Improves benchmarks

Make Virtuoso loading work
Allows to limit Rudf memory
Use bars for plot

bench/bsbm-plot.py

@@ -2,16 +2,20 @@ import xml.etree.ElementTree as ET
 import matplotlib.pyplot as plt
 from collections import defaultdict
 from glob import glob
+from numpy import array
 
-
-def plot_y_per_x_per_plot(data, xlabel, ylabel, file):
+def plot_y_per_x_per_plot(data, xlabel, ylabel, file, log=False):
     plt.figure(file)
-    for label, xys in data.items():
-        plt.plot(list(xys.keys()), list(xys.values()), '.', label=label)
+
+    bar_width = 1 / (len(data) + 1)
+    for i, (label, xys) in enumerate(sorted(data.items())):
+        plt.bar(array(list(xys.keys())) + bar_width * (i + 1 - len(data) / 2), array(list(xys.values())), bar_width, label=label)
+
     plt.legend()
     plt.xlabel(xlabel)
     plt.ylabel(ylabel)
-    # plt.yscale('log')
+    if log:
+        plt.yscale('log')
     plt.savefig(file)
 
 
@@ -23,7 +27,7 @@ for file in glob('bsbm.explore.*.xml'):
         val =  float(query.find('aqet').text)
         if val > 0:
             aqet[run][int(query.attrib['nr'])] = val
-plot_y_per_x_per_plot(aqet, 'query id', 'aqet', 'bsbm.explore.png')
+plot_y_per_x_per_plot(aqet, 'query id', 'execution time (s)', 'bsbm.explore.png')
 
 # BSBM business intelligence
 aqet = defaultdict(dict)
@@ -33,6 +37,6 @@ for file in glob('bsbm.businessIntelligence.*.xml'):
         val =  float(query.find('aqet').text)
         if val > 0:
             aqet[run][int(query.attrib['nr'])] = val
-plot_y_per_x_per_plot(aqet, 'query id', 'aqet', 'bsbm.businessIntelligence.png')
+plot_y_per_x_per_plot(aqet, 'query id', 'execution time (s) - log scale', 'bsbm.businessIntelligence.png', log=True)
 
 plt.show()

bench/bsbm_rudf.sh

@@ -1,14 +1,18 @@
 #!/usr/bin/env bash
 
 DATASET_SIZE=100000
+MEMORY_SIZE=1000000
 cd bsbm-tools
 ./generate -fc -pc ${DATASET_SIZE} -s nt -fn "explore-${DATASET_SIZE}"
 cargo build --release --manifest-path="../../server/Cargo.toml" 
-./../../target/release/rudf_server --file rudf_data &
+(
+  ulimit -d ${MEMORY_SIZE}
+  ./../../target/release/rudf_server --file rudf_data
+) &
 sleep 5
 curl -f -X POST -H 'Content-Type:application/n-triples' --data-binary "@explore-${DATASET_SIZE}.nt" http://localhost:7878/
-./testdriver -ucf usecases/explore/sparql.txt -o "../bsbm.explore.rudf.${DATASET_SIZE}.$(date +'%Y-%m-%d').xml" http://localhost:7878/query
-./testdriver -ucf usecases/businessIntelligence/sparql.txt -o "../bsbm.businessIntelligence.rudf.${DATASET_SIZE}.$(date +'%Y-%m-%d').xml" http://localhost:7878/query
+./testdriver -ucf usecases/explore/sparql.txt -o "../bsbm.explore.rudf.${DATASET_SIZE}.${MEMORY_SIZE}.$(date +'%Y-%m-%d').xml" http://localhost:7878/query
+./testdriver -ucf usecases/businessIntelligence/sparql.txt -o "../bsbm.businessIntelligence.rudf.${DATASET_SIZE}.${MEMORY_SIZE}.$(date +'%Y-%m-%d').xml" http://localhost:7878/query
 kill $!
 rm -r rudf_data
 rm "explore-${DATASET_SIZE}.nt"

bench/bsbm_virtuoso.sh

@@ -6,9 +6,12 @@ cd bsbm-tools
 cp ../virtuoso-opensource/database/virtuoso.ini.sample virtuoso.ini
 mkdir ../database
 ../virtuoso-opensource/bin/virtuoso-t -f &
-sleep 30
-curl -f --digest --user dba:dba -H 'Content-Type:application/n-triples' --data-binary "@explore-${DATASET_SIZE}.nt" 'http://localhost:8890/sparql-graph-crud-auth?graph-uri=urn:graph:test'
-curl -f -H 'Content-Type:application/sparql-query' --data "SELECT (COUNT(*) AS ?c) WHERE { ?s ?p ?o }"  'http://localhost:8890/sparql?graph-uri=urn:graph:test'
+sleep 10
+../virtuoso-opensource/bin/isql 1111 dba dba <<EOF
+SPARQL CREATE GRAPH <urn:graph:test>;
+ld_dir('$(realpath .)', 'explore-${DATASET_SIZE}.nt', 'urn:graph:test');
+rdf_loader_run();
+EOF
 ./testdriver -ucf usecases/explore/sparql.txt -o "../bsbm.explore.virtuoso.${DATASET_SIZE}.7.2.5.xml" 'http://localhost:8890/sparql?graph-uri=urn:graph:test'
 ./testdriver -ucf usecases/businessIntelligence/sparql.txt -o "../bsbm.businessIntelligence.virtuoso.${DATASET_SIZE}.7.2.5.xml" 'http://localhost:8890/sparql?graph-uri=urn:graph:test'
 kill $!