【 Kubernetes 集群】节点内存碎片化排障处理

本文档介绍如何判断 TKE 集群中存在问题是否由内存碎片化引起，并给出解决方法，请按照以下步骤进行排查并解决。

问题分析

内存页分配失败，内核日志将会出现以下报错：

mysqld: page allocation failure. order:4, mode:0x10c0d0

mysqld：为被分配内存的程序。

order：表示需要分配连续页的数量（2^order），本例中4则表示 2^4 = 16 个连续的页。

mode：内存分配模式的标识，在内核源码文件 include/linux/gfp.h 中定义，通常是多个标识项与运算的结果。不同版本内核有一定区别。例如，在新版内核中 GFP_KERNEL 是 __GFP_RECLAIM | __GFP_IO | __GFP_FS 的运算结果，而 __GFP_RECLAIM 是 ___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM 的运算结果。

注意：

当 order 值为0时，说明系统已经完全没有可用内存。

当 order 值较大时，说明内存已碎片化，无法分配连续的大页内存。

现象描述

容器启动失败

K8S 会为每个 Pod 创建 netns 来隔离 network namespace，内核初始化 netns 时会为其创建 nf_conntrack 表的 cache，需要申请大页内存，如果此时系统内存已经碎片化，无法分配到足够的大页内存内核就会出现如下报错（v2.6.33 - v4.6）：

runc:[1:CHILD]: page allocation failure: order:6, mode:0x10c0d0

Pod 将会一直处于 ContainerCreating 状态，dockerd 启动容器也将失败。日志报错如下：

Jan 23 14:15:31 dc05 dockerd: time="2019-01-23T14:15:31.288446233+08:00" level=error msg="containerd: start container" error="oci runtime error: container_linux.go:247: starting container process caused \"process_linux.go:245: running exec setns process for init caused \\\"exit status 6\\\"\"\n" id=5b9be8c5bb121264899fac8d9d36b02150269d41ce96ba6ad36d70b8640cb01c

Jan 23 14:15:31 dc05 dockerd: time="2019-01-23T14:15:31.317965799+08:00" level=error msg="Create container failed with error: invalid header field value \"oci runtime error: container_linux.go:247: starting container process caused \\\"process_linux.go:245: running exec setns process for init caused \\\\\\\"exit status 6\\\\\\\"\\\"\\n\""

Kubelet 日志报错如下：

Jan 23 14:15:31 dc05 kubelet: E0123 14:15:31.352386 26037 remote_runtime.go:91] RunPodSandbox from runtime service failed: rpc error: code = 2 desc = failed to start sandbox container for pod "matchdataserver-1255064836-t4b2w": Error response from daemon: {"message":"invalid header field value \"oci runtime error: container_linux.go:247: starting container process caused \\\"process_linux.go:245: running exec setns process for init caused \\\\\\\"exit status 6\\\\\\\"\\\"\\n\""}

Jan 23 14:15:31 dc05 kubelet: E0123 14:15:31.352496 26037 kuberuntime_sandbox.go:54] CreatePodSandbox for pod "matchdataserver-1255064836-t4b2w_basic(485fd485-1ed6-11e9-8661-0a587f8021ea)" failed: rpc error: code = 2 desc = failed to start sandbox container for pod "matchdataserver-1255064836-t4b2w": Error response from daemon: {"message":"invalid header field value \"oci runtime error: container_linux.go:247: starting container process caused \\\"process_linux.go:245: running exec setns process for init caused \\\\\\\"exit status 6\\\\\\\"\\\"\\n\""}

Jan 23 14:15:31 dc05 kubelet: E0123 14:15:31.352518 26037 kuberuntime_manager.go:618] createPodSandbox for pod "matchdataserver-1255064836-t4b2w_basic(485fd485-1ed6-11e9-8661-0a587f8021ea)" failed: rpc error: code = 2 desc = failed to start sandbox container for pod "matchdataserver-1255064836-t4b2w": Error response from daemon: {"message":"invalid header field value \"oci runtime error: container_linux.go:247: starting container process caused \\\"process_linux.go:245: running exec setns process for init caused \\\\\\\"exit status 6\\\\\\\"\\\"\\n\""}

Jan 23 14:15:31 dc05 kubelet: E0123 14:15:31.352580 26037 pod_workers.go:182] Error syncing pod 485fd485-1ed6-11e9-8661-0a587f8021ea ("matchdataserver-1255064836-t4b2w_basic(485fd485-1ed6-11e9-8661-0a587f8021ea)"), skipping: failed to "CreatePodSandbox" for "matchdataserver-1255064836-t4b2w_basic(485fd485-1ed6-11e9-8661-0a587f8021ea)" with CreatePodSandboxError: "CreatePodSandbox for pod \"matchdataserver-1255064836-t4b2w_basic(485fd485-1ed6-11e9-8661-0a587f8021ea)\" failed: rpc error: code = 2 desc = failed to start sandbox container for pod \"matchdataserver-1255064836-t4b2w\": Error response from daemon: {\"message\":\"invalid header field value \\\"oci runtime error: container_linux.go:247: starting container process caused \\\\\\\"process_linux.go:245: running exec setns process for init caused \\\\\\\\\\\\\\\"exit status 6\\\\\\\\\\\\\\\"\\\\\\\"\\\\n\\\"\"}"

Jan 23 14:15:31 dc05 kubelet: I0123 14:15:31.372181 26037 kubelet.go:1916] SyncLoop (PLEG): "matchdataserver-1255064836-t4b2w_basic(485fd485-1ed6-11e9-8661-0a587f8021ea)", event: &pleg.PodLifecycleEvent{ID:"485fd485-1ed6-11e9-8661-0a587f8021ea", Type:"ContainerDied", Data:"5b9be8c5bb121264899fac8d9d36b02150269d41ce96ba6ad36d70b8640cb01c"}

Jan 23 14:15:31 dc05 kubelet: W0123 14:15:31.372225 26037 pod_container_deletor.go:77] Container "5b9be8c5bb121264899fac8d9d36b02150269d41ce96ba6ad36d70b8640cb01c" not found in pod's containers

Jan 23 14:15:31 dc05 kubelet: I0123 14:15:31.678211 26037 kuberuntime_manager.go:383] No ready sandbox for pod "matchdataserver-1255064836-t4b2w_basic(485fd485-1ed6-11e9-8661-0a587f8021ea)" can be found. Need to start a new one

执行命令 cat /proc/buddyinfo 查看 slab，系统不存在大块内存时返回0数量较多。如下所示：

$ cat /proc/buddyinfo

Node 0, zone DMA 1 0 1 0 2 1 1 0 1 1 3

Node 0, zone DMA32 2725 624 489 178 0 0 0 0 0 0 0

Node 0, zone Normal 1163 1101 932 222 0 0 0 0 0 0 0

系统 OOM

内存碎片化严重，系统缺少大页内存，即使是当前系统总内存较多的情况下，也会出现给程序分配内存失败的现象。此时系统会做出内存不够用的误判，认为需要停止一些进程来释放内存，从而导致系统 OOM。

处理步骤

周期性地或者在发现大块内存不足时，先进行 drop_cache 操作。

echo 3 > /proc/sys/vm/drop_caches

必要时执行以下操作进行内存整理。

注意：

请谨慎执行此步骤，该操作开销较大，会造成业务卡顿。

echo 1 > /proc/sys/vm/compact_memory