Question

首先是第一件事。我的系统信息和版本：

$ lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description:    Ubuntu 13.04
Release:    13.04
Codename:   raring

$ sudo docker version
Client version: 0.9.0
Go version (client): go1.2.1
Git commit (client): 2b3fdf2
Server version: 0.9.0
Git commit (server): 2b3fdf2
Go version (server): go1.2.1

$ lxc-version
lxc version: 0.9.0

$ uname -a
Linux ip-10-0-2-86 3.8.0-19-generic #29-Ubuntu SMP Wed Apr 17 18:16:28 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux

在内部进程成为僵尸之后，我无法阻止容器。升级到docker 0.9.0后，我的服务器上看到了大量的僵尸。例如：

$ ps axo stat,ppid,pid,comm | grep -w defunct
Zl   25327 25332 node <defunct>

$ pstree -p
init(1)─┬
        ├─sh(819)───docker(831)─┬
                                ├─lxc-start(25327)───node(25332)───{node}(25378)

我可以看到lxc-start(25327)没有在节点进程25332上调用wait（）来保持僵尸活着。所以我检查了它在使用strace做了什么，它似乎卡在epoll_wait上。 stract实际上最初被卡住了，只是显示了这个：

$sudo strace -ir -ttt -T -v -p 25327
Process 25327 attached - interrupt to quit (when asked to kill)
     0.000103 [    7fe59b9d34b3] epoll_wait(8,

但是在我运行sudo docker kill 3da5764b7bc9358之后我获得了更多输出：

 0.000103 [    7fe59b9d34b3] epoll_wait(8, {{EPOLLIN, {u32=21673408, u64=21673408}}}, 10, 4294967295) = 1 <8.935002>
 8.935097 [    7fe59bcaff60] accept(4, 0, NULL) = 9 <0.000035>
 0.000095 [    7fe59bcafeb3] fcntl(9, F_SETFD, FD_CLOEXEC) = 0 <0.000027>
 0.000083 [    7fe59b9d401a] setsockopt(9, SOL_SOCKET, SO_PASSCRED, [1], 4) = 0 <0.000027>
 0.000089 [    7fe59b9d347a] epoll_ctl(8, EPOLL_CTL_ADD, 9, {EPOLLIN, {u32=21673472, u64=21673472}}) = 0 <0.000023>
 0.000087 [    7fe59b9d34b3] epoll_wait(8, {{EPOLLIN, {u32=21673472, u64=21673472}}}, 10, 4294967295) = 1 <0.000026>
 0.000090 [    7fe59bcb0130] recvmsg(9, {msg_name(0)=NULL, msg_iov(1)=[{"\3\0\0\0\0\0\0\0", 8}], msg_controllen=32, {cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS{pid=773, uid=0, gid=0}}, msg_flags=0}, 0) = 8 <0.000034>
 0.000128 [    7fe59bcb019d] sendto(9, "\0\0\0\0\0\0\0\0\364b\0\0\0\0\0\0\0\0\0\0\0\0\0\0", 24, 0, NULL, 0) = 24 <0.000029>
 0.000090 [    7fe59b9d34b3] epoll_wait(8, {{EPOLLIN|EPOLLHUP, {u32=21673472, u64=21673472}}}, 10, 4294967295) = 1 <0.000018>
 0.000091 [    7fe59bcb0130] recvmsg(9, {msg_name(0)=NULL, msg_iov(1)=[{"\3\0\0\0\0\0\0\0", 8}], msg_controllen=32, {cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS{pid=0, uid=0, gid=0}}, msg_flags=0}, 0) = 0 <0.000026>
 0.000122 [    7fe59b9d347a] epoll_ctl(8, EPOLL_CTL_DEL, 9, NULL) = 0 <0.000037>
 0.000084 [    7fe59bcafd00] close(9) = 0 <0.000048>
 0.000103 [    7fe59b9d34b3] epoll_wait(8, {{EPOLLIN, {u32=21673408, u64=21673408}}}, 10, 4294967295) = 1 <1.091839>
 1.091916 [    7fe59bcaff60] accept(4, 0, NULL) = 9 <0.000035>
 0.000093 [    7fe59bcafeb3] fcntl(9, F_SETFD, FD_CLOEXEC) = 0 <0.000027>
 0.000083 [    7fe59b9d401a] setsockopt(9, SOL_SOCKET, SO_PASSCRED, [1], 4) = 0 <0.000026>
 0.000090 [    7fe59b9d347a] epoll_ctl(8, EPOLL_CTL_ADD, 9, {EPOLLIN, {u32=21673504, u64=21673504}}) = 0 <0.000032>
 0.000100 [    7fe59b9d34b3] epoll_wait(8, {{EPOLLIN, {u32=21673504, u64=21673504}}}, 10, 4294967295) = 1 <0.000028>
 0.000088 [    7fe59bcb0130] recvmsg(9, {msg_name(0)=NULL, msg_iov(1)=[{"\3\0\0\0\0\0\0\0", 8}], msg_controllen=32, {cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS{pid=774, uid=0, gid=0}}, msg_flags=0}, 0) = 8 <0.000030>
 0.000125 [    7fe59bcb019d] sendto(9, "\0\0\0\0\0\0\0\0\364b\0\0\0\0\0\0\0\0\0\0\0\0\0\0", 24, 0, NULL, 0) = 24 <0.000032>
 0.000119 [    7fe59b9d34b3] epoll_wait(8, {{EPOLLIN|EPOLLHUP, {u32=21673504, u64=21673504}}}, 10, 4294967295) = 1 <0.000071>
 0.000139 [    7fe59bcb0130] recvmsg(9, {msg_name(0)=NULL, msg_iov(1)=[{"\3\0\0\0\0\0\0\0", 8}], msg_controllen=32, {cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS{pid=0, uid=0, gid=0}}, msg_flags=0}, 0) = 0 <0.000018>
 0.000112 [    7fe59b9d347a] epoll_ctl(8, EPOLL_CTL_DEL, 9, NULL) = 0 <0.000028>
 0.000076 [    7fe59bcafd00] close(9) = 0 <0.000027>
 0.000096 [    7fe59b9d34b3] epoll_wait(8,

然后我看了一下epoll_wait正在等什么看起来像文件8（我猜这是epoll_wait(8, {{EPOLLIN, {u32=21673408, u64=21673408}}}, 10, 4294967295) = 1 <8.935002>的形式int epoll_wait(int epfd, struct epoll_event *events, int maxevents, int timeout);

$ cat /proc/25327/fdinfo/8
pos:    0
flags:  02000002
tfd:        7 events:       19 data:          14ab830
tfd:        4 events:       19 data:          14ab5c0

还根据上面的tfd添加7和4（不确定tfd到底意味着什么）

$ cat /proc/25327/fdinfo/4
pos:    0
flags:  02000002
$ cat /proc/25327/fdinfo/7
pos:    0
flags:  02000002
sigmask:    fffffffe7ffbfab7
$ cd /proc/25327/fd
$ ls -al
lr-x------ 1 root root 64 Mar 13 22:28 0 -> /dev/null
lrwx------ 1 root root 64 Mar 13 22:28 1 -> /dev/pts/17
lrwx------ 1 root root 64 Mar 13 22:28 2 -> /dev/pts/17
l-wx------ 1 root root 64 Mar 13 22:28 3 -> /var/log/lxc/3da5764b7bc935896a72abc9371ce68d4d658d8c70b56e1090aacb631080ec0e.log
lrwx------ 1 root root 64 Mar 13 22:28 4 -> socket:[48415]
lrwx------ 1 root root 64 Mar 14 00:03 5 -> /dev/ptmx
lrwx------ 1 root root 64 Mar 14 00:03 6 -> /dev/pts/18
lrwx------ 1 root root 64 Mar 14 00:03 7 -> anon_inode:[signalfd]
lrwx------ 1 root root 64 Mar 14 00:03 8 -> anon_inode:[eventpoll]

关于socket的信息：

$ sudo netstat -anp | grep 48415
Proto RefCnt Flags       Type       State         I-Node   PID/Program name    Path
unix  2      [ ACC ]     STREAM     LISTENING     48415    25327/lxc-start     @/var/lib/lxc/3da5764b7bc935896a72abc9371ce68d4d658d8c70b56e1090aacb631080ec0e/command

在docker.log中似乎有一个共同的模式，所有不停止的容器都有这个签名：

2014/03/16 16:33:15 Container beb71548b3b23ba3337ca30c6c2efcbfcaf19d4638cf3d5ec5b8a3e4c5f1059a failed to exit within 0 seconds of SIGTERM - using the force
2014/03/16 16:33:25 Container SIGKILL failed to exit within 10 seconds of lxc-kill beb71548b3b2 - trying direct SIGKILL

此时我不知道接下来该做什么。关于如何找出导致这些容器不能退出的原因的任何建议？我应该收集的任何其他数据？我也向这个过程发送了SIGCHLD但没有用。

更多数据：将日志添加到节点进程的末尾，我们开始在容器中使用start命令：

Mon Mar 17 2014 20:52:52 GMT+0000 (UTC) process: main process = exit code: 0

这里是来自docker的日志：

2014/03/17 20:52:52 Container f8a3d55e0f... failed to exit within 0 seconds of SIGTERM - using the force
2014/03/17 20:53:02 Container SIGKILL failed to exit within 10 seconds of lxc-kill f8a3d55e0fd8 - trying direct SIGKILL

时间戳显示进程已退出@ 20:52:52

使用native和lxc docker驱动程序会发生这种情况。

编辑：重播步骤！

将其转换为bash脚本并运行并观看近50％的容器变成僵尸！

CNT=0
while true
do 
  echo $CNT
  DOCK=$(sudo docker run -d -t anandkumarpatel/zombie_bug ./node index.js)
  sleep 60 && sudo docker stop $DOCK > out.log &
  sleep 1
  CNT=$(($CNT+1))
  if [[ "$CNT" == "50" ]]; then
    exit
  fi
done

Answer 1

更改为最新内核修复了问题

发现确切的内核差异：
REPRO：linux-image-3.8.0-31-generic
NO REPRO：linux-image-3.8.0-32-generic

我认为这是解决方法：

+++ linux-3.8.0/kernel/pid_namespace.c
@@ -181,6 +181,7 @@
    int nr;
    int rc;
    struct task_struct *task, *me = current;
+   int init_pids = thread_group_leader(me) ? 1 : 2;

    /* Don't allow any more processes into the pid namespace */
    disable_pid_allocation(pid_ns);
@@ -230,7 +231,7 @@
     */
    for (;;) {
        set_current_state(TASK_UNINTERRUPTIBLE);
-       if (pid_ns->nr_hashed == 1)
+       if (pid_ns->nr_hashed == init_pids)
            break;
        schedule();
    }

来自这里： https://groups.google.com/forum/#!msg/fa.linux.kernel/u4b3n4oYDQ4/GuLrXfDIYggJ

将升级所有重新启动它的服务器并查看它是否仍然存在。

Answer 2

观察SLES 12 SP 1上没有可停靠的Docker容器（自3周起运行）

在docker exec -it命令后面显示以下错误消息：

rpc错误：代码= 13 desc =无效的头字段值“oci运行时错误：exec失败：container_linux.go：247：启动容器进程导致\“process_linux.go：83：执行setns进程导致\\”退出状态16 \\“\”\ n“

Linux内核：3.12.62-60.64.8-default

Docker版本1.12.2，构建8eab29e

在运行命令变成僵尸后，Docker容器拒绝被杀死

2 个答案: