mirror of
https://github.com/rcourtman/Pulse.git
synced 2026-05-22 03:02:35 +00:00
bb7ca93c18
Implements comprehensive mdadm RAID array monitoring for Linux hosts via pulse-host-agent. Arrays are automatically detected and monitored with real-time status updates, rebuild progress tracking, and automatic alerting for degraded or failed arrays. Key changes: **Backend:** - Add mdadm package for parsing mdadm --detail output - Extend host agent report structure with RAID array data - Integrate mdadm collection into host agent (Linux-only, best-effort) - Add RAID array processing in monitoring system - Implement automatic alerting: - Critical alerts for degraded arrays or arrays with failed devices - Warning alerts for rebuilding/resyncing arrays with progress tracking - Auto-clear alerts when arrays return to healthy state **Frontend:** - Add TypeScript types for RAID arrays and devices - Display RAID arrays in host details drawer with: - Array status (clean/degraded/recovering) with color-coded indicators - Device counts (active/total/failed/spare) - Rebuild progress percentage and speed when applicable - Green for healthy, amber for rebuilding, red for degraded **Documentation:** - Document mdadm monitoring feature in HOST_AGENT.md - Explain requirements (Linux, mdadm installed, root access) - Clarify scope (software RAID only, hardware RAID not supported) **Testing:** - Add comprehensive tests for mdadm output parsing - Test parsing of healthy, degraded, and rebuilding arrays - Verify proper extraction of device states and rebuild progress All builds pass successfully. RAID monitoring is automatic and best-effort - if mdadm is not installed or no arrays exist, host agent continues reporting other metrics normally. Related to #676
111 lines
4.8 KiB
Go
111 lines
4.8 KiB
Go
package host
|
|
|
|
import "time"
|
|
|
|
// Report represents the payload sent by the pulse-host-agent.
|
|
type Report struct {
|
|
Agent AgentInfo `json:"agent"`
|
|
Host HostInfo `json:"host"`
|
|
Metrics Metrics `json:"metrics"`
|
|
Disks []Disk `json:"disks,omitempty"`
|
|
Network []NetworkInterface `json:"network,omitempty"`
|
|
Sensors Sensors `json:"sensors,omitempty"`
|
|
RAID []RAIDArray `json:"raid,omitempty"`
|
|
Tags []string `json:"tags,omitempty"`
|
|
Timestamp time.Time `json:"timestamp"`
|
|
SequenceID string `json:"sequenceId,omitempty"`
|
|
}
|
|
|
|
// AgentInfo describes the reporting agent.
|
|
type AgentInfo struct {
|
|
ID string `json:"id"`
|
|
Version string `json:"version,omitempty"`
|
|
IntervalSeconds int `json:"intervalSeconds,omitempty"`
|
|
Hostname string `json:"hostname,omitempty"`
|
|
}
|
|
|
|
// HostInfo contains platform and identification details about the monitored host.
|
|
type HostInfo struct {
|
|
ID string `json:"id,omitempty"`
|
|
Hostname string `json:"hostname"`
|
|
DisplayName string `json:"displayName,omitempty"`
|
|
MachineID string `json:"machineId,omitempty"`
|
|
Platform string `json:"platform,omitempty"`
|
|
OSName string `json:"osName,omitempty"`
|
|
OSVersion string `json:"osVersion,omitempty"`
|
|
KernelVersion string `json:"kernelVersion,omitempty"`
|
|
Architecture string `json:"architecture,omitempty"`
|
|
CPUModel string `json:"cpuModel,omitempty"`
|
|
CPUCount int `json:"cpuCount,omitempty"`
|
|
UptimeSeconds int64 `json:"uptimeSeconds,omitempty"`
|
|
LoadAverage []float64 `json:"loadAverage,omitempty"`
|
|
}
|
|
|
|
// Metrics encapsulates primary resource metrics for a host.
|
|
type Metrics struct {
|
|
CPUUsagePercent float64 `json:"cpuUsagePercent,omitempty"`
|
|
Memory MemoryMetric `json:"memory,omitempty"`
|
|
}
|
|
|
|
// MemoryMetric captures memory usage statistics in bytes.
|
|
type MemoryMetric struct {
|
|
TotalBytes int64 `json:"totalBytes,omitempty"`
|
|
UsedBytes int64 `json:"usedBytes,omitempty"`
|
|
FreeBytes int64 `json:"freeBytes,omitempty"`
|
|
Usage float64 `json:"usage,omitempty"`
|
|
SwapTotal int64 `json:"swapTotalBytes,omitempty"`
|
|
SwapUsed int64 `json:"swapUsedBytes,omitempty"`
|
|
}
|
|
|
|
// Disk represents disk utilisation metrics.
|
|
type Disk struct {
|
|
Device string `json:"device,omitempty"`
|
|
Mountpoint string `json:"mountpoint,omitempty"`
|
|
Filesystem string `json:"filesystem,omitempty"`
|
|
Type string `json:"type,omitempty"`
|
|
TotalBytes int64 `json:"totalBytes,omitempty"`
|
|
UsedBytes int64 `json:"usedBytes,omitempty"`
|
|
FreeBytes int64 `json:"freeBytes,omitempty"`
|
|
Usage float64 `json:"usage,omitempty"`
|
|
}
|
|
|
|
// NetworkInterface summarises network adapter statistics.
|
|
type NetworkInterface struct {
|
|
Name string `json:"name"`
|
|
MAC string `json:"mac,omitempty"`
|
|
Addresses []string `json:"addresses,omitempty"`
|
|
RXBytes uint64 `json:"rxBytes,omitempty"`
|
|
TXBytes uint64 `json:"txBytes,omitempty"`
|
|
SpeedMbps *int64 `json:"speedMbps,omitempty"`
|
|
}
|
|
|
|
// Sensors captures optional sensor readings reported by the agent.
|
|
type Sensors struct {
|
|
TemperatureCelsius map[string]float64 `json:"temperatureCelsius,omitempty"`
|
|
FanRPM map[string]float64 `json:"fanRpm,omitempty"`
|
|
Additional map[string]float64 `json:"additional,omitempty"`
|
|
}
|
|
|
|
// RAIDArray represents an mdadm RAID array.
|
|
type RAIDArray struct {
|
|
Device string `json:"device"` // e.g., /dev/md0
|
|
Name string `json:"name,omitempty"` // Array name if set
|
|
Level string `json:"level"` // RAID level: raid0, raid1, raid5, raid6, raid10
|
|
State string `json:"state"` // clean, active, degraded, recovering, resyncing, etc.
|
|
TotalDevices int `json:"totalDevices"` // Total number of devices in array
|
|
ActiveDevices int `json:"activeDevices"` // Number of active devices
|
|
WorkingDevices int `json:"workingDevices"` // Number of working devices
|
|
FailedDevices int `json:"failedDevices"` // Number of failed devices
|
|
SpareDevices int `json:"spareDevices"` // Number of spare devices
|
|
UUID string `json:"uuid,omitempty"` // Array UUID
|
|
Devices []RAIDDevice `json:"devices"` // Individual devices in array
|
|
RebuildPercent float64 `json:"rebuildPercent"` // Rebuild/resync progress (0-100)
|
|
RebuildSpeed string `json:"rebuildSpeed,omitempty"` // Rebuild speed (e.g., "50000K/sec")
|
|
}
|
|
|
|
// RAIDDevice represents a single device in a RAID array.
|
|
type RAIDDevice struct {
|
|
Device string `json:"device"` // e.g., /dev/sda1
|
|
State string `json:"state"` // active, spare, faulty, removed
|
|
Slot int `json:"slot"` // Position in array (-1 if not applicable)
|
|
}
|