----------------
2007-03-31 Ted Bullock <tbullock@canada.com>
* *.c and *.h: Adjusted license to explicitly list HP copyright as
Copyright 2000-2007 Hewlett-Packard Company
2007-02-07 Ted Bullock <tbullock@canada.com>
* AUTHORS: wsseslog crash fix was actually written by David Mosberger
2007-02-07 Ted Bullock <tbullock@canada.com>
* AUTHORS: Removed Durval Menezes from AUTHORS file since his fix
has been re-written by Theodore Bullock
2007-02-07 Ted Bullock <tbullock@canada.com>
* *.c and *.h: Slightly adjusted license to explicitly point out AUTHORS file
as official list of authors
2007-02-07 Ted Bullock <tbullock@canada.com>
* httperf.1: Added correction to man page to include a missing
--wsess identification
2007-01-26 Ted Bullock <tbullock@canada.com>
* getopt.c and getopt1.c: Re-Added the to the build process
httperf now compiles on Linux, OpenBSD, FreeBSD, Solaris, HP-UX 11i
with cc and gcc and (with cc and gcc)
2007-01-26 Ted Bullock <tbullock@canada.com>
* Makefile.am: Revised Makefile.am for src directories to explicitly include the
.h files to allow make distcheck to pass
2007-01-26 Ted Bullock <tbullock@canada.com>
* getopt.c and getopt1.c: Removed from build process
* httperf.c: Wrapped call to getopt.h in pre-processor checks
2007-01-25 Ted Bullock <tbullock@canada.com>
* wsesslog.c: changed a sprintf call to the more secure snprintf
* getopt.c: changed a sprintf call to the more secure snprintf
2007-01-20 Ted Bullock <tbullock@canada.com>
* autogen.sh: Included the shell script autogen.sh to compile the necessary
autotool components.
* autogen.sh: Removed redundant configuration files from CVS, regenerate these
with the autogen.sh script (recommend autoconf 2.60 and above)
* ttest.c: Removed the ttest.c file from CVS
2007-01-16 Ted Bullock <tbullock@canada.com>
* Build System: Updated build system to a more typical directory
layout and wrote missing makefile.am files for automake
* idleconn: Now installed along with the httperf executable
* ttest: Remove program from build
2007-01-02 Ted Bullock <tbullock@canada.com>
*License: Included openssl linking exception
2006-12-08 Ted Bullock <tbullock@canada.com>
* Bug Fixes: Added a number of fixes from the mailing lists
over the last 6 years.
* compiler warnings: Compiler warnings in core.c and wsesslog.c
* configuration: Fixes a problem with the "configure" setup
where the "--prefix=" option wasn't being obeyed
* zero length: Fixes bug in http.c (parse_header)with zero
length content
* Host Header: Identify machine by FQD rather than hostname
* Persistent Connections: Added Persistent connections to HTTP 1.0
requests
* Robust alloca.h: Robust way to handle the header file that
defines the alloca function <alloca.h> for linux and stdlib.h for
BSD and others
* Time Discrepancy: Fixed a discrepancy between the data produced
by httperf and the documentation in regards to timing.
* wsesslog Crash: Fixed a problem with the wsesslog crashing
httperf due to an unhandled session failure from a burdened server
The Benchmark::Timer class allows you to time portions of code
conveniently, as well as benchmark code by allowing timings of
repeated trials. It is perfect for when you need more precise
information about the running time of portions of your code than
the Benchmark module will give you, but don't want to go all out
and profile your code.
Do it for all packages that
* mention perl, or
* have a directory name starting with p5-*, or
* depend on a package starting with p5-
like last time, for 5.18, where this didn't lead to complaints.
Let me know if you have any this time.
*) Initial pass at support for --enable-intervals (WANT_INTERVALS) for
Windows, courtesy of Jonathan Cook.
*) When in demo mode (./configure --enable-demo and a global -D
<interval> option netperf will make sure it emits "one last
interval result" when the test is terminated. This should assist
when post-processing results through the likes of rrdtool when
there is a slow-down in the performance just at the end that would
have stretched the interval to beyond the test termination.
*) A fix to have the AF_UNIX tests realize that the value for "take
the system default" socket buffer size became -1 years ago. Bug
found by Eric Dumazet.
*) Include a patch from Dave Taht to enable symbolic manipulation of
IP_TOS values.
*) Include a patch from Sachar Raindel to enable the omni tests to get
ENOBUFS under Linux when the socket buffer is larger than the tx
queue of the egress interface. This will help preclude netperf's
reporting a larger than link-rate send-side figure.
*) Fix a problem with late checking of the return from select() in
src/netserver.c. Reported by Waqar Sheikh.
*) A new global -Z option has been added to netperf and netserver.
This takes as an argument a passphrase. In the case of netserver
it will expect a control message with the passphrase as the first
thing it receives on the control connection. If netserver does not
receive a control message with the passphrase it will close the
control connection and move-on. If the netserver receives a
control message with a passprhase when it is not lookign for one,
it will be ignored. There is at present a 20 second timeout on the
attempted receipt of the request message. In the case of netperf,
the passphrase will be the first thing sent on the control
connection. There is no response to a passphrase control message.
*) Demo mode output format will now track the omni output format. So,
if the omni ouput format is CSV then the interim results will be
emitted in csv. Likewise for keyval. If the mode is human (default
and test-specific -O) then the output remains unchanged. Keyval
output includes the count of interval, with a mind towards being
able to source it in shells and whatnot. Subject to change without
notice.
*) A patch to correctly handle IPv6 addresses in the control messages,
courtesy of Bjoern Zeeb.
*) The global -F option can now be used specify a local and/or remote
fill file.
*) It is now possible to set/get the TCP congestion control algorithm
being used by either end of the test connection when using the omni
code. The output selectors are LOCAL_CONG_CONTROL and
REMOTE_CONG_CONTROL and setting is via the test-specific -K option.
*) Stop leaking file descriptors when looking-up probable egress
interface names and I/O slot numbers.
*) The global -Y option can be used to set IP_TOS on those platforms
which support it. Since this is specific to IP (v4 or v6) it may
move to a test-specific otion in the future. It is presently
global for foolish consistency with the -y option to set
SO_PRIORITY.
*) The global -y option can be used to set SO_PRIORITY on those
platforms which support it. Based on patches from Amir Vidai.
*) The control message size has been increased from 256 bytes to 512
bytes. THIS WILL BREAK COMPATABILITY WITH PREVIOUS VERSIONS OF
NETPERF. However, we need more room on the pinhead on which the
angels dance.
*) Make the "sum" field of the histogram structure a 64 bit int to
avoid having it wrap-around on tests where the sum of all the
measured latencies was larger than 31 bits. This was causing
statistics like stddev to go negative in some cases.
*) If the time delta between two events is negative, do not bother
doing any math with it in the histogram/statistics code, just
increment the ridiculous count and move-on.
*) Fixed a bug which caused local transport retransmissions to be
reported as -1 even though the getsockopt() call was
successful. (Linux). Later included remote transport
retransmissions.
*) The src/nettest_omni.c and re-written src/netserver.c code are now
known to have compiled under Windows 7 x64 with the Microsoft
WDK. There remains a timing issue with confidence intervals which
is yet to be addressed, and may have been there for ages. Netserver
has been run as a non-spawning (-f) server, netperf has been run,
both have run "classic" and "omni" tests.
1.) Comment out "MASTER_SITES". The URL no longer works and all copies
that Google can find are "pkgsrc" distfile mirrors.
2.) Fix various "pkglint" errors.
DNSPerf, ResPerf, and DHCPerf are free tools developed by Nominum that
make it simple to gather accurate latency and throughput metrics for
Domain Name Service (DNS) and Dynamic Host Configuration Protocol
(DHCP). These tools are easy-to-use and simulate typical Internet so
network operators can benchmark their naming and addressing
infrastructure and plan for upgrades. The latest version of the DNS
test tools (DNSPerf and ResPerf) can be used with new test files that
include IPv6 queries.
DNSPerf "self-paces" the DNS query load to simulate network
conditions. New features in DNSPerf improve the precision of latency
measurements and allow for per packet per-query latency reporting is
possible. DNSPerf is now multithreaded, multiple DNSPerf clients can
be supported in multicore systems (each client requires two
cores). The output of DNSPerf has also been improved so it is more
concise and useful. Latency data can be used to make detailed graphs
so it is simple for network operators to take advantage of the data.
The point of paranoia is to assess a compiler/machine environment.
Therefore, this package should be built with the default CFLAGS, and
not add options to try to get the tests to pass. This will cause
errors to be reported on i386.
Take MAINTAINERSHIP.
to address issues with NetBSD-6(and earlier)'s fontconfig not being
new enough for pango.
While doing that, also bump freetype2 dependency to current pkgsrc
version.
Suggested by tron in PR 47882
a) refer 'perl' in their Makefile, or
b) have a directory name of p5-*, or
c) have any dependency on any p5-* package
Like last time, where this caused no complaints.
File too long (should be no more than 24 lines).
Line too long (should be no more than 80 characters).
Trailing empty lines.
Trailing white-space.
Trucated the long files as best as possible while preserving the most info
contained in them.
RAMspeed, a cache and memory benchmarking tool
(for uniprocessor machines running UNIX-like operating systems).
This command line utility measures effective bandwidth of both cache and memory
subsystems. It has been written entirely in C for portability purposes, though
benchmark routines are also available in several assembly languages for
performance reasons.
The "-r" option is highly discouraged in BSD although it's reluctantly
supported. The problem is that it doesn't behave the same on all
platforms. For example, "cp -r pts-core/ destdir/" won't always give
the same results:
On NetBSD, pts-core files are put: /destdir/pts-core/<files>
On DragonFly pts-core files are put: /destdir/<files>
That messes the PLIST up.
This changes "cp -r <dir>/" to "cp -R <dir>" which has the same
behavior on different platforms. Tested on NetBSD and DragonFly
Filebench is a file system and storage benchmark that allows
to generate a high variety of workloads. It employs extensive
Workload Model Language (WML) for detailed workload specification.
Features
* Extensive Workload Model Language (WML) for workload specification
* Includes popular pre-defined workloads: webserver, fileserver,
varmail, etc.
* Reports throughput and latency histograms
Changes since version 3.397:
Revision 3.408
Bug fix for clobbering of buffer. "tfile" needed to be bigger, as its
address was loaded into filearray[] and then that was overwritten
by the mfflag causing parsed names to get loaded.
Revision 3.407
Work around for cache_line_size suddenly becoming zero and breaking fetchit()
Revision 3.406
Increase buffer size for configuration lines. They might be 700 chars long.
Revision 3.405
Reduce CPU consumption in the op_rate control mechanism.
Revision 3.404
Fix type-oh in usage message.
Revision 3.403
Add -+W to permit chid_skew. This permits adding files, and continuing
the proper sharing/dedup within each quadrant, within same seed group
and with previously existing files that were created with a different
number of threads.
Revision 3.402
Mods for DragonFly support.
Revision 3.401
bug fix for re-write rec.
Revision 3.398
Adding thread_read_test and thread_write_test.
The update from version 3.308 to 3.397 broke DragonFly 11 days after I
fixed it due to missing a macro change. An integer redeclaration was
also removed.
DESCR:
The Phoronix Test Suite is the most comprehensive testing and benchmarking
platform available for the *nix operating system. This software is designed
to effectively carry out both qualitative and quantitative benchmarks in a
clean, reproducible, and easy-to-use manner.
It appears that the authors of Iozone tried to add DragonFly support without
actually building it. The configuration was broken, and the iozone.c
was uncompilable. With the two modified patches, it will compile now, and a
quick check using "iozone -a" seemed to work as expected.
No PKGREVISION bump necessary.
Despite several additional patches, postal 0.62 wouldn't compile on
DragonFly (broke on stl vectors), so upgrading the package was the
most effective approach to restore this package.
License updated in Makefile.
Summary of changes since version 0.62
=====================================
0.65 Significant improvement, many new features and many bugs fixed!
0.66 Made GNUTLS work in BHM and added Messageld to Postal
0.67 Changed license to GPLv3
0.68 Fixed compiler warnings on GCC 4.3, make it work for OpenSolaris
0.69 Fixed compiler warnings and more GCC 4.3 compatibility work
0.70 Updated man pages and allowed build without SSL support
This commit fixes the run-libmicro command which was broken for all
platforms. It was pointing at the destdir version instead of the
installed version.
It also provides a DragonFly-specific makefile which enables it to
build and run on DragonFly.
part of, a new upstream version, but I need to talk to some people first.
(I'm keeping this separate from the previous update in case it breaks stuff.)
Changes:
roll in parts of patch-aa and patch-aq;
roll in all of patch-ar and patch-src_memsize_c;
make the ARM-only adjustment from patch-ar universal;
add enough volatile to make 'mhz' work more or less properly again;
fix the loop calibration to bail out instead of spinning forever
if things go too fast (e.g. because the compiler's optimized out
the benchmark loop);
various hacking and modernization to get sort of a clean compile;
fix some non-stdc stringifying macros;
hopefully advance the clang build a bit further.
Based on PR#44354 by Tony Young.
set LICENSE=public-domain, unit-test support by me.
Version 0.2 2002-09-11
Added unit test framework.
Read from a list of files, rather than just one, seeking evenly within
all of them based on the number of blocks in each.
Allow reading several contiguous blocks for each seek, so we can do
sequential/random and sequential read testing.
Print more and clearer information.
Added disktest shell scripts.
Release 3.7 adds support for OpenFabrics infiniband verbs module (NPibv),
and should work with the OFED-1.1 or OFED-1.2 release. It has been tested
on IBM eHCA hardware as well as Mellanox pci-express infiniband adapters.
The openfabrics verbs support is currently lacking any support for the
connection manager, and all connections are set up via TCP sockets.
* Made forced shutdown introduced in 0.4.11 optional via the --forced-shutdown
switch and off by default.
Changes 0.4.11:
* Added --oltp-reconnect-mode to the OLTP test.
* Minor fixes to remove compiler warnings and DocBook processing on Mac OS X.
* Added forced test shutdown to avoid endless execution when DB server freezes
* Backport of Windows support from the 0.5 branch
Changes 0.4.10:
* Fixed the bug with empty --mysql-create-options
* Merge two patches from Tim Cook:
- use lrand48() as random() is not thread-safe on most platforms
- use libumem/mtmalloc for memory allocation if available on the target platform
* Got rid of some unnecessary malloc() calls in drv_mysql.c
* Fixes for Linux procstat-based CPU utilization on newer kernels
from Andrew Gallatin.
* Fix for a TCP_RR hang from Michael Shuldman
* Compilation cleanups for MingW cnd MSDOS (djgpp) ourtesy of Gisle Vanem.
* Changes to enable compilation and building of netperf for
VMware. Kudos to the person who did the first port, I will be happy
to name that person when told it is OK :)
* Fixes from Adam Bidema for launching netserver children when the
path to netserver.exe is very long.
* For the first time, netperf2 has a dependency, albeit optional, on
another non-base-os bit of code - libsmbios under Linux.
* Fixes for BSD CPU utilization to deal with different BSD variants
using different types.
* The "omni" suite has been added on an experimental basis.
* Coming along for the ride are some new platform specific files to
determine the probable egress interface for each end of a test, as
well as driver information for that interface.
* The UDP_RR test now understands the global -f option to change
output units. It also understands the -B option to tag
results. Courtesy of Alexander Duyck.
* A fix has been added for hanging UDP_RR tests under Windows.
* Fixes for Solaris sendfilev usage.
* A TCP_MSS test has been added which will report the MSS for a data
connection setup as if the test were a TCP_STREAM test.
* The width of the confidence interval can be specified in fractions
of a percent for the confidence of a clean, close, comfortable
calculation. :)
* Honor the global -B option in a TCP_SENDFILE test.
* Correct the sense of Send/Recv in the banner of a TCP_MAERTS test.
bonnie++ (1.03e)
* Added the -D option to bonnie++ to use direct IO (O_DIRECT) for bulk IO.
Thanks to Dave Murch from Violin Memory - http://violin-memory.com/
-- Russell Coker <russell@coker.com.au> Wed, 10 Dec 2008 09:08:00 +1100
bonnie++ (1.03d)
* Made it compile with GCC 4.3.
* Added the URL to the man pages.
* Made zcav display the total time and average speed for a loop and also the
time that each loop completed.
* Made the zcav default block size 256M to cope with larger and faster disks.
* Made the zcav output units be in MiB/s and GiB.
* Improved the Bonnie++ man page in regard to the -y and -p options.
* Use DH_COMPAT=4 and dh_installman.
-- Russell Coker <russell@coker.com.au> Wed, 23 Jul 2008 10:54:24 +1000
LibMicro is a portable set of microbenchmarks that many Solaris engineers
used during Solaris 10 development to measure the performance of various
system and library calls. LibMicro was developed by Bart Smaalders and
Phil Harman as part of their "If Linux is faster it's a Solaris bug
performance" campaign.
pkgsrc changes:
- add 'tee' to USE_TOOLS.
- support an optional build with threads support and also support this in the
'benchmark' target.
Changes since version 2.263
-Bug fix for -k used in conjunction with -t and content
validation.
-Add DragonFly target.
-Put PER_VECTOR_OFFSET in for HP-UX
-Fix compiler warning messages
-Enforce minimum file size of page_size
-Minor fixes.
-Check fsync and close for errors.
-Adding support for testing block devices. Will be done is phases.
This is phase 1. (Single threaded mode only)
-Adding 4 token support to client_list. Each entry may now contain
4 tokens and the new one is the absolute path to the temp
file for testing.
-Add support for external monitor start & stop for throughput
tests.
-IMON_START and IMON_STOP environmental variables used.
-Bug fix for systems without O_DIRECT. Fall through in switch
statement.
-Fix for -c -t over NFS and initial writer close() when told by
another to stop
-Add Benny Halevy to contributors list.
-Fix for Cygwin environment.
-Code cleanup, and add arg to external trigger.
-Code fixes for macosx
-Add support for building with Sun's Studio 11 compiler
-Bug fix for fread/fwrite with > 2Gig files.
-Add O_DIRECT for Windows
-Add -+w dedup testing mode.
-Make remaining non-dedup data unique.
-Make non-dedupable more unique.
-Bug fix for non-dedup.
-Make random offsets unique, using Knuth shuffle.
-free memory used for random offset uniqueness.
-Make unique/random offsets 64bits.
-Add fallback for random/unique.
-Make non-dedup region more unique
-Add -+y ## to set percentage of interior dedup.
-Add -+y ## to set percentage of interior dedup.
-Bug fixes for -+w and -+y
-Minor fix for dedup
-Adding -+C to set percent of dedupable within a file.
-Add solaris to read sync O_RSYNC
-Add space to avoid field output touching each other.
-Add check for config file exceeding MAXSTREAMS.
-Add new contributor's name.
bonnie++ (1.03c) unstable; urgency=low
* Fixed some failures to check the return code of chdir().
bonnie++ (1.03b.1) unstable; urgency=low
* Fixed typos in man page.
Closes: #133714Closes: #449596
* Documented why UID==0 is bad.
Closes: #182023
bonnie++ (1.03b) unstable; urgency=low
* Added support for testing write speed to zcav.
* Documented the default chunk size in bonnie++.8.
* Improved error handling for chunk size.
Changes is unknown.
While here,
* install README file mentioned in man page, suggested in PR 38553.
* move client.txt to subdir noted in man page
* fix directory of those files in man page.
to optimize away the loop used for timing. Do something in the loop for
arm that can't be optimized away, and will also meet the 1,000
instructions in the loop requirement.
This allows mhz to calculate sensible Mhz on a StrongArm (228Mhz rather
than 56Mhz)
Other hardware probably also need fixing, as gcc probably applies the same
optimizations on them.
Also bump PKGREVISION.
Thanks for Kimura Fuyuki. OK: agc@
SysBench is a modular, cross-platform and multi-threaded benchmark
tool for evaluating OS parameters that are important for a system
running a database under intensive load.
INSTALLATION_DIRS, as well as all occurrences of ${PREFIX}/man with
${PREFIX}/${PKGMANDIR}.
Fixes PR 35265, although I did not use the patch provided therein.
that rather than having to hack our own install code. This changes what's
actually built and installed not one whit, so we do not increment the version.
or USE_X11BASE set, but don't include mk/x11.buildlink3.mk directly or
via buildlink3.mks
- introduce BUILDLINK_PREFIX.libXpm as alias for BUILDLINK_PREFIX.xpm
in the !modular case
- fix some cases where the check for libX11 couldn't work at all by using
C++ for compilation without including the proper headers
Verified using a full X11_TYPE=xorg bulk build without additional
breakage. Discussed with salo@, wiz@ and send to packages@ for feedback.
New in version 0.8:
httperf is now released under the GNU General Public License (GPL).
Preliminary support for SSL (Secure Socket Layer). See README for details.
New options (see man-page for details):
--print-reply (replaced --print-replies)
--print-request
--ssl
--ssl-ciphers
--ssl-no-reuse
New in version 0.7:
New options (see man-page for details):
--add-header
--method
--retry-on-failure
Bug fixes
- fixed some segfaults in the session workload generator
- specifying option --session-cookie when not using a session
workload generator now prints an error message instead of
core dumping
thrulay-0.8 release notes
Linux compatibility release; fixes problems with compiling the
software on some flavors of Linux.
thrulay-0.7 release notes
This release incorporates the results of the work of Bernhard Lutzmann
on his Google Summer of Code project.
since they always need a C compiler, even when the source code is
completely in C++.
For some other packages, stated in the comment that a C compiler is
really not needed.
had actually been ignoring LTCONFIG_OVERRIDE anyway and just using
the default LIBTOOL_OVERRIDE to replace libtool scripts in packages.
This just formalizes the fact that LTCONFIG_OVERRIDE is not used
meaningfully by pkgsrc.
* Change the default pattern. Samba is trying to cheat by
special casing IOZONE.tmp, and the pattern of 0xA5.
* Make the default pattern random, and based on Iozone version.
This is to prevent the hack from Richard Sharpe (in Samba)
from special casing Iozone, and lying to the user.
* bug fix in pattern gen.
* Add -+Z old data set mode.
* Add -+X constant data for short circuit testing only.
* Multi-node changes for new options. (-+Z and -+X)
* Add -+K flag for Sony.
* Move -+K outside of Windows only.
* Simplify percentage calculation
* Add error checking for -f and -F in the wrong modes.
* Bug fix for pbuffer allocation on remote clients.
* Check for max_rec_size when using ranges. -r -r -r
* Fix for Debian user bug. -r 1m -n 1m -g 2m gave bogus error.
* Bug fix for -k used in conjunction with -t and content validation.
