summaryrefslogtreecommitdiffstats
path: root/rteval
Commit message (Collapse)AuthorAgeFilesLines
* Migrated from libxslt to lxmlHEADmasterDavid Sommerseth2013-03-122-22/+63
| | | | | | | To avoid depending on libxslt-python, use the more standard Python lxml module for XSLT processing. Signed-off-by: David Sommerseth <davids@redhat.com>
* update to v1.37Clark Williams2012-12-131-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* add module-specific command line optionsClark Williams2012-12-133-17/+54
| | | | | | | | | | | | | | | | | | Add command line options: --cyclictest-priority --cyclictest-distance --cyclictest-interval --cyclictest-buckets --hackbench-jobspercore --kcompile-jobspercore These options allow setting module specific behavior for a run. Updated the rteval.8 man page to reflect this and the rteval.conf file as well. Signed-off-by: Clark Williams <williams@redhat.com>
* Changes the getcmdpath method to use only python calls to find the pathsRaphaël Beamonte2012-11-291-3/+9
| | | | | | | | | | | | | In my previous patches, I introduced a getcmdpath method which intended to replace the direct calls to binary from clear paths, using the which binary to locate the place of the searched one. This behavior was in fact not the finest as the method itself used the full path to the which binary. In this patch, I corrected the getcmdpath command to use only python calls (os.path.isfile and os.access) to identify in the PATH environment variable the place where the binary is. Signed-off-by: Raphaël Beamonte <raphael.beamonte@gmail.com> Signed-off-by: Clark Williams <williams@redhat.com>
* update to v1.36Clark Williams2012-10-231-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* Rewrite of the get_services method to make it cross-distributionRaphaël Beamonte2012-10-231-15/+58
| | | | | | | | Changes the get_services method to call the new created __get_services_sysvinit and __get_services_systemd methods to be able to manage the two different init daemons. Signed-off-by: Raphaël Beamonte <raphael.beamonte@gmail.com>
* Adds getcmdpath method to use which to locate the used commandsRaphaël Beamonte2012-10-231-1/+12
| | | | Signed-off-by: Raphaël Beamonte <raphael.beamonte@gmail.com>
* Rewrite of the get_kthreads method to make it cross-distributionRaphaël Beamonte2012-10-231-4/+3
| | | | Signed-off-by: Raphaël Beamonte <raphael.beamonte@gmail.com>
* make sure that priority parameter is converted to intClark Williams2012-08-131-3/+3
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* handle system not having dmidecode python moduleClark Williams2012-08-131-2/+16
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* version bump to 1.35Clark Williams2012-04-021-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* reenabled SIGINT and SIGTERM handlersClark Williams2012-04-021-6/+6
| | | | | | | Accidentally left SIGINT and SIGTERM signal handlers commented out when committing. Undo this thinko... Signed-off-by: Clark Williams <williams@redhat.com>
* version bump to 1.34Clark Williams2012-01-121-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* start hackbench with helper functionClark Williams2012-01-091-3/+8
| | | | | | Use a helper so we get a report when hackbench restarts Signed-off-by: Clark Williams <williams@redhat.com>
* propogate config file values to cyclictest threadClark Williams2012-01-091-0/+1
| | | | | | | We missed merging the parameters into the cyclictest config section so that numanodes was not being passed down. Signed-off-by: Clark Williams <williams@redhat.com>
* Merge branch 'master' into workClark Williams2011-09-143-39/+75
|\ | | | | | | | | Conflicts: rteval/hackbench.py
| * added --onlyload optionClark Williams2011-09-141-25/+56
| | | | | | | | | | | | | | Add mechanism to run only loads (not measuring thread) for debug and tracing purposes. Signed-off-by: Clark Williams <williams@redhat.com>
| * changed default built target, refactored a bit in kcompile.pyClark Williams2011-09-141-13/+18
| | | | | | | | | | | | | | | | | | | | Modified kernel build commands to use 'mrproper' as setup target and changed build command to just use default (rather than specifying the bzImage and modules targets). Added some debug prints. Signed-off-by: Clark Williams <williams@redhat.com>
| * allow for float as load specifierClark Williams2011-09-141-1/+1
| | | | | | | | | | | | This allows you to specify fractional loads (e.g. 1.5 jobs per core) Signed-off-by: Clark Williams <williams@redhat.com>
* | version bump to 1.33Clark Williams2011-05-141-1/+1
| | | | | | | | Signed-off-by: Clark Williams <williams@redhat.com>
* | change low-memory threshold to be 0.75GB/coreClark Williams2011-05-141-1/+1
| | | | | | | | | | | | | | | | The previous cutoff for running hackbench was 1GB/core but many systems actually report that as 0.8GB/core. Change the cutoff ratio to be 0.75GB/core to catch this. Signed-off-by: Clark Williams <williams@redhat.com>
* | Implemented simple XML-RPC call to check the database statusDavid Sommerseth2010-08-271-0/+3
| | | | | | | | | | | | This can be used to check if the XML-RPC service have access to the database Signed-off-by: David Sommerseth <dazo@users.sourceforge.net>
* | Extract IPv6 network configurationDavid Sommerseth2010-08-231-19/+48
|/ | | | | | | | This implementation will need python-ethtool v0.4 or newer to be able to extract the IPv6 information. This update makes sure older python-ethtool version will continue to work, while not extracting the IPv6 information. Signed-off-by: David Sommerseth <davids@redhat.com>
* version bump to v1.32Clark Williams2010-08-231-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* clean up rteval/rteval_text.xsl to handle old reportsClark Williams2010-08-231-1/+1
| | | | | | | Don't depend on the 'run' attribute for a load section since it was just added and old reports do not contain it. Signed-off-by: Clark Williams <williams@redhat.com>
* clean up text portion of 'command_line' tag in XMLClark Williams2010-08-231-1/+2
| | | | | | | Return None if there were no jobs, otherwise return the command line used to start hackbench Signed-off-by: Clark Williams <williams@redhat.com>
* clean up XML generationClark Williams2010-08-233-6/+8
| | | | | | | Add the 'run' attribute for load summary so that appropriate text can be generated if a load doesn't run Signed-off-by: Clark Williams <williams@redhat.com>
* modified hackbench to not run in low memory conditionsClark Williams2010-08-231-7/+14
| | | | | | | If hackbench determines the ratio of available memory to active cpucores is less than 1GB/core, it will not be run. Signed-off-by: Clark Williams <williams@redhat.com>
* default base-class members of Load to internal testing valuesClark Williams2010-08-231-2/+2
| | | | | | | default the sourcedir and buildir values of the load base class to the internal "../loadsource" and "../build" directories. Signed-off-by: Clark Williams <williams@redhat.com>
* remove refactored methods and add proper defaults to RTEval membersClark Williams2010-08-231-59/+8
| | | | | | | | Remove system parameter access methods that were moved to the util.py module and replace callsites with calls into the util versions. Signed-off-by: Clark Williams <williams@redhat.com>
* create utility module with common system tasksClark Williams2010-08-231-0/+96
| | | | | | | refactor some methods from rteval into a commmon utility module for use by loads and cyclictest. Signed-off-by: Clark Williams <williams@redhat.com>
* add "__main__" section to run hackbench for testingClark Williams2010-08-231-0/+5
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* rteval: check if the core id really existsClark Williams2010-08-211-0/+2
| | | | | | | | | | | In SMT systems like Power PC, while we turn off or control multithreading, the processor id in cpu info need not be in sequence, for the available cores. This patch adds a minor check that if the core id we range, is really found in cpu info. Signed-off-by: Gowrishankar <gowrishankar.m@in.ibm.com> Tested-by: Gowrishankar <gowrishankar.m@in.ibm.com> Signed-off-by: Clark Williams <williams@redhat.com>
* Don't create log directories before it is neededDavid Sommerseth2010-08-111-8/+8
| | | | | | | | | The directory called 'rteval-YYYYMMDD-#' and the 'logs' sub-directory was created in the RtEval constructor. Moved this directory creation to before the RtEval::measure() function was called to avoid creating empty directories when using --summarize or --raw-histogram. Signed-off-by: David Sommerseth <davids@redhat.com>
* Improved CPU socket countingDavid Sommerseth2010-08-101-3/+15
| | | | | | | | | | Some computers start with physical_package_id=1, which would return two CPU sockets with the former CPU socket counting method. This is fixed by using a more failsafe method, by counting unique physical_package_id references. Signed-off-by: David Sommerseth <davids@redhat.com>
* version bump to v1.31Clark Williams2010-07-261-1/+1
|
* Updated hackbench implementation to avoid overusing resourcesDavid Sommerseth2010-07-262-10/+4
| | | | | | | | | | | | | | | - Removed support for setting 'thread' workunit This implementation needs to be re-implemented better, as it will easily use more than 1024 file descriptors. - Changed dynmic hackbench loops to a static value To make the load more comparable no matter how many CPU cores available. Using 100 as the default value. - Reduced data size from 128 to 100 This is to match the old hackbench value. Signed-off-by: David Sommerseth <davids@redhat.com>
* Don't show NUMA node information if it's missing in the summary.xmlDavid Sommerseth2010-07-261-3/+5
| | | | Signed-off-by: David Sommerseth <davids@redhat.com>
* Show CPU cores properlyDavid Sommerseth2010-07-261-1/+12
| | | | | | | | This is is a feature regression going back to commit e5d01f24e6fb6883 where CPU topology was introduced. The displaying itself was never updated. Signed-off-by: David Sommerseth <davids@redhat.com>
* version bump to v1.30Clark Williams2010-07-211-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* cap hackbench backoff time at 60 secondsClark Williams2010-07-211-0/+2
| | | | | | | detect when out-of-memory sleep time exceeds 60 seconds and cap it at that value. Signed-off-by: Clark Williams <williams@redhat.com>
* add code to ease memory pressure from hackbenchClark Williams2010-07-211-4/+17
| | | | | | | | Catch out-of-memory errors and sleep for an increasing number of seconds (capped at 60 seconds) to let the system recover before kicking off another hackbench. Signed-off-by: Clark Williams <williams@redhat.com>
* version bump to v1.29Clark Williams2010-07-161-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* fixed incorrect type value in kcompileClark Williams2010-07-161-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* version bump to v1.28Clark Williams2010-07-161-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* added load logic to adjust load based on memory/core ratioClark Williams2010-07-163-5/+28
| | | | | | | | | Added logic to loads.py, hackbench.py and kcompile.py that adjusts the number of jobs run based on the gigabytes per core ratio. If the ratio is less than 1, then only do one job per core, else do two jobs per core. Signed-off-by: Clark Williams <williams@redhat.com>
* version update to v1.27Clark Williams2010-07-141-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
* add memsize, numanodes and duration parametersClark Williams2010-07-141-2/+3
| | | | | | | Add the memory size, number of numa nodes and the run duration to the parameter array passed to loads and cyclictest. Signed-off-by: Clark Williams <williams@redhat.com>
* change default unit of work for hackbench to be threadsClark Williams2010-07-142-3/+2
| | | | | | | Go back to using threads rather than processes to save some memory. Signed-off-by: Clark Williams <williams@redhat.com>
* version update to v1.26Clark Williams2010-07-131-1/+1
| | | | Signed-off-by: Clark Williams <williams@redhat.com>
generated by cgit (git 2.34.1) at 2026-03-01 11:37:28 +0000