容器化RDS—計算儲存分離架構下的“Split-Brain”

以阿里巴巴為例，考慮到今時今日它的規模，如果能夠實現資料庫服務的離線(ODPS)/線上叢集的混合部署，意義極其重大。關鍵問題在於，離線(ODPS)計算和線上計算對實時性要求不同，硬體配置也不同，尤其是本地儲存介質：

●     離線(ODPS)以機械磁碟為主

●     線上以 SSD / Flash 為主

如果採用本地儲存作為資料庫例項的儲存介質, 試想一下, 一個 Storage Qos 要求是 Flash 的資料庫例項無法排程到離線計算叢集, 哪怕離線計算叢集 CPU, Memory 有大量空閒.

計算儲存分離為實現離線(ODPS)/線上叢集的混合部署提供了可能。

當叢集中某個 Node 不可用後, 藉助 Kubernetes 的原生元件Node Controller, Scheduler和原生API Statefulset即可將資料庫例項排程到其他可用節點, 以實現資料庫例項的高可用.

補充一句，助 ETCD 叢集的高可用強一致，以保證 Kubernetes 叢集元資訊的一致性。

●     ETCD 基於 Raft 演算法實現。

●     Raft 演算法是一種基於訊息傳遞(state machine replicated)且具有高度容錯(fault tolerance)特性的一致性演算法(consensus algorithm)。

●     Raft 是大名鼎鼎的 Paxos 的簡化版本

●     如果對於 Raft 演算法的實現有興趣，可以看看 https://github.com/goraft/raft

所有感興趣一致性演算法的同學，都值得花精力學習。基於 goraft/raft，我實現了Network Partition Failures/Recovery TestCase，收穫不小。

Kubelet 細節如下:

●     通過 API Server  更新叢集資訊

if kl.kubeClient != nil {

  // Start syncing node status immediately, this may set up things the runtime needs to run.

  go wait.Until(kl.syncNodeStatus, kl.nodeStatusUpdateFrequency, wait.NeverStop)

}

●     定期(nodeStatusUpdateFrequency)更新對應節點狀態

nodeStatusUpdateFrequency 預設時間為 10 秒, 測試時設定的是8s

obj.NodeStatusUpdateFrequency = metav1.Duration{Duration: 10 * time.Second}

●     更新如下資訊：

func (kl *Kubelet) defaultNodeStatusFuncs() []func(*v1.Node) error {

  // initial set of node status update handlers, can be modified by Option's

  withoutError := func(f func(*v1.Node)) func(*v1.Node) error {

     return func(n *v1.Node) error {

        f(n)

        return nil

     }

  }

  return []func(*v1.Node) error{

     kl.setNodeAddress,

     withoutError(kl.setNodeStatusInfo),

     withoutError(kl.setNodeOODCondition),

     withoutError(kl.setNodeMemoryPressureCondition),

     withoutError(kl.setNodeDiskPressureCondition),

     withoutError(kl.setNodeReadyCondition),

     withoutError(kl.setNodeVolumesInUseStatus),

     withoutError(kl.recordNodeSchedulableEvent),

  }

}

●     通過 kubectl 可以獲得節點的資訊

●     定期(nodeMonitorPeriod)檢視一次節點狀態

// Incorporate the results of node status pushed from kubelet to master.

go wait.Until(func() {

  if err := nc.monitorNodeStatus(); err != nil {

     glog.Errorf("Error monitoring node status: %v", err)

  }

}, nc.nodeMonitorPeriod, wait.NeverStop)

●     nodeMonitorPeriod 預設 5秒，測試時4s

NodeMonitorPeriod:                               metav1.Duration{Duration: 5 * time.Second},

●     當超過 NodeMonitorGracePeriod 時間後，節點狀態沒有更新將節點狀態設定成 unknown

if nc.now().After(savedNodeStatus.probeTimestamp.Add(gracePeriod)) {

  // NodeReady condition was last set longer ago than gracePeriod, so update it to Unknown

  // (regardless of its current value) in the master.

  if currentReadyCondition == nil {

     glog.V(2).Infof("node %v is never updated by kubelet", node.Name)

     node.Status.Conditions = append(node.Status.Conditions, v1.NodeCondition{

        Type:               v1.NodeReady,

        Status:             v1.ConditionUnknown,

        Reason:             "NodeStatusNeverUpdated",

        Message:            fmt.Sprintf("Kubelet never posted node status."),

        LastHeartbeatTime:  node.CreationTimestamp,

        LastTransitionTime: nc.now(),

     })

  } else {

     glog.V(4).Infof("node %v hasn't been updated for %+v. Last ready condition is: %+v",

        node.Name, nc.now().Time.Sub(savedNodeStatus.probeTimestamp.Time), observedReadyCondition)

     if observedReadyCondition.Status != v1.ConditionUnknown {

        currentReadyCondition.Status = v1.ConditionUnknown

        currentReadyCondition.Reason = "NodeStatusUnknown"

        currentReadyCondition.Message = "Kubelet stopped posting node status."

        // LastProbeTime is the last time we heard from kubelet.

        currentReadyCondition.LastHeartbeatTime = observedReadyCondition.LastHeartbeatTime

        currentReadyCondition.LastTransitionTime = nc.now()

     }

  }

●     在podEvictionTimeout 後，認為該節點上 pods 需要開始驅逐

if observedReadyCondition.Status == v1.ConditionUnknown {

  if nc.useTaintBasedEvictions {

     // We want to update the taint straight away if Node is already tainted with the UnreachableTaint

     if taintutils.TaintExists(node.Spec.Taints, NotReadyTaintTemplate) {

        taintToAdd := *UnreachableTaintTemplate

        if !util.SwapNodeControllerTaint(nc.kubeClient, []*v1.Taint{&taintToAdd}, []*v1.Taint{NotReadyTaintTemplate}, node) {

           glog.Errorf("Failed to instantly swap UnreachableTaint to NotReadyTaint. Will try again in the next cycle.")

        }

     } else if nc.markNodeForTainting(node) {

        glog.V(2).Infof("Node %v is unresponsive as of %v. Adding it to the Taint queue.",

           node.Name,

           decisionTimestamp,

        )

     }

  } else {

     if decisionTimestamp.After(nc.nodeStatusMap[node.Name].probeTimestamp.Add(nc.podEvictionTimeout)) {

        if nc.evictPods(node) {

           glog.V(2).Infof("Node is unresponsive. Adding Pods on Node %s to eviction queues: %v is later than %v + %v",

              node.Name,

              decisionTimestamp,

              nc.nodeStatusMap[node.Name].readyTransitionTimestamp,

              nc.podEvictionTimeout-gracePeriod,

           )

        }

     }

  }

}

●     放到驅逐陣列中

// evictPods queues an eviction for the provided node name, and returns false if the node is already

// queued for eviction.

func (nc *Controller) evictPods(node *v1.Node) bool {

  nc.evictorLock.Lock()

  defer nc.evictorLock.Unlock()

  return nc.zonePodEvictor[utilnode.GetZoneKey(node)].Add(node.Name, string(node.UID))

}

●     驅逐 goroutine

if nc.useTaintBasedEvictions {

  // Handling taint based evictions. Because we don't want a dedicated logic in TaintManager for NC-originated

  // taints and we normally don't rate limit evictions caused by taints, we need to rate limit adding taints.

  go wait.Until(nc.doNoExecuteTaintingPass, scheduler.NodeEvictionPeriod, wait.NeverStop)

} else {

  // Managing eviction of nodes:

  // When we delete pods off a node, if the node was not empty at the time we then

  // queue an eviction watcher. If we hit an error, retry deletion.

  go wait.Until(nc.doEvictionPass, scheduler.NodeEvictionPeriod, wait.NeverStop)

}

●     通過刪除 pods 的方式驅逐

func (nc *Controller) doEvictionPass() {

  nc.evictorLock.Lock()

  defer nc.evictorLock.Unlock()

  for k := range nc.zonePodEvictor {

     // Function should return 'false' and a time after which it should be retried, or 'true' if it shouldn't (it succeeded).

     nc.zonePodEvictor[k].Try(func(value scheduler.TimedValue) (bool, time.Duration) {

        node, err := nc.nodeLister.Get(value.Value)

        if apierrors.IsNotFound(err) {

           glog.Warningf("Node %v no longer present in nodeLister!", value.Value)

        } else if err != nil {

           glog.Warningf("Failed to get Node %v from the nodeLister: %v", value.Value, err)

        } else {

           zone := utilnode.GetZoneKey(node)

           evictionsNumber.WithLabelValues(zone).Inc()

        }

        nodeUID, _ := value.UID.(string)

        remaining, err := util.DeletePods(nc.kubeClient, nc.recorder, value.Value, nodeUID, nc.daemonSetStore)

        if err != nil {

           utilruntime.HandleError(fmt.Errorf("unable to evict node %q: %v", value.Value, err))

           return false, 0

        }

        if remaining {

           glog.Infof("Pods awaiting deletion due to Controller eviction")

        }

        return true, 0

     })

  }

}

2017-12-01 10:19:47 5628 [Note] mysqld (mysqld 5.7.19-log) starting as process 963 ...

2017-12-01 10:19:47 5628 [Note] InnoDB: PUNCH HOLE support available

2017-12-01 10:19:47 5628 [Note] InnoDB: Mutexes and rw_locks use GCC atomic builtins

2017-12-01 10:19:47 5628 [Note] InnoDB: Uses event mutexes

2017-12-01 10:19:47 5628 [Note] InnoDB: GCC builtin __atomic_thread_fence() is used for memory barrier

2017-12-01 10:19:47 5628 [Note] InnoDB: Compressed tables use zlib 1.2.3

2017-12-01 10:19:47 5628 [Note] InnoDB: Using Linux native AIO

2017-12-01 10:19:47 5628 [Note] InnoDB: Number of pools: 1

2017-12-01 10:19:47 5628 [Note] InnoDB: Using CPU crc32 instructions

2017-12-01 10:19:47 5628 [Note] InnoDB: Initializing buffer pool, total size = 3.25G, instances = 2, chunk size = 128M

2017-12-01 10:19:47 5628 [Note] InnoDB: Completed initialization of buffer pool

2017-12-01 10:19:47 5628 [Note] InnoDB: If the mysqld execution user is authorized, page cleaner thread priority can be changed. See the man page of setpriority().

2017-12-01 10:19:47 5628 [Note] InnoDB: Highest supported file format is Barracuda.

2017-12-01 10:19:47 5628 [Note] InnoDB: Log scan progressed past the checkpoint lsn 406822323

2017-12-01 10:19:47 5628 [Note] InnoDB: Doing recovery: scanned up to log sequence number 406823190

2017-12-01 10:19:47 5628 [Note] InnoDB: Database was not shutdown normally!

2017-12-01 10:19:47 5628 [Note] InnoDB: Starting crash recovery.

2017-12-01 10:19:47 5669 [Note] InnoDB: Starting an apply batch of log records to the database...

InnoDB: Progress in  percent: 89 90 91 92 93 94 95 96 97 98 99

2017-12-01 10:19:47 5669 [Note] InnoDB: Apply batch completed

2017-12-01 10:19:47 5669 [Note] InnoDB: Last MySQL binlog file position 0 428730, file name mysql-bin.000004

2017-12-01 10:19:47 5669 [Note] InnoDB: Removed temporary tablespace data file: "ibtmp1"

2017-12-01 10:19:47 5669 [Note] InnoDB: Creating shared tablespace for temporary tables

2017-12-01 10:19:47 5669 [Note] InnoDB: Setting file './ibtmp1' size to 12 MB. Physically writing the file full; Please wait ...

2017-12-01 10:19:47 5669 [Note] InnoDB: File './ibtmp1' size is now 12 MB.

2017-12-01 10:19:47 5669 [Note] InnoDB: 96 redo rollback segment(s) found. 96 redo rollback segment(s) are active.

2017-12-01 10:19:47 5669 [Note] InnoDB: 32 non-redo rollback segment(s) are active.

2017-12-01 10:19:47 5669 [Note] InnoDB: Waiting for purge to start

2017-12-01 10:19:47 0x7fcb08928700  InnoDB: Assertion failure in thread 140509998909184 in file trx0purge.cc line 168

InnoDB: Failing assertion: purge_sys->iter.trx_no <= purge_sys->rseg->last_trx_no

InnoDB: We intentionally generate a memory trap.

InnoDB: Submit a detailed bug report to http://bugs.mysql.com.

InnoDB: If you get repeated assertion failures or crashes, even

InnoDB: immediately after the mysqld startup, there may be

InnoDB: corruption in the InnoDB tablespace. Please refer to

InnoDB: http://dev.mysql.com/doc/refman/5.7/en/forcing-innodb-recovery.html

InnoDB: about forcing recovery.

10:19:47 5669 - mysqld got signal 6 ;