
-            .with_description(
-                "The total number of machines with a given PCR value at a given PCR index.",
-            )
+            .with_description("Number of machines with a given PCR value at a given PCR index.")
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {
                     for (pcr_register, total) in metrics.num_machines_per_pcr_value.iter() {

crates/api-core/src/measured_boot/tests/test_data/test_metrics_collector.txt

@@ -1,38 +1,38 @@
-# HELP carbide_measured_boot_bundles_total The total number of measured boot bundles.
+# HELP carbide_measured_boot_bundles_total Number of measured boot bundles.
 # TYPE carbide_measured_boot_bundles_total gauge
 carbide_measured_boot_bundles_total 4
-# HELP carbide_measured_boot_machines_per_bundle_state_total The total number of machines per a given measured boot bundle state.
+# HELP carbide_measured_boot_machines_per_bundle_state_total Number of machines in each measured boot bundle state.
 # TYPE carbide_measured_boot_machines_per_bundle_state_total gauge
 carbide_measured_boot_machines_per_bundle_state_total{bundle_state="Active"} 1
 carbide_measured_boot_machines_per_bundle_state_total{bundle_state="Obsolete"} 1
 carbide_measured_boot_machines_per_bundle_state_total{bundle_state="Pending"} 1
 carbide_measured_boot_machines_per_bundle_state_total{bundle_state="Retired"} 3
 carbide_measured_boot_machines_per_bundle_state_total{bundle_state="Revoked"} 4
-# HELP carbide_measured_boot_machines_per_bundle_total The total number of machines per measured boot bundle.
+# HELP carbide_measured_boot_machines_per_bundle_total Number of machines per measured boot bundle.
 # TYPE carbide_measured_boot_machines_per_bundle_total gauge
 carbide_measured_boot_machines_per_bundle_total{bundle_id="33be881e-5871-4519-b7dd-84946f3b758a"} 4
 carbide_measured_boot_machines_per_bundle_total{bundle_id="3e4ec902-f834-448c-9c0d-aca7da84d5d7"} 3
 carbide_measured_boot_machines_per_bundle_total{bundle_id="53008cc3-988e-459c-a4c1-acb0ea44a884"} 2
 carbide_measured_boot_machines_per_bundle_total{bundle_id="f567ae32-690c-4108-8ee8-5116c64ff3f0"} 1
-# HELP carbide_measured_boot_machines_per_machine_state_total The total number of machines per a given measured boot machine state.
+# HELP carbide_measured_boot_machines_per_machine_state_total Number of machines in each measured boot machine state.
 # TYPE carbide_measured_boot_machines_per_machine_state_total gauge
 carbide_measured_boot_machines_per_machine_state_total{machine_state="Discovered"} 1
 carbide_measured_boot_machines_per_machine_state_total{machine_state="Measured"} 3
 carbide_measured_boot_machines_per_machine_state_total{machine_state="MeasuringFailed"} 4
 carbide_measured_boot_machines_per_machine_state_total{machine_state="PendingBundle"} 2
-# HELP carbide_measured_boot_machines_per_pcr_value_total The total number of machines with a given PCR value at a given PCR index.
+# HELP carbide_measured_boot_machines_per_pcr_value_total Number of machines with a given PCR value at a given PCR index.
 # TYPE carbide_measured_boot_machines_per_pcr_value_total gauge
 carbide_measured_boot_machines_per_pcr_value_total{pcr_index="0",pcr_value="aa"} 5
 carbide_measured_boot_machines_per_pcr_value_total{pcr_index="1",pcr_value="bb"} 5
-# HELP carbide_measured_boot_machines_per_profile_total The total number of machines per measured boot system profile.
+# HELP carbide_measured_boot_machines_per_profile_total Number of machines per measured boot system profile.
 # TYPE carbide_measured_boot_machines_per_profile_total gauge
 carbide_measured_boot_machines_per_profile_total{profile_id="254542a1-0fb2-4250-91df-b5ecfa52645e"} 2
 carbide_measured_boot_machines_per_profile_total{profile_id="4ed2dea5-c325-4317-aeb3-e9766956d9fc"} 3
 carbide_measured_boot_machines_per_profile_total{profile_id="bf13aaeb-c9e6-4e42-9b2f-5aa525c56124"} 1
 carbide_measured_boot_machines_per_profile_total{profile_id="c5c926f3-a454-497c-95ff-d21647590631"} 4
-# HELP carbide_measured_boot_machines_total The total number of machines reporting measurements.
+# HELP carbide_measured_boot_machines_total Number of machines reporting measurements.
 # TYPE carbide_measured_boot_machines_total gauge
 carbide_measured_boot_machines_total 10
-# HELP carbide_measured_boot_profiles_total The total number of measured boot profiles.
+# HELP carbide_measured_boot_profiles_total Number of measured boot profiles.
 # TYPE carbide_measured_boot_profiles_total gauge
 carbide_measured_boot_profiles_total 10