Fix data sizes

chdb/benchmark.sh

@@ -22,4 +22,4 @@ cat log.txt | grep -P '^\d|Killed|Segmentation' | sed -r -e 's/^.*(Killed|Segmen
     awk '{ if (i % 3 == 0) { printf "[" }; printf $1; if (i % 3 != 2) { printf "," } else { print "]," }; ++i; }'
 
 echo -n "Data size: "
-du -bcs .clickbench
+du -bcs .clickbench | grep total

databend/benchmark.sh

@@ -62,7 +62,7 @@ command time -f '%e' curl -XPUT 'http://root:@127.0.0.1:8000/v1/streaming_load'
 curl 'http://default@localhost:8124/' --data-binary "select count() from hits"
 
 echo -n "Data size: "
-du -bcs _data
+du -bcs _data | grep total
 # 20922561953     _data
 # 20922561953     total
 

druid/benchmark.sh

@@ -42,4 +42,4 @@ pigz -d -f hits.tsv.gz
 kill %1
 
 echo -n "Data size: "
-du -bcs ./apache-druid-${VERSION}/var
+du -bcs ./apache-druid-${VERSION}/var | grep total

duckdb-vortex-partitioned/benchmark.sh

@@ -38,4 +38,4 @@ cat log-p.txt |
   sed -r -e 's/^.*(Killed|Segmentation).*$/null\nnull\nnull/; s/^Run Time \(s\): real\s*([0-9.]+).*$/\1/' |
   awk '{ if (i % 3 == 0) { printf "[" }; printf $1; if (i % 3 != 2) { printf "," } else { print "]," }; ++i; }'
 
-echo "Data size: $(du -bcs hits_*.vortex)"
+echo "Data size: $(du -bcs hits_*.vortex | grep total)"

glaredb-partitioned/benchmark.sh

@@ -21,7 +21,7 @@ mkdir -p "${script_dir}/data"
 pushd "${script_dir}/data"
 
 seq 0 99 | xargs -P100 -I{} bash -c 'wget --continue --progress=dot:giga https://datasets.clickhouse.com/hits_compatible/athena_partitioned/hits_{}.parquet'
-echo "Data size: $(du -bcs hits*.parquet)"
+echo "Data size: $(du -bcs hits*.parquet | grep total)"
 popd
 
 # Ensure working directory is the script dir. The view that gets created uses a

glaredb/benchmark.sh

@@ -21,7 +21,7 @@ mkdir -p "${script_dir}/data"
 pushd "${script_dir}/data"
 
 wget --continue --progress=dot:giga https://clickhouse-public-datasets.s3.eu-central-1.amazonaws.com/hits_compatible/athena/hits.parquet
-echo "Data size: $(du -bcs hits*.parquet)"
+echo "Data size: $(du -bcs hits*.parquet | grep total)"
 popd
 
 # Ensure working directory is the script dir. The view that gets created uses a

heavyai/benchmark.sh

@@ -47,7 +47,7 @@ popd
 ./run.sh 2>&1 | tee log.txt
 
 echo -n "Data size: "
-du -bcs /var/lib/heavyai/
+du -bcs /var/lib/heavyai/ | grep total
 
 cat log.txt | grep -P 'Total time|null' | sed -r -e 's/^.*Total time: ([0-9]+) ms$/\1/' |
   awk '{ if ($1 == "null") { print } else { print $1 / 1000 } }' |

parseable/benchmark.sh

@@ -49,7 +49,7 @@ sleep 180
 cat result.csv | sed -r -e 's/^([0-9\.]+) ([0-9\.]+) ([0-9\.]+)$/[\1, \2, \3]/'
 
 echo -n "Data size: "
-du -bcs local-store
+du -bcs local-store | grep total
 
 #kill parseable
 kill $PARSEABLE_PID

pinot/benchmark.sh

@@ -45,4 +45,4 @@ command time -f '%e' ./apache-pinot-$PINOT_VERSION-bin/bin/pinot-admin.sh Launch
 kill %1
 
 echo -n "Data size: "
-du -bcs ./batch
+du -bcs ./batch | grep total

questdb/benchmark.sh

@@ -54,7 +54,7 @@ curl -s -S -G --data-urlencode "query=select datediff('s', start, finish) took_s
 ./run.sh 2>&1 | tee log.txt
 
 echo -n "Data size: "
-du -bcs ~/.questdb/db/hits*
+du -bcs ~/.questdb/db/hits* | grep total
 
 cat log.txt | grep -P '"timings"|"error"|null' | sed -r -e 's/^.*"error".*$/null/; s/^.*"execute":([0-9]*),.*$/\1/' |
   awk '{ print ($1) / 1000000000 }' | sed -r -e 's/^0$/null/' |

starrocks/benchmark.sh

@@ -64,7 +64,7 @@ echo "Load data costs $LOADTIME seconds"
 # This is because the trashed data generated during the compaction process.
 # After about tens of minutes, when the gc is completed, the system includes about 16.5GB of data.
 echo -n "Data size: "
-du -bcs StarRocks-${VERSION}/storage/
+du -bcs StarRocks-${VERSION}/storage/ | grep total
 # Dataset contains 99997497 rows
 mysql -h 127.0.0.1 -P9030 -uroot hits -e "SELECT count(*) FROM hits"
 

umbra/benchmark.sh

@@ -35,7 +35,7 @@ echo "Load Time: $(( (end - start) / 1000 ))"
 # Calculate persistence size
 sudo chmod 777 -R db # otherwise 'du' complains about permission denied
 echo -n "Data size: "
-du -bcs db
+du -bcs db | grep total
 
 # Pretty-printing
 cat log.txt | grep -oP 'Time: \d+\.\d+ ms' | sed -r -e 's/Time: ([0-9]+\.[0-9]+) ms/\1/' |