Last updated: $Date: 2011-08-16 18:43:20 -0400 (Tue, 16 Aug 2011) $ by $Author: CloyceS $
(To check for possible updates to this document, please see http://www.spec.org/cpu2006/Docs/ )
Contents
Monitoring Hooks in Header Section
Monitoring Hooks Per Benchmark
monitor_pre_bench and monitor_post_bench
build_pre_bench and build_post_bench
Considerations for Writing Monitoring Scripts
Note: links to SPEC CPU2006 documents on this web page assume that you are reading the page from a directory that also contains the other SPEC CPU2006 documents. If by some chance you are reading this web page from a location where the links do not work, try accessing the referenced documents at one of the following locations:
While some users will be using the SPEC CPU2006 suite to benchmark the system under test (SUT) using the SPEC provided tools, others might be inclined to understand and evaluate the performance bottlenecks when running the benchmarks on the SUT. Performance evaluation requires performance data to be collected either on a suite-wide basis or for individual benchmarks. To facilitate the collection of performance data or to run any command-line task/utility at specific execution points of the runspec script, SPEC CPU2006 provides several "monitoring hooks" which can be set up in the configuration file. These hooks allow you to run arbitrary shell commands while still using the SPEC recommended way of running SPEC CPU2006; which is using the runspec command utility. This document explains the various hooks that are available in SPEC CPU2006.
All monitoring hooks are specified in the configuration file. This document, therefore assumes that you have a working familiarity with the construction and layout of the benchmark configuration files.
The monitor hooks have been a little-known feature of the SPEC CPU toolset for many years. They were first described in the ACM SIGARCH article SPEC CPU2006 Benchmark Tools and now are explained further in this document. The monitor hooks allow advanced users to instrument the suite in a variety of ways. SPEC can provide only limited support for their use; if your monitors break files or processes that the suite expects to find, you should be prepared to do significant diagnostic work on your own.
In order to illustrate the usage of monitoring hooks facility in SPEC CPU2006, this document will extensively use the Example-monitors-macosx.cfg configuration file which comes with your standard SPEC installation. You can find this configuration file located in the $SPEC/config directory of your SPEC installation tree. You will also find on your kit an example oriented toward users of Microsoft Windows: Example-monitor-windows.cfg
The monitoring facility in CPU2006 is not limited to simple examples presented here. Scripts and programs of any level of complexity may be used to examine command arguments and executables and change their monitoring actions accordingly. In this way only a specific part of a benchmark's workload may be monitored while not wasting time or other resources tracing uninteresting workloads.
There are two monitoring hooks that can be set in the header section of the configuration file:
When the SPEC provided (and approved) script, runspec, is used to run the CPU2006 suite, it breaks down the benchmarks specified on the command line into one or more sets and runs each set as a separate unit. A set of benchmarks that comprise a specific unit is defined by the tuple of data size (test, train, and ref) and extension. It is therefore possible for runspec to run multiple sets of benchmarks, one after another, for one invocation of runspec.
The monitor_pre hook is invoked before while the monitor_post hook is invoked after the execution of each run configuration set. Therefore, for a single runspec invocation, these hooks might be executed multiple times, as shown in examples below.
If you do not run at least one benchmark then monitor_pre and monitor_post are not used (e.g. if you use "--action setup" or "--action build").
Note - stdout/stderr: The stdout and stderr for the monitor_pre and monitor_post commands are redirected to the files monitor_{pre|post}.out and monitor_{pre|post}.err in your current working directory.
The runspec command below requests one input data set; so monitor_pre and monitor_post will each be called once. Here is the sample output printed to the screen (monitor_pre and monitor_post markers are highlighted in red):
spec002:~/benchmarks/cpu2006-kit100 peg$ runspec -c Example-monitors-macosx.cfg -n 1 -i test 999 runspec v5354 - Copyright 1999-2007 Standard Performance Evaluation Corporation Using 'macosx' tools Reading MANIFEST... 18300 files Loading runspec modules................ Locating benchmarks...found 31 benchmarks in 13 benchsets. Reading config file '/Users/peg/benchmarks/cpu2006-kit100/config/Example-monitors-macosx.cfg' Benchmarks selected: 999.specrand Executing monitor_pre: echo "monitor_pre" Compiling Binaries Up to date 999.specrand test base example-monitors default Setting Up Run Directories Setting up 999.specrand test base example-monitors default: existing (run_base_test_example-monitors.0000) Running Benchmarks Running 999.specrand test base example-monitors default Executing monitor_pre_bench: echo "monitor_pre_bench" Executing monitor_post_bench: echo "monitor_post_bench" Success: 1x999.specrand Executing monitor_post: echo "monitor_post" Producing Raw Reports mach: default ext: example-monitors size: test set: int set: fp The log for this run is in /Users/peg/benchmarks/cpu2006-kit100/result/CPU2006.022.log runspec finished at Mon Jul 30 12:47:13 2007; 6 total seconds elapsed
The runspec -i test,train command below requests two input data sets, and effectively causes two runs; so monitor_pre and monitor_post will each be called twice. Here is the sample output printed to the screen:
spec002:~/benchmarks/cpu2006-kit100 peg$ runspec -c Example-monitors-macosx.cfg -n 1 -i test,train --tune=base 999 runspec v5354 - Copyright 1999-2007 Standard Performance Evaluation Corporation Using 'macosx' tools Reading MANIFEST... 18300 files Loading runspec modules................ Locating benchmarks...found 31 benchmarks in 13 benchsets. Reading config file '/Users/peg/benchmarks/cpu2006-kit100/config/Example-monitors-macosx.cfg' Benchmarks selected: 999.specrand Executing monitor_pre: echo "monitor_pre"
Compiling Binaries Up to date 999.specrand test base example-monitors default Setting Up Run Directories Setting up 999.specrand test base example-monitors default: existing (run_base_test_example-monitors.0000) Running Benchmarks Running 999.specrand test base example-monitors default Executing monitor_pre_bench: echo "monitor_pre_bench" Executing monitor_post_bench: echo "monitor_post_bench" Success: 1x999.specrand Executing monitor_post: echo "monitor_post" Producing Raw Reports mach: default ext: example-monitors size: test set: int set: fp Benchmarks selected: 999.specrand Executing monitor_pre: echo "monitor_pre" Compiling Binaries Up to date 999.specrand train base example-monitors default Setting Up Run Directories Setting up 999.specrand train base example-monitors default: existing (run_base_train_example-monitors.0000) Running Benchmarks Running 999.specrand train base example-monitors default Executing monitor_pre_bench: echo "monitor_pre_bench" Executing monitor_post_bench: echo "monitor_post_bench" Success: 1x999.specrand Producing Raw Reports Executing monitor_post: echo "monitor_post" mach: default ext: example-monitors size: train set: int set: fp The log for this run is in /Users/peg/benchmarks/cpu2006-kit100/result/CPU2006.024.log runspec finished at Mon Jul 30 15:41:51 2007; 13 total seconds elapsed
The SPEC tools allow the following monitoring hooks to be set for individual benchmark:
These monitoring hooks can be added to any Named Section to control which benchmarks will be affected by the hooks.
The monitoring hooks called as monitor_pre_bench and monitor_post_bench allow programs to be executed before and after specinvoke is called to run the benchmark. This could be used to harvest files written by an instrumented binary or to start and stop a system-level profiler. As as example, here is the part of the configuration file written to collect branch and basic block data profiles to evaluate the correspondence of training workloads to the reference workloads in SPEC CPU2006 under Solaris OS using a custom profiling tool called Binary Improvement Tool (bit).
monitor_pre_bench = bit instrument ${commandexe}; \
cp ${commandexe} ${commandexe}.orig; \
cp ${commandexe}.instr ${commandexe}
monitor_post_bench = bit analyze -o $[top]/analysis/branches.${benchmark}.${size}.csv -a branch ${commandexe}; \
bit analyze -o $[top]/analysis/blocks.${benchmark}.${size}.csv -a bbc ${commandexe}; \
cp ${commandexe}.orig ${commandexe}
Before the run, via (monitor_pre_bench), the Binary Improvement Tool (bit), is used to instrument the binary executable. After the run, via (monitor_post_bench), bit is again used to dump statistics from the run into files in the $SPEC/analysis/ directory.
The values for ${commandexe}, ${benchmark} and ${size} are provided by the tools at run time; there are many other variables available. The variables that are available vary depending on what is being done. For a list of variables available for substitution, execute your runspec command with verbosity set to 35 or greater. This can be accomplished by specifying "runspec -v 35". For more information on variable substitution, see the config.html section on variable substitution.
Note - stdout/stderr: The stdout and stderr for the monitor_pre_bench and monitor_post_bench commands are redirected to the files monitor_{pre|post}_bench.out and monitor_{pre|post}_bench.err in the run directory for each benchmark.
Note that the execution time for the commands specified by the $monitor_pre_bench, and $monitor_post_bench are not included in the benchmark's reported time.
It is also possible to instrument each invocation of a benchmark binary using the monitor_wrapper. This allows profiling or tracing of the individual workload components without measuring the overhead of specinvoke. One potential disadvantage is that the execution time of these commands is counted as part of the benchmark's reported run time. Here is an example of how you would collect a system call trace in Linux for individual benchmark workloads and save output files directly in to the profile directory:
strace -f -o $benchmark.calls.\$\$ $command; \ mkdir -p $[top]/calls.$lognum; \ mv $benchmark.calls.\$\$ $[top]/calls.$lognum
One very important point to note about monitor_wrapper is that by default any output that the monitoring software writes to stdout will be mixed with the benchmark's output.
A setting such as the following will cause many benchmarks to fail validation:
monitor_wrapper = date; $command
The benchmark's expected output certainly does not include the current time of the run. This is a contrived example of a real problem that can occur even if the monitoring program outputs only benign static status information. This is because normally the output redirections are set up by specinvoke before executing the benchmark. A similar problem can occur with inputs, if the monitoring application consumes input that the benchmark expects to find on stdin.
The way around this problem of misdirected stdin and stdout when using monitor_wrapper is a configuration file switch called command_add_redirect.
Normally input and output files are opened by specinvoke and attached directly to new process's file descriptors. Setting command_add_redirect in the header section of the configuration file causes that step to be skipped and instead modifies the benchmark command to include shell redirection operators. So, in Bourne shell syntax, by default the above example translates to something like:
(date; $command) < in > out 2>> err
With the command_add_redirect set, this becomes:
date; $command < in > out 2>> err
The output from the date command is still stored but in a file speccmds.stdout in the run directory that is not subject to validation.
By using monitor_specrun_wrapper, it is possible to directly monitor specinvoke, and by extension the entire benchmark iteration, no matter how many separate executions (workloads) it involves. For example, to generate a system call trace for specinvoke and all of its children on a Linux system, you could set up monitor_specrun_wrapper as follows:
monitor_specrun_wrapper = strace -ff -o $benchmark.calls $command; \ mkdir -p $[top]/calls.$lognum; \ mv $benchmark.calls* $[top]/calls.$lognum
In this example, the crucial point is the $command; it expands to the full command to be run, including arguments. If $command is omitted or replaced, something other than the desired command will be traced, and the benchmark will not validate.
Note that the execution time for the commands specified by the $monitor_specrun_wrapper is not included in the benchmark's reported time.
The monitoring hooks build_pre_bench and build_post_bench are executed before and after the individual benchmark is built.
Note - stdout/stderr: The stdout and stderr for the build_pre_bench and build_post_bench commands are redirected to the files build_{pre|post}_bench.out and build_{pre|post}_bench.err in the run directory for each benchmark.
You can specify a lot of shell commands separated by semicolons, but for ease of understanding and maintenance, you might prefer to have scripts that do the work. Here are a few things to keep in mind when writing scripts that will run with the monitoring hooks:
$CWD points to the current run directory, whether you are building or running the benchmark.
$PATH is modified to include the $SPEC/bin directory. So if you put your executables or scripts in the $SPEC/bin directory, they will be in the path when the SPEC environment is set.
If you are using monitor_wrapper, ensure that the monitoring applications and/or scripts do not use the stdin and stdout pipes. However, if they do use them, set the variable command_add_redirect in the header section of the configuration file to avoid unintended failures with the CPU2006 benchmarks. See section on monitor_wrapper for more discussion.
If you are saving data collected from your monitoring run in files, they are most likely being saved in $CWD, which is set to the current run directory. It is a good idea to move these files from the run directories to some other directory which does not get modified by the SPEC's runspec command. The run directories, by default, get over-written if you run the benchmark again.
Copyright 1999-2011 Standard Performance Evaluation Corporation
All Rights Reserved