kernbuild

Standard kernel build with the anticipatory scheduler.

volanomark

A java benchmark that measures raw server performance and network scalability. It creates client connections in groups of 20 and measures how long it takes for the clients to take turns broadcasting their messages to the group. At the end of the tests, it reports a score as the average number of messages transferred by the server per second.

http://www.volano.com/benchmarks.html

lmbench

suite of portable micro-benchmarks for UNIX, measures key system performance

http://www.bitmover.com/lmbench

aiostress

benchmark measures AIO performance on file system and raw device

ftp://ftp.suse.com/pub/people/mason/utils/aio-stress.c

netperf

A benchmark that measures the performance of many different types of networking. It provides tests for both unidirecitonal throughput, and end-to-end latency. The environments currently measureable by netperf include: TCP and UDP via BSD Sockets; DLPI; Unix Domain Sockets; Fore ATM API; and HP HiPPI Link Level Access.

http://www.netperf.org/netperf/NetperfPage.html

Short name	Description
TCP-S-112k	TCP Stream test with 112KB socket buffers and 4KB sends
TCP-S-64k	TCP Stream test with 64KB socket buffers and 4KB sends
TCP-RR-1	TCP Request/Response test with 1 byte requests and 1 byte responses
UDP-RR-1	UDP Request/Response test with 1 byte requests and 1 byte responses
UDP-RR-516	UDP Request/Response test with 516 byte requests and 4 byte responses
UDP-U-4k	UDP Unidirectional stream test with 64KB socket buffers and 4KB sends
UDP-U-1k	UDP Unidirectional stream test with 64KB socket buffers and 1KB sends

aim

suite of tests measures network, memory, and disk operation

http://sourceforge.net/projects/re-aim-7

fileio

One component of sysbench. This test mode can be used to produce various kinds of file I/O workloads. At the prepare stage it creates a specified number of files with a specified total size, then at the run stage, each thread performs specified I/O operations on this set of files.

http://sysbench.sourceforge.net

iozone

IOzone is a filesystem benchmark tool. The benchmark generates and measures a variety of file operations. It is useful for performing a broad filesystem analysis. The benchmark tests file I/O performance for the following operations: read, write, re-read, re-write, read backwards, read strided, fread, fwrite, random read, pread , mmap, aio_read, aio_write.

http://www.iozone.org

dbench/tbench

emulates netbench and measures performance of fileservers. dbench produces only the filesystem load. It does all the same IO calls that the smbd server in Samba would produce when confronted with a netbench run. It does no networking calls. tbench produces only the TCP and process load. It does the same socket calls that smbd would do under a netbench load. It does no filesystem calls. The idea behind tbench is to eliminate smbd from the netbench test, as though the smbd code could be made infinately fast. The throughput results of tbench tell us how fast a netbench run could go if we eliminated all filesystem IO and SMB packet processing. tbench is built as part of the dbench package.

ftp://samba.org/pub/tridge/dbench

vmregress

in-kernel test module that exercise virtual memory subsystem

http://www.skynet.ie/~mel/projects/vmregress

JAVA*

An industry standard java business benchmark .

cpu-int

An industry standard cpu intensive benchmark suite.

cpu-fp

An industry standard cpu intensive benchmark suite.

mmbench

mmbench measures memory menagement subsystem performance. The test creats page accesses stream with lognormal distribution of pages accesses frequency. Accessed area size by default is 12% greater than main memory size. Linux kernel boot option mem=1G is set before test start.

mmbench reports

avrg_access_time	- average page access time;
max_access_time	- max page access time;
num_major_faults	- number of page faults longer than 100 microsecond;
num_05sec_faults	- number of page faults longer than 0.5 sec;
num_075sec_faults	- number of page faults longer than 0.75 sec;
quality vs.2Q	- measured to 2Q page faults ratio;
quality vs.P1	- measured to P1 page faults ratio (P1 - all most frequently used pages are locked in main memory);

tiobench

Tiobench ( http://sourceforge.net/projects/tiobench/ ) measures throughput (MB/s) and read/write functions latencies (ms) for sequential and random reads and writes in multiple threads. Tiobench is configured to run 32 threads with 80 Mb test files (or 2,56 Gb summary) for Anticipatory, CFQ and Noop IO schedulers while main memory size is set to 1Gb.

Result table legend:

tio_thr	- Throughput
tio_lat	- Average latency
as - Anticipatory
cfq - CFQ
noop - noop
ddl - deadline
fc_wr	- File Create + sequential Write
rnd_wr	- Random Write
seq_rd	- Sequential Read
rnd_rd	- Random Read
seq_wr	- Sequential Write

Linux is a registered trademark of Linus Torvalds. Intel, Itanium, and Xeon are trademarks or registered trademarks of Intel Corporation. All trademarks are property of their respective owners.

*Other names and brands may be claimed as the property of others.

Performance tests and ratings are measured using specific computer systems and/or hardware and software components and reflect the approximate performance of these components as measured by those tests. Any difference in system hardware or software design or configuration may affect actual performance.