logging and diagnostic features added

internal/metrics/collector.go

@@ -0,0 +1,217 @@
+package metrics
+
+import (
+	"fmt"
+	"sync"
+	"time"
+
+	"gitea.avt.data-center.id/othman.suseno/atlas/internal/models"
+)
+
+// Collector gathers system metrics
+type Collector struct {
+	mu sync.RWMutex
+
+	// ZFS metrics
+	poolCount      int
+	datasetCount   int
+	zvolCount      int
+	snapshotCount  int
+	totalCapacity  uint64
+	totalAllocated uint64
+	totalFree      uint64
+
+	// Service metrics
+	smbSharesCount     int
+	nfsExportsCount    int
+	iscsiTargetsCount  int
+	smbServiceStatus   int // 1 = running, 0 = stopped
+	nfsServiceStatus   int
+	iscsiServiceStatus int
+
+	// Job metrics
+	jobsTotal     int
+	jobsRunning   int
+	jobsCompleted int
+	jobsFailed    int
+
+	// System metrics
+	uptimeSeconds int64
+	lastUpdate    time.Time
+}
+
+// NewCollector creates a new metrics collector
+func NewCollector() *Collector {
+	return &Collector{
+		lastUpdate: time.Now(),
+	}
+}
+
+// UpdateZFSMetrics updates ZFS-related metrics
+func (c *Collector) UpdateZFSMetrics(pools []models.Pool, datasets []models.Dataset, zvols []models.ZVOL, snapshots []models.Snapshot) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	c.poolCount = len(pools)
+	c.datasetCount = len(datasets)
+	c.zvolCount = len(zvols)
+	c.snapshotCount = len(snapshots)
+
+	c.totalCapacity = 0
+	c.totalAllocated = 0
+	c.totalFree = 0
+
+	for _, pool := range pools {
+		c.totalCapacity += pool.Size
+		c.totalAllocated += pool.Allocated
+		c.totalFree += pool.Free
+	}
+
+	c.lastUpdate = time.Now()
+}
+
+// UpdateServiceMetrics updates storage service metrics
+func (c *Collector) UpdateServiceMetrics(smbShares, nfsExports, iscsiTargets int, smbStatus, nfsStatus, iscsiStatus bool) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	c.smbSharesCount = smbShares
+	c.nfsExportsCount = nfsExports
+	c.iscsiTargetsCount = iscsiTargets
+
+	if smbStatus {
+		c.smbServiceStatus = 1
+	} else {
+		c.smbServiceStatus = 0
+	}
+
+	if nfsStatus {
+		c.nfsServiceStatus = 1
+	} else {
+		c.nfsServiceStatus = 0
+	}
+
+	if iscsiStatus {
+		c.iscsiServiceStatus = 1
+	} else {
+		c.iscsiServiceStatus = 0
+	}
+
+	c.lastUpdate = time.Now()
+}
+
+// UpdateJobMetrics updates job-related metrics
+func (c *Collector) UpdateJobMetrics(total, running, completed, failed int) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	c.jobsTotal = total
+	c.jobsRunning = running
+	c.jobsCompleted = completed
+	c.jobsFailed = failed
+
+	c.lastUpdate = time.Now()
+}
+
+// SetUptime sets the system uptime
+func (c *Collector) SetUptime(seconds int64) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	c.uptimeSeconds = seconds
+}
+
+// Collect returns metrics in Prometheus format
+func (c *Collector) Collect() string {
+	c.mu.RLock()
+	defer c.mu.RUnlock()
+
+	var output string
+
+	// Build info
+	output += "# HELP atlas_build_info Build information\n"
+	output += "# TYPE atlas_build_info gauge\n"
+	output += `atlas_build_info{version="v0.1.0-dev"} 1` + "\n\n"
+
+	// System uptime
+	output += "# HELP atlas_uptime_seconds System uptime in seconds\n"
+	output += "# TYPE atlas_uptime_seconds gauge\n"
+	output += fmt.Sprintf("atlas_uptime_seconds %d\n\n", c.uptimeSeconds)
+
+	// ZFS metrics
+	output += "# HELP atlas_zfs_pools_total Total number of ZFS pools\n"
+	output += "# TYPE atlas_zfs_pools_total gauge\n"
+	output += fmt.Sprintf("atlas_zfs_pools_total %d\n\n", c.poolCount)
+
+	output += "# HELP atlas_zfs_datasets_total Total number of ZFS datasets\n"
+	output += "# TYPE atlas_zfs_datasets_total gauge\n"
+	output += fmt.Sprintf("atlas_zfs_datasets_total %d\n\n", c.datasetCount)
+
+	output += "# HELP atlas_zfs_zvols_total Total number of ZFS ZVOLs\n"
+	output += "# TYPE atlas_zfs_zvols_total gauge\n"
+	output += fmt.Sprintf("atlas_zfs_zvols_total %d\n\n", c.zvolCount)
+
+	output += "# HELP atlas_zfs_snapshots_total Total number of ZFS snapshots\n"
+	output += "# TYPE atlas_zfs_snapshots_total gauge\n"
+	output += fmt.Sprintf("atlas_zfs_snapshots_total %d\n\n", c.snapshotCount)
+
+	output += "# HELP atlas_zfs_capacity_bytes Total ZFS pool capacity in bytes\n"
+	output += "# TYPE atlas_zfs_capacity_bytes gauge\n"
+	output += fmt.Sprintf("atlas_zfs_capacity_bytes %d\n\n", c.totalCapacity)
+
+	output += "# HELP atlas_zfs_allocated_bytes Total ZFS pool allocated space in bytes\n"
+	output += "# TYPE atlas_zfs_allocated_bytes gauge\n"
+	output += fmt.Sprintf("atlas_zfs_allocated_bytes %d\n\n", c.totalAllocated)
+
+	output += "# HELP atlas_zfs_free_bytes Total ZFS pool free space in bytes\n"
+	output += "# TYPE atlas_zfs_free_bytes gauge\n"
+	output += fmt.Sprintf("atlas_zfs_free_bytes %d\n\n", c.totalFree)
+
+	// Service metrics
+	output += "# HELP atlas_smb_shares_total Total number of SMB shares\n"
+	output += "# TYPE atlas_smb_shares_total gauge\n"
+	output += fmt.Sprintf("atlas_smb_shares_total %d\n\n", c.smbSharesCount)
+
+	output += "# HELP atlas_nfs_exports_total Total number of NFS exports\n"
+	output += "# TYPE atlas_nfs_exports_total gauge\n"
+	output += fmt.Sprintf("atlas_nfs_exports_total %d\n\n", c.nfsExportsCount)
+
+	output += "# HELP atlas_iscsi_targets_total Total number of iSCSI targets\n"
+	output += "# TYPE atlas_iscsi_targets_total gauge\n"
+	output += fmt.Sprintf("atlas_iscsi_targets_total %d\n\n", c.iscsiTargetsCount)
+
+	output += "# HELP atlas_smb_service_status SMB service status (1=running, 0=stopped)\n"
+	output += "# TYPE atlas_smb_service_status gauge\n"
+	output += fmt.Sprintf("atlas_smb_service_status %d\n\n", c.smbServiceStatus)
+
+	output += "# HELP atlas_nfs_service_status NFS service status (1=running, 0=stopped)\n"
+	output += "# TYPE atlas_nfs_service_status gauge\n"
+	output += fmt.Sprintf("atlas_nfs_service_status %d\n\n", c.nfsServiceStatus)
+
+	output += "# HELP atlas_iscsi_service_status iSCSI service status (1=running, 0=stopped)\n"
+	output += "# TYPE atlas_iscsi_service_status gauge\n"
+	output += fmt.Sprintf("atlas_iscsi_service_status %d\n\n", c.iscsiServiceStatus)
+
+	// Job metrics
+	output += "# HELP atlas_jobs_total Total number of jobs\n"
+	output += "# TYPE atlas_jobs_total gauge\n"
+	output += fmt.Sprintf("atlas_jobs_total %d\n\n", c.jobsTotal)
+
+	output += "# HELP atlas_jobs_running Number of running jobs\n"
+	output += "# TYPE atlas_jobs_running gauge\n"
+	output += fmt.Sprintf("atlas_jobs_running %d\n\n", c.jobsRunning)
+
+	output += "# HELP atlas_jobs_completed_total Total number of completed jobs\n"
+	output += "# TYPE atlas_jobs_completed_total counter\n"
+	output += fmt.Sprintf("atlas_jobs_completed_total %d\n\n", c.jobsCompleted)
+
+	output += "# HELP atlas_jobs_failed_total Total number of failed jobs\n"
+	output += "# TYPE atlas_jobs_failed_total counter\n"
+	output += fmt.Sprintf("atlas_jobs_failed_total %d\n\n", c.jobsFailed)
+
+	// API status
+	output += "# HELP atlas_up Whether the atlas-api process is up\n"
+	output += "# TYPE atlas_up gauge\n"
+	output += "atlas_up 1\n"
+
+	return output
+}