ops: Signal disk-tier attach pending vs ready
Large disk caches can look memory-only/broken during async DiskFS attach. Expose disk_tier_ready in /metrics, pending/ready logs for disk-only and mixed modes, and X-SteamCache-Disk-Tier on /lancache-heartbeat. GetMetrics skips blocking disk.Size() while attach is pending so /metrics stays usable. Closes #33
This commit is contained in:
@@ -200,23 +200,33 @@ func New(address string, memorySize string, diskSize string, diskPath, upstream,
|
||||
|
||||
if disksize == 0 && memorysize != 0 {
|
||||
// memory only mode - no disk
|
||||
sc.metrics.SetDiskTierReady(1) // no disk — N/A / not pending
|
||||
c.SetSlow(mgc)
|
||||
} else if disksize != 0 && memorysize == 0 {
|
||||
// disk only mode: delay attach until disk ready (pure-proxy during scan; Create returns ErrNotFound until slow tier Set)
|
||||
sc.metrics.SetDiskTierReady(0)
|
||||
logger.Logger.Info().Msg("Disk slow tier attach pending; Size barrier in progress")
|
||||
sc.wg.Add(1)
|
||||
go func() {
|
||||
defer sc.wg.Done()
|
||||
t0 := time.Now()
|
||||
_ = d.Size() // block on barrier per design (all Size callers during window do this; documented)
|
||||
select {
|
||||
case <-sc.shutdownCh:
|
||||
return // Shutdown raced; do not attach or SetSlow after stop
|
||||
default:
|
||||
c.SetSlow(dgc)
|
||||
sc.metrics.SetDiskTierReady(1)
|
||||
logger.Logger.Info().
|
||||
Dur("attach_delay", time.Since(t0)).
|
||||
Msg("Disk slow tier attached (disk-only mode); prior traffic had no disk tier")
|
||||
}
|
||||
}()
|
||||
} else if disksize != 0 && memorysize != 0 {
|
||||
// memory and disk mode: fast mem immediate, disk delayed (mem-only during scan)
|
||||
c.SetFast(mgc)
|
||||
sc.metrics.SetDiskTierReady(0)
|
||||
logger.Logger.Info().Msg("Disk slow tier attach pending; Size barrier in progress")
|
||||
sc.wg.Add(1)
|
||||
go func() {
|
||||
defer sc.wg.Done()
|
||||
@@ -227,6 +237,7 @@ func New(address string, memorySize string, diskSize string, diskPath, upstream,
|
||||
return
|
||||
default:
|
||||
c.SetSlow(dgc)
|
||||
sc.metrics.SetDiskTierReady(1)
|
||||
logger.Logger.Info().
|
||||
Dur("attach_delay", time.Since(t0)).
|
||||
Msg("Disk slow tier attached (mixed mode); prior traffic was memory-only")
|
||||
@@ -326,15 +337,13 @@ func (sc *SteamCache) Shutdown() {
|
||||
|
||||
// GetMetrics returns current metrics
|
||||
func (sc *SteamCache) GetMetrics() *metrics.Stats {
|
||||
// Update cache sizes
|
||||
if sc.memory != nil {
|
||||
sc.metrics.SetMemoryCacheSize(sc.memory.Size())
|
||||
}
|
||||
if sc.disk != nil {
|
||||
// Note: blocks on initDone (post-eviction state) for accurate post-attach size during long disk init window.
|
||||
// Skip disk.Size() while attach pending — Size() blocks on initDone and would hang /metrics.
|
||||
if sc.disk != nil && sc.metrics.GetDiskTierReady() == 1 {
|
||||
sc.metrics.SetDiskCacheSize(sc.disk.Size())
|
||||
}
|
||||
|
||||
return sc.metrics.GetStats()
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user