systemd-udevd - CPU usage high 98%

[Latenights]

Yesteday this started. The top command shows

Code: Select all

 PID USER      PR  NI    VIRT    RES    SHR S  %CPU %MEM     TIME+ COMMAND
 852 root      20   0  315772 268696   1076 R  98.0  7.2  15:58.83 systemd-udevd
7334 root      20   0  243728 198048   1112 R  25.6  5.3   3:53.25 systemd-udevd

I did an strace and found this seems to be looping. But I don't know what it is

Code: Select all

strace: Process 903 attached
read(7, "\226\371\0\0\0\200\0\0\0\0\0\0\0\0\0\0", 272) = 16
readlink("/run/udev/watch/63894", 0x7ffe8485d470, 512) = -1 ENOENT (No such file or directory)
open("/run/udev/queue", O_WRONLY|O_CREAT|O_TRUNC|O_NOFOLLOW|O_CLOEXEC, 0444) = 12
close(12)                               = 0
epoll_wait(11, [{EPOLLIN, {u32=4, u64=4}}, {EPOLLIN, {u32=9, u64=9}}], 8, 3000) = 2
recvfrom(9, "?q\0\0\0\0\0\0", 8, MSG_DONTWAIT, NULL, NULL) = 8
recvfrom(9, 0x7ffe8485db50, 8, MSG_DONTWAIT, NULL, NULL) = -1 EAGAIN (Resource temporarily unavailable)
recvmsg(4, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000001}, msg_iov(1)=[{"change@/devices/pci0000:00/0000:"..., 8192}], msg_controllen=32, [{cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS, {pid=0, uid=0, gid=0}}], msg_flags=0}, 0) = 289
sendmsg(4, {msg_name(12)={sa_family=AF_NETLINK, pid=903, groups=00000000}, msg_iov(2)=[{"libudev\0\376\355\312\376(\0\0\0(\0\0\0\362\0\0\0\360\3\35\267{\313\305\356"..., 40}, {"ACTION=change\0DEVNAME=/dev/sdb\0D"..., 242}], msg_controllen=0, msg_flags=0}, 0) = 282
open("/run/udev/queue", O_WRONLY|O_CREAT|O_TRUNC|O_NOFOLLOW|O_CLOEXEC, 0444) = 12
close(12)                               = 0
open("/run/udev/queue", O_WRONLY|O_CREAT|O_TRUNC|O_NOFOLLOW|O_CLOEXEC, 0444) = 12
close(12)                               = 0
epoll_wait(11, [{EPOLLIN, {u32=4, u64=4}}, {EPOLLIN, {u32=7, u64=7}}], 8, 3000) = 2
recvmsg(4, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000001}, msg_iov(1)=[{"change@/devices/pci0000:00/0000:"..., 8192}], msg_controllen=32, [{cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS, {pid=0, uid=0, gid=0}}], msg_flags=0}, 0) = 309
read(7, "\227\371\0\0\0\200\0\0\0\0\0\0\0\0\0\0", 272) = 16
readlink("/run/udev/watch/63895", 0x7ffe8485d470, 512) = -1 ENOENT (No such file or directory)
open("/run/udev/queue", O_WRONLY|O_CREAT|O_TRUNC|O_NOFOLLOW|O_CLOEXEC, 0444) = 12
close(12)                               = 0
epoll_wait(11, [{EPOLLIN, {u32=4, u64=4}}], 8, 3000) = 1
recvmsg(4, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000001}, msg_iov(1)=[{"change@/devices/pci0000:00/0000:"..., 8192}], msg_controllen=32, [{cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS, {pid=0, uid=0, gid=0}}], msg_flags=0}, 0) = 289
open("/run/udev/queue", O_WRONLY|O_CREAT|O_TRUNC|O_NOFOLLOW|O_CLOEXEC, 0444) = 12
close(12)                               = 0
open("/run/udev/queue", O_WRONLY|O_CREAT|O_TRUNC|O_NOFOLLOW|O_CLOEXEC, 0444) = 12
close(12)                               = 0
epoll_wait(11, [{EPOLLIN, {u32=4, u64=4}}, {EPOLLIN, {u32=9, u64=9}}], 8, 3000) = 2
recvfrom(9, "?q\0\0\0\0\0\0", 8, MSG_DONTWAIT, NULL, NULL) = 8
recvfrom(9, 0x7ffe8485db50, 8, MSG_DONTWAIT, NULL, NULL) = -1 EAGAIN (Resource temporarily unavailable)

goes forever.

I reboot but it starts again a few minutes later

What is the problem?

[hunter86_bg]

Most probably you are running an old CentOS 7.3 or 7.4 .
Update the system and try again.