MeiliSearch/benchmarks/benches/utils.rs

120 lines
4.1 KiB
Rust
Raw Normal View History

2021-04-14 16:26:21 +02:00
use std::fs::{create_dir_all, remove_dir_all, File};
use criterion::BenchmarkId;
2021-04-14 13:13:33 +02:00
use heed::EnvOpenOptions;
use milli::{
update::{IndexDocumentsMethod, Settings, UpdateBuilder, UpdateFormat},
2021-06-03 10:33:42 +02:00
FilterCondition, Index,
2021-04-14 13:13:33 +02:00
};
pub struct Conf<'a> {
/// where we are going to create our database.mmdb directory
/// each benchmark will first try to delete it and then recreate it
pub database_name: &'a str,
/// the dataset to be used, it must be an uncompressed csv
pub dataset: &'a str,
pub group_name: &'a str,
2021-04-14 13:13:33 +02:00
pub queries: &'a [&'a str],
/// here you can change which criterion are used and in which order.
/// - if you specify something all the base configuration will be thrown out
/// - if you don't specify anything (None) the default configuration will be kept
pub criterion: Option<&'a [&'a str]>,
/// the last chance to configure your database as you want
pub configure: fn(&mut Settings),
2021-06-03 10:33:42 +02:00
pub filter: Option<&'a str>,
/// enable or disable the optional words on the query
pub optional_words: bool,
/// primary key, if there is None we'll auto-generate docids for every documents
pub primary_key: Option<&'a str>,
}
impl Conf<'_> {
pub const BASE: Self = Conf {
database_name: "benches.mmdb",
dataset: "",
group_name: "",
queries: &[],
criterion: None,
2021-06-02 17:09:21 +02:00
configure: |_| (),
2021-06-03 10:33:42 +02:00
filter: None,
optional_words: true,
primary_key: None,
};
}
pub fn base_setup(conf: &Conf) -> Index {
match remove_dir_all(&conf.database_name) {
Ok(_) => (),
Err(e) if e.kind() == std::io::ErrorKind::NotFound => (),
Err(e) => panic!("{}", e),
}
create_dir_all(&conf.database_name).unwrap();
let mut options = EnvOpenOptions::new();
options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
options.max_readers(10);
let index = Index::new(options, conf.database_name).unwrap();
if let Some(primary_key) = conf.primary_key {
let mut wtxn = index.write_txn().unwrap();
index.put_primary_key(&mut wtxn, primary_key).unwrap();
}
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.settings(&mut wtxn, &index);
if let Some(criterion) = conf.criterion {
2021-06-03 10:33:42 +02:00
builder.reset_filterable_fields();
builder.reset_criteria();
builder.reset_stop_words();
let criterion = criterion.iter().map(|s| s.to_string()).collect();
builder.set_criteria(criterion);
}
(conf.configure)(&mut builder);
builder.execute(|_, _| ()).unwrap();
wtxn.commit().unwrap();
let update_builder = UpdateBuilder::new(0);
let mut wtxn = index.write_txn().unwrap();
let mut builder = update_builder.index_documents(&mut wtxn, &index);
if let None = conf.primary_key {
builder.enable_autogenerate_docids();
}
builder.update_format(UpdateFormat::Csv);
builder.index_documents_method(IndexDocumentsMethod::ReplaceDocuments);
let reader = File::open(conf.dataset)
.expect(&format!("could not find the dataset in: {}", conf.dataset));
builder.execute(reader, |_, _| ()).unwrap();
wtxn.commit().unwrap();
index
}
pub fn run_benches(c: &mut criterion::Criterion, confs: &[Conf]) {
for conf in confs {
let index = base_setup(conf);
let mut group = c.benchmark_group(&format!("{}: {}", conf.dataset, conf.group_name));
for &query in conf.queries {
group.bench_with_input(BenchmarkId::from_parameter(query), &query, |b, &query| {
b.iter(|| {
let rtxn = index.read_txn().unwrap();
let mut search = index.search(&rtxn);
search.query(query).optional_words(conf.optional_words);
2021-06-03 10:33:42 +02:00
if let Some(filter) = conf.filter {
let filter =
FilterCondition::from_str(&rtxn, &index, filter).unwrap();
search.filter(filter);
}
let _ids = search.execute().unwrap();
});
});
}
group.finish();
}
}