Merge pull request #5670 from meilisearch/export-and-transfer-route

Introduce a new route to export indexes
This commit is contained in:
Mubelotix
2025-07-01 14:37:02 +00:00
committed by GitHub
36 changed files with 990 additions and 27 deletions

View File

@ -48,6 +48,9 @@ pub(crate) enum Batch {
IndexSwap {
task: Task,
},
Export {
task: Task,
},
UpgradeDatabase {
tasks: Vec<Task>,
},
@ -104,6 +107,7 @@ impl Batch {
Batch::TaskCancelation { task, .. }
| Batch::Dump(task)
| Batch::IndexCreation { task, .. }
| Batch::Export { task }
| Batch::IndexUpdate { task, .. } => {
RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
}
@ -143,6 +147,7 @@ impl Batch {
| TaskDeletions(_)
| SnapshotCreation(_)
| Dump(_)
| Export { .. }
| UpgradeDatabase { .. }
| IndexSwap { .. } => None,
IndexOperation { op, .. } => Some(op.index_uid()),
@ -168,6 +173,7 @@ impl fmt::Display for Batch {
Batch::IndexUpdate { .. } => f.write_str("IndexUpdate")?,
Batch::IndexDeletion { .. } => f.write_str("IndexDeletion")?,
Batch::IndexSwap { .. } => f.write_str("IndexSwap")?,
Batch::Export { .. } => f.write_str("Export")?,
Batch::UpgradeDatabase { .. } => f.write_str("UpgradeDatabase")?,
};
match index_uid {
@ -427,9 +433,10 @@ impl IndexScheduler {
/// 0. We get the *last* task to cancel.
/// 1. We get the tasks to upgrade.
/// 2. We get the *next* task to delete.
/// 3. We get the *next* snapshot to process.
/// 4. We get the *next* dump to process.
/// 5. We get the *next* tasks to process for a specific index.
/// 3. We get the *next* export to process.
/// 4. We get the *next* snapshot to process.
/// 5. We get the *next* dump to process.
/// 6. We get the *next* tasks to process for a specific index.
#[tracing::instrument(level = "trace", skip(self, rtxn), target = "indexing::scheduler")]
pub(crate) fn create_next_batch(
&self,
@ -501,7 +508,17 @@ impl IndexScheduler {
return Ok(Some((Batch::TaskDeletions(tasks), current_batch)));
}
// 3. we batch the snapshot.
// 3. we batch the export.
let to_export = self.queue.tasks.get_kind(rtxn, Kind::Export)? & enqueued;
if !to_export.is_empty() {
let task_id = to_export.iter().next().expect("There must be at least one export task");
let mut task = self.queue.tasks.get_task(rtxn, task_id)?.unwrap();
current_batch.processing([&mut task]);
current_batch.reason(BatchStopReason::TaskKindCannotBeBatched { kind: Kind::Export });
return Ok(Some((Batch::Export { task }, current_batch)));
}
// 4. we batch the snapshot.
let to_snapshot = self.queue.tasks.get_kind(rtxn, Kind::SnapshotCreation)? & enqueued;
if !to_snapshot.is_empty() {
let mut tasks = self.queue.tasks.get_existing_tasks(rtxn, to_snapshot)?;
@ -511,7 +528,7 @@ impl IndexScheduler {
return Ok(Some((Batch::SnapshotCreation(tasks), current_batch)));
}
// 4. we batch the dumps.
// 5. we batch the dumps.
let to_dump = self.queue.tasks.get_kind(rtxn, Kind::DumpCreation)? & enqueued;
if let Some(to_dump) = to_dump.min() {
let mut task =
@ -524,7 +541,7 @@ impl IndexScheduler {
return Ok(Some((Batch::Dump(task), current_batch)));
}
// 5. We make a batch from the unprioritised tasks. Start by taking the next enqueued task.
// 6. We make a batch from the unprioritised tasks. Start by taking the next enqueued task.
let task_id = if let Some(task_id) = enqueued.min() { task_id } else { return Ok(None) };
let mut task =
self.queue.tasks.get_task(rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;