Eval investigation

report/all_benchmarks

@@ -10,48 +10,30 @@ unix_50/full10m
 unix_50/full100m
 unix_50/full1g
 dgsh/1
-dgsh/1-100M
-dgsh/1-1G
-dgsh/1-10G
 dgsh/1-10x
 dgsh/1-100x
 dgsh/1-1000x
 dgsh/2
 dgsh/3
 dgsh/4
 dgsh/5
-dgsh/5-100M
-dgsh/5-1G
-dgsh/5-10G
 dgsh/5-10x
 dgsh/5-100x
 dgsh/5-1000x
 dgsh/6
-dgsh/6-100M
-dgsh/6-1G
-dgsh/6-10G
 dgsh/6-10x
 dgsh/6-100x
 dgsh/6-1000x
 dgsh/7
-dgsh/7-100M
-dgsh/7-1G
-dgsh/7-10G
 dgsh/7-10x
 dgsh/7-100x
 dgsh/7-1000x
 dgsh/8
-dgsh/8-100M
-dgsh/8-1G
-dgsh/8-10G
 dgsh/8-10x
 dgsh/8-100x
 dgsh/8-1000x
 dgsh/9
 dgsh/17
-dgsh/17-100M
-dgsh/17-1G
-dgsh/17-10G
 dgsh/17-10x
 dgsh/17-100x
 dgsh/17-1000x
@@ -157,7 +139,6 @@ nlp1000x/8.3_3
 sklearn
 sklearn_large
 web-index/web-index-100m
-web-index/web-index-100m500k
 web-index/web-index-100m1m
 teraseq/5TERA
 teraseq/5TERA-short

report/benchmarks/log-analysis/inner/setup

@@ -1,12 +1,13 @@
 #!/bin/bash
-
+set -x
 export PATH=$PATH:$HOME/.local/bin
 export PASH_SPEC_TOP=${PASH_SPEC_TOP:-$(git rev-parse --show-toplevel --show-superproject-working-tree)}
 
 download_dir="$PASH_SPEC_TOP/report/resources/log-analysis-full"
 download_dir_small="$PASH_SPEC_TOP/report/resources/log-analysis-small"
 download_dir_medium="$PASH_SPEC_TOP/report/resources/log-analysis-medium"
 benchmark_dir="$PASH_SPEC_TOP/report/benchmarks/log-analysis/"
+ita_public_tools_dir="$benchmark_dir/ita_public_tools"
 
 # Create the download directory if it doesn’t exist
 mkdir -p "$download_dir"
@@ -15,13 +16,11 @@ mkdir -p "$download_dir_medium"
 
 IN_ROOT=${IN_ROOT:-'https://atlas-group.cs.brown.edu/data/web-logs/world-cup'}
 
-wget "${IN_ROOT}/WorldCup_tools.tar" -P "${benchmark_dir}"
-tar -xf "$benchmark_dir/WorldCup_tools.tar" && rm $benchmark_dir/WorldCup_tools.tar
-( cd "${benchmark_dir}/ita_public_tools" && make && mv bin/recreate "${benchmark_dir}" && mv state/object_mappings.sort "${benchmark_dir}")
+( cd "${benchmark_dir}/ita_public_tools" && make && cp "$ita_public_tools_dir/bin/recreate" "$benchmark_dir" && cp "$ita_public_tools_dir/state/object_mappings.sort" "$benchmark_dir")
 
 # Read each line from links.txt and download the file
-wget -r -np -nH --cut-dirs=6 -P "${download_dir}" "${IN_ROOT}/"
-rm -rf ${download_dir}/robots.txt ${download_dir}/index.html* ${download_dir}/WorldCup_tools.tar
+# wget -r -np -nH --cut-dirs=6 -P "${download_dir}" "${IN_ROOT}/"
+# rm -rf ${download_dir}/robots.txt ${download_dir}/index.html* ${download_dir}/WorldCup_tools.tar
 
 # Download only the specific files
 files_to_copy_small=(

report/benchmarks/micro/100echos/foo

@@ -0,0 +1 @@
+foo

report/benchmarks/micro/100echos/run_trace

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_trace_base

report/benchmarks/micro/100echos/run_trace_parse

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_trace_parse_base

report/benchmarks/micro/100echos/run_try

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_try_base

report/benchmarks/micro/100echos2/run_trace

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_trace_base

report/benchmarks/micro/100echos2/run_trace_parse

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_trace_parse_base

report/benchmarks/micro/100echos2/run_try

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_try_base

report/benchmarks/micro/giant_file/run_trace

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_trace_base

report/benchmarks/micro/giant_file/run_trace_parse

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_trace_parse_base

report/benchmarks/micro/giant_file/run_try

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_try_base

report/benchmarks/micro/giant_file2/run_trace

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_trace_base

report/benchmarks/micro/giant_file2/run_trace_parse

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_trace_parse_base

report/benchmarks/micro/giant_file2/run_try

@@ -0,0 +1 @@
+/mydata/dynamic-parallelizer/report/run_try_base

report/benchmarks/micro/inner/100echos/run_trace

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/100echos.strace.sh
+output_file="$hs_base/report/output/micro/100echos/strace_time"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//'> "$output_file" 

report/benchmarks/micro/inner/100echos/run_trace_parse

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/100echos.strace.parse.sh
+output_file="$hs_base/report/output/micro/100echos/strace_parse_time"
+
+export PARSE="python3 $hs_base/parallel-orch/trace_v2.py"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+# Capture and save the real time
+{ time $run_script >/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/100echos/run_try

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/100echos.try.sh
+output_file="$hs_base/report/output/micro/100echos/try_time"
+
+export try="$hs_base/deps/try/try"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/100echos2/run_trace

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/100echos2.strace.sh
+output_file="$hs_base/report/output/micro/100echos2/strace_time"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/100echos2/run_trace_parse

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/100echos2.strace.parse.sh
+output_file="$hs_base/report/output/micro/100echos2/strace_parse_time"
+
+export PARSE="python3 $hs_base/parallel-orch/trace_v2.py"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+# Capture and save the real time
+{ time $run_script >/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/100echos2/run_try

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/100echos2.try.sh
+output_file="$hs_base/report/output/micro/100echos2/try_time"
+
+export try="$hs_base/deps/try/try"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//'  > "$output_file"

report/benchmarks/micro/inner/giant_file/run_trace

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/giant_file.strace.sh
+output_file="$hs_base/report/output/micro/giant_file/strace_time"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/giant_file/run_trace_parse

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/giant_file.strace.parse.sh
+output_file="$hs_base/report/output/micro/giant_file/strace_parse_time"
+
+export PARSE="python3 $hs_base/parallel-orch/trace_v2.py"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/giant_file/run_try

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/giant_file.try.sh
+output_file="$hs_base/report/output/micro/giant_file/try_time"
+
+export try="$hs_base/deps/try/try"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' | sed 's/^0://' > "$output_file"

report/benchmarks/micro/inner/giant_file2/run_trace

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/giant_file2.strace.sh
+output_file="$hs_base/report/output/micro/giant_file2/strace_time"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/giant_file2/run_trace_parse

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/giant_file2.strace.parse.sh
+output_file="$hs_base/report/output/micro/giant_file2/strace_parse_time"
+
+export PARSE="python3 $hs_base/parallel-orch/trace_v2.py"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/giant_file2/run_try

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/giant_file2.try.sh
+output_file="$hs_base/report/output/micro/giant_file2/try_time"
+
+export try="$hs_base/deps/try/try"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' | sed 's/^0://' > "$output_file"

report/benchmarks/micro/inner/multi_files/run_trace

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/multi_files.strace.sh
+output_file="$hs_base/report/output/micro/multi_files/strace_time"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/multi_files/run_trace_parse

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/multi_files.strace.parse.sh
+output_file="$hs_base/report/output/micro/multi_files/strace_parse_time"
+
+export PARSE="python3 $hs_base/parallel-orch/trace_v2.py"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/multi_files/run_try

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+hs_base=$(git rev-parse --show-toplevel)
+benchmark_dir="$hs_base/report/benchmarks/micro/scripts"
+run_script=$benchmark_dir/multi_files.try.sh
+output_file="$hs_base/report/output/micro/multi_files/try_time"
+
+export try="$hs_base/deps/try/try"
+
+# Ensure the output directory exists
+mkdir -p "$(dirname "$output_file")"
+
+
+
+# Capture and save the real time
+{ time $run_script>/dev/null; }  2>&1 | grep real | awk '{print $2}' | awk -F'm' '{print ($1 * 60) + $2}' | sed 's/s//' > "$output_file"

report/benchmarks/micro/inner/run_trace_only

@@ -39,7 +39,7 @@ def do_strace_run(test_base: Path, script_name: str, output_base: Path, env: dic
     with open(output_base / f"{Path(script_name).stem}" / "strace_log", 'w') as log:
         result = run(cmd, stdout=PIPE, stderr=log, env=env)
     duration = time.time() - before
-    with open(output_base / f"{Path(script_name).stem}" / "strace_time", 'w') as f:
+    with open(output_base / f"{Path(script_name).stem}" / "sstrace_time", 'w') as f:
         f.write(f'{duration}\n')
     return result.returncode, result.stdout
 
@@ -55,7 +55,7 @@ def do_strace_parse_run(test_base: Path, script_name: str, output_base: Path, en
     with open(output_base / f"{Path(script_name).stem}" / "trace_v2_log_parsed", 'w') as log:
         result = run(cmd2, stdout=PIPE, stderr=log, env=env)
     duration = time.time() - before
-    with open(output_base / f"{Path(script_name).stem}" / "strace_parse_time", 'w') as f:
+    with open(output_base / f"{Path(script_name).stem}" / "sstrace_parse_time", 'w') as f:
         f.write(f'{duration}\n')
     return result.returncode, result.stdout