以下各节的脚本展示了如何跟踪网络相关的函数和剖析（profile）网络活动。
本节展示SystemTap中剖析网络活动的方式。下面的nettop.stp允许我们一窥每个进程的网络流量使用情况。
nettop.stp
#! /usr/bin/env stap
global ifxmit, ifrecv
global ifmerged
probe netdev.transmit
{
ifxmit[pid(), dev_name, execname(), uid()] <<< length
}
probe netdev.receive
{
ifrecv[pid(), dev_name, execname(), uid()] <<< length
}
function print_activity()
{
printf("%5s %5s %-7s %7s %7s %7s %7s %-15s\n",
"PID", "UID", "DEV", "XMIT_PK", "RECV_PK",
"XMIT_KB", "RECV_KB", "COMMAND")
foreach ([pid, dev, exec, uid] in ifrecv) {
ifmerged[pid, dev, exec, uid] += @count(ifrecv[pid,dev,exec,uid]);
}
foreach ([pid, dev, exec, uid] in ifxmit) {
ifmerged[pid, dev, exec, uid] += @count(ifxmit[pid,dev,exec,uid]);
}
foreach ([pid, dev, exec, uid] in ifmerged-) {
n_xmit = @count(ifxmit[pid, dev, exec, uid])
n_recv = @count(ifrecv[pid, dev, exec, uid])
printf("%5d %5d %-7s %7d %7d %7d %7d %-15s\n",
pid, uid, dev, n_xmit, n_recv,
n_xmit ? @sum(ifxmit[pid, dev, exec, uid])/1024 : 0,
n_recv ? @sum(ifrecv[pid, dev, exec, uid])/1024 : 0,
exec)
}
print("\n")
delete ifxmit
delete ifrecv
delete ifmerged
}
probe timer.ms(5000), end, error
{
print_activity()
}注意看print_activity()的这几个表达式：
n_xmit ? @sum(ifxmit[pid, dev, exec, uid])/1024 : 0
n_recv ? @sum(ifrecv[pid, dev, exec, uid])/1024 : 0它们也是if/else语句，等价于如下的伪代码：
if n_recv != 0 then
@sum(ifrecv[pid, dev, exec, uid])/1024
else
0nettop.stp跟踪用了网络流量的进程，并逐个进程输出如下的信息：
eth0、eth1。nettop.stp每隔5秒就会取样一次。你可以修改probe timer.ms(5000)来调整取样间隔。nettop.stp在20秒内的输出如下：
[...]
PID UID DEV XMIT_PK RECV_PK XMIT_KB RECV_KB COMMAND
0 0 eth0 0 5 0 0 swapper
11178 0 eth0 2 0 0 0 synergyc
PID UID DEV XMIT_PK RECV_PK XMIT_KB RECV_KB COMMAND
2886 4 eth0 79 0 5 0 cups-polld
11362 0 eth0 0 61 0 5 firefox
0 0 eth0 3 32 0 3 swapper
2886 4 lo 4 4 0 0 cups-polld
11178 0 eth0 3 0 0 0 synergyc
PID UID DEV XMIT_PK RECV_PK XMIT_KB RECV_KB COMMAND
0 0 eth0 0 6 0 0 swapper
2886 4 lo 2 2 0 0 cups-polld
11178 0 eth0 3 0 0 0 synergyc
3611 0 eth0 0 1 0 0 Xorg
PID UID DEV XMIT_PK RECV_PK XMIT_KB RECV_KB COMMAND
0 0 eth0 3 42 0 2 swapper
11178 0 eth0 43 1 3 0 synergyc
11362 0 eth0 0 7 0 0 firefox
3897 0 eth0 0 1 0 0 multiload-apple
[...]本节展示如何跟踪内核的net/socket.c中的函数的调用情况。这将帮助你从细节上看清各进程是怎么跟内核的网络功能打交道的。
socket-trace.stp
#! /usr/bin/env stap
probe kernel.function("*@net/socket.c").call {
printf ("%s -> %s\n", thread_indent(1), ppfunc())
}
probe kernel.function("*@net/socket.c").return {
printf ("%s <- %s\n", thread_indent(-1), ppfunc())
}socket-trace.stp这个脚本其实在我们之前在第3章介绍thread_indent()的时候已经见过了。下面是它在3秒内的输出：
[...]
0 Xorg(3611): -> sock_poll
3 Xorg(3611): <- sock_poll
0 Xorg(3611): -> sock_poll
3 Xorg(3611): <- sock_poll
0 gnome-terminal(11106): -> sock_poll
5 gnome-terminal(11106): <- sock_poll
0 scim-bridge(3883): -> sock_poll
3 scim-bridge(3883): <- sock_poll
0 scim-bridge(3883): -> sys_socketcall
4 scim-bridge(3883): -> sys_recv
8 scim-bridge(3883): -> sys_recvfrom
12 scim-bridge(3883):-> sock_from_file
16 scim-bridge(3883):<- sock_from_file
20 scim-bridge(3883):-> sock_recvmsg
24 scim-bridge(3883):<- sock_recvmsg
28 scim-bridge(3883): <- sys_recvfrom
31 scim-bridge(3883): <- sys_recv
35 scim-bridge(3883): <- sys_socketcall
[...]本节展示如何监控TCP连接的创建。这可以帮助你第一时间识别出任何未授权的、可疑的或其它不请自来的网络连接。
tcp_connections.stp
#! /usr/bin/env stap
probe begin {
printf("%6s %16s %6s %6s %16s\n",
"UID", "CMD", "PID", "PORT", "IP_SOURCE")
}
probe kernel.function("tcp_accept").return?,
kernel.function("inet_csk_accept").return? {
sock = $return
if (sock != 0)
printf("%6d %16s %6d %6d %16s\n", uid(), execname(), pid(),
inet_get_local_port(sock), inet_get_ip_source(sock))
}当tcp_connections.stp运行时，它会实时输出新创建的TCP连接的如下信息：
UID CMD PID PORT IP_SOURCE
0 sshd 3165 22 10.64.0.227
0 sshd 3165 22 10.64.0.227本节展示如何监控收到的TCP包。这可以帮助你分析应用的流量使用情况。
tcpdumplike.stp
#! /usr/bin/env stap
// A TCP dump like example
probe begin, timer.s(1) {
printf("-----------------------------------------------------------------\n")
printf(" Source IP Dest IP SPort DPort U A P R S F \n")
printf("-----------------------------------------------------------------\n")
}
probe udp.recvmsg /* ,udp.sendmsg */ {
printf(" %15s %15s %5d %5d UDP\n",
saddr, daddr, sport, dport)
}
probe tcp.receive {
printf(" %15s %15s %5d %5d %d %d %d %d %d %d\n",
saddr, daddr, sport, dport, urg, ack, psh, rst, syn, fin)
}当tcpdumplike.stp运行时，它会实时输出收到的TCP包的如下信息：
tcpdumplike.stp使用了以下函数来获取包的标识信息：
上述函数返回1或0来表示包中是否存在对应的标识。
-----------------------------------------------------------------
Source IP Dest IP SPort DPort U A P R S F
-----------------------------------------------------------------
209.85.229.147 10.0.2.15 80 20373 0 1 1 0 0 0
92.122.126.240 10.0.2.15 80 53214 0 1 0 0 1 0
92.122.126.240 10.0.2.15 80 53214 0 1 0 0 0 0
209.85.229.118 10.0.2.15 80 63433 0 1 0 0 1 0
209.85.229.118 10.0.2.15 80 63433 0 1 0 0 0 0
209.85.229.147 10.0.2.15 80 21141 0 1 1 0 0 0
209.85.229.147 10.0.2.15 80 21141 0 1 1 0 0 0
209.85.229.147 10.0.2.15 80 21141 0 1 1 0 0 0
209.85.229.147 10.0.2.15 80 21141 0 1 1 0 0 0
209.85.229.147 10.0.2.15 80 21141 0 1 1 0 0 0
209.85.229.118 10.0.2.15 80 63433 0 1 1 0 0 0
[...]某些情况下Linux网络栈会丢包。有些版本的Linux内核包含静态内核探测点kernel.trace("kfree_skb")，它可以帮助你跟踪包丢掉的原因。dropwatch.stp就使用了它来跟踪丢包；这个脚本每五秒统计一次丢包的位置。
dropwatch.stp
#! /usr/bin/env stap
############################################################
# Dropwatch.stp
# Author: Neil Horman <nhorman@redhat.com>
# An example script to mimic the behavior of the dropwatch utility
# http://fedorahosted.org/dropwatch
############################################################
# Array to hold the list of drop points we find
global locations
# Note when we turn the monitor on and off
probe begin { printf("Monitoring for dropped packets\n") }
probe end { printf("Stopping dropped packet monitor\n") }
# increment a drop counter for every location we drop at
probe kernel.trace("kfree_skb") { locations[$location] <<< 1 }
# Every 5 seconds report our drop locations
probe timer.sec(5)
{
printf("\n")
foreach (l in locations-) {
printf("%d packets dropped at %s\n",
@count(locations[l]), symname(l))
}
delete locations
}kernel.trace("kfree_skb")跟踪内核中网络包被丢弃的位置。它有两个参数：一个指向将被释放的缓冲区的指针$skb，和释放缓冲区时的内核位置$location。如果可以获取$location所存储的内核地址上对应的函数名，dropwatch.stp脚本可以把它的值映射成对应的函数。这个映射默认不会启用。对于1.4及以上的SystemTap，你可以指定--all-modules选项来启用该映射：
stap --all-modules dropwatch.stp在低版本的SystemTap，你可以使用下面的命令模拟--all-modules选项：
stap -dkernel \
`cat /proc/modules | awk 'BEGIN { ORS = " " } {print "-d"$1}'` \
dropwatch.stp运行dropwatch.stp15秒会输出类似下面的结果。输出的结果会按函数名或地址聚合丢包的次数。
Monitoring for dropped packets
1762 packets dropped at unix_stream_recvmsg
4 packets dropped at tun_do_read
2 packets dropped at nf_hook_slow
467 packets dropped at unix_stream_recvmsg
20 packets dropped at nf_hook_slow
6 packets dropped at tun_do_read
446 packets dropped at unix_stream_recvmsg
4 packets dropped at tun_do_read
4 packets dropped at nf_hook_slow
Stopping dropped packet monitor当运行脚本的机器不支持--all-modules和/proc/modules时，symname只会输出原始的地址。你可以通过/boot/System.map-$(uname -r)按地址找出对应的函数。下面的/boot/System.map-$(uname -r)片段中，地址0xffffffff8149a8ed映射到函数unix_stream_recvmsg：
[...]
ffffffff8149a420 t unix_dgram_poll
ffffffff8149a5e0 t unix_stream_recvmsg
ffffffff8149ad00 t unix_find_other
[...]