Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

datastore: early exit missing components at table level #1554

Merged
merged 2 commits into from
Mar 10, 2023
Merged

datastore: early exit missing components at table level #1554

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a6d2a6a
early exit at index table level
teh-cmc Mar 10, 2023
c723e73
worst-case benchmark
teh-cmc Mar 10, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 15 additions & 7 deletions crates/re_arrow_store/benches/data_store.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ static GLOBAL: mimalloc::MiMalloc = mimalloc::MiMalloc;
use arrow2::array::{Array, UnionArray};
use criterion::{criterion_group, criterion_main, Criterion};

use re_arrow_store::{DataStore, LatestAtQuery, RangeQuery, TimeInt, TimeRange};
use re_arrow_store::{DataStore, DataStoreConfig, LatestAtQuery, RangeQuery, TimeInt, TimeRange};
use re_log_types::{
component_types::{InstanceKey, Rect2D},
datagen::{build_frame_nr, build_some_instances, build_some_rects},
Expand Down Expand Up @@ -35,15 +35,15 @@ fn insert(c: &mut Criterion) {
(NUM_RECTS * NUM_FRAMES) as _,
));
group.bench_function("insert", |b| {
b.iter(|| insert_messages(InstanceKey::name(), msgs.iter()));
b.iter(|| insert_messages(Default::default(), InstanceKey::name(), msgs.iter()));
});
}
}

fn latest_at_batch(c: &mut Criterion) {
{
let msgs = build_messages(NUM_RECTS as usize);
let store = insert_messages(InstanceKey::name(), msgs.iter());
let store = insert_messages(Default::default(), InstanceKey::name(), msgs.iter());
let mut group = c.benchmark_group("datastore/latest_at/batch/rects");
group.throughput(criterion::Throughput::Elements(NUM_RECTS as _));
group.bench_function("query", |b| {
Expand All @@ -62,9 +62,16 @@ fn latest_at_batch(c: &mut Criterion) {
}

fn latest_at_missing_components(c: &mut Criterion) {
// Simulate the worst possible case: many many buckets.
let config = DataStoreConfig {
index_bucket_size_bytes: 0,
index_bucket_nb_rows: 0,
..Default::default()
};

{
let msgs = build_messages(NUM_RECTS as usize);
let store = insert_messages(InstanceKey::name(), msgs.iter());
let store = insert_messages(config.clone(), InstanceKey::name(), msgs.iter());
let mut group = c.benchmark_group("datastore/latest_at/missing_components");
group.throughput(criterion::Throughput::Elements(NUM_RECTS as _));
group.bench_function("primary", |b| {
Expand All @@ -78,7 +85,7 @@ fn latest_at_missing_components(c: &mut Criterion) {

{
let msgs = build_messages(NUM_RECTS as usize);
let store = insert_messages(InstanceKey::name(), msgs.iter());
let store = insert_messages(config, InstanceKey::name(), msgs.iter());
let mut group = c.benchmark_group("datastore/latest_at/missing_components");
group.throughput(criterion::Throughput::Elements(NUM_RECTS as _));
group.bench_function("secondaries", |b| {
Expand All @@ -103,7 +110,7 @@ fn latest_at_missing_components(c: &mut Criterion) {
fn range_batch(c: &mut Criterion) {
{
let msgs = build_messages(NUM_RECTS as usize);
let store = insert_messages(InstanceKey::name(), msgs.iter());
let store = insert_messages(Default::default(), InstanceKey::name(), msgs.iter());
let mut group = c.benchmark_group("datastore/range/batch/rects");
group.throughput(criterion::Throughput::Elements(
(NUM_RECTS * NUM_FRAMES) as _,
Expand Down Expand Up @@ -155,10 +162,11 @@ fn build_messages(n: usize) -> Vec<MsgBundle> {
}

fn insert_messages<'a>(
config: DataStoreConfig,
cluster_key: ComponentName,
msgs: impl Iterator<Item = &'a MsgBundle>,
) -> DataStore {
let mut store = DataStore::new(cluster_key, Default::default());
let mut store = DataStore::new(cluster_key, config);
msgs.for_each(|msg_bundle| store.insert(msg_bundle).unwrap());
store
}
Expand Down
5 changes: 5 additions & 0 deletions crates/re_arrow_store/src/store_read.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -657,6 +657,11 @@ impl IndexTable {
) -> Option<[Option<RowIndex>; N]> {
crate::profile_function!();

// Early-exit if this entire table is unaware of this component.
if !self.all_components.contains(&primary) {
return None;
}

let timeline = self.timeline;

// The time we're looking for gives us an upper bound: all components must be indexed
Expand Down