Skip to content

Commit

Permalink
feat(pageserver): support partial gc-compaction for delta layers (#9611)
Browse files Browse the repository at this point in the history 
Signed-off-by: Alex Chi Z <[email protected]>

partial address comments

Signed-off-by: Alex Chi Z <[email protected]>
  • Loading branch information
@skyzh
skyzh committed Nov 11, 2024
1 parent 48c06d9 commit ff00ba0
Show file tree
Hide file tree
Showing 4 changed files with 368 additions and 159 deletions.
9 changes: 9 additions & 0 deletions pageserver/compaction/src/helpers.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,15 @@ pub fn overlaps_with<T: Ord>(a: &Range<T>, b: &Range<T>) -> bool {
!(a.end <= b.start || b.end <= a.start)
}

/// Whether a fully contains b, example as below
/// ```plain
/// | a |
/// | b |
/// ```
pub fn fully_contains<T: Ord>(a: &Range<T>, b: &Range<T>) -> bool {
a.start <= b.start && a.end >= b.end
}

pub fn union_to_keyspace<K: Ord>(a: &mut CompactionKeySpace<K>, b: CompactionKeySpace<K>) {
let x = std::mem::take(a);
let mut all_ranges_iter = [x.into_iter(), b.into_iter()]
Expand Down
219 changes: 160 additions & 59 deletions pageserver/src/tenant.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -9229,6 +9229,23 @@ mod tests {
Ok(())
}

fn sort_layer_key(k1: &PersistentLayerKey, k2: &PersistentLayerKey) -> std::cmp::Ordering {
(
k1.is_delta,
k1.key_range.start,
k1.key_range.end,
k1.lsn_range.start,
k1.lsn_range.end,
)
.cmp(&(
k2.is_delta,
k2.key_range.start,
k2.key_range.end,
k2.lsn_range.start,
k2.lsn_range.end,
))
}

async fn inspect_and_sort(
tline: &Arc<Timeline>,
filter: Option<std::ops::Range<Key>>,
Expand All @@ -9237,25 +9254,30 @@ mod tests {
if let Some(filter) = filter {
all_layers.retain(|layer| overlaps_with(&layer.key_range, &filter));
}
all_layers.sort_by(|k1, k2| {
(
k1.is_delta,
k1.key_range.start,
k1.key_range.end,
k1.lsn_range.start,
k1.lsn_range.end,
)
.cmp(&(
k2.is_delta,
k2.key_range.start,
k2.key_range.end,
k2.lsn_range.start,
k2.lsn_range.end,
))
});
all_layers.sort_by(sort_layer_key);
all_layers
}

#[cfg(feature = "testing")]
fn check_layer_map_key_eq(
mut left: Vec<PersistentLayerKey>,
mut right: Vec<PersistentLayerKey>,
) {
left.sort_by(sort_layer_key);
right.sort_by(sort_layer_key);
if left != right {
eprintln!("---LEFT---");
for left in left.iter() {
eprintln!("{}", left);
}
eprintln!("---RIGHT---");
for right in right.iter() {
eprintln!("{}", right);
}
assert_eq!(left, right);
}
}

#[cfg(feature = "testing")]
#[tokio::test]
async fn test_simple_partial_bottom_most_compaction() -> anyhow::Result<()> {
Expand Down Expand Up @@ -9348,127 +9370,206 @@ mod tests {

let cancel = CancellationToken::new();

// Do a partial compaction on key range 0..4, we should generate a image layer; no other layers
// can be removed because they might be used for other key ranges.
// Do a partial compaction on key range 0..2
tline
.partial_compact_with_gc(Some(get_key(0)..get_key(4)), &cancel, EnumSet::new(), &ctx)
.partial_compact_with_gc(Some(get_key(0)..get_key(2)), &cancel, EnumSet::new(), &ctx)
.await
.unwrap();
let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
assert_eq!(
check_layer_map_key_eq(
all_layers,
vec![
// newly-generated image layer for the partial compaction range 0-2
PersistentLayerKey {
key_range: get_key(0)..get_key(4),
key_range: get_key(0)..get_key(2),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(0)..get_key(10),
lsn_range: Lsn(0x10)..Lsn(0x11),
is_delta: false
is_delta: false,
},
// delta1 is split and the second part is rewritten
PersistentLayerKey {
key_range: get_key(1)..get_key(4),
key_range: get_key(2)..get_key(4),
lsn_range: Lsn(0x20)..Lsn(0x48),
is_delta: true
is_delta: true,
},
PersistentLayerKey {
key_range: get_key(5)..get_key(7),
lsn_range: Lsn(0x20)..Lsn(0x48),
is_delta: true
is_delta: true,
},
PersistentLayerKey {
key_range: get_key(8)..get_key(10),
lsn_range: Lsn(0x48)..Lsn(0x50),
is_delta: true
}
]
is_delta: true,
},
],
);

// Do a partial compaction on key range 4..10
// Do a partial compaction on key range 2..4
tline
.partial_compact_with_gc(Some(get_key(4)..get_key(10)), &cancel, EnumSet::new(), &ctx)
.partial_compact_with_gc(Some(get_key(2)..get_key(4)), &cancel, EnumSet::new(), &ctx)
.await
.unwrap();
let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
assert_eq!(
check_layer_map_key_eq(
all_layers,
vec![
PersistentLayerKey {
key_range: get_key(0)..get_key(4),
key_range: get_key(0)..get_key(2),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false
is_delta: false,
},
PersistentLayerKey {
// if (in the future) GC kicks in, this layer will be removed
key_range: get_key(0)..get_key(10),
lsn_range: Lsn(0x10)..Lsn(0x11),
is_delta: false
is_delta: false,
},
// image layer generated for the compaction range 2-4
PersistentLayerKey {
key_range: get_key(4)..get_key(10),
key_range: get_key(2)..get_key(4),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false
is_delta: false,
},
// we have key2/key3 above the retain_lsn, so we still need this delta layer
PersistentLayerKey {
key_range: get_key(1)..get_key(4),
key_range: get_key(2)..get_key(4),
lsn_range: Lsn(0x20)..Lsn(0x48),
is_delta: true
is_delta: true,
},
PersistentLayerKey {
key_range: get_key(5)..get_key(7),
lsn_range: Lsn(0x20)..Lsn(0x48),
is_delta: true
is_delta: true,
},
PersistentLayerKey {
key_range: get_key(8)..get_key(10),
lsn_range: Lsn(0x48)..Lsn(0x50),
is_delta: true
}
]
is_delta: true,
},
],
);

// Do a partial compaction on key range 0..10, all image layers below LSN 20 can be replaced with new ones.
// Do a partial compaction on key range 4..9
tline
.partial_compact_with_gc(Some(get_key(0)..get_key(10)), &cancel, EnumSet::new(), &ctx)
.partial_compact_with_gc(Some(get_key(4)..get_key(9)), &cancel, EnumSet::new(), &ctx)
.await
.unwrap();
let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
assert_eq!(
check_layer_map_key_eq(
all_layers,
vec![
PersistentLayerKey {
key_range: get_key(0)..get_key(4),
key_range: get_key(0)..get_key(2),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(0)..get_key(10),
lsn_range: Lsn(0x10)..Lsn(0x11),
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(2)..get_key(4),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(4)..get_key(10),
key_range: get_key(2)..get_key(4),
lsn_range: Lsn(0x20)..Lsn(0x48),
is_delta: true,
},
// image layer generated for this compaction range
PersistentLayerKey {
key_range: get_key(4)..get_key(9),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(8)..get_key(10),
lsn_range: Lsn(0x48)..Lsn(0x50),
is_delta: true,
},
],
);

// Do a partial compaction on key range 9..10
tline
.partial_compact_with_gc(Some(get_key(9)..get_key(10)), &cancel, EnumSet::new(), &ctx)
.await
.unwrap();
let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
check_layer_map_key_eq(
all_layers,
vec![
PersistentLayerKey {
key_range: get_key(0)..get_key(2),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(0)..get_key(10),
lsn_range: Lsn(0x10)..Lsn(0x11),
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(1)..get_key(4),
key_range: get_key(2)..get_key(4),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(2)..get_key(4),
lsn_range: Lsn(0x20)..Lsn(0x48),
is_delta: true
is_delta: true,
},
PersistentLayerKey {
key_range: get_key(5)..get_key(7),
key_range: get_key(4)..get_key(9),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false,
},
// image layer generated for the compaction range
PersistentLayerKey {
key_range: get_key(9)..get_key(10),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(8)..get_key(10),
lsn_range: Lsn(0x48)..Lsn(0x50),
is_delta: true,
},
],
);

// Do a partial compaction on key range 0..10, all image layers below LSN 20 can be replaced with new ones.
tline
.partial_compact_with_gc(Some(get_key(0)..get_key(10)), &cancel, EnumSet::new(), &ctx)
.await
.unwrap();
let all_layers = inspect_and_sort(&tline, Some(get_key(0)..get_key(10))).await;
check_layer_map_key_eq(
all_layers,
vec![
// aha, we removed all unnecessary image/delta layers and got a very clean layer map!
PersistentLayerKey {
key_range: get_key(0)..get_key(10),
lsn_range: Lsn(0x20)..Lsn(0x21),
is_delta: false,
},
PersistentLayerKey {
key_range: get_key(2)..get_key(4),
lsn_range: Lsn(0x20)..Lsn(0x48),
is_delta: true
is_delta: true,
},
PersistentLayerKey {
key_range: get_key(8)..get_key(10),
lsn_range: Lsn(0x48)..Lsn(0x50),
is_delta: true
}
]
is_delta: true,
},
],
);

Ok(())
Expand Down
4 changes: 4 additions & 0 deletions pageserver/src/tenant/storage_layer/delta_layer.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -653,6 +653,10 @@ impl DeltaLayerWriter {
})
}

pub fn is_empty(&self) -> bool {
self.inner.as_ref().unwrap().num_keys == 0
}

///
/// Append a key-value pair to the file.
///
Expand Down
Loading

0 comments on commit ff00ba0

Please sign in to comment.