snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-27 12:35:05 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Merge #315

Browse Source 
315: Rewrite the indexing benchmarks r=Kerollmops a=irevoire

There was a panic on the benchmark and while I was trying to understand what was happening I decided to rewrite the way the benchmarks were working.

Before we were creating a database with the good setting, and then for each benchmarks we were:
1. Deleting all documents in the database
2. Indexing a batch of documents

Now for each iteration we recreate entirely a new database from scratch.
Since deleting all the documents in a database may not be the same as starting with a fresh new database I prefer this solution.

Co-authored-by: Irevoire <tamo@meilisearch.com>
This commit is contained in:
bors[bot] 2021-08-24 15:34:50 +00:00 committed by GitHub
commit 794c0f64a9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 129 additions and 155 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

266
benchmarks/benches/indexing.rs
View File

@ -31,48 +31,43 @@ fn setup_index() -> Index {
}
fn indexing_songs_default(c: &mut Criterion) {
let index = setup_index();
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.settings(&mut wtxn, &index);
builder.set_primary_key("id".to_owned());
let displayed_fields = ["title", "album", "artist", "genre", "country", "released", "duration"]
.iter()
.map(|s| s.to_string())
.collect();
builder.set_displayed_fields(displayed_fields);
let searchable_fields = ["title", "album", "artist"].iter().map(|s| s.to_string()).collect();
builder.set_searchable_fields(searchable_fields);
let faceted_fields = ["released-timestamp", "duration-float", "genre", "country", "artist"]
.iter()
.map(|s| s.to_string())
.collect();
builder.set_filterable_fields(faceted_fields);
builder.execute(|_, _| ()).unwrap();
wtxn.commit().unwrap();
let index_ref = &index;
let mut group = c.benchmark_group("indexing");
group.sample_size(10);
group.bench_function("Indexing songs with default settings", |b| {
b.iter_with_setup(
move || {
let index = setup_index();
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let builder = update_builder.delete_documents(&mut wtxn, index_ref).unwrap();
builder.execute().unwrap();
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.settings(&mut wtxn, &index);
builder.set_primary_key("id".to_owned());
let displayed_fields =
["title", "album", "artist", "genre", "country", "released", "duration"]
.iter()
.map(|s| s.to_string())
.collect();
builder.set_displayed_fields(displayed_fields);
let searchable_fields =
["title", "album", "artist"].iter().map(|s| s.to_string()).collect();
builder.set_searchable_fields(searchable_fields);
let faceted_fields =
["released-timestamp", "duration-float", "genre", "country", "artist"]
.iter()
.map(|s| s.to_string())
.collect();
builder.set_filterable_fields(faceted_fields);
builder.execute(|_, _| ()).unwrap();
wtxn.commit().unwrap();
()
index
},
move |_| {
move |index| {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, index_ref);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, &index);
builder.update_format(UpdateFormat::Csv);
builder.index_documents_method(IndexDocumentsMethod::ReplaceDocuments);
@ -82,69 +77,19 @@ fn indexing_songs_default(c: &mut Criterion) {
));
builder.execute(reader, |_, _| ()).unwrap();
wtxn.commit().unwrap();
index.prepare_for_closing().wait();
},
)
});
index.prepare_for_closing().wait();
}
fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
let index = setup_index();
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.settings(&mut wtxn, &index);
builder.set_primary_key("id".to_owned());
let displayed_fields = ["title", "album", "artist", "genre", "country", "released", "duration"]
.iter()
.map(|s| s.to_string())
.collect();
builder.set_displayed_fields(displayed_fields);
let searchable_fields = ["title", "album", "artist"].iter().map(|s| s.to_string()).collect();
builder.set_searchable_fields(searchable_fields);
let faceted_fields = ["genre", "country", "artist"].iter().map(|s| s.to_string()).collect();
builder.set_filterable_fields(faceted_fields);
builder.execute(|_, _| ()).unwrap();
wtxn.commit().unwrap();
let index_ref = &index;
let mut group = c.benchmark_group("indexing");
group.sample_size(10);
group.bench_function("Indexing songs without faceted numbers", |b| {
b.iter_with_setup(
move || {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let builder = update_builder.delete_documents(&mut wtxn, index_ref).unwrap();
builder.execute().unwrap();
wtxn.commit().unwrap();
()
},
move |_| {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, index_ref);
builder.update_format(UpdateFormat::Csv);
builder.index_documents_method(IndexDocumentsMethod::ReplaceDocuments);
let reader = File::open(datasets_paths::SMOL_SONGS).expect(&format!(
"could not find the dataset in: {}",
datasets_paths::SMOL_SONGS
));
builder.execute(reader, |_, _| ()).unwrap();
wtxn.commit().unwrap();
},
)
});
index.prepare_for_closing().wait();
}
fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
let index = setup_index();
let update_builder = UpdateBuilder::new(0);
@ -152,35 +97,28 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
let mut builder = update_builder.settings(&mut wtxn, &index);
builder.set_primary_key("id".to_owned());
let displayed_fields = ["title", "album", "artist", "genre", "country", "released", "duration"]
let displayed_fields =
["title", "album", "artist", "genre", "country", "released", "duration"]
.iter()
.map(|s| s.to_string())
.collect();
builder.set_displayed_fields(displayed_fields);
let searchable_fields = ["title", "album", "artist"].iter().map(|s| s.to_string()).collect();
let searchable_fields =
["title", "album", "artist"].iter().map(|s| s.to_string()).collect();
builder.set_searchable_fields(searchable_fields);
let faceted_fields =
["genre", "country", "artist"].iter().map(|s| s.to_string()).collect();
builder.set_filterable_fields(faceted_fields);
builder.execute(|_, _| ()).unwrap();
wtxn.commit().unwrap();
let index_ref = &index;
let mut group = c.benchmark_group("indexing");
group.sample_size(10);
group.bench_function("Indexing songs without any facets", |b| {
b.iter_with_setup(
move || {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let builder = update_builder.delete_documents(&mut wtxn, index_ref).unwrap();
builder.execute().unwrap();
wtxn.commit().unwrap();
()
index
},
move |_| {
move |index| {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, index_ref);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, &index);
builder.update_format(UpdateFormat::Csv);
builder.index_documents_method(IndexDocumentsMethod::ReplaceDocuments);
@ -190,13 +128,19 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
));
builder.execute(reader, |_, _| ()).unwrap();
wtxn.commit().unwrap();
index.prepare_for_closing().wait();
},
)
});
index.prepare_for_closing().wait();
}
fn indexing_wiki(c: &mut Criterion) {
fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
let mut group = c.benchmark_group("indexing");
group.sample_size(10);
group.bench_function("Indexing songs without any facets", |b| {
b.iter_with_setup(
move || {
let index = setup_index();
let update_builder = UpdateBuilder::new(0);
@ -204,7 +148,55 @@ fn indexing_wiki(c: &mut Criterion) {
let mut builder = update_builder.settings(&mut wtxn, &index);
builder.set_primary_key("id".to_owned());
let displayed_fields = ["title", "body", "url"].iter().map(|s| s.to_string()).collect();
let displayed_fields =
["title", "album", "artist", "genre", "country", "released", "duration"]
.iter()
.map(|s| s.to_string())
.collect();
builder.set_displayed_fields(displayed_fields);
let searchable_fields =
["title", "album", "artist"].iter().map(|s| s.to_string()).collect();
builder.set_searchable_fields(searchable_fields);
builder.execute(|_, _| ()).unwrap();
wtxn.commit().unwrap();
index
},
move |index| {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, &index);
builder.update_format(UpdateFormat::Csv);
builder.index_documents_method(IndexDocumentsMethod::ReplaceDocuments);
let reader = File::open(datasets_paths::SMOL_SONGS).expect(&format!(
"could not find the dataset in: {}",
datasets_paths::SMOL_SONGS
));
builder.execute(reader, |_, _| ()).unwrap();
wtxn.commit().unwrap();
index.prepare_for_closing().wait();
},
)
});
}
fn indexing_wiki(c: &mut Criterion) {
let mut group = c.benchmark_group("indexing");
group.sample_size(10);
group.bench_function("Indexing wiki", |b| {
b.iter_with_setup(
move || {
let index = setup_index();
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.settings(&mut wtxn, &index);
builder.set_primary_key("id".to_owned());
let displayed_fields =
["title", "body", "url"].iter().map(|s| s.to_string()).collect();
builder.set_displayed_fields(displayed_fields);
let searchable_fields = ["title", "body"].iter().map(|s| s.to_string()).collect();
@ -214,25 +206,12 @@ fn indexing_wiki(c: &mut Criterion) {
builder.execute(|_, _| ()).unwrap();
wtxn.commit().unwrap();
let index_ref = &index;
let mut group = c.benchmark_group("indexing");
group.sample_size(10);
group.bench_function("Indexing wiki", |b| {
b.iter_with_setup(
move || {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let builder = update_builder.delete_documents(&mut wtxn, index_ref).unwrap();
builder.execute().unwrap();
wtxn.commit().unwrap();
()
index
},
move |_| {
move |index| {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, index_ref);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, &index);
builder.update_format(UpdateFormat::Csv);
builder.index_documents_method(IndexDocumentsMethod::ReplaceDocuments);
@ -242,13 +221,19 @@ fn indexing_wiki(c: &mut Criterion) {
));
builder.execute(reader, |_, _| ()).unwrap();
wtxn.commit().unwrap();
index.prepare_for_closing().wait();
},
)
});
index.prepare_for_closing().wait();
}
fn indexing_movies_default(c: &mut Criterion) {
let mut group = c.benchmark_group("indexing");
group.sample_size(10);
group.bench_function("Indexing movies with default settings", |b| {
b.iter_with_setup(
move || {
let index = setup_index();
let update_builder = UpdateBuilder::new(0);
@ -262,33 +247,22 @@ fn indexing_movies_default(c: &mut Criterion) {
.collect();
builder.set_displayed_fields(displayed_fields);
let searchable_fields = ["title", "overview"].iter().map(|s| s.to_string()).collect();
let searchable_fields =
["title", "overview"].iter().map(|s| s.to_string()).collect();
builder.set_searchable_fields(searchable_fields);
let faceted_fields = ["released_date", "genres"].iter().map(|s| s.to_string()).collect();
let faceted_fields =
["released_date", "genres"].iter().map(|s| s.to_string()).collect();
builder.set_filterable_fields(faceted_fields);
builder.execute(|_, _| ()).unwrap();
wtxn.commit().unwrap();
let index_ref = &index;
let mut group = c.benchmark_group("indexing");
group.sample_size(10);
group.bench_function("Indexing movies with default settings", |b| {
b.iter_with_setup(
move || {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let builder = update_builder.delete_documents(&mut wtxn, index_ref).unwrap();
builder.execute().unwrap();
wtxn.commit().unwrap();
()
index
},
move |_| {
move |index| {
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index_ref.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, index_ref);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, &index);
builder.update_format(UpdateFormat::Json);
builder.index_documents_method(IndexDocumentsMethod::ReplaceDocuments);
@ -296,11 +270,11 @@ fn indexing_movies_default(c: &mut Criterion) {
.expect(&format!("could not find the dataset in: {}", datasets_paths::MOVIES));
builder.execute(reader, |_, _| ()).unwrap();
wtxn.commit().unwrap();
index.prepare_for_closing().wait();
},
)
});
index.prepare_for_closing().wait();
}
criterion_group!(