Re: [Ganglia-developers] Gmetad Platform Poll
Hi Devon,
I use gmetad on IBM Power systems with mostly AIX but also Linux as I
provide readily compiled Ganglia binary versions for all AIX versions
and all supported Linux on Power flavors on my website
(http://www.perzl.org/ganglia).
Judging from the feedback I received over the last 6-7 years I would
estimate that at least a couple thousand (3000+) IBM customers
world-wide run Ganglia on AIX (and to a lesser degree also Linux on Power).
Regards,
Michael
On 12/11/2013 04:49 PM, Devon H. O'Dell wrote:
Hi all,
I'm intending to continue working on performance improvements for
gmetad. I'm curious if anybody uses gmetad on architectures that are
not:
* ARM
* PPC
* PPC64
* SPARCv9
* i386
* amd64
or on systems that are not:
* Linux
* ${any}BSD
* Solaris
(I'd also be interested in hearing if people are using gmond on
architectures other than those mentioned above; less interested about
the operating systems for that one.)
Kind regards,
--dho
--
Rapidly troubleshoot problems before they affect your business. Most IT
organizations don't have a clear picture of how application performance
affects their revenue. With AppDynamics, you get 100% visibility into your
Java,.NET, PHP application. Start your 15-day FREE TRIAL of AppDynamics Pro!
http://pubads.g.doubleclick.net/gampad/clk?id=84349831iu=/4140/ostg.clktrk
___
Ganglia-developers mailing list
Ganglia-developers@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-developers
--
Rapidly troubleshoot problems before they affect your business. Most IT
organizations don't have a clear picture of how application performance
affects their revenue. With AppDynamics, you get 100% visibility into your
Java,.NET, PHP application. Start your 15-day FREE TRIAL of AppDynamics Pro!
http://pubads.g.doubleclick.net/gampad/clk?id=84349831iu=/4140/ostg.clktrk
___
Ganglia-developers mailing list
Ganglia-developers@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] [Ganglia-general] Gmetad Platform Poll
I can certainly test and verify this on a variety of different AIX levels.
Regards,
Michael
On 12/11/2013 07:27 PM, Devon H. O'Dell wrote:
Thanks. I think the work I'm doing should work with AIX on POWER.
Would anybody with a builder be able to test and verify this?
2013/12/11 Morten Torstensen morten.torsten...@evry.com:
We are using ganglia for aix on power, and possibly linux on power too in
the close future.
We use binaries from Michael Perzl, http://www.perzl.org/ganglia/
Best regards
Morten Torstensen
Chief Solution Architect, BA Nordic Open Systems
Future Proof Service Development
morten.torsten...@evry.com
M +47 46819584
-Original Message-
From: Devon H. O'Dell [mailto:devon.od...@gmail.com]
Sent: Wednesday, 11 December, 2013 16:49
To: ganglia-developers@lists.sourceforge.net;
ganglia-gene...@lists.sourceforge.net
Subject: [Ganglia-general] Gmetad Platform Poll
Hi all,
I'm intending to continue working on performance improvements for gmetad.
I'm curious if anybody uses gmetad on architectures that are
not:
* ARM
* PPC
* PPC64
* SPARCv9
* i386
* amd64
or on systems that are not:
* Linux
* ${any}BSD
* Solaris
(I'd also be interested in hearing if people are using gmond on
architectures other than those mentioned above; less interested about the
operating systems for that one.)
Kind regards,
--dho
--
Rapidly troubleshoot problems before they affect your business. Most IT
organizations don't have a clear picture of how application performance
affects their revenue. With AppDynamics, you get 100% visibility into your
Java,.NET, PHP application. Start your 15-day FREE TRIAL of AppDynamics
Pro!
http://pubads.g.doubleclick.net/gampad/clk?id=84349831iu=/4140/ostg.clktrk
___
Ganglia-general mailing list
ganglia-gene...@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-general
--
Rapidly troubleshoot problems before they affect your business. Most IT
organizations don't have a clear picture of how application performance
affects their revenue. With AppDynamics, you get 100% visibility into your
Java,.NET, PHP application. Start your 15-day FREE TRIAL of AppDynamics Pro!
http://pubads.g.doubleclick.net/gampad/clk?id=84349831iu=/4140/ostg.clktrk
___
Ganglia-general mailing list
ganglia-gene...@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-general
--
Rapidly troubleshoot problems before they affect your business. Most IT
organizations don't have a clear picture of how application performance
affects their revenue. With AppDynamics, you get 100% visibility into your
Java,.NET, PHP application. Start your 15-day FREE TRIAL of AppDynamics Pro!
http://pubads.g.doubleclick.net/gampad/clk?id=84349831iu=/4140/ostg.clktrk
___
Ganglia-developers mailing list
Ganglia-developers@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] 3.3.3 tagged
I verified that this tar.gz release builds cleanly with my autoreconf on the following OS versions: AIX 5.1, AIX 5.3 RHEL 4 U3, RHEL 6, SLES 9 SP3, SLES 10, SLES 11 (all on Power Systems) Regards, Michael On 03/21/2012 10:32 AM, Daniel Pocock wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA256 Release 3.3.3 The release has now been tagged in git commit = c8531e5d57f6126eee6f47f1ad8734e86c1e9cb5 Filename: ganglia-3.3.3.tar.gz SHA256 checksum: 96cd90f2f978bb5e6c471798fa8d4b599a9910dfdae19bbfd7353abcb1497548 It is still on the pre-release page on Sourceforge, if no problems are found in the next 7 days then it can become the official release. https://sourceforge.net/projects/ganglia/files/pre-release/ -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.10 (GNU/Linux) iQIcBAEBCAAGBQJPaaFLAAoJEGxlgOd711bEz/sP/RWF1uMcMMGho+EVx44KIvVA hwtV0Wi2hMYkoqRPLcI2Bg+y/UzkMaVvGTuaRQQs4xF4sxw0UlJv+L649eV3/viJ zhnAQyJ7GQCOPns9sgra5R+FcclUsdEUZwmDZmWJoRvCSfsxacQHJkhsgfvTLCYD 96UhAaANUOq/7GpoCt46spOdD2ZdbObu/J7lj7pSEy4nDJjYOBQtQWx50nc42OMQ yiOHzlg+2p4oZBHDkqkquT4O5f+kl5e6Ot2EkA4egpcBEWChpCLs7Jptn4kxMLLJ 3HtIC44cUVHo4cb1Lk/3nRna0zUhfvqSPpTTtAhrjDrZPYly5UhA1EA4DEhSwK0o gg0O4tYcNcApsD3Ihoj1ARkJN70mHITEhu777FMsv+fb9DOUxC+ZRMrOhR55KiEG xkJHQOAtXhDXcAZvG3TVXbcGeHaNhIj5GlrOTDxIRj4xndxNehImS9wxjc8WNf9v T3nK7cFO5cMIvAmHZdwb/esrPa33IOQPefdK+TLZmokip2nvdqCraXAWih2URu1W wUa+I1vWAIo0ilqQZH/EcQBhdfwgCvq2RCOWgrf5OT3vO1yYsdnHd0cUrVBr0zd3 Mmfb325Eq0Eb4L5fwQ5BwAPUdIDgFN8XNFlz4uKx0JrwNykPY5DoD7rQwh7K1Xdb PQ9qPLoP/oy+Fh51m4U5 =g4Xd -END PGP SIGNATURE- -- This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers -- This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] releasing 3.3.2 today?
I tested the tarball and it still does not contain the following files: ganglia-3.3.2/ChangeLog ganglia-3.3.2/libmetrics/ChangeLog ganglia-3.3.2/libmetrics/INSTALL Those files are necessary if you do a autoreconf -fi which is necessary if you add something to any *.am file in the source tree. I build all the additional gmond modules for AIX and Linux on Power this way. Therefore, I have in the respective spec-file a statement like this in %prep: %prep %setup -q # autoreconf seems to need this one touch ChangeLog libmetrics/ChangeLog libmetrics/INSTALL I have verified this and get the exact same behavior on all platforms that I use which include: AIX 5.1, AIX 5.3, SLES9, SLES10, SLES11, RHEL4, RHEL6 So I assume this is nothing specific to AIX but a general issue. Ganglia version 3.3.1 was the first one where this is required, any previous version did not requires this. Before you release version 3.3.2 could you please add (dummy) files for those? Regards, Michael On 03/20/2012 03:07 PM, Daniel Pocock wrote: On 20/03/2012 12:09, Daniel Pocock wrote: I've updated the document at https://github.com/ganglia/monitor-core/wiki/BuildingARelease and been able to follow the steps there to build a working tarball (at least the tarball works for me). The main change is that it now relies on `make dist' rather than scripts/package-ganglia-release to decide what belongs in the tarball. Does anyone want to sneak in any last minute changes before I tag 3.3.2 and make the tarball available for testing? Where should I put the tarball for people to test before general release? I've put a pre-release tarball here: https://sourceforge.net/projects/ganglia/files/pre-release/ It is based on commit e59f87da325bf66d128b086054656ec280b200e2 which has not yet been tagged If there are no loud objections, I'll tag it later today The SHA-256 checksum for this tarball is: 10c587b2f913c47b1ed06e7d00c33192604fe4bf2b3ad113d67abf178b241972 -- This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers -- This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] releasing 3.3.2 today?
Besides the autoreconf issue I mentioned in my previous email, the tarball compiles cleanly on AIX5.1, AIX5.3, RHEL4, RHEL6, SLES9, SLES10, SLES11 Regards, Michael On 03/20/2012 03:07 PM, Daniel Pocock wrote: On 20/03/2012 12:09, Daniel Pocock wrote: I've updated the document at https://github.com/ganglia/monitor-core/wiki/BuildingARelease and been able to follow the steps there to build a working tarball (at least the tarball works for me). The main change is that it now relies on `make dist' rather than scripts/package-ganglia-release to decide what belongs in the tarball. Does anyone want to sneak in any last minute changes before I tag 3.3.2 and make the tarball available for testing? Where should I put the tarball for people to test before general release? I've put a pre-release tarball here: https://sourceforge.net/projects/ganglia/files/pre-release/ It is based on commit e59f87da325bf66d128b086054656ec280b200e2 which has not yet been tagged If there are no loud objections, I'll tag it later today The SHA-256 checksum for this tarball is: 10c587b2f913c47b1ed06e7d00c33192604fe4bf2b3ad113d67abf178b241972 -- This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers -- This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] re-bootstrapping Ganglia
On 03/20/2012 06:19 PM, Daniel Pocock wrote: b) should Michael (or anyone else) need to modify Makefile.am from a tarball? If there are regular changes to Makefile.am after releases are made, shouldn't we find a way to incorporate such changes into trunk, or provide more variables for people to set things at build time? Let me explain my motivation to make changes to Makefile.am: I am maintaining for AIX and Linux on Power a couple of additional gmond DSO modules written in C. As those are probably only useful for people running AIX (or Linux on Power) I don't see a generic way to incorporate such changes into trunk. In order to compile and package the gmond module I intentionally keep the release tar.gz unchanged, i.e., any module is represented by a large source code patch against the respective release tar.gz. This is also the RPM-way of doing things (i.e., keep the vanilla source unchanged and anything else should be provided as a source code patch). So the patch for example for a metric called mod_netif adds or changes the following files/directories: ./gmond/modules/conf.d/netif.conf ./gmond/modules/netif/mod_netif-linux.c ./gmond/modules/netif/Makefile.am ./gmond/modules/Makefile.am ./gmond/Makefile.am ./configure.in Now one needs to run autoreconf -fi to incorporate the applied patches and that the respective Makefile.in files are generated from the patched Makefile.am files. I also keep separate SPEC files for all modules and have thus a clean separation of the original Ganglia release tar.gz files and my modules. In addition I can change the RPM release number independently of the core ganglia RPM release number which provides further flexibility. Regards, Michael -- This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] releasing 3.3.2 today?
On 03/20/2012 08:23 PM, Jesse Becker wrote:
If the Ganglia community releases a tarball called, 3.3.3-2.tar.gz, for
example, then someone building RPM packages might release 3.3.3-2-1
If the Ganglia project really did release 3.3.3-2.tar.gz, we should
have our heads examined. :)
But yes, the resulting RPM could potentiall appear as you described,
and it would be a mess.
Yes absolutely. Judging from my own experience having built thousands of
RPMs every time any release number that incorporates non-numbers just
leads to more or less confusion. Thus for a released tarball I would
definitely stay away from non-numbers and just stick with something like
X.Y.Z (X,Y,Z in [0..9]*). And just let the package maintainers (Debian,
RHEL etc.) maintain the X.Y.Z-R release number (R) for their package.
The most complicated, non-contrived version/releases I've see are in
the kernel RPM packages. Here are some examples from a production
Centos 5 host. First, the full package is shown, including the name,
version, release and arch of the package:
$ rpm -q kernel
kernel-2.6.18-194.32.1.el5.centos.plus.x86_64
kernel-2.6.18-238.9.1.el5.centos.plus.x86_64
Now, just showing the version and release:
$ rpm -q --qf %{version} %{release}\n kernel
2.6.18 194.32.1.el5.centos.plus
2.6.18 238.9.1.el5.centos.plus
This works correctly because of the leading numbers in the release
tag--even though there is a bunch of extra non-numeric content as
well.
That is because you really can't put any distro-specific version schemes
in the RPM %{version} number but in %{release}. That's why RHEL,
Mandrake etc. define a %{dist} that is typically added to %{release}.
And thankfully we have not run into %{epoch} here which makes things
even more complicated. :-)
Regards,
Michael
--
This SF email is sponsosred by:
Try Windows Azure free for 90 days Click Here
http://p.sf.net/sfu/sfd2d-msazure
___
Ganglia-developers mailing list
Ganglia-developers@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] Ganglia 3.3.1 configure.in broken, 3.3.2 needed
If you do an update to 3.3.2 could you also please make sure that the
following files exist:
ChangeLog
libmetrics/ChangeLog
libmetrics/INSTALL
As with the 3.3.1 tar.gz file they don't exist thus preventing a
autoreconf -fiv that I need to perform for all my additional Ganglia
modules. Here is the code snippet from one of the SPEC files. This was
not necessary with any previous version before.
##
## PREP
##
%prep
%setup -q -n ganglia-%{version}
export PATH=/opt/freeware/bin:$PATH
# apply all necessary AIX patches
%patch0
%patch1
# apply the patch for the mod_ibmpower module
%patch2
*# autoreconf seems to need this one
touch ChangeLog libmetrics/ChangeLog libmetrics/INSTALL*
##
## BUILD
##
%build
export CC=xlc_r -U_AIX43
export LDFLAGS=-L/opt/freeware/lib -Wl,-bmaxdata:0x8000 -Wl,-brtl
autoreconf -fiv
./configure \
Thanks.
Regards,
Michael
On 03/08/2012 03:33 PM, Daniel Pocock wrote:
I notice that configure.in was only updated to 3.3.1 after the package
was put out on Sourceforge
This breaks the OpenCSW package build and may impact other people too
Can I propose a 3.3.2 release?
I was going to add a release manager document on the wiki, but I don't
have write access (can someone please help me with that). Here are the
steps that I use with ganglia-modules-linux, I believe it is the same
for Ganglia now that git is in use, but any further feedback would be
helpful:
a) review the changes from the last release (git diff 3.3.1 3.3.2) -
look for anything that might impact binary compatibility with existing
3rd party modules, etc
b) run git log (from the previous release) and note all the changes, add
them to the changelog (where is it now? couldn't find it in git for
monitor-core)
c) update monitor-core/configure.in, in particular:
GANGLIA_MAJOR_VERSION=3
GANGLIA_MINOR_VERSION=3
GANGLIA_MICRO_VERSION=2
and commit that change together with change log:
git add configure.in Changelog
git commit -m 'Prepare v3.3.2 release'
git push
d) clone the repo into a fresh directory, bootstrap, build a tarball:
git clone git:///github/ganglia ganglia-dist
cd ganglia-dist ./bootstrap ./configure make dist
e) test the tarball
f) if the tarball is good, tag the clone
git tag -s -m 'Tag v3.3.2' 3.3.2
git push --tags
g) get a checksum of the tarball
sha256sum ganglia-3.3.2.tar.gz
h) upload the tarball to sourceforge
i) announce it on the mailing list, publish both the checksum and the
commit number of the tag, sign the email with the same PGP key used to tag
j) update other web sites (e.g. ganglia.info)
I'm sure that other optional steps could be added (e.g. more tests to
run on the tarball prior to distribution, building binary packages for
Debian/RH,...) but the steps above are probably the essential ones
--
Virtualization Cloud Management Using Capacity Planning
Cloud computing makes use of virtualization - but cloud computing
also focuses on allowing computing to be delivered as a service.
http://www.accelacomm.com/jaw/sfnl/114/51521223/
___
Ganglia-developers mailing list
Ganglia-developers@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-developers
--
Virtualization Cloud Management Using Capacity Planning
Cloud computing makes use of virtualization - but cloud computing
also focuses on allowing computing to be delivered as a service.
http://www.accelacomm.com/jaw/sfnl/114/51521223/___
Ganglia-developers mailing list
Ganglia-developers@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] Gauging interest in writing a Ganglia eBook
Hi Matt, I would definitely be interested in joining such an effort. Since I started using Ganglia for AIX and Linux on Power I have certainly given 25+ presentations on Ganglia - certainly with a focus on AIX and IBM Power systems - but there is surely enough suitable common material available, mostly in PowerPoint presentations that I could chip in Regards, Michael On 12/01/2011 08:31 PM, Matt Massie wrote: There's an O'reilly editor who's interested in publishing a ~50-page eBook on ganglia. I have no doubt the ganglia community would benefit from a book covering topics like: * Ganglia's components and overall architecture * Typical deployment configurations including simple steps for verifying an installation (e.g. unicast/multicast, single cluster/multiple distributed clusters/datacenter) * Navigating and using the new web interface * Tips for extending ganglia's functionality (e.g. gmetric, modules) * Common integration points (e.g. Hadoop metrics, Nagios) * A simple step-by-step checklist for debugging common ganglia issues with pointers to our web site, mailing lists, irc channel, etc. * Supported platforms and core metrics * Scaling to clusters 1000 nodes These are just ideas off the top of my head and not meant to final or comprehensive but meant to provide a list for discussion. Of course, let me know if there's topics the community would like to know more (or less) about. The purpose of the book is to serve as a first-read book for people new to ganglia. Keep in mind, for much of the book, we won't be starting from scratch. We already have a good amount of documentation that just needs to be organized and edited. I'll be happy to contribute time to make this eBook a reality; however, I want the book authors to be the leaders and experts in the ganglia community. I think it best we divide and conquer and write the book as a team. Who is interesting in helping write the book? -Matt -- All the data continuously generated in your IT infrastructure contains a definitive record of customers, application performance, security threats, fraudulent activity, and more. Splunk takes this data and makes sense of it. IT sense. And common sense. http://p.sf.net/sfu/splunk-novd2d ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers -- All the data continuously generated in your IT infrastructure contains a definitive record of customers, application performance, security threats, fraudulent activity, and more. Splunk takes this data and makes sense of it. IT sense. And common sense. http://p.sf.net/sfu/splunk-novd2d___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
[Ganglia-developers] Question about Ganglia
I have a question regarding the PHP web code of Ganglia:
My setup looks like that:
* I have one Grid and several Clusters.
* Each Cluster has between 10-250 nodes, all running on AIX LPARs
(but the question is independent of the OS).
* I have clustered on a logical level, i.e., not according to the
different hardware systems but for instance, all SAP systems, all
TSM systems etc.
* I have lots of additional metrics, provided via a C-DSO.
* One of the additional metrics is a system-identifier, i.e., a
hardware identifier that I want to use to identify the hardware
that each LPAR is running on.
Now in addition to the logical view I want to introduce a physical
view, i.e., a view of all LPARs running on a specific system with a
certain hardware identifier. This is were my illiteracy regarding PHP
comes into play.
Basically, I want to have a list of ALL Ganglia nodes so that I can loop
over and group them according to their hardware identifier.
I was able to accomplish someting in cluster_view.php with the following
code snippet but have failed miserably so far in meta_view.php.
$sysids = array();
$sysid_count = 0;
foreach ($metrics as $host = $val)
{
if (isset( $val[serial_num]['VAL'] ))
{
$id = $val[serial_num]['VAL'];
if (! in_array( $id, $sysids ))
{
$sysids[$sysid_count] = $id;
$sysid_count++;
}
}
}
sort( $sysids );
$cv = @fopen(/tmp/cv.txt,w);
foreach ($hosts_up as $host = $val)
{
fputs($cv,$host\n);
}
fputs($cv,=\n);
fputs($cv,sysid_count = $sysid_count\n);
fputs($cv,=\n);
foreach ($sysids as $id)
{
fputs($cv,$id\n);
}
fputs($cv,=\n);
foreach ($sysids as $id)
{
fputs($cv,--- $id\n);
foreach ($hosts_up as $host = $h)
{
if ( $metrics[$host][serial_num]['VAL'] == $id )
{
fputs($cv,$host\n);
}
}
}
fclose($cv);
Any help/hints regarding how a loop over all Ganglia nodes can be
accomplished in metaview.php would be highly welcome. Thanks.
Regards,
Michael
--
Beautiful is writing same markup. Internet Explorer 9 supports
standards for HTML5, CSS3, SVG 1.1, ECMAScript5, and DOM L2 L3.
Spend less time writing and rewriting code and more time creating great
experiences on the web. Be a part of the beta today
http://p.sf.net/sfu/msIE9-sfdev2dev___
Ganglia-developers mailing list
Ganglia-developers@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] [Ganglia-general] Ganglia 3.1.7 ready for testing
I have successfully compiled and tested 3.1.7 on - AIX 5.1 ML04 - AIX 5.3 ML00 - AIX 5.3 TL07 - AIX 6.1 TL03 Regards, Michael On 02/22/2010 12:15 PM, Daniel Pocock wrote: Just a reminder - any feedback is welcome, or feel free to discuss 3.1.7 on IRC It would be good to have positive confirmation of which platforms this has been tested on, so far, I have tested - Debian lenny, - RHEL3/4/5, - CentOS 5, - Solaris 8 and - Cygwin. and Brad has done some testing on SLES10 Regards, Daniel Daniel Pocock wrote: I've tagged 3.1.7 and built a tarball: http://ganglia.info/testing/ganglia-3.1.7.tar.gz The md5sum for 3.1.7 is: 6aa5e2109c2cc8007a6def0799cf1b4c Since 3.1.6, only two things have changed and may need to be tested again by those who tested 3.1.6: - the build system (support for commas in CFLAGS) - the multicpu module - percentages reported differently This is not confirmation that the release is in GA status - a further notification will be sent when the testing period has elapsed without any serious defect. Users are invited to test the tarball and submit feedback. Please do not commit on branches/monitor-core-3.1 until after 3.1.7 goes GA, in case further tweaks are needed to facilitate a successful release. Below are the release notes from the STATUS file. Other documentation has also changed since 3.1.2 and should be reviewed: GANGLIA 3.1 STATUS: -*-text-*- Last modified at [$Date: 2010-02-17 11:01:08 + (Wed, 17 Feb 2010) $] The current version of this file can be found at: * http://ganglia.svn.sourceforge.net/svnroot/ganglia/branches/monitor-core-3.1/STATUS Release history: 3.1.7 : Tagged: Feb 17, 2010 3.1.6 : Tagged: Feb 4, 2010 (not released for GA) 3.1.5(hargrave) : Tagged: Nov 24, 2009 (not released for GA) 3.1.4(hargrave) : Tagged: Oct 26, 2009 (not released for GA) 3.1.3(avenger): Tagged: Sep 19, 2009 (not released for GA) 3.1.2(langley): Released: Feb 17, 2009 3.1.1(wien) : Released: Sep 10, 2008 3.1.0(amelia) : Released: Jul 30, 2008 Contributors looking for a mission: * Just do an egrep on TODO, XXX or FIXME in the source. * Review the bug database at: http://bugzilla.ganglia.info/ * Open bugs in the bug database. * Implement a feature from the wishlist at: http://sourceforge.net/apps/trac/ganglia/wiki/ganglia_wish-list CURRENT RELEASE NOTES: (Please update this area with a brief description of bug fixes and enhancements that have been backported for the current release) Note: 3.1.3, 3.1.4, 3.1.5 and 3.1.6 never became GA, therefore, the release notes for all of them are combined below. 3.1.7: * Fix build support for RHEL5/issue with commas in CFLAGS * multicpu module: show CPU utilization as a value between 0-100% for each core 3.1.6: * Merge commit 1966 from trunk to fix contrib/removespikes.pl * Bootstrapping with Debian 5.0 (lenny) versions of autotools for this and future releases. http://www.mail-archive.com/ganglia-developers@lists.sourceforge.net/msg05352.html http://www.mail-archive.com/ganglia-gene...@lists.sourceforge.net/msg04688.html * Require user to explicitly specify sysconfdir when building from source, due to the fact that the old behavior was not consistent with the documented behavior. * Configuration files and scripts are now created during the install phase rather than during configure. This allows values such as @sysconfdir@ to be used in the template configuration files. * Abolish the use of release names - only release numbers will be used to distinguish versions in future * libmetrics: workaround system header conflict in DFBSD= 2.4 (BUG245) * Use PCRE regex matching to configure metrics using the name_match directive * rrdcached support * gmetad now uses apr and the sleep intervals between polls are randomized in a way that supports shorter polling intervals * FreeBSD support: fixes for crashes and disk statistics (BUG153) * Further tweaks to Solaris build support (remove C99 hack) * Eliminate conflict with ncpus symbol name on older Solaris * AIX support: determine if the host is a virtual server (BUG226) * AIX support: setting linker flags (BUG227), add -lm * AIX support: tweaks for AIX= v6.1 * AIX support: revised init scripts for gmond and gmetad * Check for Python.h explicitly * Include the necessary Python files in the distribution tarball, regardless of how BUILD_PYTHON is set (r2215). * Remove references to GNU toolchain in documentation * Fortify write_data_to_rrd against overflows * Web interface: minor formatting changes * mcast_if implementation tweaked so that the send channel will be bound to the IP of the outgoing interface
Re: [Ganglia-developers] ganglia 3.1.2 files
Hi Eric, in my opinion they should go into ganglia-gmond as they are the dynamically loaded modules by gmond and nobody else except gmond uses them. Regards, Michael On 02/10/2010 10:54 PM, Eric Shubert wrote: I'm attempting to update the ganglia packages I found at the epel repo for myself and possible inclusion at rpmforge. There are some apparently new files with this release, and I'd like to be sure I put them with the appropriate packages. I'm guessing that these files should go in the ganglia-devel package: /usr/include/ganglia_gexec.h /usr/include/gm_metric.h /usr/include/gm_mmn.h /usr/include/gm_msg.h /usr/include/gm_protocol.h /usr/include/gm_value.h The possible packages are: ganglia ganglia-gmetad ganglia-gmond ganglia-devel ganglia-web I don't know for sure where these modules should go: /usr/lib/ganglia/modcpu.so /usr/lib/ganglia/moddisk.so /usr/lib/ganglia/modload.so /usr/lib/ganglia/modmem.so /usr/lib/ganglia/modmulticpu.so /usr/lib/ganglia/modnet.so /usr/lib/ganglia/modproc.so /usr/lib/ganglia/modsys.so Can someone tell me relatively easily where they belong, or should I dig into the code to make my own determination? -- SOLARIS 10 is the OS for Data Centers - provides features such as DTrace, Predictive Self Healing and Award Winning ZFS. Get Solaris 10 NOW http://p.sf.net/sfu/solaris-dev2dev ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] AIX 3.1 branch, Michael's patches (BUG226, BUG227)
Hi Daniel,
I gave this tar-ball a quick try and here is the outcome:
I built it on my AIX 5.3 build host and you have to have the following
RPMs installed as prereqs for Ganglia to compile (you can get all those
from my website http://www.perzl.org/aix):
Here are the versions I used:
apr-1.3.9 and apr-devel-1.3.9
libconfuse-2.6 and libconfuse-devel-2.6
expat-2.0.1 and expat-devel-2.0.1
rrdtool-1.2.30 and rrdtool-devel 1.2.30
Please keep in mind that these RPMs again have prereqs which I am not
listing here.
Then I started the configure process as follows (using bash as shell):
CC=xlc_r -U_AIX43 ./configure --prefix=/var/tmp/gg --enable-shared
--disable-static --with-gmetad --disable-python --sysconfdir=/etc/ganglia
which finished successfully. The compilation (just using make) ran
successfully until the gmond link step.
The changed patch of BUG227 looks good to me, however now that fabsf()
is required the link step fails as no -lm is specified for the gmond
link step.
Just adding -lm to the link step (see below) did it:
/opt/freeware/bin/bash ../libtool --tag=CC--mode=link xlc_r -U_AIX43
-qlanglvl=extc99 -I../lib -I../include/ -I../libmetrics
-D_LARGEFILE64_SOURCE -DSYSCONFDIR='/etc/ganglia' -qmaxmem=16384
-DSYSV -D_AIX -D_AIX32 -D_AIX41 -D_AIX43 -D_AIX51 -D_AIX52 -D_AIX53
-D_ALL_SOURCE -DFUNCPROTO=15 -O -I/opt/freeware/include -D_ALL_SOURCE
-DAIX -DHAVE_PERFSTAT -Wl,-bexpfull -L/opt/freeware/lib
-L/opt/freeware/lib -o gmond gmond.o cmdline.o g25_config.o
core_metrics.o ../libmetrics/libmetrics.la ../lib/libganglia.la
../lib/libgetopthelper.a -ldl -lperfstat -lcfg -lodm -lnsl -lnsl
-lpcre -lexpat -lconfuse -lapr-1 -lpthreads -lpthread -lm
The remaining compilation then runs without any errors until finished.
So the GNU autotools guru need to figure out how to add an -lm to
gmond/Makefile.am (please see the patch in a different content below).
Some more comments on the libmetrics/aix/metrics file:
Please note all patches are done on the Ganglia 3.1.2 version, so the
line numbers might be slightly off for the 3.1.5 version.
The following patch is absolutely required to get it working on AIX 6.1:
***
*** 814,822
*/
/*
* AIX 4.2 uses bos.mp or bos.up
*/
getit = ODM_FIRST;
! while ((rc = (int)odm_get_obj(my_cl, name like bos.?p,
productobj, getit)) != 0) {
getit = ODM_NEXT;
if (rc == -1) {
--- 834,843
*/
/*
* AIX 4.2 uses bos.mp or bos.up
+ * AIX = 6.1 uses bos.mp64
*/
getit = ODM_FIRST;
! while ((rc = (int)odm_get_obj(my_cl, name like bos.?p*,
productobj, getit)) != 0) {
getit = ODM_NEXT;
if (rc == -1) {
The following patch is just cosmetics but nevertheless:
***
*** 832,838
}
}
/*
! * AIX 4.2 uses bos.mp or bos.up
*/
if (!found) {
getit = ODM_FIRST;
--- 853,859
}
}
/*
! * AIX 4.2 uses bos.rte.mp or bos.rte.up
*/
if (!found) {
getit = ODM_FIRST;
Now the more serious issue with DSOs on AIX:
In the current gmond compilation setup DSOs unfortunately don't work:
ganglia-3.1.5.2236/gmond ./gmond -m
Cannot load /var/tmp/gg/lib/ganglia/modcpu.so metric module:0509-022
Cannot load module /var/tmp/gg/lib/ganglia/modcpu.so.
0509-026 System error: A file or directory in the path name
does not exist.
Cannot load /var/tmp/gg/lib/ganglia/moddisk.so metric module: 0509-022
Cannot load module /var/tmp/gg/lib/ganglia/moddisk.so.
0509-026 System error: A file or directory in the path name
does not exist.
Cannot load /var/tmp/gg/lib/ganglia/modload.so metric module: 0509-022
Cannot load module /var/tmp/gg/lib/ganglia/modload.so.
0509-026 System error: A file or directory in the path name
does not exist.
Cannot load /var/tmp/gg/lib/ganglia/modmem.so metric module:0509-022
Cannot load module /var/tmp/gg/lib/ganglia/modmem.so.
0509-026 System error: A file or directory in the path name
does not exist.
Cannot load /var/tmp/gg/lib/ganglia/modnet.so metric module:0509-022
Cannot load module /var/tmp/gg/lib/ganglia/modnet.so.
0509-026 System error: A file or directory in the path name
does not exist.
Cannot load /var/tmp/gg/lib/ganglia/modproc.so metric module: 0509-022
Cannot load module /var/tmp/gg/lib/ganglia/modproc.so.
0509-026 System error: A file or directory in the path name
does not exist.
Cannot load /var/tmp/gg/lib/ganglia/modsys.so metric module:0509-022
Cannot load module /var/tmp/gg/lib/ganglia/modsys.so.
0509-026 System error: A file or directory in the path name
does not exist.
Cannot load /var/tmp/gg/lib/ganglia/modibmpower.so metric module:
0509-022 Cannot load module /var/tmp/gg/lib/ganglia/modibmpower.so.
0509-026 System error: A file or directory in the path name
does not exist.
heartbeat
Re: [Ganglia-developers] AIX 3.1 branch, Michael's patches (BUG226, BUG227)
On 01/15/2010 05:39 PM, Daniel Pocock wrote: I built it on my AIX 5.3 build host and you have to have the following RPMs installed as prereqs for Ganglia to compile (you can get all those from my website http://www.perzl.org/aix): Here are the versions I used: apr-1.3.9 and apr-devel-1.3.9 libconfuse-2.6 and libconfuse-devel-2.6 expat-2.0.1 and expat-devel-2.0.1 rrdtool-1.2.30 and rrdtool-devel 1.2.30 Do I need to take any action, e.g. do you want configure to check for these? Are you trying to use the spec file and do you want it to enforce those versions, or is this information just for the README? No, I was just summarizing what prereqs I was using for my tests. This is definitely something for the README. which finished successfully. The compilation (just using make) ran successfully until the gmond link step. The changed patch of BUG227 looks good to me, however now that fabsf() is required the link step fails as no -lm is specified for the gmond link step. For AIX 5.2, it should be using fabs, not fabsf. The macro causes the fabsf call to be redirected to fabs -lm will definitely be in the next snapshot I give you - is this needed for all AIX versions or just some versions? yes, for AIX 5.1 the macro is expanded to fabs. On my build hosts (AIX 5.1, 5.2, 5.3 and 6.1) -lm is always needed. I was looking at a document that told me _AIX52 would be defined on all versions = 5.2 - do you believe that is correct, or is it only defined on that exact version? Speaking for the IBM XLC/C++ compiler this is definitely true, for GCC I still have to check. I always set the appropriate environment variables on the different levels of AIX (I don't want to run into any surprises :-) ) as documented at: http://www.perzl.org/aix/index.php?n=Main.Instructions The following patch is absolutely required to get it working on AIX 6.1: I will apply this patch for the next snapshot - this will be safe on any AIX version? Yes, I have just verified it on AIX 5.1, 5.2, 5.3 and 6.1. I had already applied that on the branch, but to make the code portable between AIX and other platforms, I did this by setting EXPORT_SYMBOLS_DYNAMIC in configure.in and using it's value in gmond/Makefile.am Can you please look at whether EXPORT_SYMBOLS_DYNAMIC is being used properly? Please share the output of this command: egrep 'DYN|STATIC' config.status Here the output against config.status in the Ganglia root directory: s,@STATIC_BUILD_TRUE@,|#_!!_#|#,g s,@STATIC_BUILD_FALSE@,|#_!!_#|,g s,@STATIC_USER_MODULES@,|#_!!_#|,g s,@EXPORT_SYMBOLS_DYNAMIC@,|#_!!_#|-Wl\,-bexpfull,g The output against libmetrics/config.status is empty. I also had to apply the following patch to libmetrics/aclocal.m4 (essentially removing any -berok occurrences): I want to avoid patching aclocal.m4 and try to find the right way to make this work Looking at the comments in the code, do you know about the -brtl suggestion? Can you try that flag in your LDFLAGS? I will comment this separately, this takes longer :-) Could you also post this particular issue on the list autom...@gnu.org? Someone else may already know the solution straight away. Ok, good tip. Regards, Michael -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] AIX 3.1 branch, Michael's patches (BUG226, BUG227)
On 01/15/2010 06:18 PM, Daniel Pocock wrote: Here the output against config.status in the Ganglia root directory: s,@STATIC_BUILD_TRUE@,|#_!!_#|#,g s,@STATIC_BUILD_FALSE@,|#_!!_#|,g s,@STATIC_USER_MODULES@,|#_!!_#|,g s,@EXPORT_SYMBOLS_DYNAMIC@,|#_!!_#|-Wl\,-bexpfull,g The output against libmetrics/config.status is empty. I haven't implemented it for libmetrics/configure.in (yet) - it is needed there too? My current implementation of that is only used in gmond/Makefile.am, but I can duplicate it to libmetrics if it is needed there Yes please, this seems to be vital. Here is the difference in the output of gmond -m for gmond linked with libmetrics (linked without -Wl,-bexpfull): # ./gmond -m Cannot locate internal module structure 'core_metrics' in file : The system call does not exist on this system. (core_metrics) Possibly an incorrect module language designation []. load_oneOne minute load average (module load_module) os_release Operating system release date (module sys_module) mem_total Total amount of memory displayed in KBs (module mem_module) cpu_intrcpu_intr (module cpu_module) .. gmond linked with libmetrics (linked WITH -Wl,-bexpfull): # ./gmond -m load_oneOne minute load average (module load_module) os_release Operating system release date (module sys_module) mem_total Total amount of memory displayed in KBs (module mem_module) cpu_intrcpu_intr (module cpu_module) I also had to apply the following patch to libmetrics/aclocal.m4 (essentially removing any -berok occurrences): I want to avoid patching aclocal.m4 and try to find the right way to make this work Looking at the comments in the code, do you know about the -brtl suggestion? Can you try that flag in your LDFLAGS? I will comment this separately, this takes longer :-) Could you also post this particular issue on the list autom...@gnu.org? Someone else may already know the solution straight away. Ok, good tip. Maybe doing the step (libmetrics with -Wl,-bexpfull) might be sufficient and not require the steps above anymore... Regards, Michael -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] Question on the Ganglia RRD Database
Hi Martin, I think this is how the default monitoring intervals have to be interpreted: RRAs \ RRA:AVERAGE:0.5:1:240\ RRA:AVERAGE:0.5:24:240 \ RRA:AVERAGE:0.5:168:240 \ RRA:AVERAGE:0.5:672:240 \ RRA:AVERAGE:0.5:5760:370 used for display of Take 240 samples at15 seconds intervalshour Take 240 samples at 24 × 15 seconds (= 6 minutes) intervalsday Take 240 samples at 168 × 15 seconds (= 42 minutes) intervalsweek Take 240 samples at 672 × 15 seconds (= 168 minutes) intervalsmonth Take 370 samples at 5760 × 15 seconds (= 24 hours)intervalsyear So I think for your case you have to decide how many samples of the chosen sampling rate (20 minutes, 8 hours etc.) you want to collect which then determines the overall time interval covered by this specific sampling rate. The main question is: How granular do you want the sampling rate to be for a given time interval? This then determines: a) the number of multiples of 15 seconds (to get the sampling rate) b) the total number of samples required (number of samples x sampling rate = time interval) Hope that helps. Regards, Michael On 11/25/2009 02:24 PM, Martin Knoblauch wrote: Hi folks, currently I am setting up monitoring for a cluster, where the demand is to have additional monitoring intervalls. We want to see stuff like 20-minutes, 8-hours, 2-weeks, 3-month and 6-month. Doing so seems easy, but I have a question on the RRA definitions. The default setup seems to be (assuming a 15 second polling intervall): hour- RRA:AVERAGE:0.5:1:244 day - RRA:AVERAGE:0.5:24:244 week - RRA:AVERAGE:0.5:168:244 month - RRA:AVERAGE:0.5:672:244 (more like 4-weeks :-) year- RRA:AVERAGE:0.5:5760:374 (367.86 days) So from hour to month we have 244 datapoints with nicely increasing steps (1,24*1,7*24*1,4*7*24*1). So why are we doing it differently for the year? I would have expected the year RRA to be RRA:AVERAGE:0.5:8784:244 (366 days). Any particular reasons for this? Cheers Martin -- Martin Knoblauch email: k n o b i AT knobisoft DOT de www: http://www.knobisoft.de -- Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day trial. Simplify your report design, integration and deployment - and focus on what you do best, core application coding. Discover what's new with Crystal Reports now. http://p.sf.net/sfu/bobj-july ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers -- Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day trial. Simplify your report design, integration and deployment - and focus on what you do best, core application coding. Discover what's new with Crystal Reports now. http://p.sf.net/sfu/bobj-july ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
[Ganglia-developers] New DSO gmond module with IBM POWER5/6 specific extensions for Linux on POWER
Dear Ganglia developers, I have submitted a patch (bugzilla #225 with attachment #184) which provides a new DSO gmond module for IBM AIX systems. This gmond module implements IBM POWER5- and POWER6-specific extensions like: - SPLPAR - SMT - CPU Entitlement - Capped/Uncapped - etc. The code has been tested with on the following systems (all PowerPC-based): - SLES 9 and SLES 10 - RHEL 4 AS and RHEL 5 AS - openSUSE 10.0, 10.1, 10.2 and 10.3 - Fedora Core 4, 5, 6, 7, 8. 9 and 10 This should go into a separate gmond/modules/ subdirectory and would be best called ibmpower. Regards, Michael -- This SF.net email is sponsored by: SourcForge Community SourceForge wants to tell your story. http://p.sf.net/sfu/sf-spreadtheword ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
[Ganglia-developers] New DSO gmond module with IBM POWER5/6 specific extensions for AIX
Dear Ganglia developers, I have submitted a patch (bugzilla #224 with attachment #183) which provides a new DSO gmond module for IBM AIX systems. This gmond module implements IBM POWER5- and POWER6-specific extensions like: - SPLPAR - SMT - CPU Entitlement - Capped/Uncapped - etc. The libperfstat API is used and it can deal with a 32-bit and a 64-bit kernel and does not require root authority. The code has been tested with AIX 5.1, AIX 5.2, AIX 5.3 and AIX 6.1 on different systems. This should go into a separate gmond/modules/ subdirectory and would be best called ibmpower. Regards, Michael -- This SF.net email is sponsored by: SourcForge Community SourceForge wants to tell your story. http://p.sf.net/sfu/sf-spreadtheword ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
[Ganglia-developers] Patch for AIX libmetrics implementation to discover a Virtual I/O Server
Dear Ganglia developers, I have submitted a patch (bugzilla #226 with attachment #185) which enhances the AIX libmetrics implementation to discover if it is running on an IBM Virtual I/O Server. The code has been tested with AIX 5.1, AIX 5.2, AIX 5.3 and AIX 6.1 on different systems. Regards, Michael -- This SF.net email is sponsored by: SourcForge Community SourceForge wants to tell your story. http://p.sf.net/sfu/sf-spreadtheword___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
[Ganglia-developers] IBM POWER5/6-aware Ganglia version 3.0.7 and RPMs for AIX and Linux on Power available
POWER5/6-aware Ganglia version 3.0.7 and RPMs for AIX and Linux on Power are now available from my website at http://www.perzl.org/ganglia/ I have updated my POWER5/6 modifications and applied them to Ganglia version 3.0.7. On my website you'll find the POWER5/6 modifications, binary and source RPMs for all AIX versions as well as most Linux distributions which run on POWER5/6. Thanks and have fun with the stuff... Michael - This SF.net email is sponsored by the 2008 JavaOne(SM) Conference Register now and save $200. Hurry, offer ends at 11:59 p.m., Monday, April 7! Use priority code J8TLD2. http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
[Ganglia-developers] IBM POWER5/6-aware Ganglia version 3.0.5 and RPMs for AIX and Linux on POWER available
IBM POWER5/6-aware Ganglia version 3.0.5 and RPMs for AIX and Linux on POWER are now available on my personal Ganglia website. This will hopefully make it easier for people interested in Ganglia on POWER5/6 to get ahold of the adapted versions for POWER5/6. Here is the URL: http://www.perzl.org/ganglia/ I have updated my POWER5/6 modifications and applied them to Ganglia version 3.0.5. The following fixes are included: * Linux: POWER5/6-only 'disk_write' and 'disk_read' statistics were corrected * AIX: The network overflow problem (network throughput in the Petabyte range) should be fixed now. I have also updated the version 3.0.4 RPMs and they also include the fixes mentioned above. On my website you'll find the POWER5/6 modifications, binary and source RPMs for all AIX 5L versions as well as most Linux distributions which run on POWER5/6. Have fun with the stuff... Michael - This SF.net email is sponsored by: Splunk Inc. Still grepping through log files to find problems? Stop. Now Search log events and configuration files using AJAX and a browser. Download your FREE copy of Splunk now http://get.splunk.com/___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] IBM POWER5/6-aware Ganglia version 3.0.5 and RPMs for AIX and Linux on POWER available
Hi Bernard, no problem, just let me know when I should integrate my patches for AIX into ganglia.spec.in and I'll do it. Regards, Michael Bernard Li wrote: Hi Michael: Once we make changes to ganglia.spec.in in trunk, do you mind re-basing your patch for trunk and get it integrated? I am sorry for the email-tag that prevented us from getting this integrated, but let's dedicate some time frame in the next little while to ensure that we both have time to work on this and get it fully integrated. Thanks, Bernard On 10/17/07, Michael Perzl [EMAIL PROTECTED] wrote: IBM POWER5/6-aware Ganglia version 3.0.5 and RPMs for AIX and Linux on POWER are now available on my personal Ganglia website. This will hopefully make it easier for people interested in Ganglia on POWER5/6 to get ahold of the adapted versions for POWER5/6. Here is the URL: http://www.perzl.org/ganglia/ I have updated my POWER5/6 modifications and applied them to Ganglia version 3.0.5. The following fixes are included: Linux: POWER5/6-only 'disk_write' and 'disk_read' statistics were corrected AIX: The network overflow problem (network throughput in the Petabyte range) should be fixed now. I have also updated the version 3.0.4 RPMs and they also include the fixes mentioned above. On my website you'll find the POWER5/6 modifications, binary and source RPMs for all AIX 5L versions as well as most Linux distributions which run on POWER5/6. Have fun with the stuff... Michael - This SF.net email is sponsored by: Splunk Inc. Still grepping through log files to find problems? Stop. Now Search log events and configuration files using AJAX and a browser. Download your FREE copy of Splunk now http://get.splunk.com/ ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers - This SF.net email is sponsored by: Splunk Inc. Still grepping through log files to find problems? Stop. Now Search log events and configuration files using AJAX and a browser. Download your FREE copy of Splunk now http://get.splunk.com/ ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] Ganglia 3.0.x development
Hi Bernard, I have submitted via Bugzilla (bug #146) the complete rewrite of the gmond implementation for AIX which can be used as a drop-in replacement. It also contains all the POWER5 specific enhancements as described on my website http://www.perzl.org/ganglia. In order to get the POWER5 specific metrics enabled in Ganglia some more patches to Ganglia source files need to be applied. This gmond implementation has been tested on and works on the following AIX levels: - AIX v4.3.3 - AIX v5.1 - AIX v5.2 - AIX v5.3 It has been tested as a drop-in replacement against the following Ganglia versions: - 3.0.4 - 3.0.5.200705231853 Regards, Michael Bernard Li wrote: Hi Ulf: If Michael can provide us with patches against branch/trunk, someone will be able to review them and check them in. However, I haven't heard from him for a while now. Cheers, Bernard On 5/16/07, Ulf [EMAIL PROTECTED] wrote: Hi, have you ever checked out http://www.perzl.org/ganglia/ , these will add some power 5 metrics to ganglia, which are working fine. Tested for about 2 months on AIX 5.3. Is it possible to integrate them, or will it conflict with some kind of license? Best regads, Ulf Bernard Li schrieb: Do we currently have plans for Ganglia 3.0.5 release? I would personally like to see a release very soon -- we have made a few enhancements to the webfrontend plus other cleanups to the code. Also, given our developer base, we should probably wrap up 3.0.x branch and start focusing on 3.1.x (unless we have other plans for 3.0.x branch). However, it looks like since the branch was created, most changes were still done to trunk (my changes included). Can we agree on what changes should go into 3.0.x branch vs trunk? I would think that all the dynamically link libraries work which Brad has been working on should stay in trunk -- however, if there are conflicting changes done to the branch, they should be reverted. I could try to go through my recent changes and make sure that they go into the branch as well -- I hope that other developers can do the same. Makes sense? Thanks in advance, Bernard - This SF.net email is sponsored by DB2 Express Download DB2 Express C - the FREE version of DB2 express and take control of your XML. No limits. Just data. Click to get it now. http://sourceforge.net/powerbar/db2/ ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers - This SF.net email is sponsored by DB2 Express Download DB2 Express C - the FREE version of DB2 express and take control of your XML. No limits. Just data. Click to get it now. http://sourceforge.net/powerbar/db2/ ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers - This SF.net email is sponsored by DB2 Express Download DB2 Express C - the FREE version of DB2 express and take control of your XML. No limits. Just data. Click to get it now. http://sourceforge.net/powerbar/db2/___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] AIX Consolidation
Hi Bernard,
I took a closer look and though I think it could be done it might be
very ugly for the following reasons:
- AIX is still using RPM version 3.0.5 and I am not aware of any
intentions to upgrade anytime soon
- Like I said I think it could be consolidated, however, that would
probably require tons of %ifarch ppc and %ifnarch ppc defines which
would make the SPEC file rather hard to read
- AIX RPM is installing all the software under the /opt/freeware
directory hierarchy (to better distinguish from the AIX base filesets),
therefore lots of different file locations in the SPEC file would have
to ifdef'ed as mentioned above.
- All the Linux specific stuff like chkconfig would have to be
%ifdef'ed appropriately.
A quick solution would probably to just rename the committed
ganglia.aix.spec to maybe ganglia.spec.aix so your rpmbuild command
doesn't get mixed up.
I'll give it a try and see how far I get along but the end result might
be ugly :-)
Regards,
Michael
Bernard Li wrote:
Hi Michael:
Any chance you can also work on merging the ganglia.aix.spec file back
to the mainstream .spec file? I'm about to change configure.in to
only include the specific spec file depending on the OS, but I think
the better solution is just to merge the two. Right now I cannot just
generate the distribution tarball and run 'rpmbuild -ta' since there
are 2 spec files.
Thanks in advance,
Bernard
On 4/2/07, Michael Perzl [EMAIL PROTECTED] wrote:
Hi Martin,
if possible I would like to somehow take my version (after some
reviewing)
:-), as it contains all the new POWER5 stuff already.
My understanding is - as it would require some changes to protocol.x
- that
my changes won't have a chance to get into the core Ganglia source code
until version 3.1 comes along.
This code and everything else (RPMs) can be found on my website
http://www.perzl.org/ganglia/.
This stuff is actually in use at quite many customer sites already
(runs on
AIX 4.3.3, 5.1, 5.2 and 5.3) so I would like to keep that
POWER5-stuff in if
possible. Actually, an AIX gmond implementation without the POWER5-stuff
based on my implementation could be done very easy (just stripping
off the
POWER5-addons).
Regards,
Michael
Martin Knoblauch wrote:
Michael, Andreas,
any chance that you could consolidate the two versions of the AIX
metrics that seem to be around? Seem you are the ones who have worked
most recently on the AIX implementation.
Cheers
Martin
--- Michael Perzl [EMAIL PROTECTED] wrote:
Andreas,
thank you for taking the blame but you are off the hook here. ;-)
If I understood David correctly, he is using my AIX Ganglia RPM
packages
with POWER5 extensions. Here most if not all implementation of how
the
metrics are collected under AIX have been changed. Everything is
documented on my homepage (http://www.perzl.org/ganglia/) though.
So everything what goes wrong here is entiremy my fault :-[
After some investigating and some discussions with Nigel I have come
to
terms with the following facts regarding the bytes_in/bytes_out
problem:
- libperfstat (the library on AIX which obtains all the system
performance data) uses u_longlong_t data types (these are definitely
64-bit large).
- The AIX kernel internally, though, may probably not be using 64-bit
data types - more realistic is probably unsigned 32-bit - in order
not
to break compatibility (my personal opinion)
- The consequence now is that integer overrun may occur much easier
with
32-bit data types than with 64-bit data types (we all probably don't
live long enough to see that happen).
Please take a look at my implementation of the bytes_in metric (the
bytes_out implementation is accordingly):
01 g_val_t
02 bytes_in_func( void )
03 {
04 g_val_t val;
05 perfstat_netinterface_total_t n;
06 static u_longlong_t last_bytes_in = 0, bytes_in;
07 static double last_time = 0.0;
08 double now, delta_t;
09 struct timeval timeValue;
10 struct timezone timeZone;
11
12 gettimeofday( timeValue, timeZone );
13
14 now = (double) (timeValue.tv_sec - boottime) +
(timeValue.tv_usec
/ 100.0);
15
16 if (perfstat_netinterface_total( NULL, n, sizeof(
perfstat_netinterface_total_t ), 1 ) == -1)
17 val.f = 0.0;
18 else
19 {
20 bytes_in = n.ibytes;
21
22 delta_t = now - last_time;
23
24 if ( delta_t )
25 val.f = (double) (bytes_in - last_bytes_in) / delta_t;
26 else
27 val.f = 0.0;
28
29 last_bytes_in = bytes_in;
30 }
31
32 last_time = now;
33
34 return( val );
35 }
In my opinion the overrun occurs in line #25 when bytes_in
last_bytes_in.
In my naivity I had assumed as both are of type u_longlong_t that an
integer overrun might never happen.
So to solve the overrun a check for bytes_in last_bytes_in must
be
introduced, something like:
u_longlong_t d;
d = bytes_in - last_bytes_in;
if (d 0) d += ULONG_MAX;
and line #25 would essentially become
25 val.f = (double) d / delta_t;
Comments ?
Regards,
Michael
PS: David, the reason why you don't see it happen
Re: [Ganglia-developers] AIX Consolidation
Hi Bernard,
I now have a consolidated SPEC file (I think it is ugly :-) ), so how do
you want me to send it to you (I guess not posting to the mailing list
:-) ) ?
Regards,
Michael
Bernard Li wrote:
Hi Michael:
Thanks for looking into this. Yes, I am aware the spec file may get
bloated but I think ultimately this will be better for one (or more
person) to manage (as opposed to managing multiple files).
What do other devs/users think?
BTW, I'm cc: Marcus to see if he has any specific insights on this :-)
Cheers,
Bernard
On 4/2/07, Michael Perzl [EMAIL PROTECTED] wrote:
Hi Bernard,
I took a closer look and though I think it could be done it might be
very ugly for the following reasons:
- AIX is still using RPM version 3.0.5 and I am not aware of any
intentions to upgrade anytime soon
- Like I said I think it could be consolidated, however, that would
probably require tons of %ifarch ppc and %ifnarch ppc defines which
would make the SPEC file rather hard to read
- AIX RPM is installing all the software under the /opt/freeware
directory hierarchy (to better distinguish from the AIX base filesets),
therefore lots of different file locations in the SPEC file would have
to ifdef'ed as mentioned above.
- All the Linux specific stuff like chkconfig would have to be
%ifdef'ed appropriately.
A quick solution would probably to just rename the committed
ganglia.aix.spec to maybe ganglia.spec.aix so your rpmbuild command
doesn't get mixed up.
I'll give it a try and see how far I get along but the end result might
be ugly :-)
Regards,
Michael
Bernard Li wrote:
Hi Michael:
Any chance you can also work on merging the ganglia.aix.spec file back
to the mainstream .spec file? I'm about to change configure.in to
only include the specific spec file depending on the OS, but I think
the better solution is just to merge the two. Right now I cannot just
generate the distribution tarball and run 'rpmbuild -ta' since there
are 2 spec files.
Thanks in advance,
Bernard
On 4/2/07, Michael Perzl [EMAIL PROTECTED] wrote:
Hi Martin,
if possible I would like to somehow take my version (after some
reviewing)
:-), as it contains all the new POWER5 stuff already.
My understanding is - as it would require some changes to protocol.x
- that
my changes won't have a chance to get into the core Ganglia source
code
until version 3.1 comes along.
This code and everything else (RPMs) can be found on my website
http://www.perzl.org/ganglia/.
This stuff is actually in use at quite many customer sites already
(runs on
AIX 4.3.3, 5.1, 5.2 and 5.3) so I would like to keep that
POWER5-stuff in if
possible. Actually, an AIX gmond implementation without the
POWER5-stuff
based on my implementation could be done very easy (just stripping
off the
POWER5-addons).
Regards,
Michael
Martin Knoblauch wrote:
Michael, Andreas,
any chance that you could consolidate the two versions of the AIX
metrics that seem to be around? Seem you are the ones who have worked
most recently on the AIX implementation.
Cheers
Martin
--- Michael Perzl [EMAIL PROTECTED] wrote:
Andreas,
thank you for taking the blame but you are off the hook here. ;-)
If I understood David correctly, he is using my AIX Ganglia RPM
packages
with POWER5 extensions. Here most if not all implementation of how
the
metrics are collected under AIX have been changed. Everything is
documented on my homepage (http://www.perzl.org/ganglia/) though.
So everything what goes wrong here is entiremy my fault :-[
After some investigating and some discussions with Nigel I have come
to
terms with the following facts regarding the bytes_in/bytes_out
problem:
- libperfstat (the library on AIX which obtains all the system
performance data) uses u_longlong_t data types (these are definitely
64-bit large).
- The AIX kernel internally, though, may probably not be using 64-bit
data types - more realistic is probably unsigned 32-bit - in order
not
to break compatibility (my personal opinion)
- The consequence now is that integer overrun may occur much easier
with
32-bit data types than with 64-bit data types (we all probably don't
live long enough to see that happen).
Please take a look at my implementation of the bytes_in metric (the
bytes_out implementation is accordingly):
01 g_val_t
02 bytes_in_func( void )
03 {
04 g_val_t val;
05 perfstat_netinterface_total_t n;
06 static u_longlong_t last_bytes_in = 0, bytes_in;
07 static double last_time = 0.0;
08 double now, delta_t;
09 struct timeval timeValue;
10 struct timezone timeZone;
11
12 gettimeofday( timeValue, timeZone );
13
14 now = (double) (timeValue.tv_sec - boottime) +
(timeValue.tv_usec
/ 100.0);
15
16 if (perfstat_netinterface_total( NULL, n, sizeof(
perfstat_netinterface_total_t ), 1 ) == -1)
17 val.f = 0.0;
18 else
19 {
20 bytes_in = n.ibytes;
21
22 delta_t = now - last_time;
23
24 if ( delta_t )
25 val.f
Re: [Ganglia-developers] AIX Consolidation
Hi Bernard,
ok, here you go the SPEC file as attachment.
Some remarks still:
a) Lines #39-#41 I couldn't get RPM v3.0.5 on AIX get to understand that
%if directive, also when I googled I think that the %if statement is
not supported with RPM v.3.05, so I commented those 3 lines for the moment.
b) Line #387 (%config(noreplace) %{web_prefixdir}/conf.php) gave me
always file listed twice RPM errors so I commented it for the moment.
Regards,
Michael
Bernard Li wrote:
Hi Michael:
Filing a bug and attaching the patch would be nice. Or you could just
post it here.
Thanks,
Bernard
On 4/2/07, Michael Perzl [EMAIL PROTECTED] wrote:
Hi Bernard,
I now have a consolidated SPEC file (I think it is ugly :-) ), so how do
you want me to send it to you (I guess not posting to the mailing list
:-) ) ?
Regards,
Michael
Bernard Li wrote:
Hi Michael:
Thanks for looking into this. Yes, I am aware the spec file may get
bloated but I think ultimately this will be better for one (or more
person) to manage (as opposed to managing multiple files).
What do other devs/users think?
BTW, I'm cc: Marcus to see if he has any specific insights on this :-)
Cheers,
Bernard
On 4/2/07, Michael Perzl [EMAIL PROTECTED] wrote:
Hi Bernard,
I took a closer look and though I think it could be done it might be
very ugly for the following reasons:
- AIX is still using RPM version 3.0.5 and I am not aware of any
intentions to upgrade anytime soon
- Like I said I think it could be consolidated, however, that would
probably require tons of %ifarch ppc and %ifnarch ppc defines
which
would make the SPEC file rather hard to read
- AIX RPM is installing all the software under the /opt/freeware
directory hierarchy (to better distinguish from the AIX base
filesets),
therefore lots of different file locations in the SPEC file would
have
to ifdef'ed as mentioned above.
- All the Linux specific stuff like chkconfig would have to be
%ifdef'ed appropriately.
A quick solution would probably to just rename the committed
ganglia.aix.spec to maybe ganglia.spec.aix so your rpmbuild command
doesn't get mixed up.
I'll give it a try and see how far I get along but the end result
might
be ugly :-)
Regards,
Michael
Bernard Li wrote:
Hi Michael:
Any chance you can also work on merging the ganglia.aix.spec
file back
to the mainstream .spec file? I'm about to change configure.in to
only include the specific spec file depending on the OS, but I
think
the better solution is just to merge the two. Right now I
cannot just
generate the distribution tarball and run 'rpmbuild -ta' since
there
are 2 spec files.
Thanks in advance,
Bernard
On 4/2/07, Michael Perzl [EMAIL PROTECTED] wrote:
Hi Martin,
if possible I would like to somehow take my version (after some
reviewing)
:-), as it contains all the new POWER5 stuff already.
My understanding is - as it would require some changes to
protocol.x
- that
my changes won't have a chance to get into the core Ganglia source
code
until version 3.1 comes along.
This code and everything else (RPMs) can be found on my website
http://www.perzl.org/ganglia/.
This stuff is actually in use at quite many customer sites
already
(runs on
AIX 4.3.3, 5.1, 5.2 and 5.3) so I would like to keep that
POWER5-stuff in if
possible. Actually, an AIX gmond implementation without the
POWER5-stuff
based on my implementation could be done very easy (just stripping
off the
POWER5-addons).
Regards,
Michael
Martin Knoblauch wrote:
Michael, Andreas,
any chance that you could consolidate the two versions of the AIX
metrics that seem to be around? Seem you are the ones who have
worked
most recently on the AIX implementation.
Cheers
Martin
--- Michael Perzl [EMAIL PROTECTED] wrote:
Andreas,
thank you for taking the blame but you are off the hook here. ;-)
If I understood David correctly, he is using my AIX Ganglia RPM
packages
with POWER5 extensions. Here most if not all implementation of how
the
metrics are collected under AIX have been changed. Everything is
documented on my homepage (http://www.perzl.org/ganglia/) though.
So everything what goes wrong here is entiremy my fault :-[
After some investigating and some discussions with Nigel I have
come
to
terms with the following facts regarding the bytes_in/bytes_out
problem:
- libperfstat (the library on AIX which obtains all the system
performance data) uses u_longlong_t data types (these are
definitely
64-bit large).
- The AIX kernel internally, though, may probably not be using
64-bit
data types - more realistic is probably unsigned 32-bit - in order
not
to break compatibility (my personal opinion)
- The consequence now is that integer overrun may occur much
easier
with
32-bit data types than with 64-bit data types (we all probably
don't
live
[Ganglia-developers] IBM POWER5-aware Ganglia version 3.0.4 and RPMs for AIX and Linux on POWER available
Please take a look at my personal Ganglia website which will hopefully make it easier for people interested in Ganglia on POWER5 to get ahold of the adapted versions for POWER5. Here is the URL: http://www.perzl.org/ganglia/ I have updated my POWER5 modifications and applied them to Ganglia version 3.0.4. Also a mistake in the POWER5-only 'disk_write' and 'disk_read' was corrected (occurred on Linux only) and newer versions of the v3.0.3 RPMS for Linux are also available. On my website you'll find the POWER5 modifications, a unified context diff and binary and source RPMs for all AIX 5L versions as well as most Linux distributions which run on POWER5. Thanks and have fun with the stuff... Michael
[Ganglia-developers] IBM POWER5-aware Ganglia version and RPMs for AIX and Linux on POWER available
Please take a look at my personal Ganglia website which will hopefully make it easier for people interested in Ganglia on POWER5 to get ahold of the adapted version for POWER5. Here is the URL: http://www.perzl.org/ganglia/ There you'll find the POWER5 modifications, a unified context diff and binary and source RPMs for all AIX 5L versions as well as most Linux distributions which run on POWER5. Ganglia is currently at version v3.0.3. My proposed patches will not make it entirely into the upcoming release v3.0.4 but hopefully into the future release v3.1. However, as soon as version v3.0.4 comes out I will update my personal website again and provide the same stuff for v3.0.4 as I currently do for v3.0.3. Thanks and have fun with the stuff... Michael
[Ganglia-developers] New stuff for AIX as previously announced
I have submitted via Bugzilla (http://bugzilla.ganglia.info) the following entries: new gmond init script for AIX: Bugzilla entry #106 new gmetad init script for AIX: Bugzilla entry #107 RPM SPEC file for AIX (uses the IBM compilers): Bugzilla entry #108 Alternatively, you can also find the stuff at: http://www.perzl.org/gangia/ Regards, Michael
Re: [Ganglia-developers] New stuff for AIX as previously announced
Sorry, just noticed I had a small typo in the URL... Michael Perzl wrote: I have submitted via Bugzilla (http://bugzilla.ganglia.info) the following entries: new gmond init script for AIX: Bugzilla entry #106 new gmetad init script for AIX: Bugzilla entry #107 RPM SPEC file for AIX (uses the IBM compilers): Bugzilla entry #108 Alternatively, you can also find the stuff at: http://www.perzl.org/gangia/ This should read of course: http://www.perzl.org/ganglia/ Regards, Michael Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnkkid=120709bid=263057dat=121642 ___ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
Re: [Ganglia-developers] New Ganglia metrics for AIX and Linux on POWER
Hi Martin, please find everything for review on the following web site: http://www.perzl.org/ganglia/ The only thing missing there is still the general description on how to add metrics to Ganglia. Regards, Michael Martin Knoblauch wrote: Hi Michael, --- Michael Perzl [EMAIL PROTECTED] wrote: Dear Ganglia developers, working for technical support in IBM a colleague (Nigel Griffiths ([EMAIL PROTECTED])) and myself have in our spare time extended the current (v3.0.3) Ganglia metrics for AIX and Linux. This was done to make Ganglia aware of the virtualization capabilities of IBM POWER5 systems (like Shared Processor LPARs etc.). Also some corrections to existing metrics were done. We would like to contribute these extensions now. Specifically, the list of changes/extensions includes: - new POWER5 metrics for AIX - new POWER5 metrics for Linux A more explicit description of the new stuff would be good. - inclusion of the new metrics into Ganglia framework - RPM SPEC file for AIX (uses the IBM compilers) - init scripts (for gmond and gmetad) for AIX Cool. We have also written some documents which we would like to contribute: - Description of the new metrics on AIX - Description of the new metrics for Linux on POWER Pointers? And patches :-) - General description on how to add metrics to Ganglia (might be useful for any platform) Definitely more than useful :-) Extending the core metrics set is a tedious process and not good documented so far. Can someone please recommend what would be the best way to contribute some or all of that stuff? I assume posting to that list is not the best idea :-) Actually, to discuss the concepts the list is the best place. If you want to contribute code, one way would be to open a bugzilla entry and add your patches. These new metrics have been tested (for a couple of months now) on the following systems: - POWER3 standalone systems - POWER4 standalone and LPAR-systems - POWER5 LPAR systems (virtualized environment) The following OS versions have been tested with these extensions: - AIX 5L v5.1, v5.2 and v5.3 and IBM Virtual I/O Server - SLES9 on POWER, RHEL4 on POWER - openSUSE 10.0 and 10.1 on POWER - Fedora Core 4 and 5 on POWER Also we did put up some documentation on the IBM AIX wiki pages (http://www.ibm.com/collaboration/wiki/display/WikiPtype/). A general discussion about AIX and Open Source programs can be found here (specifically if you want to run a recent version of Apache httpd and PHP on AIX as required for gmetad): http://www.ibm.com/collaboration/wiki/display/WikiPtype/aixopen Comprehensive Ganglia setup instructions for first time users are available at: http://www.ibm.com/collaboration/wiki/display/WikiPtype/ganglia Any feedback/comments very much welcome... Regards, Michael Cheers Martin -- Martin Knoblauch email: k n o b i AT knobisoft DOT de www: http://www.knobisoft.de
[Ganglia-developers] New Ganglia metrics for AIX and Linux on POWER
Dear Ganglia developers, working for technical support in IBM a colleague (Nigel Griffiths ([EMAIL PROTECTED])) and myself have in our spare time extended the current (v3.0.3) Ganglia metrics for AIX and Linux. This was done to make Ganglia aware of the virtualization capabilities of IBM POWER5 systems (like Shared Processor LPARs etc.). Also some corrections to existing metrics were done. We would like to contribute these extensions now. Specifically, the list of changes/extensions includes: - new POWER5 metrics for AIX - new POWER5 metrics for Linux - inclusion of the new metrics into Ganglia framework - RPM SPEC file for AIX (uses the IBM compilers) - init scripts (for gmond and gmetad) for AIX We have also written some documents which we would like to contribute: - Description of the new metrics on AIX - Description of the new metrics for Linux on POWER - General description on how to add metrics to Ganglia (might be useful for any platform) Can someone please recommend what would be the best way to contribute some or all of that stuff? I assume posting to that list is not the best idea :-) These new metrics have been tested (for a couple of months now) on the following systems: - POWER3 standalone systems - POWER4 standalone and LPAR-systems - POWER5 LPAR systems (virtualized environment) The following OS versions have been tested with these extensions: - AIX 5L v5.1, v5.2 and v5.3 and IBM Virtual I/O Server - SLES9 on POWER, RHEL4 on POWER - openSUSE 10.0 and 10.1 on POWER - Fedora Core 4 and 5 on POWER Also we did put up some documentation on the IBM AIX wiki pages (http://www.ibm.com/collaboration/wiki/display/WikiPtype/). A general discussion about AIX and Open Source programs can be found here (specifically if you want to run a recent version of Apache httpd and PHP on AIX as required for gmetad): http://www.ibm.com/collaboration/wiki/display/WikiPtype/aixopen Comprehensive Ganglia setup instructions for first time users are available at: http://www.ibm.com/collaboration/wiki/display/WikiPtype/ganglia Any feedback/comments very much welcome... Regards, Michael
