template roll

飯坂剛一

Version:4.3

Release: Oct 2007

Copyright 2007

概要

scsdiagロールはNPACI Rocksへダイアグコマンドを 追加するためのロールです。

追加されるコマンド

scsdiagロールによって追加されるコマンドは以下のものになります。

フロントエンドノードだけにインストールされるツール

フロントエンドノードと計算ノード両方にインストールされるツール

コマンドの概要


Name        : arpalert
URL         : http://www.arpalert.org/
Summary     : Monitor ethernet networks
Description :
arpalert listens on a network interface (without using 'promiscuous' mode)
and catches all conversations of MAC address to IP request.

It then compares the mac addresses it detected with a pre-configured list
of authorized MAC addresses. If the MAC is not in list, arpalert launches
a pre-defined user script with the MAC address and IP address as parameters.
This software can run in daemon mode; it's very fast (low CPU and memory
consumption).
Name        : atop
URL         : ftp://ftp.atcomputing.nl/pub/tools/linux/
Summary     : AT Computing System and Process Monitor
Description :
The program atop is an interactive monitor to view the load on
a Linux-system. It shows the occupation of the most critical
hardware-resources (from a performance point of view) on system-level,
i.e. cpu, memory, disk and network. It also shows which processes are
responsible for the indicated load (again cpu-, memory-, disk- and
network-load on process-level).

The program atop can also be used to log system- and process-level
information in raw format for long-term analysis.
Name        : bandwidth
URL         : http://home.comcast.net/~fbui/bandwidth.html
Summary     : Artificial benchmark for measuring memory bandwidth
Description :
bandwidth is an artificial benchmark for measuring memory bandwidth,
useful for identifying a computer's weak areas.
Name        : bing
URL         : http://web.cnam.fr/reseau/bing.html
Summary     : Measures bandwidth between two point-to-point connections
Description :
Bing determines the real (raw, as opposed to available or average)
throughput on a link by measuring ICMP echo requests roundtrip times
for different packet sizes for each end of the link.
Name        : bmon
URL         : http://people.suug.ch/~tgr/bmon/
Summary     : Console interface bandwidth usage monitor
Description :
bmon is an interface bandwidth monitor.
Name        : bonnie++
URL         : http://www.coker.com.au/bonnie++/
Summary     : Benchmark suite for hard drive and file system performance
Description :
Bonnie++ is a benchmark suite that is aimed at performing a number of
simple tests of hard drive and file system performance. Then you can
decide which test is important and decide how to compare different
systems after running it. I have no plans to ever have it produce a
single number, because I don't think that a single number can be useful
when comparing such things.
Name        : bwm
URL         : http://packages.debian.org/unstable/net/bwm.html
Summary     : Bandwidth Monitor
Description :
Bandwidth monitor is a very simple utility that allows the user to
view the bandwidth currently being consumed to and from each network
interface, the total bandwidth in use on each interface, and the total
bandwidth in use on all interfaces.
Name        : bwm-ng
URL         : http://www.gropp.org/
Summary     : Curses based bandwidth monitor
Description :
Bandwidth Monitor NG is a small and simple console-based live bandwidth
monitor.

Short list of features:
- supports /proc/net/dev, netstat, getifaddr, sysctl, kstat and libstatgrab
- unlimited number of interfaces supported
- interfaces are added or removed dynamically from list
- white-/blacklist of interfaces
- output of KB/s, Kb/s, packets, errors, average, max and total sum
- output in curses, plain console, CSV or HTML
- configfile
Name        : coretrace
URL         : http://www.arbetsmyra.dyndns.org/coretrace/
Summary     : Tool for debugging of embedded Linux applications
Description :
Coretrace is a tool for debugging of embedded Linux applications. It works
by analysing core files from crashed applications and outputs a short
plain-text backtrace, suitable for putting into logfiles.
Name        : darkstat
URL         : http://dmr.ath.cx/net/darkstat/
Summary     : Network traffic analyzer
Description :
darkstat is a network traffic analyzer. It's basically a packet sniffer
which runs as a background process on a cable/DSL router and gathers
all sorts of useless but interesting statistics.
Name        : dhcpdump
URL         : http://sourceforge.net/projects/mavetju/
Summary     : Parse tcpdump DHCP packets
Description :
dhcpdump is a tool to post-process tcpdump output in order analyse
sniffed DHCP packets.
Name        : dhcping
URL         : http://sourceforge.net/projects/mavetju/
Summary     : DHCP daemon ping program
Description :
Dhcping allows the system administrator to check if a remote DHCP
server is still functioning.
Name        : dstat
URL         : http://dag.wieers.com/home-made/dstat/
Summary     : Versatile vmstat, iostat and ifstat replacement
Description :
Dstat is a versatile replacement for vmstat, iostat and ifstat. Dstat
overcomes some of the limitations and adds some extra features.

Dstat allows you to view all of your system resources instantly,
you can eg. compare disk usage in combination with interrupts from
your IDE controller, or compare the network bandwidth numbers
directly with the disk throughput (in the same interval).

Dstat also cleverly gives you the most detailed information in
columns and clearly indicates in what magnitude and unit the output
is displayed. Less confusion, less mistakes.

Dstat is also unique in letting you aggregate block device throughput
for a certain diskset or network bandwidth for a group of interfaces,
ie. you can see the throughput for all the block devices that make up
a single filesystem or storage system.

You can customize your dstat output from /etc/dstat.conf and you can
write your own dstat modules to plug into the dstat output.

Dstat's output, in its current form, is not very useful to be post-
processed by other tools. It's mostly meant for allowing humans to
interprete real-time data as easy as possible.
Name        : filelight
URL         : http://www.methylblue.com/filelight/
Summary     : Graphical disk usage statistics
Description :
Filelight graphically represents a file system as a set of concentric
segmented-rings, indicating where diskspace is being used. Segments
expanding from the center represent files (including directories),
with each segment's size being proportional to the file's size and
directories having child segments.
Name        : fio
Summary     : I/O benchmark and stress/hardware verification tool
Description :
fio is an I/O tool meant to be used both for benchmark and stress/hardware
verification. It has support for 6 different types of I/O engines (sync,
mmap, libaio, posixaio, SG v3, splice), I/O priorities (for newer Linux
kernels), rate I/O, forked or threaded jobs, and much more.

It can work on block devices as well as files. fio accepts job descriptions
in a simple-to-understand text format. Several example job files are included.
fio displays all sorts of I/O performance information, such as completion and
submission latencies (avg/mean/deviation), bandwidth stats, CPU, and disk
utilization, and more. It supports Linux, FreeBSD, and OpenSolaris.
Name        : fping
URL         : http://www.fping.com/
Summary     : Utility to ping multiple hosts at once
Description :
fping is a ping-like program which uses the Internet Control Message
Protocol (ICMP) echo request to determine if a target host is responding.

fping is different from ping in that you can specify any number of hosts
on the command line, or specify a file containing the lists of hosts to
ping. Instead of trying one host until it timeouts or replies, fping will
send out a ping packet and move on to the next host in a round-robin fashion.

If a host replies, it is noted and removed from the list of hosts to check.
If a host does not respond within a certain time limit and/or retry limit it
will be considered unreachable.
Name        : iftop
URL         : http://www.ex-parrot.com/~pdw/iftop/
Summary     : Display bandwidth usage on an interface
Description :
iftop does for network usage what top(1) does for CPU usage. It listens
to network traffic on a named interface and displays a table of current
bandwidth usage by pairs of hosts. Handy for answering the question
"why is our ADSL link so slow?".
Name        : iogen
URL         : http://www.peereboom.us/iogen/
Summary     : I/O generator
Description :
iogen is an I/O generator. It forks child processes that each run a mix
of reads and writes. The idea is to generate heavily fragmented files
to make the hardware suffer as much as possible. This tool has been
used to test filesystems, drivers, firmware, and hardware devices.

It is by no means meant as a performance measuring tool since it tries
to recreate the worst case scenario I/O.
Name        : netperf
URL         : http://www.netperf.org/netperf/NetperfPage.html
Summary     : Performance testing tool for TCP/UDP
Description :
Netperf is a tool to measure TCP/UDP performance.
Name        : netpipe
URL         : http://www.scl.ameslab.gov/netpipe/
Summary     : Protocol independent performance tool
Description :
NetPIPE is a protocol independent performance tool that visually represents
the network performance under a variety of conditions. It performs simple
ping-pong tests, bouncing messages of increasing size between two processes,
whether across a network or within an SMP system. Message sizes are chosen
at regular intervals, and with slight perturbations, to provide a complete
test of the communication system. Each data point involves many ping-pong
tests to provide an accurate timing. Latencies are calculated by dividing
the round trip time in half for small messages ( < 64 Bytes ).
Name        : nettop
URL         : http://srp.portico.org/scripts/
Summary     : Top like program for network activity
Description :
This program was written as a top like program for
network activity. It is licensed under a BSD type
license, so you are free to do pretty much as you
like with this.
Name        : nfswatch
URL         : http://nfswatch.sourceforge.net/
Summary     : Command line tool to monitor NFS traffic
Description :
nfswatch is a command-line tool for monitoring NFS traffic. nfswatch
can capture and analyze the NFS packets on a particular network
interface or on all interfaces.
Name        : nload
URL         : http://www.roland-riegel.de/nload/
Summary     : Console application which monitors network traffic and bandwidth usage in real time
Description :
nload is a console application which monitors network traffic and bandwidth
usage in real time. It visualizes the in and outgoing traffic using two graphs
and provides additional info like total amount of transfered data and min/max
network usage.
Name        : stress
URL         : http://weather.ou.edu/~apw/projects/stress/
Summary     : tool to impose stress on a POSIX-compliant operating system
Description :
Stress is a tool which imposes a configurable amount of CPU, memory, I/O,
or disk stress on a POSIX-compliant operating system. Stress is written
in highly-portable ANSI C, and uses the GNU Autotools to compile on a
great number of UNIX-like operating systems.

Stress is not a benchmark, it is rather a tool which puts the system under
a repeatable, defined amount of load so that a systems programmer or system
administrator can analyze the performance characteristics of the system or
specific components thereof.
Name        : tcping
URL         : http://www.linuxco.de/tcping/tcping.html
Summary     : Check TCP connection to a given ip/port
Description :
tcping does a TCP connect to the given ip/port combination. The user
can specify a timeout in seconds. This is useful in shell scripts
running in firewalled environments. Often SYNs are just being dropped
by firewalls, thus connection establishment will be retried several
times (for minutes) until a TCP timeout is reached. With tcping it
is possible to check first if the desired port is reachable and then
start connection establishment.
Name        : tcpshow
URL         : http://www.cs.berkeley.edu/~daw/mike/
Summary     : Prints dump files created by tcpdump
Description :
Utility to print raw packet dumps from tcpdump(8).
Name        : tcpspray
Packager    : Dag Wieers <dag@wieers.com>
URL         : http://ftp.linux.org.uk/pub/linux/Networking/attic/Other/tcpspray/
Summary     : Print average throughput for a tcp connection
Description :
Print average throughput for a tcp connection.
Name        : tcpstat
URL         : http://www.frenchfries.net/paul/tcpstat/
Summary     : Reports certain network interface statistics
Description :
tcpstat reports certain network interface statistics much like vmstat does
for system statistics.

tcpstat gets its information by either monitoring a specific interface, or
by reading previously saved tcpdump data from a file.
Name        : vnstat
URL         : http://humdi.net/vnstat/
Summary     : Console-based network traffic monitor
Description :
vnstat is a network traffic monitor that keeps a log of daily network
traffic for the selected interface(s). vnstat is not a packet sniffer.