Merge pull request iovisor#1618 from rmanyari/tool-tcpsubnet

Tool tcpsubnet

README.md

@@ -82,6 +82,7 @@ pair of .c and .py files, and some are directories of files.
 #### Tools:
 <center><a href="images/bcc_tracing_tools_2017.png"><img src="images/bcc_tracing_tools_2017.png" border=0 width=700></a></center>
 
+
 - tools/[argdist](tools/argdist.py): Display function parameter values as a histogram or frequency count. [Examples](tools/argdist_example.txt).
 - tools/[bashreadline](tools/bashreadline.py): Print entered bash commands system wide. [Examples](tools/bashreadline_example.txt).
 - tools/[biolatency](tools/biolatency.py): Summarize block device I/O latency as a histogram. [Examples](tools/biolatency_example.txt).
@@ -140,6 +141,7 @@ pair of .c and .py files, and some are directories of files.
 - tools/[tcpconnlat](tools/tcpconnlat.py): Trace TCP active connection latency (connect()). [Examples](tools/tcpconnlat_example.txt).
 - tools/[tcplife](tools/tcplife.py): Trace TCP sessions and summarize lifespan. [Examples](tools/tcplife_example.txt).
 - tools/[tcpretrans](tools/tcpretrans.py): Trace TCP retransmits and TLPs. [Examples](tools/tcpretrans_example.txt).
+- tools/[tcpsubnet](tools/tcpsubnet.py): Summarize and aggregate TCP send by subnet. [Examples](tools/tcpsubnet_example.txt).
 - tools/[tcptop](tools/tcptop.py): Summarize TCP send/recv throughput by host. Top for TCP. [Examples](tools/tcptop_example.txt).
 - tools/[tcptracer](tools/tcptracer.py): Trace TCP established connections (connect(), accept(), close()). [Examples](tools/tcptracer_example.txt).
 - tools/[tplist](tools/tplist.py): Display kernel tracepoints or USDT probes and their formats. [Examples](tools/tplist_example.txt).

man/man8/tcpsubnet.8

@@ -0,0 +1,100 @@
+.TH tcpsubnet 8 "2018-03-01" "USER COMMANDS"
+.SH NAME
+tcpsubnet \- Summarize and aggregate IPv4 TCP traffic by subnet.
+.SH SYNOPSIS
+.B tcpsubnet [\-h] [\-v] [\--ebpf] [\-J] [\-f FORMAT] [\-i INTERVAL] [subnets]
+.SH DESCRIPTION
+This tool summarizes and aggregates IPv4 TCP sent to the subnets
+passed in argument and prints to stdout on a fixed interval.
+
+This uses dynamic tracing of kernel TCP send/receive functions, and will
+need to be updated to match kernel changes.
+
+The traced data is summarized in-kernel using a BPF map to reduce overhead.
+At very high TCP event rates, the overhead may still be measurable.
+See the OVERHEAD section for more details.
+
+Since this uses BPF, only the root user can use this tool.
+.SH REQUIREMENTS
+CONFIG_BPF and bcc.
+.SH OPTIONS
+.TP
+\-h
+Print USAGE message.
+.TP
+\-v
+Run in verbose mode. Will output subnet evaluation and the BPF program
+.TP
+\-J
+Format output in JSON.
+.TP
+\-i
+Interval between updates, seconds (default 1).
+.TP
+\-f
+Format output units. Supported values are bkmBKM. When using
+kmKM the output will be rounded to floor.
+.TP
+\--ebpf
+Prints the BPF program.
+.TP
+subnets
+Comma separated list of subnets. Traffic will be categorized
+in theses subnets. Order matters.
+(default 127.0.0.1/32,10.0.0.0/8,172.16.0.0/12,192.168.0.0/16,0.0.0.0/0)
+.SH EXAMPLES
+.TP
+Summarize TCP traffic by the default subnets:
+#
+.B tcpsubnet
+.TP
+Summarize all TCP traffic:
+#
+.B tcpsubnet 0.0.0.0/0
+.TP
+Summarize all TCP traffic and output in JSON and Kb:
+#
+.B tcpsubnet -J -fk 0.0.0.0/0
+.SH FIELDS
+.TP
+(Standad output) Left hand side column:
+Subnet
+.TP
+(Standard output) Right hand side column:
+Aggregate traffic in units passed as argument
+.TP
+(JSON output) date
+Current date formatted in the system locale
+.TP
+(JSON output) time
+Current time formatted in the system locale
+.TP
+(JSON output) entries
+Map of subnets to aggregates. Values will be in format passed to -f
+.SH OVERHEAD
+This traces all tcp_sendmsg function calls in the TCP/IP stack.
+It summarizes data in-kernel to reduce overhead.
+A simple iperf test (v2.0.5) with the default values shows a loss
+of ~5% throughput. On 10 runs without tcpsubnet running the average
+throughput was 32.42Gb/s, with tcpsubnet enabled it was 31.26Gb/s.
+This is not meant to be used as a long running service. Use it
+for troubleshooting or for a controlled interval. As always,
+try it out in a test environment first.
+
+.SH SOURCE
+This is from bcc.
+.IP
+https://github.com/iovisor/bcc
+.PP
+Also look in the bcc distribution for a companion _examples.txt file containing
+example usage, output, and commentary for this tool.
+.SH OS
+Linux
+.SH STABILITY
+Unstable - in development.
+.SH AUTHOR
+Rodrigo Manyari
+.SH INSPIRATION
+tcptop(8) by Brendan Gregg
+.SH SEE ALSO
+netlink(7)

tools/tcpsubnet.py

@@ -0,0 +1,264 @@
+#!/usr/bin/python
+# @lint-avoid-python-3-compatibility-imports
+#
+# tcpsubnet Summarize TCP bytes sent to different subnets.
+# For Linux, uses BCC, eBPF. Embedded C.
+#
+# USAGE: tcpsubnet [-h] [-v] [--ebpf] [-J] [-f FORMAT] [-i INTERVAL] [subnets]
+#
+# This uses dynamic tracing of kernel functions, and will need to be updated
+# to match kernel changes.
+#
+# This is an adaptation of tcptop from written by Brendan Gregg.
+#
+# WARNING: This traces all send at the TCP level, and while it
+# summarizes data in-kernel to reduce overhead, there may still be some
+# overhead at high TCP send/receive rates (eg, ~13% of one CPU at 100k TCP
+# events/sec. This is not the same as packet rate: funccount can be used to
+# count the kprobes below to find out the TCP rate). Test in a lab environment
+# first. If your send rate is low (eg, <1k/sec) then the overhead is
+# expected to be negligible.
+#
+# Copyright 2017 Rodrigo Manyari
+# Licensed under the Apache License, Version 2.0 (the "License")
+#
+# 03-Oct-2017 Rodrigo Manyari Created this based on tcptop.
+# 13-Feb-2018 Rodrigo Manyari Fix pep8 errors, some refactoring.
+# 05-Mar-2018 Rodrigo Manyari Add date time to output.
+
+import argparse
+import json
+import logging
+import struct
+import socket
+from bcc import BPF
+from datetime import datetime as dt
+from time import sleep
+
+# arguments
+examples = """examples:
+ ./tcpsubnet # Trace TCP sent to the default subnets:
+ # 127.0.0.1/32,10.0.0.0/8,172.16.0.0/12,
+ # 192.168.0.0/16,0.0.0.0/0
+ ./tcpsubnet -f K # Trace TCP sent to the default subnets
+ # aggregated in KBytes.
+ ./tcpsubnet 10.80.0.0/24 # Trace TCP sent to 10.80.0.0/24 only
+ ./tcpsubnet -J # Format the output in JSON.
+"""
+
+default_subnets = "127.0.0.1/32,10.0.0.0/8," \
+ "172.16.0.0/12,192.168.0.0/16,0.0.0.0/0"
+
+parser = argparse.ArgumentParser(
+ description="Summarize TCP send and aggregate by subnet",
+ formatter_class=argparse.RawDescriptionHelpFormatter,
+ epilog=examples)
+parser.add_argument("subnets", help="comma separated list of subnets",
+ type=str, nargs="?", default=default_subnets)
+parser.add_argument("-v", "--verbose", action="store_true",
+ help="output debug statements")
+parser.add_argument("-J", "--json", action="store_true",
+ help="format output in JSON")
+parser.add_argument("--ebpf", action="store_true",
+ help=argparse.SUPPRESS)
+parser.add_argument("-f", "--format", default="B",
+ help="[bkmBKM] format to report: bits, Kbits, Mbits, bytes, " +
+ "KBytes, MBytes (default B)", choices=["b", "k", "m", "B", "K", "M"])
+parser.add_argument("-i", "--interval", default=1, type=int,
+ help="output interval, in seconds (default 1)")
+args = parser.parse_args()
+
+level = logging.INFO
+if args.verbose:
+ level = logging.DEBUG
+
+logging.basicConfig(level=level)
+
+logging.debug("Starting with the following args:")
+logging.debug(args)
+
+# args checking
+if int(args.interval) <= 0:
+ logging.error("Invalid interval, must be > 0. Exiting.")
+ exit(1)
+else:
+ args.interval = int(args.interval)
+
+# map of supported formats
+formats = {
+ "b": lambda x: (x * 8),
+ "k": lambda x: ((x * 8) / 1024),
+ "m": lambda x: ((x * 8) / pow(1024, 2)),
+ "B": lambda x: x,
+ "K": lambda x: x / 1024,
+ "M": lambda x: x / pow(1024, 2)
+}
+
+# Let's swap the string with the actual numeric value
+# once here so we don't have to do it on every interval
+formatFn = formats[args.format]
+
+# define the basic structure of the BPF program
+bpf_text = """
+#include <uapi/linux/ptrace.h>
+#include <net/sock.h>
+#include <bcc/proto.h>
+
+struct index_key_t {
+ u32 index;
+};
+
+BPF_HASH(ipv4_send_bytes, struct index_key_t);
+
+int kprobe__tcp_sendmsg(struct pt_regs *ctx, struct sock *sk,
+ struct msghdr *msg, size_t size)
+{
+ u16 family = sk->__sk_common.skc_family;
+ u64 *val, zero = 0;
+
+ if (family == AF_INET) {
+ u32 dst = sk->__sk_common.skc_daddr;
+ unsigned categorized = 0;
+ __SUBNETS__
+ }
+ return 0;
+}
+"""
+
+
+# Takes in a mask and returns the integer equivalent
+# e.g.
+# mask_to_int(8) returns 4278190080
+def mask_to_int(n):
+ return ((1 << n) - 1) << (32 - n)
+
+# Takes in a list of subnets and returns a list
+# of tuple-3 containing:
+# - The subnet info at index 0
+# - The addr portion as an int at index 1
+# - The mask portion as an int at index 2
+#
+# e.g.
+# parse_subnets([10.10.0.0/24]) returns
+# [
+# ['10.10.0.0/24', 168427520, 4294967040],
+# ]
+def parse_subnets(subnets):
+ m = []
+ for s in subnets:
+ parts = s.split("/")
+ if len(parts) != 2:
+ msg = "Subnet [%s] is invalid, please refer to the examples." % s
+ raise ValueError(msg)
+ netaddr_int = 0
+ mask_int = 0
+ try:
+ netaddr_int = struct.unpack("!I", socket.inet_aton(parts[0]))[0]
+ except:
+ msg = ("Invalid net address in subnet [%s], " +
+ "please refer to the examples.") % s
+ raise ValueError(msg)
+ try:
+ mask_int = int(parts[1])
+ except:
+ msg = "Invalid mask in subnet [%s]. Mask must be an int" % s
+ raise ValueError(msg)
+ if mask_int < 0 or mask_int > 32:
+ msg = ("Invalid mask in subnet [%s]. Must be an " +
+ "int between 0 and 32.") % s
+ raise ValueError(msg)
+ mask_int = mask_to_int(int(parts[1]))
+ m.append([s, netaddr_int, mask_int])
+ return m
+
+def generate_bpf_subnets(subnets):
+ template = """
+ if (!categorized && (__NET_ADDR__ & __NET_MASK__) ==
+ (dst & __NET_MASK__)) {
+ struct index_key_t key = {.index = __POS__};
+ val = ipv4_send_bytes.lookup_or_init(&key, &zero);
+ categorized = 1;
+ (*val) += size;
+ }
+ """
+ bpf = ''
+ for i, s in enumerate(subnets):
+ branch = template
+ branch = branch.replace("__NET_ADDR__", str(socket.htonl(s[1])))
+ branch = branch.replace("__NET_MASK__", str(socket.htonl(s[2])))
+ branch = branch.replace("__POS__", str(i))
+ bpf += branch
+ return bpf
+
+subnets = []
+if args.subnets:
+ subnets = args.subnets.split(",")
+
+subnets = parse_subnets(subnets)
+
+logging.debug("Packets are going to be categorized in the following subnets:")
+logging.debug(subnets)
+
+bpf_subnets = generate_bpf_subnets(subnets)
+
+# initialize BPF
+bpf_text = bpf_text.replace("__SUBNETS__", bpf_subnets)
+
+logging.debug("Done preprocessing the BPF program, " +
+ "this is what will actually get executed:")
+logging.debug(bpf_text)
+
+if args.ebpf:
+ print(bpf_text)
+ exit()
+
+b = BPF(text=bpf_text)
+
+ipv4_send_bytes = b["ipv4_send_bytes"]
+
+if not args.json:
+ print("Tracing... Output every %d secs. Hit Ctrl-C to end" % args.interval)
+
+# output
+exiting = 0
+while (1):
+
+ try:
+ sleep(args.interval)
+ except KeyboardInterrupt:
+ exiting = 1
+
+ # IPv4: build dict of all seen keys
+ keys = ipv4_send_bytes
+ for k, v in ipv4_send_bytes.items():
+ if k not in keys:
+ keys[k] = v
+
+ # to hold json data
+ data = {}
+
+ # output
+ now = dt.now()
+ data['date'] = now.strftime('%x')
+ data['time'] = now.strftime('%X')
+ data['entries'] = {}
+ if not args.json:
+ print(now.strftime('[%x %X]'))
+ for k, v in reversed(sorted(keys.items(), key=lambda keys: keys[1].value)):
+ send_bytes = 0
+ if k in ipv4_send_bytes:
+ send_bytes = int(ipv4_send_bytes[k].value)
+ subnet = subnets[k.index][0]
+ send = formatFn(send_bytes)
+ if args.json:
+ data['entries'][subnet] = send
+ else:
+ print("%-21s %6d" % (subnet, send))
+
+ if args.json:
+ print(json.dumps(data))
+
+ ipv4_send_bytes.clear()
+
+ if exiting:
+ exit(0)