mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-18 20:18:27 +02:00
* admin: honour persisted task configs when building the maintenance policy
buildPolicyFromTaskConfigs passed a literal nil to vacuum, erasure_coding
and balance LoadConfigFromPersistence. Those functions look for their
LoadXTaskPolicy() accessor via a type assertion, which a nil interface can
never satisfy, so every call fell through to NewDefaultConfig() and the
policy came back with the compiled-in defaults - Enabled: true among them.
A task disabled on disk was therefore still scheduled, and the only trace
was a glog.V(1) "Using default ... configuration" line.
Thread the real ConfigPersistence through instead. There are two copies of
this function: the one in weed/admin/dash builds config.Policy on the
normal admin startup path and can simply take cp as its receiver, and the
one in weed/admin/maintenance is the fallback used when the config carries
no policy yet, which now receives the store from NewMaintenanceManager.
weed/admin/dash already imports weed/admin/maintenance, so the maintenance
side has to keep the duck-typed interface{} parameter that the task
loaders already use rather than importing the concrete type back.
The store is only handed over when a data directory is configured: an
unconfigured one has nothing to read, and a typed nil pointer would pass
the loaders' type assertion and then panic on first use.
Fixes #10874
* admin: restore the maintenance scan cadence after an error backoff
scanLoop shortens its ticker to the error backoff delay after a failed
scan, but it decided whether to replace the ticker by comparing the
target interval against the configured scan interval instead of against
the interval the ticker was actually running at. Once the errors stopped,
getScanInterval returned the configured interval again, the comparison
came out false, and the ticker was left at the backoff delay - so a
single transient scan failure pinned the scanner to one scan per second
for the rest of the process lifetime. That is the ~1/second cadence in
issue #10874: 658 KB/s of "Cancelled N stale pending balance tasks
before re-detection" and 193k orphaned task files over two days.
Track the interval the ticker is running at and compare against that, so
both entering the backoff and returning to the normal cadence replace the
ticker.
While in here:
- defer ticker.Stop() bound the ticker that was current when the defer
was registered, so every replacement ticker leaked on return. Wrap it
in a closure.
- running was written by Start/Stop and read by all three background
loops without synchronisation. Guard it with the existing mutex, fold
the running check in triggerScanInternal into the lock it already
takes, and make Stop a no-op when not running so a second call cannot
close the stop channel twice.
Refs #10874
* admin: make the maintenance policy actually reach the task detectors
Loading the persisted task configs into the maintenance policy only
matters if something reads that policy, and nothing did.
MaintenanceIntegration pushes the policy into every registered detector
and scheduler through interface{ SetEnabled(bool) } and
interface{ SetMaxConcurrent(int) } type assertions. Every task registered
through base.RegisterTask is backed by base.GenericDetector and
base.GenericScheduler, and neither implemented either method, so all four
assertions failed silently for every task on every startup. The policy's
enabled flag reached nothing: ScanWithTaskDetectors gates on
detector.IsEnabled(), and the queue's policy lookups for max concurrent
and repeat interval are fallbacks that only fire when the scheduler
reports zero, which the generic scheduler never does.
Add the setters, delegating to the TaskConfig.SetEnabled the interface
already declares and to TaskDefinition.MaxConcurrent, which is what
GetMaxConcurrent returns.
Applying the policy required three more fixes, because with the
assertions working the policy could now do damage as well as good:
- IsTaskEnabled reports false for a task type the policy has no entry
for, so applying it unconditionally would have disabled every task the
policy does not list. Skip task types with no policy entry: no entry
means no opinion, not disabled.
- ec_balance was exactly such a task. It is registered like the other
three but had no entry in the policy builder and no accessor on
ConfigPersistence at all, so its configuration could never be
persisted. Add SaveEcBalanceTaskPolicy/LoadEcBalanceTaskPolicy, the
task_ec_balance.pb file, the SaveTaskPolicy dispatcher case, and the
policy entry.
- InitMaintenanceManager ran before loadTaskConfigurationsFromPersistence,
which replaces each task's whole config object, so the policy was
applied and then immediately thrown away. Swap the order. Both read the
same files, so the policy is now the last writer and stays
authoritative.
MaintenanceManager.UpdateConfig also updated the queue's and the
scanner's policy but not the integration's, so a policy changed at
runtime never reached the detectors. Add MaintenanceIntegration.SetPolicy
and call it.
While building the policy, stop hand-copying each task's fields and use
the task's own ToTaskPolicy(). The hand-written version was a second
definition of every task's policy and had already lost the erasure coding
preferred tags and replica placement and the balance IO rate limit. For
the same reason, the "nothing persisted yet" branches of
LoadVacuumTaskPolicy, LoadErasureCodingTaskPolicy and
LoadBalanceTaskPolicy now derive from each task's NewDefaultConfig()
instead of a third hand-written copy. Those copies had drifted, so with a
data directory but no config file on disk the effective defaults differed
from what the task and the admin UI schema both advertise:
vacuum scan interval 24h -> 2h
balance scan interval 6h -> 30m
balance imbalance 0.1 -> 0.2
erasure coding scan interval 168h -> 1h
erasure coding fullness 0.90 -> 0.95
erasure coding min volume 1024MB -> 30MB
Finally, weed/admin/dash and weed/admin/maintenance each carried a copy
of the policy builder and they had already diverged. Export the
maintenance one as BuildPolicyFromTaskConfigs and have dash call it.
Refs #10874
* worker: warn when a config store cannot supply a task's persisted config
LoadConfigFromPersistence logged a single glog.V(1) "Using default X
configuration" for every way of not loading anything, so the bug in
issue #10874 - a store handed in that the type assertion rejects, leaving
a task running on compiled-in defaults - looked exactly like the normal
"no data directory configured" case. The reporter had to read the source
to work out why their disabled task kept running, and asked for this
specifically.
Separate the cases. A non-nil store that does not provide the accessor is
always a wiring bug and is now logged at warning level, naming the type
and the missing method. A read error or a policy that will not apply is
also a warning. No persistence configured, and a store with nothing saved
yet, stay at V(1): those are normal.
Refs #10874
* admin: stop GetTaskPolicy panicking on a maintenance policy that is nil
GetTaskPolicy dereferenced its MaintenancePolicy argument to look at
TaskPolicies, so IsTaskEnabled, GetMaxConcurrent and GetRepeatInterval
all took the admin process down when handed a nil policy. A nil policy is
not a programming error here: MaintenanceConfig.Policy is unset until
something builds one, DefaultMaintenanceConfig returns a config with no
policy at all, and UpdateConfig installs whatever config it is given.
Found by calling IsTaskEnabled with the policy from a freshly defaulted
MaintenanceConfig.
Treat a nil policy as "no entry": no task enabled, the safe concurrency
default of 1, and a repeat interval of 0 so callers fall back to their
own default instead of reading DefaultRepeatIntervalSeconds off nil.
Also add the startup test this was found with. It walks the admin
server's startup sequence over a data directory that has balance saved as
disabled and checks the state that decides whether issue #10874 happens:
the balance detector reports disabled, vacuum stays enabled, and tasks
whose config was never saved keep their compiled-in default.
Refs #10874
* admin: document the synchronisation SetPolicy would need beyond startup
ConfigureTasksFromPolicy now really writes TaskDefinition.Config and
TaskDefinition.MaxConcurrent, which the scan loop reads through
detector.IsEnabled() with nothing synchronising the two. Every caller
runs during admin server startup today, before the scan loop exists, so
there is no live race - but the next caller has to add the locking, and
the same already applies to UpdateAllConfigs replacing the whole config
object. Write it down at the seam instead of leaving it to be
rediscovered.
Refs #10874
677 lines
22 KiB
Go
677 lines
22 KiB
Go
package maintenance
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
|
|
stats_collect "github.com/seaweedfs/seaweedfs/weed/stats"
|
|
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/balance"
|
|
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/ec_balance"
|
|
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/erasure_coding"
|
|
"github.com/seaweedfs/seaweedfs/weed/worker/tasks/vacuum"
|
|
"github.com/seaweedfs/seaweedfs/weed/worker/types"
|
|
)
|
|
|
|
// BuildPolicyFromTaskConfigs loads each registered task's configuration and builds the
|
|
// MaintenancePolicy the maintenance system runs on.
|
|
//
|
|
// Every entry is produced by the task's own ToTaskPolicy(), so a policy entry always carries
|
|
// exactly what that task's config holds. Hand-copying the fields here instead made this a
|
|
// second, silently diverging definition of every task's policy: it dropped the erasure
|
|
// coding preferred tags and replica placement and the balance IO rate limit outright.
|
|
//
|
|
// Every task registered through base.RegisterTask needs an entry, because a task type the
|
|
// policy does not list has no enabled flag and no concurrency limit of its own -
|
|
// IsTaskEnabled reports false for a missing entry.
|
|
//
|
|
// configPersistence is duck-typed as interface{} because weed/admin/dash already imports this
|
|
// package, so importing *dash.ConfigPersistence back here would create an import cycle. It must be
|
|
// a value implementing the LoadXTaskPolicy() accessors the task loaders assert on; passing nil (or
|
|
// anything else) makes every task fall back to its compiled-in defaults.
|
|
func BuildPolicyFromTaskConfigs(configPersistence interface{}) *worker_pb.MaintenancePolicy {
|
|
policy := &worker_pb.MaintenancePolicy{
|
|
GlobalMaxConcurrent: 4,
|
|
DefaultRepeatIntervalSeconds: 6 * 3600, // 6 hours in seconds
|
|
DefaultCheckIntervalSeconds: 12 * 3600, // 12 hours in seconds
|
|
TaskPolicies: make(map[string]*worker_pb.TaskPolicy),
|
|
}
|
|
|
|
if vacuumConfig := vacuum.LoadConfigFromPersistence(configPersistence); vacuumConfig != nil {
|
|
policy.TaskPolicies[string(types.TaskTypeVacuum)] = vacuumConfig.ToTaskPolicy()
|
|
}
|
|
|
|
if ecConfig := erasure_coding.LoadConfigFromPersistence(configPersistence); ecConfig != nil {
|
|
policy.TaskPolicies[string(types.TaskTypeErasureCoding)] = ecConfig.ToTaskPolicy()
|
|
}
|
|
|
|
if balanceConfig := balance.LoadConfigFromPersistence(configPersistence); balanceConfig != nil {
|
|
policy.TaskPolicies[string(types.TaskTypeBalance)] = balanceConfig.ToTaskPolicy()
|
|
}
|
|
|
|
if ecBalanceConfig := ec_balance.LoadConfigFromPersistence(configPersistence); ecBalanceConfig != nil {
|
|
policy.TaskPolicies[string(types.TaskTypeECBalance)] = ecBalanceConfig.ToTaskPolicy()
|
|
}
|
|
|
|
glog.V(1).Infof("Built maintenance policy from separate task configs - %d task policies loaded", len(policy.TaskPolicies))
|
|
return policy
|
|
}
|
|
|
|
// MaintenanceManager coordinates the maintenance system
|
|
type MaintenanceManager struct {
|
|
config *MaintenanceConfig
|
|
scanner *MaintenanceScanner
|
|
queue *MaintenanceQueue
|
|
adminClient AdminClient
|
|
running bool
|
|
stopChan chan struct{}
|
|
// Error handling and backoff
|
|
errorCount int
|
|
lastError error
|
|
lastErrorTime time.Time
|
|
backoffDelay time.Duration
|
|
mutex sync.RWMutex
|
|
scanInProgress bool
|
|
}
|
|
|
|
// NewMaintenanceManager creates a new maintenance manager.
|
|
//
|
|
// configPersistence is the config store to read persisted task configs from when the policy has to
|
|
// be built here. See BuildPolicyFromTaskConfigs for why it is duck-typed; pass nil when no config
|
|
// store is available.
|
|
func NewMaintenanceManager(adminClient AdminClient, config *MaintenanceConfig, configPersistence interface{}) *MaintenanceManager {
|
|
if config == nil {
|
|
config = DefaultMaintenanceConfig()
|
|
}
|
|
|
|
// Use the policy from the config (which is populated from separate task files in LoadMaintenanceConfig)
|
|
policy := config.Policy
|
|
if policy == nil {
|
|
// Fallback: build policy from separate task configuration files if not already populated
|
|
policy = BuildPolicyFromTaskConfigs(configPersistence)
|
|
}
|
|
|
|
queue := NewMaintenanceQueue(policy)
|
|
scanner := NewMaintenanceScanner(adminClient, policy, queue)
|
|
|
|
return &MaintenanceManager{
|
|
config: config,
|
|
scanner: scanner,
|
|
queue: queue,
|
|
adminClient: adminClient,
|
|
stopChan: make(chan struct{}),
|
|
backoffDelay: time.Second, // Start with 1 second backoff
|
|
}
|
|
}
|
|
|
|
// Start begins the maintenance manager
|
|
func (mm *MaintenanceManager) Start() error {
|
|
if !mm.config.Enabled {
|
|
glog.V(1).Infof("Maintenance system is disabled")
|
|
return nil
|
|
}
|
|
|
|
// Validate configuration durations to prevent ticker panics
|
|
if err := mm.validateConfig(); err != nil {
|
|
return fmt.Errorf("invalid maintenance configuration: %w", err)
|
|
}
|
|
|
|
mm.mutex.Lock()
|
|
mm.running = true
|
|
mm.mutex.Unlock()
|
|
|
|
// Start background processes
|
|
go mm.scanLoop()
|
|
go mm.cleanupLoop()
|
|
go mm.topologyStatusLoop() // Periodic diagnostic logging
|
|
|
|
glog.Infof("Maintenance manager started with scan interval %ds", mm.config.ScanIntervalSeconds)
|
|
return nil
|
|
}
|
|
|
|
// validateConfig validates the maintenance configuration durations
|
|
func (mm *MaintenanceManager) validateConfig() error {
|
|
if mm.config.ScanIntervalSeconds <= 0 {
|
|
glog.Warningf("Invalid scan interval %ds, using default 30m", mm.config.ScanIntervalSeconds)
|
|
mm.config.ScanIntervalSeconds = 30 * 60 // 30 minutes in seconds
|
|
}
|
|
|
|
if mm.config.CleanupIntervalSeconds <= 0 {
|
|
glog.Warningf("Invalid cleanup interval %ds, using default 24h", mm.config.CleanupIntervalSeconds)
|
|
mm.config.CleanupIntervalSeconds = 24 * 60 * 60 // 24 hours in seconds
|
|
}
|
|
|
|
if mm.config.WorkerTimeoutSeconds <= 0 {
|
|
glog.Warningf("Invalid worker timeout %ds, using default 5m", mm.config.WorkerTimeoutSeconds)
|
|
mm.config.WorkerTimeoutSeconds = 5 * 60 // 5 minutes in seconds
|
|
}
|
|
|
|
if mm.config.TaskTimeoutSeconds <= 0 {
|
|
glog.Warningf("Invalid task timeout %ds, using default 2h", mm.config.TaskTimeoutSeconds)
|
|
mm.config.TaskTimeoutSeconds = 2 * 60 * 60 // 2 hours in seconds
|
|
}
|
|
|
|
if mm.config.RetryDelaySeconds <= 0 {
|
|
glog.Warningf("Invalid retry delay %ds, using default 15m", mm.config.RetryDelaySeconds)
|
|
mm.config.RetryDelaySeconds = 15 * 60 // 15 minutes in seconds
|
|
}
|
|
|
|
if mm.config.TaskRetentionSeconds <= 0 {
|
|
glog.Warningf("Invalid task retention %ds, using default 168h", mm.config.TaskRetentionSeconds)
|
|
mm.config.TaskRetentionSeconds = 7 * 24 * 60 * 60 // 7 days in seconds
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
// IsRunning returns whether the maintenance manager is currently running.
|
|
// running is guarded by mm.mutex because the background loops read it on every
|
|
// iteration while Start and Stop are called from the admin server's goroutines.
|
|
func (mm *MaintenanceManager) IsRunning() bool {
|
|
mm.mutex.RLock()
|
|
defer mm.mutex.RUnlock()
|
|
return mm.running
|
|
}
|
|
|
|
// Stop terminates the maintenance manager. It is a no-op when the manager is not
|
|
// running, so a second call cannot close the already closed stop channel.
|
|
func (mm *MaintenanceManager) Stop() {
|
|
mm.mutex.Lock()
|
|
if !mm.running {
|
|
mm.mutex.Unlock()
|
|
return
|
|
}
|
|
mm.running = false
|
|
close(mm.stopChan)
|
|
mm.mutex.Unlock()
|
|
|
|
glog.Infof("Maintenance manager stopped")
|
|
}
|
|
|
|
// scanLoop periodically scans for maintenance tasks with adaptive timing
|
|
func (mm *MaintenanceManager) scanLoop() {
|
|
scanInterval := time.Duration(mm.config.ScanIntervalSeconds) * time.Second
|
|
|
|
// activeInterval is the interval the ticker is actually running at right now. It has
|
|
// to be tracked separately from the configured scanInterval, because the error backoff
|
|
// replaces the ticker with a much shorter one. Comparing the target against the
|
|
// configured interval instead never restores the normal cadence: once the errors stop,
|
|
// getScanInterval returns scanInterval again, the comparison comes out false, and the
|
|
// ticker is left at the backoff delay. A single transient scan failure therefore pinned
|
|
// the scanner to one scan per second forever - see issue #10874, where that produced a
|
|
// ~658 KB/s log flood and 193k orphaned task files.
|
|
activeInterval := scanInterval
|
|
ticker := time.NewTicker(activeInterval)
|
|
// Wrapped in a closure so the replacement ticker is stopped, not the one that happened
|
|
// to be current when the defer was registered.
|
|
defer func() { ticker.Stop() }()
|
|
|
|
for mm.IsRunning() {
|
|
select {
|
|
case <-mm.stopChan:
|
|
return
|
|
case <-ticker.C:
|
|
glog.V(1).Infof("Performing maintenance scan every %v", activeInterval)
|
|
|
|
// Use the same synchronization as TriggerScan to prevent concurrent scans
|
|
if err := mm.triggerScanInternal(false); err != nil {
|
|
glog.V(1).Infof("Scheduled scan skipped: %v", err)
|
|
}
|
|
|
|
// Adjust ticker interval based on error state (read error state safely)
|
|
currentInterval := mm.getScanInterval(scanInterval)
|
|
|
|
// Reset ticker whenever the target differs from what the ticker is running at,
|
|
// which covers both entering the backoff and returning to the normal cadence.
|
|
if currentInterval != activeInterval {
|
|
ticker.Stop()
|
|
ticker = time.NewTicker(currentInterval)
|
|
glog.V(1).Infof("Maintenance scan cadence changed from %v to %v", activeInterval, currentInterval)
|
|
activeInterval = currentInterval
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// getScanInterval safely reads the current scan interval with error backoff
|
|
func (mm *MaintenanceManager) getScanInterval(baseInterval time.Duration) time.Duration {
|
|
mm.mutex.RLock()
|
|
defer mm.mutex.RUnlock()
|
|
|
|
if mm.errorCount > 0 {
|
|
// Use backoff delay when there are errors
|
|
currentInterval := mm.backoffDelay
|
|
if currentInterval > baseInterval {
|
|
// Don't make it longer than the configured interval * 10
|
|
maxInterval := baseInterval * 10
|
|
if currentInterval > maxInterval {
|
|
currentInterval = maxInterval
|
|
}
|
|
}
|
|
return currentInterval
|
|
}
|
|
return baseInterval
|
|
}
|
|
|
|
// cleanupLoop periodically cleans up old tasks and stale workers
|
|
func (mm *MaintenanceManager) cleanupLoop() {
|
|
cleanupInterval := time.Duration(mm.config.CleanupIntervalSeconds) * time.Second
|
|
ticker := time.NewTicker(cleanupInterval)
|
|
defer ticker.Stop()
|
|
|
|
for mm.IsRunning() {
|
|
select {
|
|
case <-mm.stopChan:
|
|
return
|
|
case <-ticker.C:
|
|
mm.performCleanup()
|
|
}
|
|
}
|
|
}
|
|
|
|
// topologyStatusLoop periodically logs topology status for diagnostics
|
|
func (mm *MaintenanceManager) topologyStatusLoop() {
|
|
// Log topology status every 5 minutes for diagnostic purposes
|
|
statusInterval := 5 * time.Minute
|
|
ticker := time.NewTicker(statusInterval)
|
|
defer ticker.Stop()
|
|
|
|
for mm.IsRunning() {
|
|
select {
|
|
case <-mm.stopChan:
|
|
return
|
|
case <-ticker.C:
|
|
mm.logTopologyStatus()
|
|
}
|
|
}
|
|
}
|
|
|
|
// logTopologyStatus logs current topology and worker status for diagnostics
|
|
func (mm *MaintenanceManager) logTopologyStatus() {
|
|
if mm.scanner == nil || mm.scanner.integration == nil {
|
|
glog.V(2).Infof("Topology status: scanner/integration not available")
|
|
return
|
|
}
|
|
|
|
activeTopology := mm.scanner.integration.GetActiveTopology()
|
|
if activeTopology == nil {
|
|
glog.V(1).Infof("Topology status: ActiveTopology is nil")
|
|
return
|
|
}
|
|
|
|
diskCount := activeTopology.GetDiskCount()
|
|
nodeCount := len(activeTopology.GetAllNodes())
|
|
|
|
// Get queue stats
|
|
stats := mm.queue.GetStats()
|
|
workerCount := len(mm.queue.GetWorkers())
|
|
|
|
mm.mutex.RLock()
|
|
errorCount := mm.errorCount
|
|
mm.mutex.RUnlock()
|
|
|
|
glog.V(1).Infof("Topology status: %d nodes, %d disks, %d workers, %d pending tasks, %d running tasks, errors: %d",
|
|
nodeCount, diskCount, workerCount,
|
|
stats.TasksByStatus[TaskStatusPending],
|
|
stats.TasksByStatus[TaskStatusInProgress]+stats.TasksByStatus[TaskStatusAssigned],
|
|
errorCount)
|
|
}
|
|
|
|
// performScan executes a maintenance scan with error handling and backoff
|
|
func (mm *MaintenanceManager) performScan() {
|
|
defer func() {
|
|
// Always reset scan in progress flag when done
|
|
mm.mutex.Lock()
|
|
mm.scanInProgress = false
|
|
mm.mutex.Unlock()
|
|
}()
|
|
|
|
glog.Infof("Starting maintenance scan...")
|
|
|
|
results, err := mm.scanner.ScanForMaintenanceTasks()
|
|
stats_collect.AdminMaintenanceLastScanTimestampSeconds.SetToCurrentTime()
|
|
if err != nil {
|
|
// Handle scan error
|
|
mm.mutex.Lock()
|
|
mm.handleScanError(err)
|
|
mm.mutex.Unlock()
|
|
glog.Warningf("Maintenance scan failed: %v", err)
|
|
return
|
|
}
|
|
|
|
// Scan succeeded - update state and process results
|
|
mm.handleScanSuccess(results)
|
|
}
|
|
|
|
// handleScanSuccess processes successful scan results with proper lock management
|
|
func (mm *MaintenanceManager) handleScanSuccess(results []*TaskDetectionResult) {
|
|
// Update manager state first
|
|
mm.mutex.Lock()
|
|
mm.resetErrorTracking()
|
|
taskCount := len(results)
|
|
mm.mutex.Unlock()
|
|
|
|
if taskCount > 0 {
|
|
// Count tasks by type for logging (outside of lock)
|
|
taskCounts := make(map[MaintenanceTaskType]int)
|
|
for _, result := range results {
|
|
taskCounts[result.TaskType]++
|
|
}
|
|
|
|
// Add tasks to queue (no manager lock held)
|
|
mm.queue.AddTasksFromResults(results)
|
|
|
|
// Log detailed scan results
|
|
glog.Infof("Maintenance scan completed: found %d tasks", taskCount)
|
|
for taskType, count := range taskCounts {
|
|
glog.Infof(" - %s: %d tasks", taskType, count)
|
|
}
|
|
} else {
|
|
glog.Infof("Maintenance scan completed: no maintenance tasks needed")
|
|
}
|
|
}
|
|
|
|
// handleScanError handles scan errors with exponential backoff and reduced logging
|
|
func (mm *MaintenanceManager) handleScanError(err error) {
|
|
now := time.Now()
|
|
mm.errorCount++
|
|
mm.lastError = err
|
|
mm.lastErrorTime = now
|
|
|
|
// Use exponential backoff with jitter
|
|
if mm.errorCount > 1 {
|
|
mm.backoffDelay = mm.backoffDelay * 2
|
|
if mm.backoffDelay > 5*time.Minute {
|
|
mm.backoffDelay = 5 * time.Minute // Cap at 5 minutes
|
|
}
|
|
}
|
|
|
|
// Reduce log frequency based on error count and time
|
|
shouldLog := false
|
|
if mm.errorCount <= 3 {
|
|
// Log first 3 errors immediately
|
|
shouldLog = true
|
|
} else if mm.errorCount <= 10 && mm.errorCount%3 == 0 {
|
|
// Log every 3rd error for errors 4-10
|
|
shouldLog = true
|
|
} else if mm.errorCount%10 == 0 {
|
|
// Log every 10th error after that
|
|
shouldLog = true
|
|
}
|
|
|
|
if shouldLog {
|
|
// Check if it's a connection error to provide better messaging
|
|
if isConnectionError(err) {
|
|
if mm.errorCount == 1 {
|
|
glog.Errorf("Maintenance scan failed: %v (will retry with backoff)", err)
|
|
} else {
|
|
glog.Errorf("Maintenance scan still failing after %d attempts: %v (backoff: %v)",
|
|
mm.errorCount, err, mm.backoffDelay)
|
|
}
|
|
} else {
|
|
glog.Errorf("Maintenance scan failed: %v", err)
|
|
}
|
|
} else {
|
|
// Use debug level for suppressed errors
|
|
glog.V(3).Infof("Maintenance scan failed (error #%d, suppressed): %v", mm.errorCount, err)
|
|
}
|
|
}
|
|
|
|
// resetErrorTracking resets error tracking when scan succeeds
|
|
func (mm *MaintenanceManager) resetErrorTracking() {
|
|
if mm.errorCount > 0 {
|
|
glog.V(1).Infof("Maintenance scan recovered after %d failed attempts", mm.errorCount)
|
|
mm.errorCount = 0
|
|
mm.lastError = nil
|
|
mm.backoffDelay = time.Second // Reset to initial delay
|
|
}
|
|
}
|
|
|
|
// isConnectionError checks if the error is a connection-related error
|
|
func isConnectionError(err error) bool {
|
|
if err == nil {
|
|
return false
|
|
}
|
|
errStr := err.Error()
|
|
return strings.Contains(errStr, "connection refused") ||
|
|
strings.Contains(errStr, "connection error") ||
|
|
strings.Contains(errStr, "dial tcp") ||
|
|
strings.Contains(errStr, "connection timeout") ||
|
|
strings.Contains(errStr, "no route to host") ||
|
|
strings.Contains(errStr, "network unreachable")
|
|
}
|
|
|
|
// performCleanup cleans up old tasks and stale workers
|
|
func (mm *MaintenanceManager) performCleanup() {
|
|
glog.V(2).Infof("Starting maintenance cleanup")
|
|
|
|
taskRetention := time.Duration(mm.config.TaskRetentionSeconds) * time.Second
|
|
workerTimeout := time.Duration(mm.config.WorkerTimeoutSeconds) * time.Second
|
|
|
|
removedTasks := mm.queue.CleanupOldTasks(taskRetention)
|
|
removedWorkers := mm.queue.RemoveStaleWorkers(workerTimeout)
|
|
|
|
// Clean up stale pending operations (operations running for more than 4 hours)
|
|
staleOperationTimeout := 4 * time.Hour
|
|
removedOperations := 0
|
|
if mm.scanner != nil && mm.scanner.integration != nil {
|
|
pendingOps := mm.scanner.integration.GetPendingOperations()
|
|
if pendingOps != nil {
|
|
removedOperations = pendingOps.CleanupStaleOperations(staleOperationTimeout)
|
|
}
|
|
}
|
|
|
|
if removedTasks > 0 || removedWorkers > 0 || removedOperations > 0 {
|
|
glog.V(1).Infof("Cleanup completed: removed %d old tasks, %d stale workers, and %d stale operations",
|
|
removedTasks, removedWorkers, removedOperations)
|
|
}
|
|
}
|
|
|
|
// GetQueue returns the maintenance queue
|
|
func (mm *MaintenanceManager) GetQueue() *MaintenanceQueue {
|
|
return mm.queue
|
|
}
|
|
|
|
// GetConfig returns the maintenance configuration
|
|
func (mm *MaintenanceManager) GetConfig() *MaintenanceConfig {
|
|
return mm.config
|
|
}
|
|
|
|
// GetStats returns maintenance statistics
|
|
func (mm *MaintenanceManager) GetStats() *MaintenanceStats {
|
|
stats := mm.queue.GetStats()
|
|
|
|
mm.mutex.RLock()
|
|
defer mm.mutex.RUnlock()
|
|
|
|
stats.LastScanTime = time.Now() // Would need to track this properly
|
|
|
|
// Calculate next scan time based on current error state
|
|
scanInterval := time.Duration(mm.config.ScanIntervalSeconds) * time.Second
|
|
nextScanInterval := scanInterval
|
|
if mm.errorCount > 0 {
|
|
nextScanInterval = mm.backoffDelay
|
|
maxInterval := scanInterval * 10
|
|
if nextScanInterval > maxInterval {
|
|
nextScanInterval = maxInterval
|
|
}
|
|
}
|
|
stats.NextScanTime = time.Now().Add(nextScanInterval)
|
|
|
|
return stats
|
|
}
|
|
|
|
// ReloadTaskConfigurations reloads task configurations from the current policy
|
|
func (mm *MaintenanceManager) ReloadTaskConfigurations() error {
|
|
mm.mutex.Lock()
|
|
defer mm.mutex.Unlock()
|
|
|
|
// Trigger configuration reload in the integration layer
|
|
if mm.scanner != nil && mm.scanner.integration != nil {
|
|
mm.scanner.integration.ConfigureTasksFromPolicy()
|
|
glog.V(1).Infof("Task configurations reloaded from policy")
|
|
return nil
|
|
}
|
|
|
|
return fmt.Errorf("integration not available for configuration reload")
|
|
}
|
|
|
|
// GetErrorState returns the current error state for monitoring
|
|
func (mm *MaintenanceManager) GetErrorState() (errorCount int, lastError error, backoffDelay time.Duration) {
|
|
mm.mutex.RLock()
|
|
defer mm.mutex.RUnlock()
|
|
return mm.errorCount, mm.lastError, mm.backoffDelay
|
|
}
|
|
|
|
// GetTasks returns tasks with filtering
|
|
func (mm *MaintenanceManager) GetTasks(status MaintenanceTaskStatus, taskType MaintenanceTaskType, limit int) []*MaintenanceTask {
|
|
return mm.queue.GetTasks(status, taskType, limit)
|
|
}
|
|
|
|
// GetWorkers returns all registered workers
|
|
func (mm *MaintenanceManager) GetWorkers() []*MaintenanceWorker {
|
|
return mm.queue.GetWorkers()
|
|
}
|
|
|
|
// GetWorkerSlots returns used/max task slots per worker ID.
|
|
func (mm *MaintenanceManager) GetWorkerSlots() map[string]WorkerSlots {
|
|
return mm.queue.GetWorkerSlots()
|
|
}
|
|
|
|
// TriggerScan manually triggers a maintenance scan
|
|
func (mm *MaintenanceManager) TriggerScan() error {
|
|
return mm.triggerScanInternal(true)
|
|
}
|
|
|
|
// triggerScanInternal handles both manual and automatic scan triggers
|
|
func (mm *MaintenanceManager) triggerScanInternal(isManual bool) error {
|
|
// running and scanInProgress are checked under one lock so a Stop that lands
|
|
// between the two checks cannot leave a scan running after shutdown.
|
|
mm.mutex.Lock()
|
|
if !mm.running {
|
|
mm.mutex.Unlock()
|
|
return fmt.Errorf("maintenance manager is not running")
|
|
}
|
|
|
|
// Prevent multiple concurrent scans
|
|
if mm.scanInProgress {
|
|
mm.mutex.Unlock()
|
|
if isManual {
|
|
glog.V(1).Infof("Manual scan already in progress, ignoring trigger request")
|
|
} else {
|
|
glog.V(2).Infof("Automatic scan already in progress, ignoring scheduled scan")
|
|
}
|
|
return fmt.Errorf("scan already in progress")
|
|
}
|
|
mm.scanInProgress = true
|
|
mm.mutex.Unlock()
|
|
|
|
go mm.performScan()
|
|
return nil
|
|
}
|
|
|
|
// UpdateConfig updates the maintenance configuration
|
|
func (mm *MaintenanceManager) UpdateConfig(config *MaintenanceConfig) error {
|
|
if config == nil {
|
|
return fmt.Errorf("config cannot be nil")
|
|
}
|
|
|
|
mm.config = config
|
|
mm.queue.policy = config.Policy
|
|
mm.scanner.policy = config.Policy
|
|
|
|
// Propagate global policy changes to individual task configuration files
|
|
if config.Policy != nil {
|
|
mm.saveTaskConfigsFromPolicy(config.Policy)
|
|
}
|
|
|
|
// The integration holds its own reference to the policy and is what pushes the
|
|
// enabled flag and the concurrency limit into the registered detectors and
|
|
// schedulers. Without this the queue and the scanner saw the new policy while the
|
|
// detectors kept scanning under the old one until the next restart.
|
|
if mm.scanner != nil && mm.scanner.integration != nil {
|
|
mm.scanner.integration.SetPolicy(config.Policy)
|
|
}
|
|
|
|
glog.V(1).Infof("Maintenance configuration updated")
|
|
return nil
|
|
}
|
|
|
|
// saveTaskConfigsFromPolicy propagates global policy settings to separate task configuration files
|
|
func (mm *MaintenanceManager) saveTaskConfigsFromPolicy(policy *worker_pb.MaintenancePolicy) {
|
|
if mm.queue.persistence == nil || policy == nil {
|
|
return
|
|
}
|
|
|
|
glog.V(1).Infof("Propagating maintenance policy changes to separate task configs")
|
|
for taskType, taskPolicy := range policy.TaskPolicies {
|
|
if err := mm.queue.persistence.SaveTaskPolicy(taskType, taskPolicy); err != nil {
|
|
glog.Errorf("Failed to save task policy for %s: %v", taskType, err)
|
|
}
|
|
}
|
|
}
|
|
|
|
// CancelTask cancels a pending task
|
|
func (mm *MaintenanceManager) CancelTask(taskID string) error {
|
|
mm.queue.mutex.Lock()
|
|
defer mm.queue.mutex.Unlock()
|
|
|
|
task, exists := mm.queue.tasks[taskID]
|
|
if !exists {
|
|
return fmt.Errorf("task %s not found", taskID)
|
|
}
|
|
|
|
if task.Status == TaskStatusPending {
|
|
task.Status = TaskStatusCancelled
|
|
task.CompletedAt = &[]time.Time{time.Now()}[0]
|
|
|
|
// Remove from pending tasks
|
|
for i, pendingTask := range mm.queue.pendingTasks {
|
|
if pendingTask.ID == taskID {
|
|
mm.queue.pendingTasks = append(mm.queue.pendingTasks[:i], mm.queue.pendingTasks[i+1:]...)
|
|
break
|
|
}
|
|
}
|
|
|
|
// Notify ActiveTopology to release capacity
|
|
if mm.scanner != nil && mm.scanner.integration != nil {
|
|
if at := mm.scanner.integration.GetActiveTopology(); at != nil {
|
|
_ = at.CompleteTask(taskID)
|
|
}
|
|
}
|
|
|
|
glog.V(2).Infof("Cancelled task %s", taskID)
|
|
return nil
|
|
}
|
|
|
|
return fmt.Errorf("task %s cannot be cancelled (status: %s)", taskID, task.Status)
|
|
}
|
|
|
|
// RegisterWorker registers a new worker
|
|
func (mm *MaintenanceManager) RegisterWorker(worker *MaintenanceWorker) {
|
|
mm.queue.RegisterWorker(worker)
|
|
}
|
|
|
|
// GetNextTask returns the next task for a worker
|
|
func (mm *MaintenanceManager) GetNextTask(workerID string, capabilities []MaintenanceTaskType) *MaintenanceTask {
|
|
return mm.queue.GetNextTask(workerID, capabilities)
|
|
}
|
|
|
|
// CompleteTask marks a task as completed
|
|
func (mm *MaintenanceManager) CompleteTask(taskID string, error string) {
|
|
mm.queue.CompleteTask(taskID, error)
|
|
}
|
|
|
|
// UpdateTaskProgress updates task progress
|
|
func (mm *MaintenanceManager) UpdateTaskProgress(taskID string, progress float64) {
|
|
mm.queue.UpdateTaskProgress(taskID, progress)
|
|
}
|
|
|
|
// UpdateWorkerHeartbeat updates worker heartbeat
|
|
func (mm *MaintenanceManager) UpdateWorkerHeartbeat(workerID string) {
|
|
mm.queue.UpdateWorkerHeartbeat(workerID)
|
|
}
|