论坛徽章:: 0

电梯直达

1楼 [收藏(0)] [报告]

发表于 2012-11-07 14:24 |只看该作者 |倒序浏览

操作系统：redhat-os 6.2
硬件平台：SUGON服务器

使用KVM虚拟出来的机器，通过抓包发现，会在同一个网断内，非常频繁的发送IGMP的组播包，造成交换机CPU过高。
物理机上:
#brctl show
onebr1149             8000.00e0ed1ce77c    no             bond1.1149
                                                      vnet0
虚拟机上:
# tcpdump -i eth0 -p igmp
tcpdump: verbose output suppressed, use -v or -vv for full protocol decode
listening on eth0, link-type EN10MB (Ethernet), capture size 65535 bytes
14:19:02.190291 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:02.283960 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:05.106707 IP 192.168.124.107 > 224.0.0.251: igmp v2 report 224.0.0.251
14:19:06.115417 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:08.273780 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:09.153157 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:10.239935 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:11.314077 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:12.018703 IP 192.168.124.107 > 224.0.0.251: igmp v2 report 224.0.0.251
14:19:13.424009 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:15.445067 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:15.967668 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:16.076040 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:17.217732 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:19.094567 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:20.275401 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2
14:19:20.648091 IP 0.0.0.0 > all-systems.mcast.net: igmp query v2

从以上看到，从本机发出的IGMP包几乎每秒都有数据包发出。

# netstat -g
IPv6/IPv4 Group Memberships
Interface    RefCnt Group
--------------- ------ ---------------------
lo             1    all-systems.mcast.net
eth0          1    224.0.0.251
eth0          1    all-systems.mcast.net
lo             1    ff02::1
eth0          1    ff02::202
eth0          1    ff02::1:ffa8:7c6b
eth0          1    ff02::1

想知道这是什么原因导致的？或者能够track到具体是的程序触发的吗？