From d7ddf4925e7ca5b4a444a7f14fe5f3035242f522 Mon Sep 17 00:00:00 2001 From: Tamo Date: Wed, 17 May 2023 14:25:50 +0200 Subject: [PATCH] Revert "Disable autobatching of additions and deletions" This reverts commit a94e78ffb051193ece752a9dd19858a05922f706. --- index-scheduler/src/autobatcher.rs | 103 ++++++++++++++++++++--------- index-scheduler/src/lib.rs | 99 +++++++++++++++++++++++++++ 2 files changed, 169 insertions(+), 33 deletions(-) diff --git a/index-scheduler/src/autobatcher.rs b/index-scheduler/src/autobatcher.rs index d738cc5e4..096bcce14 100644 --- a/index-scheduler/src/autobatcher.rs +++ b/index-scheduler/src/autobatcher.rs @@ -321,9 +321,18 @@ impl BatchKind { }) } ( - this @ BatchKind::DocumentOperation { .. }, + BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids }, K::DocumentDeletion, - ) => Break(this), + ) => { + operation_ids.push(id); + + Continue(BatchKind::DocumentOperation { + method, + allow_index_creation, + primary_key, + operation_ids, + }) + } // but we can't autobatch documents if it's not the same kind // this match branch MUST be AFTER the previous one ( @@ -346,7 +355,35 @@ impl BatchKind { deletion_ids.push(id); Continue(BatchKind::DocumentClear { ids: deletion_ids }) } - // we can't autobatch a deletion and an import + // we can autobatch the deletion and import if the index already exists + ( + BatchKind::DocumentDeletion { mut deletion_ids }, + K::DocumentImport { method, allow_index_creation, primary_key } + ) if index_already_exists => { + deletion_ids.push(id); + + Continue(BatchKind::DocumentOperation { + method, + allow_index_creation, + primary_key, + operation_ids: deletion_ids, + }) + } + // we can autobatch the deletion and import if both can't create an index + ( + BatchKind::DocumentDeletion { mut deletion_ids }, + K::DocumentImport { method, allow_index_creation, primary_key } + ) if !allow_index_creation => { + deletion_ids.push(id); + + Continue(BatchKind::DocumentOperation { + method, + allow_index_creation, + primary_key, + operation_ids: deletion_ids, + }) + } + // we can't autobatch a deletion and an import if the index does not exists but would be created by an addition ( this @ BatchKind::DocumentDeletion { .. }, K::DocumentImport { .. } @@ -648,36 +685,36 @@ mod tests { debug_snapshot!(autobatch_from(false,None, [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))"); debug_snapshot!(autobatch_from(false,None, [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))"); - // We can't autobatch document addition with document deletion - debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); - debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); - debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###); - debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###); - debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###); - debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###); - debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); - debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); - debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###); - debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###); - debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###); - debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###); - // we also can't do the only way around - debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); - debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))"); + // We can autobatch document addition with document deletion + debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))"); + debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))"); + debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###); + debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###); + debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))"); + debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))"); + debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###); + debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###); + debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + // And the other way around + debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); + debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); + debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); } #[test] diff --git a/index-scheduler/src/lib.rs b/index-scheduler/src/lib.rs index af20ba1ae..f245bb186 100644 --- a/index-scheduler/src/lib.rs +++ b/index-scheduler/src/lib.rs @@ -2017,6 +2017,105 @@ mod tests { snapshot!(snapshot_index_scheduler(&index_scheduler), name: "both_task_succeeded"); } + #[test] + fn document_addition_and_document_deletion() { + let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]); + + let content = r#"[ + { "id": 1, "doggo": "jean bob" }, + { "id": 2, "catto": "jorts" }, + { "id": 3, "doggo": "bork" } + ]"#; + + let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap(); + let documents_count = read_json(content.as_bytes(), file.as_file_mut()).unwrap(); + file.persist().unwrap(); + index_scheduler + .register(KindWithContent::DocumentAdditionOrUpdate { + index_uid: S("doggos"), + primary_key: Some(S("id")), + method: ReplaceDocuments, + content_file: uuid, + documents_count, + allow_index_creation: true, + }) + .unwrap(); + snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_first_task"); + index_scheduler + .register(KindWithContent::DocumentDeletion { + index_uid: S("doggos"), + documents_ids: vec![S("1"), S("2")], + }) + .unwrap(); + snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_second_task"); + + handle.advance_one_successful_batch(); // The addition AND deletion should've been batched together + snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_processing_the_batch"); + + let index = index_scheduler.index("doggos").unwrap(); + let rtxn = index.read_txn().unwrap(); + let field_ids_map = index.fields_ids_map(&rtxn).unwrap(); + let field_ids = field_ids_map.ids().collect::>(); + let documents = index + .all_documents(&rtxn) + .unwrap() + .map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap()) + .collect::>(); + snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents"); + } + + #[test] + fn document_deletion_and_document_addition() { + let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]); + index_scheduler + .register(KindWithContent::DocumentDeletion { + index_uid: S("doggos"), + documents_ids: vec![S("1"), S("2")], + }) + .unwrap(); + snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_first_task"); + + let content = r#"[ + { "id": 1, "doggo": "jean bob" }, + { "id": 2, "catto": "jorts" }, + { "id": 3, "doggo": "bork" } + ]"#; + + let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap(); + let documents_count = read_json(content.as_bytes(), file.as_file_mut()).unwrap(); + file.persist().unwrap(); + index_scheduler + .register(KindWithContent::DocumentAdditionOrUpdate { + index_uid: S("doggos"), + primary_key: Some(S("id")), + method: ReplaceDocuments, + content_file: uuid, + documents_count, + allow_index_creation: true, + }) + .unwrap(); + snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_second_task"); + + // The deletion should have failed because it can't create an index + handle.advance_one_failed_batch(); + snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_failing_the_deletion"); + + // The addition should works + handle.advance_one_successful_batch(); + snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_last_successful_addition"); + + let index = index_scheduler.index("doggos").unwrap(); + let rtxn = index.read_txn().unwrap(); + let field_ids_map = index.fields_ids_map(&rtxn).unwrap(); + let field_ids = field_ids_map.ids().collect::>(); + let documents = index + .all_documents(&rtxn) + .unwrap() + .map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap()) + .collect::>(); + snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents"); + } + #[test] fn do_not_batch_task_of_different_indexes() { let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);