From 2a82fe4f757ad01dd61d59f1ef75ae65b009de45 Mon Sep 17 00:00:00 2001
From: Tpt <thomaspt@hotmail.fr>
Date: Thu, 4 Nov 2021 18:37:34 +0100
Subject: [PATCH] Adds on-disk benchmarks

---
 lib/benches/store.rs | 123 ++++++++++++++++++++++++++++++-------------
 1 file changed, 85 insertions(+), 38 deletions(-)

diff --git a/lib/benches/store.rs b/lib/benches/store.rs
index 815b9590..37f479d6 100644
--- a/lib/benches/store.rs
+++ b/lib/benches/store.rs
@@ -4,9 +4,11 @@ use oxigraph::io::GraphFormat;
 use oxigraph::model::GraphNameRef;
 use oxigraph::sparql::{Query, QueryResults, Update};
 use oxigraph::store::Store;
-use std::fs::File;
+use rand::random;
+use std::env::temp_dir;
+use std::fs::{remove_dir_all, File};
 use std::io::{BufRead, BufReader, Cursor, Read};
-use std::path::Path;
+use std::path::{Path, PathBuf};
 
 fn store_load(c: &mut Criterion) {
     let mut data = Vec::new();
@@ -17,27 +19,22 @@ fn store_load(c: &mut Criterion) {
     let mut group = c.benchmark_group("store load");
     group.throughput(Throughput::Bytes(data.len() as u64));
     group.sample_size(10);
-    group.bench_function("load BSBM explore 1000", |b| {
+    group.bench_function("load BSBM explore 1000 in memory", |b| {
         b.iter(|| {
             let store = Store::new().unwrap();
-            store
-                .load_graph(
-                    Cursor::new(&data),
-                    GraphFormat::NTriples,
-                    GraphNameRef::DefaultGraph,
-                    None,
-                )
-                .unwrap();
+            do_load(&store, &data);
+        })
+    });
+    group.bench_function("load BSBM explore 1000 in on disk", |b| {
+        b.iter(|| {
+            let path = TempDir::default();
+            let store = Store::open(&path.0).unwrap();
+            do_load(&store, &data);
         })
     });
 }
 
-fn store_query_and_update(c: &mut Criterion) {
-    let mut data = Vec::new();
-    read_data("explore-1000.nt.zst")
-        .read_to_end(&mut data)
-        .unwrap();
-    let store = Store::new().unwrap();
+fn do_load(store: &Store, data: &[u8]) {
     store
         .load_graph(
             Cursor::new(&data),
@@ -46,6 +43,14 @@ fn store_query_and_update(c: &mut Criterion) {
             None,
         )
         .unwrap();
+}
+
+fn store_query_and_update(c: &mut Criterion) {
+    let mut data = Vec::new();
+    read_data("explore-1000.nt.zst")
+        .read_to_end(&mut data)
+        .unwrap();
+
     let operations = read_data("mix-exploreAndUpdate-1000.tsv.zst")
         .lines()
         .map(|l| {
@@ -60,32 +65,59 @@ fn store_query_and_update(c: &mut Criterion) {
             }
         })
         .collect::<Vec<_>>();
+    let query_operations = operations
+        .iter()
+        .filter(|o| matches!(o, Operation::Query(_)))
+        .cloned()
+        .collect::<Vec<_>>();
 
     let mut group = c.benchmark_group("store operations");
     group.throughput(Throughput::Elements(operations.len() as u64));
     group.sample_size(10);
-    group.bench_function("BSBM explore 1000 queryAndUpdate", |b| {
-        b.iter(|| {
-            for operation in &operations {
-                match operation {
-                    Operation::Query(q) => match store.query(q.clone()).unwrap() {
-                        QueryResults::Boolean(_) => (),
-                        QueryResults::Solutions(s) => {
-                            for s in s {
-                                s.unwrap();
-                            }
-                        }
-                        QueryResults::Graph(g) => {
-                            for t in g {
-                                t.unwrap();
-                            }
-                        }
-                    },
-                    Operation::Update(u) => store.update(u.clone()).unwrap(),
+
+    {
+        let memory_store = Store::new().unwrap();
+        do_load(&memory_store, &data);
+        group.bench_function("BSBM explore 1000 query in memory", |b| {
+            b.iter(|| run_operation(&memory_store, &query_operations))
+        });
+        group.bench_function("BSBM explore 1000 queryAndUpdate in memory", |b| {
+            b.iter(|| run_operation(&memory_store, &operations))
+        });
+    }
+
+    {
+        let path = TempDir::default();
+        let disk_store = Store::open(&path.0).unwrap();
+        do_load(&disk_store, &data);
+        group.bench_function("BSBM explore 1000 query on disk", |b| {
+            b.iter(|| run_operation(&disk_store, &query_operations))
+        });
+        group.bench_function("BSBM explore 1000 queryAndUpdate on disk", |b| {
+            b.iter(|| run_operation(&disk_store, &operations))
+        });
+    }
+}
+
+fn run_operation(store: &Store, operations: &[Operation]) {
+    for operation in operations {
+        match operation {
+            Operation::Query(q) => match store.query(q.clone()).unwrap() {
+                QueryResults::Boolean(_) => (),
+                QueryResults::Solutions(s) => {
+                    for s in s {
+                        s.unwrap();
+                    }
                 }
-            }
-        })
-    });
+                QueryResults::Graph(g) => {
+                    for t in g {
+                        t.unwrap();
+                    }
+                }
+            },
+            Operation::Update(u) => store.update(u.clone()).unwrap(),
+        }
+    }
 }
 
 criterion_group!(store, store_query_and_update, store_load);
@@ -113,7 +145,22 @@ fn read_data(file: &str) -> impl BufRead {
     BufReader::new(zstd::Decoder::new(File::open(file).unwrap()).unwrap())
 }
 
+#[derive(Clone)]
 enum Operation {
     Query(Query),
     Update(Update),
 }
+
+struct TempDir(PathBuf);
+
+impl Default for TempDir {
+    fn default() -> Self {
+        Self(temp_dir().join(format!("oxigraph-bench-{}", random::<u128>())))
+    }
+}
+
+impl Drop for TempDir {
+    fn drop(&mut self) {
+        remove_dir_all(&self.0).unwrap()
+    }
+}