summaryrefslogtreecommitdiff
path: root/util
AgeCommit message (Collapse)Author
2006-03-11Bump up NFS wait time in qdo (since this has been causingSteve Reinhardt
problems in pool regressions). util/qdo: Bump up hardcoded NFS wait time from 45 sec to 90 sec (and print threshold from 10 sec to 30 sec). Would be even nicer to make these cmd-line params, but nobody would use them anyway. --HG-- extra : convert_revision : 1e9b3ad43a5dbf5e30758069e5a8cde3749cc1a6
2006-02-28Add quiesceNs, quiesceTime, quiesceCycles, and m5panic pseudo ops.Ali Saidi
This changeset removes a check that prevents quiescing when an interrupt is pending. *** You should only call quiesce if that isn't a problem. *** arch/alpha/isa/decoder.isa: sim/pseudo_inst.cc: sim/pseudo_inst.hh: Add quiesceNs, quiesceCycles, quisceTime and m5panic pseudo ops. These quiesce for a number of ns, cycles, report how long we were quiesced for, and panic the simulator respectively. The latter is added to the panic() function in the console and linux kernel instead of executing an infinite loop until someone notices. cpu/exec_context.cc: cpu/exec_context.hh: Add a quiesce end event to the execution contexted which upon executing wakes up a CPU for quiesceCycles/quiesceNs. util/m5/Makefile: Make the makefile more reasonable util/m5/m5.c: update the m5op executable to use the files from the linux tree util/m5/m5op.S: update m5op.S from linux tree util/m5/m5op.h: update m5op.h from linux tree --HG-- rename : util/m5/m5op.s => util/m5/m5op.S extra : convert_revision : 3be18525e811405b112e33f24a8c4e772d15462d
2006-02-26fix some minor stats stuffNathan Binkert
util/stats/stats.py: fix up a few of the stats. --HG-- extra : convert_revision : 61c600cd146900c8cc0cf60a9036f2e999a5e244
2006-02-26Allow graph_group to not be selected so we can have aNathan Binkert
normal ungrouped barchart --HG-- extra : convert_revision : 7d55440c9bb060607eddbb72448a3413944bb6ba
2006-02-26better function categorizationNathan Binkert
util/stats/categories.py: bit more stuff for categorizing functions --HG-- extra : convert_revision : 03617246a9254a580684dce82836517d1efdfc5b
2006-02-26fix small python bug in database processing codeNathan Binkert
util/stats/db.py: fix usage of hasattr --HG-- extra : convert_revision : b384e1efeda76921c565f9f391694c27273edcec
2006-02-26code cleanupNathan Binkert
util/stats/barchart.py: clean up some of lisa's messy code remove trailing whitespace while I'm at it. --HG-- extra : convert_revision : f2fe6777fb4b458fa1d5b5b743f6274014c229ad
2006-02-26forgot to add a chart optionNathan Binkert
util/stats/chart.py: add a bool config option for determining if the legend is inside or outside the figure --HG-- extra : convert_revision : e862d1832a0cc3c1837758cc247bc77c0a02ec12
2006-02-26add error bars and more options for legend placementNathan Binkert
util/stats/barchart.py: Add support for error bars util/stats/barchart.py: add support to choose between a legend inside or outside the figure. --HG-- extra : convert_revision : 14273e385c106bf27a2013991f9f34ca6551b96c
2006-02-25better colors for barchartsNathan Binkert
util/stats/barchart.py: If there are fewer than 5 colors, pick from a subset of 5 so there is more consistency in colors between graphs --HG-- extra : convert_revision : 6cf64c2f8ed81e714e24a3ebe5a7a60ca168b231
2006-02-24Merge zizzer:/bk/m5Lisa Hsu
into zed.eecs.umich.edu:/z/hsul/work/m5/clean --HG-- extra : convert_revision : 34314698d4248a078c7b43125b2d048280ff576d
2006-02-241) make it pretty for large clustersLisa Hsu
2) make subticks vertical so they can be longer 3) make inner and outer axes farther apart to make room for subtick's vertical labels --HG-- extra : convert_revision : 91a1aab3f1078921edd53428e6712744210c9f1b
2006-02-23don't add an empty suboption descriptionNathan Binkert
--HG-- extra : convert_revision : 594744c3d438aed08a23db376959930071b2c368
2006-02-23make it possible to add filters for job names so thatNathan Binkert
parts of the full crossproduct of jobs can be ignored. --HG-- extra : convert_revision : c44b3daea0cf4b487b1d99eae92da16573b15930
2006-02-18few changes for nate:Lisa Hsu
1) cosmetic - removing visibility of meta axes except for the tick labels. 2) unless subticklabels defined, don't do meta axes. (instead of assuming if you have 3D graph, do meta axes) --HG-- extra : convert_revision : 396011ffaa51ea4066b34257f6fd5b3faac9d242
2006-02-18remove print statementsLisa Hsu
--HG-- extra : convert_revision : abd635034424eeb9685aea777440a02887ce81a6
2006-02-18more changes for subtick labels.Lisa Hsu
util/stats/barchart.py: oop forgot this for 1D graph cases. util/stats/chart.py: need to add default param to chart. --HG-- extra : convert_revision : f4e6c6c614d584e7928ed905e97608716455ab6c
2006-02-18Merge zizzer:/bk/m5Lisa Hsu
into zed.eecs.umich.edu:/z/hsul/work/m5/clean --HG-- extra : convert_revision : 5f7c75eb3f82d9b04edc0efece3b054b5d0fe81f
2006-02-18Now you can have sublabels for every bar using the self.xsubticklabels ↵Lisa Hsu
parameter. --HG-- extra : convert_revision : a6bdf3a972e81c84947b7d6ae76f828494a125c8
2006-01-30Make the M5 Emacs C style default to inserting spaces insteadNathan Binkert
of tabs so using different editors is consistent util/emacs/m5-c-style.el: Default to inserting spaces instead of tabs so using different editors is consistent --HG-- extra : convert_revision : 719e5e980e088b0f4787b198de18cddceabd0140
2005-12-19Create the ProxyError Exception. Raise it when an unproxyNathan Binkert
operation fails because information is wrong or not available. --HG-- extra : convert_revision : 1fd90c1291618b09752179cfa6894f1df495fffd
2005-12-19Add a little bit of support to grab info for making graphsNathan Binkert
without using the jobfile. util/stats/db.py: util/stats/profile.py: Make it possible to send job as a string and to set the system separately from the job. --HG-- extra : convert_revision : 08aaebd3f9a1643bd41953b43f3b80dc97e6592f
2005-11-22Major improvements in the graph output code. Mostly adding moreNathan Binkert
options, making existing options more visible and dealing with holes in data better. util/stats/barchart.py: - move the options for BarChart to a base class ChartOptions so they can be more easily set and copied. - add an option to set the chart size (so you can adjust the aspect ratio) - don't do the add_subplot thing, use add_axes directly so we can affect the size of the figure itself to make room for the legend - make the initial array bottom floating point so we don't lose precision - add an option to set the limits on the y axis - use a figure legend instead of an axes legend so we can put the legend outside of the actual chart. Also add an option to set the fontsize of the legend. - initial hack at outputting csv files util/stats/db.py: don't print out an error when the run is missing from the database just return None, the error will be print elsewhere. util/stats/output.py: - make StatOutput derive from ChartOptions so that it's easier to set default chart options. - make the various output functions (graph, display, etc.) take the name of the data as a parameter instead of making it a parameter to __init__. This allows me to create the StatOutput object with generic parameters while still being able to specialize the name after the fact - add support for graph_group and graph_bars to be applied to multiple configuration groups. This results in a cross product of the groups to be generated and used. - flush the html file output as we go so that we can load the file while graphs are still being generated. - make the proxy a parameter to the graph function so the proper system's data can be graphed - for any groups or bars that are completely missing, remove them from the graph. This way, if we decide not to do a set of runs, there won't be holes in the data. - output eps and ps by default in addition to the png. util/stats/profile.py: - clean up the data structures that are used to store the function profile information and try our best to avoid keeping extra data around that isn't used. - make get() return None if a job is missing so we know it was missing rather than the all zeroes thing. - make the function profile categorization stuff total up to 100% - Fixup the x-axis and y-axis labels. - fix the dot file output stuff. util/stats/stats.py: support the new options stuff for StatOutput --HG-- extra : convert_revision : fae35df8c57a36257ea93bc3e0a0e617edc46bb7
2005-11-22Change the set of statistics that are generated when specifying "all"Nathan Binkert
--HG-- extra : convert_revision : 8b803b1b3bbec0b35b6805593b0dd598e5b519cf
2005-11-22More changes from cpus named fullX to runXNathan Binkert
--HG-- extra : convert_revision : e3c117dc5751be13bd4b014a7fa6df0debfb48f0
2005-11-22make the NUMCPUS parameter always refer to the total number of cpusNathan Binkert
on the test system. add an option for pio_delay_write to run.py util/stats/stats.py: full0 -> run0 due to run.py change sim_ticks doesn't make sense with tick = ps, so use one of the cpu's numCycles paramter --HG-- extra : convert_revision : db9dbe014549d823edc10395f5241db5e907df01
2005-11-20Deal with divide by zero in the python stats stuff.Nathan Binkert
util/stats/info.py: If an operation results in a divide by zero, just return None --HG-- extra : convert_revision : 19cb4319734a3a9cf02bb1966fed42eb0c8a8ade
2005-11-20implement __str__ for all of the proxy stuff so we canNathan Binkert
actually print out a statistic. --HG-- extra : convert_revision : 043be6bd729e74d2220c5ae8aa1fc739aa247715
2005-11-11Add checktrace.sh. Checks all the ethertrace files in */ethertraceAli Saidi
for retransmissions, out of order packets, lost packets, duplicate ack, window full, etc. Easy way to see if you have a problem with a run. --HG-- extra : convert_revision : 95d8e8650b0fb3d120df107cd5281c56fefc3a1d
2005-11-03Qdo should kill its subordinate qsub more aggressivelySteve Reinhardt
on a timeout. util/qdo: Qsub needs a kill -9 to die; kill -15 doesn't cut it. --HG-- extra : convert_revision : 7696b3ecf1a084b68dd909b138ab6aa1b380b5a7
2005-11-02Merge zizzer:/bk/m5Ali Saidi
into zeep.eecs.umich.edu:/z/saidi/work/m5 --HG-- extra : convert_revision : 3cc23080d19cc464a8ba7c1c93b6e5d45af7d463
2005-11-02Change the output of stability info a little bitAli Saidi
--HG-- extra : convert_revision : bc467a40593234a1e3b694a741b4a7c2154a95ea
2005-11-02add a few more options to the help menuAli Saidi
--HG-- extra : convert_revision : b2481bedac786e4a6bb0d577954242d7f4c144a0
2005-11-02Simple updates to pbs and send.pyNathan Binkert
util/pbs/pbs.py: Change the default so that we do not get mail under any circumstances from pbs. util/pbs/send.py: Add a -n flag to send.py that causes the Base directory to *not* sync with the Link directory --HG-- extra : convert_revision : 6e872153b6b2c34b61ec2ddbf3e5536876f4b43b
2005-10-23Fix qdo job name setting.Steve Reinhardt
util/qdo: Don't automatically set qsub job name, as this causes qsub to fail if the job name is too long or otherwise unsuitable. --HG-- extra : convert_revision : 5ba48767574efaaff2c328549adee295780f7f70
2005-10-21Fix a couple of bug in the values() vector accessorNathan Binkert
util/stats/db.py: need to import the values function util/stats/info.py: it's just run --HG-- extra : convert_revision : 3cb67d8112a1a5fdf761b73732859a71f585bd1f
2005-10-21Minor updates to the profile code.Nathan Binkert
util/stats/profile.py: Pass around the number of symbols limit deal with categorization a bit better. --HG-- extra : convert_revision : 908410e296efd4514f2dfc0eb9e6e42834585560
2005-10-21Merge zizzer.eecs.umich.edu:/bk/m5Nathan Binkert
into zizzer.eecs.umich.edu:/.automount/ziff/z/binkertn/research/m5/work --HG-- extra : convert_revision : 8ef6ed2d770d45ac11d44a449e2c4f74ef656d87
2005-10-21Major cleanup of the statistics handling codeNathan Binkert
util/stats/db.py: Build a result object as the result of a query operation so it is easier to populate and contains a bit more information than just a big dict. Also change the next level data into a matrix instead of a dict of dicts. Move the "get" function into the Database object. (The get function is used by the output parsing function as the interface for accessing backend storage, same interface for profile stuff.) Change the old get variable to the method variable, it describes how the get works, (whether using sum, stdev, etc.) util/stats/display.py: Clean up the display functions, mostly formatting. Handle values the way they should be now. util/stats/info.py: Totally re-work how values are accessed from their data store. Access individual values on demand instead of calculating everything and passing up a huge result from the bottom. This impacts the way that proxying works, and in general, everything is now esentially a proxy for the lower level database. Provide new operators: unproxy, scalar, vector, value, values, total, and len which retrieve the proper result from the object they are called on. Move the ProxyGroup stuff (proxies of proxies!) here from the now gone proxy.py file and integrate the shared parts of the code. The ProxyGroup stuff allows you to write formulas without specifying the statistics until evaluation time. Get rid of global variables! util/stats/output.py: Move the dbinfo stuff into the Database itself. Each source should have it's own get() function for accessing it's data. This get() function behaves a bit differently than before in that it can return vectors as well, deal with these vectors and with no result conditions better. util/stats/stats.py: the info module no longer has the source global variable, just create the database source and pass it around as necessary --HG-- extra : convert_revision : 8e5aa228e5d3ae8068ef9c40f65b3a2f9e7c0cff
2005-10-20Add qdo options for setting the PBS job name and destination queue.Steve Reinhardt
util/qdo: Add options for setting the PBS job name and destination queue. --HG-- extra : convert_revision : dcb46a03b8fd7a93e2ba656a9e5c806e250f5ac9
2005-10-19fix pbs dependency stuffNathan Binkert
util/pbs/pbs.py: after -> afterok --HG-- extra : convert_revision : ee0af716bcc0f83c4103632bd277a5680b0d2c23
2005-10-18Default jobfile for statsNathan Binkert
util/stats/stats.py: Make the default jobfile Test.py in the current directory add the -J flag to tell it not to use a jobfile --HG-- extra : convert_revision : 5cf5bb2f32ed9c9701a94eabc9b2a538581acf94
2005-10-18Add new function profiling stuff, wrap the pc_sample stuff into it.Nathan Binkert
SConscript: Get rid of the pc_sample stuff and move to the new profiling stuff base/traceflags.py: DPRINTF Stack stuff cpu/base.cc: cpu/base.hh: cpu/exec_context.cc: cpu/exec_context.hh: cpu/simple/cpu.cc: Add profiling stuff kern/kernel_stats.hh: Use a smart pointer sim/system.cc: sim/system.hh: Create a new symbol table that has all of the symbols for a particular system util/stats/categories.py: change around the categories, add categories for function profiling stuff util/stats/profile.py: No profile parsing and display code to deal with function profiling stuff, graph, dot, and text outputs. --HG-- extra : convert_revision : b3de0cdc8bd468e42647966e2640ae009bda9eb8
2005-10-18Better pool job handlingNathan Binkert
util/pbs/job.py: the default jobfile is now Test.py in the root of the jobs directory util/pbs/pbs.py: Clean up the qsub options handling and add job dependencies util/pbs/send.py: the default jobfile is now Test.py in the root of the jobs directory add a flag to depend on your checkpoint add a flag to specify your node type create the base directory if it doesn't exist --HG-- extra : convert_revision : dfffa4a5b0e68b2550a28fbb06b9d6a208ea1f2e
2005-10-18Improvements to the graphing outputNathan Binkert
util/stats/output.py: Create the graph directory if it doesn't exist Don't write out a graph if all of the jobs for that graph are missing --HG-- extra : convert_revision : 7993baf1a4be33a062f86a4f09791f01eaafa43c
2005-10-12don't write the pbs jobid here, do it in send.py so we knowNathan Binkert
what it is sooner Don't handle sigstop since you're not allowed to. util/pbs/send.py: write the pbs jobid here in send.py so we know what it is sooner --HG-- extra : convert_revision : 93292d046cb4b628031e0e57e39eb4470b598ed8
2005-10-01Commit regression script. The cron job uses a copy in m5test'sSteve Reinhardt
home directory (/z/m5/regression), so for now any modifications should be manually copied there as well. Note that this script is designed to be useful for running full regressions outside of the cron job as well. --HG-- extra : convert_revision : 052ec5d58b5ff765d8f3a9b50849ef34d62c8d66
2005-09-29Fix for qdo & new pool node build.Steve Reinhardt
util/qdo: unset PROMPT_COMMAND in shell in case system sets it for us. --HG-- extra : convert_revision : f9f20f7dc6b9585b60f3ce53aadd06e7d64f5179
2005-09-22Support for compiling and testing on pool via 'qdo' script.Steve Reinhardt
For this to work qdo must be on your path. I've copied it into /usr/local/bin on zizzer. build/SConstruct: Add BATCH and BATCH_CMD options to support compiling/testing on pool via qdo. --HG-- extra : convert_revision : b7fc46465e897f7f15ed4a67f6735886917a6c4b
2005-09-17Totally re-work the way that jobfiles are done so there is moreNathan Binkert
information that can be used for other aspects of sending jobs. New graphing output stuff with matplotlib. util/pbs/job.py: Shuffle code around and create the JobDir class which encapsulates all of the functionality needed for making, organizing, and cleaning a job directory. Better status output util/pbs/jobfile.py: Majory re-working of the jobfile code. A job file now consists of several objects that describe how jobs should be run, it includes information about checkpoints, and graphing. util/pbs/send.py: use the new jobfile code. deal with the 15 character limit of pbs by truncating the name and using the raj hack. util/stats/db.py: fix the __str__ function for nodes provide __getitem__ for the Database class util/stats/stats.py: use the jobfile stuff to figure out what the proper naming and organziation of the graphs should be. move all output code to output.py, get rid of ploticus and use matplotlib --HG-- rename : util/categories.py => util/stats/categories.py extra : convert_revision : 0d793cbf6ad9492290e8ec875ce001c84095e1f7