Refactor telemetry initialization for non-production environments (#789)

* add dep `scopeguard`

* improve for tracing

* fix

* fix

* improve code for import

* add logger trace id

* fix

* fix

* fix

* fix

* fix

crates/ahm/src/error.rs

@@ -14,6 +14,10 @@
 
 use thiserror::Error;
 
+/// Custom error type for AHM operations
+/// This enum defines various error variants that can occur during
+/// the execution of AHM-related tasks, such as I/O errors, storage errors,
+/// configuration errors, and specific errors related to healing operations.
 #[derive(Debug, Error)]
 pub enum Error {
     #[error("I/O error: {0}")]
@@ -85,9 +89,13 @@ pub enum Error {
     ProgressTrackingFailed { message: String },
 }
 
+/// A specialized Result type for AHM operations
+///This type is a convenient alias for results returned by functions in the AHM crate,
+/// using the custom Error type defined above.
 pub type Result<T, E = Error> = std::result::Result<T, E>;
 
 impl Error {
+    /// Create an Other error from any error type
     pub fn other<E>(error: E) -> Self
     where
         E: Into<Box<dyn std::error::Error + Send + Sync>>,

crates/ahm/src/heal/channel.rs

@@ -12,18 +12,17 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::Result;
+use crate::Result;
 use crate::heal::{
     manager::HealManager,
     task::{HealOptions, HealPriority, HealRequest, HealType},
 };
-
 use rustfs_common::heal_channel::{
     HealChannelCommand, HealChannelPriority, HealChannelReceiver, HealChannelRequest, HealChannelResponse, HealScanMode,
 };
 use std::sync::Arc;
 use tokio::sync::mpsc;
-use tracing::{error, info};
+use tracing::{debug, error, info};
 
 /// Heal channel processor
 pub struct HealChannelProcessor {
@@ -60,7 +59,7 @@ impl HealChannelProcessor {
                             }
                         }
                         None => {
-                            info!("Heal channel receiver closed, stopping processor");
+                            debug!("Heal channel receiver closed, stopping processor");
                             break;
                         }
                     }

crates/ahm/src/heal/erasure_healer.rs

@@ -12,12 +12,12 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
 use crate::heal::{
     progress::HealProgress,
     resume::{CheckpointManager, ResumeManager, ResumeUtils},
     storage::HealStorageAPI,
 };
+use crate::{Error, Result};
 use futures::future::join_all;
 use rustfs_common::heal_channel::{HealOpts, HealScanMode};
 use rustfs_ecstore::disk::DiskStore;
@@ -182,7 +182,7 @@ impl ErasureSetHealer {
 
             // check cancel status
             if self.cancel_token.is_cancelled() {
-                info!("Heal task cancelled");
+                warn!("Heal task cancelled");
                 return Err(Error::TaskCancelled);
             }
 
@@ -222,7 +222,7 @@ impl ErasureSetHealer {
         resume_manager: &ResumeManager,
         checkpoint_manager: &CheckpointManager,
     ) -> Result<()> {
-        info!("Starting heal for bucket: {} from object index {}", bucket, current_object_index);
+        info!(target: "rustfs:ahm:heal_bucket_with_resume" ,"Starting heal for bucket: {} from object index {}", bucket, current_object_index);
 
         // 1. get bucket info
         let _bucket_info = match self.storage.get_bucket_info(bucket).await? {
@@ -260,7 +260,7 @@ impl ErasureSetHealer {
 
             if !object_exists {
                 info!(
-                    "Object {}/{} no longer exists, skipping heal (likely deleted intentionally)",
+                    target: "rustfs:ahm:heal_bucket_with_resume" ,"Object {}/{} no longer exists, skipping heal (likely deleted intentionally)",
                     bucket, object
                 );
                 checkpoint_manager.add_processed_object(object.clone()).await?;

crates/ahm/src/heal/manager.rs

@@ -12,12 +12,12 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
 use crate::heal::{
     progress::{HealProgress, HealStatistics},
     storage::HealStorageAPI,
     task::{HealOptions, HealPriority, HealRequest, HealTask, HealTaskStatus, HealType},
 };
+use crate::{Error, Result};
 use rustfs_ecstore::disk::DiskAPI;
 use rustfs_ecstore::disk::error::DiskError;
 use rustfs_ecstore::global::GLOBAL_LOCAL_DISK_MAP;

crates/ahm/src/heal/resume.rs

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
+use crate::{Error, Result};
 use rustfs_ecstore::disk::{BUCKET_META_PREFIX, DiskAPI, DiskStore, RUSTFS_META_BUCKET};
 use serde::{Deserialize, Serialize};
 use std::path::Path;

crates/ahm/src/heal/storage.rs

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
+use crate::{Error, Result};
 use async_trait::async_trait;
 use rustfs_common::heal_channel::{HealOpts, HealScanMode};
 use rustfs_ecstore::{

crates/ahm/src/heal/task.rs

@@ -12,9 +12,9 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
 use crate::heal::ErasureSetHealer;
 use crate::heal::{progress::HealProgress, storage::HealStorageAPI};
+use crate::{Error, Result};
 use rustfs_common::heal_channel::{HealOpts, HealScanMode};
 use serde::{Deserialize, Serialize};
 use std::sync::Arc;

crates/ahm/src/lib.rs

@@ -12,17 +12,16 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use std::sync::{Arc, OnceLock};
-use tokio_util::sync::CancellationToken;
-use tracing::{error, info};
-
-pub mod error;
+mod error;
 pub mod heal;
 pub mod scanner;
 
 pub use error::{Error, Result};
 pub use heal::{HealManager, HealOptions, HealPriority, HealRequest, HealType, channel::HealChannelProcessor};
 pub use scanner::Scanner;
+use std::sync::{Arc, OnceLock};
+use tokio_util::sync::CancellationToken;
+use tracing::{error, info};
 
 // Global cancellation token for AHM services (scanner and other background tasks)
 static GLOBAL_AHM_SERVICES_CANCEL_TOKEN: OnceLock<CancellationToken> = OnceLock::new();

crates/ahm/src/scanner/checkpoint.rs

@@ -12,18 +12,16 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use crate::scanner::node_scanner::ScanProgress;
+use crate::{Error, Result};
+use serde::{Deserialize, Serialize};
 use std::{
     path::{Path, PathBuf},
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tokio::sync::RwLock;
 use tracing::{debug, error, info, warn};
 
-use super::node_scanner::ScanProgress;
-use crate::{Error, error::Result};
-
 #[derive(Debug, Serialize, Deserialize, Clone)]
 pub struct CheckpointData {
     pub version: u32,

crates/ahm/src/scanner/data_scanner.rs

@@ -12,46 +12,39 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+// IO throttling component is integrated into NodeScanner
+use crate::{
+    Error, HealRequest, Result, get_ahm_services_cancel_token,
+    heal::HealManager,
+    scanner::{
+        BucketMetrics, DecentralizedStatsAggregator, DecentralizedStatsAggregatorConfig, DiskMetrics, MetricsCollector,
+        NodeScanner, NodeScannerConfig, ScannerMetrics,
+        lifecycle::ScannerItem,
+        local_scan::{self, LocalObjectRecord, LocalScanOutcome},
+    },
+};
+use rustfs_common::data_usage::{DataUsageInfo, SizeSummary};
+use rustfs_common::metrics::{Metric, Metrics, global_metrics};
+use rustfs_ecstore::{
+    self as ecstore, StorageAPI,
+    bucket::versioning::VersioningApi,
+    bucket::versioning_sys::BucketVersioningSys,
+    data_usage::{aggregate_local_snapshots, store_data_usage_in_backend},
+    disk::{Disk, DiskAPI, DiskStore, RUSTFS_META_BUCKET, WalkDirOptions},
+    set_disk::SetDisks,
+    store_api::ObjectInfo,
+};
+use rustfs_filemeta::{MetacacheReader, VersionType};
+use s3s::dto::{BucketVersioningStatus, VersioningConfiguration};
 use std::{
     collections::HashMap,
     sync::Arc,
     time::{Duration, SystemTime},
 };
 use time::OffsetDateTime;
-
-use ecstore::{
-    disk::{Disk, DiskAPI, DiskStore, WalkDirOptions},
-    set_disk::SetDisks,
-};
-use rustfs_ecstore::store_api::ObjectInfo;
-use rustfs_ecstore::{
-    self as ecstore, StorageAPI,
-    data_usage::{aggregate_local_snapshots, store_data_usage_in_backend},
-};
-use rustfs_filemeta::{MetacacheReader, VersionType};
-use s3s::dto::{BucketVersioningStatus, VersioningConfiguration};
 use tokio::sync::{Mutex, RwLock};
 use tokio_util::sync::CancellationToken;
 use tracing::{debug, error, info, warn};
-
-use super::metrics::{BucketMetrics, DiskMetrics, MetricsCollector, ScannerMetrics};
-use super::node_scanner::{NodeScanner, NodeScannerConfig};
-use super::stats_aggregator::{DecentralizedStatsAggregator, DecentralizedStatsAggregatorConfig};
-// IO throttling component is integrated into NodeScanner
-use crate::heal::HealManager;
-use crate::scanner::lifecycle::ScannerItem;
-use crate::scanner::local_scan::{self, LocalObjectRecord, LocalScanOutcome};
-use crate::{
-    HealRequest,
-    error::{Error, Result},
-    get_ahm_services_cancel_token,
-};
-
-use rustfs_common::data_usage::{DataUsageInfo, SizeSummary};
-use rustfs_common::metrics::{Metric, Metrics, globalMetrics};
-use rustfs_ecstore::bucket::versioning::VersioningApi;
-use rustfs_ecstore::bucket::versioning_sys::BucketVersioningSys;
-use rustfs_ecstore::disk::RUSTFS_META_BUCKET;
 use uuid;
 
 /// Custom scan mode enum for AHM scanner
@@ -772,7 +765,7 @@ impl Scanner {
 
     /// Get global metrics from common crate
     pub async fn get_global_metrics(&self) -> rustfs_madmin::metrics::ScannerMetrics {
-        (*globalMetrics).report().await
+        global_metrics().report().await
     }
 
     /// Perform a single scan cycle using optimized node scanner
@@ -802,7 +795,7 @@ impl Scanner {
             cycle_completed: vec![chrono::Utc::now()],
             started: chrono::Utc::now(),
         };
-        (*globalMetrics).set_cycle(Some(cycle_info)).await;
+        global_metrics().set_cycle(Some(cycle_info)).await;
 
         self.metrics.set_current_cycle(self.state.read().await.current_cycle);
         self.metrics.increment_total_cycles();

crates/ahm/src/scanner/histogram.rs

@@ -12,13 +12,12 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use serde::{Deserialize, Serialize};
 use std::{
     collections::HashMap,
     sync::atomic::{AtomicU64, Ordering},
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tracing::info;
 
 /// Scanner metrics

crates/ahm/src/scanner/io_monitor.rs

@@ -12,6 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use serde::{Deserialize, Serialize};
 use std::{
     collections::VecDeque,
     sync::{
@@ -20,8 +21,6 @@ use std::{
     },
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tokio::sync::RwLock;
 use tokio_util::sync::CancellationToken;
 use tracing::{debug, error, info, warn};

crates/ahm/src/scanner/io_throttler.rs

@@ -12,6 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use crate::scanner::LoadLevel;
 use std::{
     sync::{
         Arc,
@@ -19,12 +20,9 @@ use std::{
     },
     time::{Duration, SystemTime},
 };
-
 use tokio::sync::RwLock;
 use tracing::{debug, info, warn};
 
-use super::node_scanner::LoadLevel;
-
 /// IO throttler config
 #[derive(Debug, Clone)]
 pub struct IOThrottlerConfig {

crates/ahm/src/scanner/lifecycle.rs

@@ -12,25 +12,28 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use std::sync::Arc;
-use std::sync::atomic::{AtomicU64, Ordering};
-
-use crate::error::Result;
+use crate::Result;
 use rustfs_common::data_usage::SizeSummary;
 use rustfs_common::metrics::IlmAction;
-use rustfs_ecstore::bucket::lifecycle::{
-    bucket_lifecycle_audit::LcEventSrc,
-    bucket_lifecycle_ops::{GLOBAL_ExpiryState, apply_lifecycle_action, eval_action_from_lifecycle},
-    lifecycle,
-    lifecycle::Lifecycle,
+use rustfs_ecstore::bucket::{
+    lifecycle::{
+        bucket_lifecycle_audit::LcEventSrc,
+        bucket_lifecycle_ops::{GLOBAL_ExpiryState, apply_lifecycle_action, eval_action_from_lifecycle},
+        lifecycle,
+        lifecycle::Lifecycle,
+    },
+    metadata_sys::get_object_lock_config,
+    object_lock::objectlock_sys::{BucketObjectLockSys, enforce_retention_for_deletion},
+    versioning::VersioningApi,
+    versioning_sys::BucketVersioningSys,
 };
-use rustfs_ecstore::bucket::metadata_sys::get_object_lock_config;
-use rustfs_ecstore::bucket::object_lock::objectlock_sys::{BucketObjectLockSys, enforce_retention_for_deletion};
-use rustfs_ecstore::bucket::versioning::VersioningApi;
-use rustfs_ecstore::bucket::versioning_sys::BucketVersioningSys;
 use rustfs_ecstore::store_api::{ObjectInfo, ObjectToDelete};
 use rustfs_filemeta::FileInfo;
 use s3s::dto::{BucketLifecycleConfiguration as LifecycleConfig, VersioningConfiguration};
+use std::sync::{
+    Arc,
+    atomic::{AtomicU64, Ordering},
+};
 use time::OffsetDateTime;
 use tracing::info;
 

crates/ahm/src/scanner/local_stats.rs

@@ -12,22 +12,19 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use crate::scanner::node_scanner::{BucketStats, DiskStats, LocalScanStats};
+use crate::{Error, Result};
+use rustfs_common::data_usage::DataUsageInfo;
+use serde::{Deserialize, Serialize};
 use std::{
     path::{Path, PathBuf},
     sync::Arc,
     sync::atomic::{AtomicU64, Ordering},
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tokio::sync::RwLock;
 use tracing::{debug, error, info, warn};
 
-use rustfs_common::data_usage::DataUsageInfo;
-
-use super::node_scanner::{BucketStats, DiskStats, LocalScanStats};
-use crate::{Error, error::Result};
-
 /// local stats manager
 pub struct LocalStatsManager {
     /// node id

crates/ahm/src/scanner/metrics.rs

@@ -12,13 +12,12 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use serde::{Deserialize, Serialize};
 use std::{
     collections::HashMap,
     sync::atomic::{AtomicU64, Ordering},
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tracing::info;
 
 /// Scanner metrics

crates/ahm/src/scanner/mod.rs

@@ -27,8 +27,10 @@ pub mod stats_aggregator;
 pub use checkpoint::{CheckpointData, CheckpointInfo, CheckpointManager};
 pub use data_scanner::{ScanMode, Scanner, ScannerConfig, ScannerState};
 pub use io_monitor::{AdvancedIOMonitor, IOMetrics, IOMonitorConfig};
-pub use io_throttler::{AdvancedIOThrottler, IOThrottlerConfig, ResourceAllocation, ThrottleDecision};
+pub use io_throttler::{AdvancedIOThrottler, IOThrottlerConfig, MetricsSnapshot, ResourceAllocation, ThrottleDecision};
 pub use local_stats::{BatchScanResult, LocalStatsManager, ScanResultEntry, StatsSummary};
-pub use metrics::ScannerMetrics;
+pub use metrics::{BucketMetrics, DiskMetrics, MetricsCollector, ScannerMetrics};
 pub use node_scanner::{IOMonitor, IOThrottler, LoadLevel, LocalScanStats, NodeScanner, NodeScannerConfig};
-pub use stats_aggregator::{AggregatedStats, DecentralizedStatsAggregator, NodeClient, NodeInfo};
+pub use stats_aggregator::{
+    AggregatedStats, DecentralizedStatsAggregator, DecentralizedStatsAggregatorConfig, NodeClient, NodeInfo,
+};

crates/ahm/src/scanner/node_scanner.rs

@@ -12,6 +12,15 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use crate::Result;
+use crate::scanner::{
+    AdvancedIOMonitor, AdvancedIOThrottler, BatchScanResult, CheckpointManager, IOMonitorConfig, IOThrottlerConfig,
+    LocalStatsManager, MetricsSnapshot, ScanResultEntry,
+};
+use rustfs_common::data_usage::DataUsageInfo;
+use rustfs_ecstore::StorageAPI;
+use rustfs_ecstore::disk::{DiskAPI, DiskStore};
+use serde::{Deserialize, Serialize};
 use std::{
     collections::{HashMap, HashSet},
     path::{Path, PathBuf},
@@ -21,22 +30,10 @@ use std::{
     },
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tokio::sync::RwLock;
 use tokio_util::sync::CancellationToken;
 use tracing::{debug, error, info, warn};
 
-use rustfs_common::data_usage::DataUsageInfo;
-use rustfs_ecstore::StorageAPI;
-use rustfs_ecstore::disk::{DiskAPI, DiskStore}; // Add this import
-
-use super::checkpoint::CheckpointManager;
-use super::io_monitor::{AdvancedIOMonitor, IOMonitorConfig};
-use super::io_throttler::{AdvancedIOThrottler, IOThrottlerConfig, MetricsSnapshot};
-use super::local_stats::{BatchScanResult, LocalStatsManager, ScanResultEntry};
-use crate::error::Result;
-
 /// SystemTime serde
 mod system_time_serde {
     use serde::{Deserialize, Deserializer, Serialize, Serializer};

crates/ahm/src/scanner/stats_aggregator.rs

@@ -12,24 +12,21 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use crate::scanner::{
+    local_stats::StatsSummary,
+    node_scanner::{BucketStats, LoadLevel, ScanProgress},
+};
+use crate::{Error, Result};
+use rustfs_common::data_usage::DataUsageInfo;
+use serde::{Deserialize, Serialize};
 use std::{
     collections::HashMap,
     sync::Arc,
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tokio::sync::RwLock;
 use tracing::{debug, info, warn};
 
-use rustfs_common::data_usage::DataUsageInfo;
-
-use super::{
-    local_stats::StatsSummary,
-    node_scanner::{BucketStats, LoadLevel, ScanProgress},
-};
-use crate::{Error, error::Result};
-
 /// node client config
 #[derive(Debug, Clone)]
 pub struct NodeClientConfig {