searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-11-22 12:54:26 +01:00
Code Issues Releases Wiki Activity

make the generated filter valid

Browse Source
This commit is contained in:
Tamo 2023-04-26 13:55:02 +02:00 committed by Louis Dureuil
parent 9ca6f59546
commit dcbfecf42c
No known key found for this signature in database
8 changed files with 451 additions and 278 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
index-scheduler/src/lib.rs
View File

@ -51,6 +51,7 @@ use meilisearch_types::milli::{self, CboRoaringBitmapCodec, Index, RoaringBitmap
use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
use roaring::RoaringBitmap;
use synchronoise::SignalEvent;
use time::format_description::well_known::Rfc3339;
use time::OffsetDateTime;
use utils::{filter_out_references_to_newer_tasks, keep_tasks_within_datetimes, map_bound};
use uuid::Uuid;
@ -1118,7 +1119,6 @@ impl IndexScheduler {
let finished = self.status.get(&rtxn, &Status::Succeeded)?.unwrap_or_default()
| self.status.get(&rtxn, &Status::Failed)?.unwrap_or_default()
| self.status.get(&rtxn, &Status::Canceled)?.unwrap_or_default();
drop(rtxn);
let to_delete = RoaringBitmap::from_iter(finished.into_iter().rev().take(100_000));
@ -1135,11 +1135,15 @@ impl IndexScheduler {
to_delete.len()
);
// it's safe to unwrap here because we checked the len above
let newest_task_id = to_delete.iter().last().unwrap();
let task = self.get_task(&rtxn, newest_task_id)?.ok_or(Error::CorruptedTaskQueue)?;
drop(rtxn);
self.register(KindWithContent::TaskDeletion {
query: format!(
"?from={},limit={},status=succeeded,failed,canceled",
to_delete.iter().last().unwrap_or(u32::MAX),
to_delete.len(),
"?beforeEnqueuedAt={},status=succeeded,failed,canceled",
task.enqueued_at.format(&Rfc3339).map_err(|_| Error::CorruptedTaskQueue)?,
),
tasks: to_delete,
})?;
@ -1404,7 +1408,7 @@ mod tests {
use big_s::S;
use crossbeam::channel::RecvTimeoutError;
use file_store::File;
use meili_snap::snapshot;
use meili_snap::{json_string, snapshot};
use meilisearch_auth::AuthFilter;
use meilisearch_types::document_formats::DocumentFormatError;
use meilisearch_types::error::ErrorCode;
@ -3860,8 +3864,6 @@ mod tests {
handle.advance_one_failed_batch();
// at this point the max number of tasks is reached
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "max_number_of_tasks");
// we can still enqueue multiple tasks
index_scheduler
.register(KindWithContent::IndexCreation { index_uid: S("doggo"), primary_key: None })
@ -3870,22 +3872,43 @@ mod tests {
.register(KindWithContent::IndexCreation { index_uid: S("doggo"), primary_key: None })
.unwrap();
// at this point the max number of tasks is reached
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "above_the_max_number_of_tasks");
let rtxn = index_scheduler.env.read_txn().unwrap();
let tasks = index_scheduler.get_task_ids(&rtxn, &Query { ..Default::default() }).unwrap();
let tasks = index_scheduler.get_existing_tasks(&rtxn, tasks).unwrap();
snapshot!(json_string!(tasks, { "[].enqueuedAt" => "[date]", "[].startedAt" => "[date]", "[].finishedAt" => "[date]" }), name: "task_queue_is_full");
drop(rtxn);
// now we're above the max number of tasks
// and if we try to advance in the tick function a new task deletion should be enqueued
handle.advance_till([Start, BatchCreated]);
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "task_deletion_have_been_enqueued");
let rtxn = index_scheduler.env.read_txn().unwrap();
let tasks = index_scheduler.get_task_ids(&rtxn, &Query { ..Default::default() }).unwrap();
let tasks = index_scheduler.get_existing_tasks(&rtxn, tasks).unwrap();
snapshot!(json_string!(tasks, { "[].enqueuedAt" => "[date]", "[].startedAt" => "[date]", "[].finishedAt" => "[date]", ".**.original_filter" => "[filter]", ".**.query" => "[query]" }), name: "task_deletion_have_been_enqueued");
drop(rtxn);
handle.advance_till([InsideProcessBatch, ProcessBatchSucceeded, AfterProcessing]);
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "task_deletion_have_been_processed");
let rtxn = index_scheduler.env.read_txn().unwrap();
let tasks = index_scheduler.get_task_ids(&rtxn, &Query { ..Default::default() }).unwrap();
let tasks = index_scheduler.get_existing_tasks(&rtxn, tasks).unwrap();
snapshot!(json_string!(tasks, { "[].enqueuedAt" => "[date]", "[].startedAt" => "[date]", "[].finishedAt" => "[date]", ".**.original_filter" => "[filter]", ".**.query" => "[query]" }), name: "task_deletion_have_been_processed");
drop(rtxn);
handle.advance_one_failed_batch();
// a new task deletion has been enqueued
handle.advance_one_successful_batch();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_the_second_task_deletion");
let rtxn = index_scheduler.env.read_txn().unwrap();
let tasks = index_scheduler.get_task_ids(&rtxn, &Query { ..Default::default() }).unwrap();
let tasks = index_scheduler.get_existing_tasks(&rtxn, tasks).unwrap();
snapshot!(json_string!(tasks, { "[].enqueuedAt" => "[date]", "[].startedAt" => "[date]", "[].finishedAt" => "[date]", ".**.original_filter" => "[filter]", ".**.query" => "[query]" }), name: "after_the_second_task_deletion");
drop(rtxn);
handle.advance_one_failed_batch();
handle.advance_one_successful_batch();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "everything_has_been_processed");
let rtxn = index_scheduler.env.read_txn().unwrap();
let tasks = index_scheduler.get_task_ids(&rtxn, &Query { ..Default::default() }).unwrap();
let tasks = index_scheduler.get_existing_tasks(&rtxn, tasks).unwrap();
snapshot!(json_string!(tasks, { "[].enqueuedAt" => "[date]", "[].startedAt" => "[date]", "[].finishedAt" => "[date]", ".**.original_filter" => "[filter]", ".**.query" => "[query]" }), name: "everything_has_been_processed");
drop(rtxn);
}
}

49
index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/above_the_max_number_of_tasks.snap
View File

@ -1,49 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: succeeded, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggo` already exists.", error_code: "index_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_already_exists" }, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
2 {uid: 2, status: enqueued, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
3 {uid: 3, status: enqueued, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
----------------------------------------------------------------------
### Status:
enqueued [2,3,]
succeeded [0,]
failed [1,]
----------------------------------------------------------------------
### Kind:
"indexCreation" [0,1,2,3,]
----------------------------------------------------------------------
### Index Tasks:
doggo [0,1,2,3,]
----------------------------------------------------------------------
### Index Mapper:
doggo: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,]
[timestamp] [3,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

106
index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/after_the_second_task_deletion.snap
View File

@ -1,44 +1,68 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
3 {uid: 3, status: enqueued, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
5 {uid: 5, status: succeeded, details: { matched_tasks: 2, deleted_tasks: Some(2), original_filter: "?from=4,limit=2,status=succeeded,failed,canceled" }, kind: TaskDeletion { query: "?from=4,limit=2,status=succeeded,failed,canceled", tasks: RoaringBitmap<[2, 4]> }}
----------------------------------------------------------------------
### Status:
enqueued [3,]
succeeded [5,]
failed []
----------------------------------------------------------------------
### Kind:
"indexCreation" [3,]
"taskDeletion" [5,]
----------------------------------------------------------------------
### Index Tasks:
doggo [3,]
----------------------------------------------------------------------
### Index Mapper:
doggo: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [3,]
[timestamp] [5,]
----------------------------------------------------------------------
### Started At:
[timestamp] [5,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [5,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------
[
{
"uid": 3,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 5,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"TaskDeletion": {
"matched_tasks": 2,
"deleted_tasks": 2,
"original_filter": "[filter]"
}
},
"status": "succeeded",
"kind": {
"taskDeletion": {
"query": "[query]",
"tasks": [
58,
48,
0,
0,
1,
0,
0,
0,
0,
0,
1,
0,
16,
0,
0,
0,
2,
0,
4,
0
]
}
}
}
]

83
index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/everything_has_been_processed.snap
View File

@ -1,41 +1,48 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
6 {uid: 6, status: succeeded, details: { matched_tasks: 2, deleted_tasks: Some(2), original_filter: "?from=5,limit=2,status=succeeded,failed,canceled" }, kind: TaskDeletion { query: "?from=5,limit=2,status=succeeded,failed,canceled", tasks: RoaringBitmap<[3, 5]> }}
----------------------------------------------------------------------
### Status:
enqueued []
succeeded [6,]
failed []
----------------------------------------------------------------------
### Kind:
"indexCreation" []
"taskDeletion" [6,]
----------------------------------------------------------------------
### Index Tasks:
----------------------------------------------------------------------
### Index Mapper:
doggo: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [6,]
----------------------------------------------------------------------
### Started At:
[timestamp] [6,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [6,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------
[
{
"uid": 6,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"TaskDeletion": {
"matched_tasks": 2,
"deleted_tasks": 2,
"original_filter": "[filter]"
}
},
"status": "succeeded",
"kind": {
"taskDeletion": {
"query": "[query]",
"tasks": [
58,
48,
0,
0,
1,
0,
0,
0,
0,
0,
1,
0,
16,
0,
0,
0,
3,
0,
5,
0
]
}
}
}
]

45
index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/max_number_of_tasks.snap
View File

@ -1,45 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: succeeded, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggo` already exists.", error_code: "index_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_already_exists" }, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
----------------------------------------------------------------------
### Status:
enqueued []
succeeded [0,]
failed [1,]
----------------------------------------------------------------------
### Kind:
"indexCreation" [0,1,]
----------------------------------------------------------------------
### Index Tasks:
doggo [0,1,]
----------------------------------------------------------------------
### Index Mapper:
doggo: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

179
index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/task_deletion_have_been_enqueued.snap
View File

@ -1,52 +1,133 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[4,]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: succeeded, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggo` already exists.", error_code: "index_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_already_exists" }, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
2 {uid: 2, status: enqueued, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
3 {uid: 3, status: enqueued, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
4 {uid: 4, status: enqueued, details: { matched_tasks: 2, deleted_tasks: None, original_filter: "?from=1,limit=2,status=succeeded,failed,canceled" }, kind: TaskDeletion { query: "?from=1,limit=2,status=succeeded,failed,canceled", tasks: RoaringBitmap<[0, 1]> }}
----------------------------------------------------------------------
### Status:
enqueued [2,3,4,]
succeeded [0,]
failed [1,]
----------------------------------------------------------------------
### Kind:
"indexCreation" [0,1,2,3,]
"taskDeletion" [4,]
----------------------------------------------------------------------
### Index Tasks:
doggo [0,1,2,3,]
----------------------------------------------------------------------
### Index Mapper:
doggo: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,]
[timestamp] [3,]
[timestamp] [4,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------
[
{
"uid": 0,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "succeeded",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 1,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": {
"message": "Index `doggo` already exists.",
"code": "index_already_exists",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#index_already_exists"
},
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "failed",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 2,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 3,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 4,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"TaskDeletion": {
"matched_tasks": 2,
"deleted_tasks": null,
"original_filter": "[filter]"
}
},
"status": "enqueued",
"kind": {
"taskDeletion": {
"query": "[query]",
"tasks": [
58,
48,
0,
0,
1,
0,
0,
0,
0,
0,
1,
0,
16,
0,
0,
0,
0,
0,
1,
0
]
}
}
}
]

128
index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/task_deletion_have_been_processed.snap
View File

@ -1,46 +1,88 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
2 {uid: 2, status: enqueued, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
3 {uid: 3, status: enqueued, details: { primary_key: None }, kind: IndexCreation { index_uid: "doggo", primary_key: None }}
4 {uid: 4, status: succeeded, details: { matched_tasks: 2, deleted_tasks: Some(2), original_filter: "?from=1,limit=2,status=succeeded,failed,canceled" }, kind: TaskDeletion { query: "?from=1,limit=2,status=succeeded,failed,canceled", tasks: RoaringBitmap<[0, 1]> }}
----------------------------------------------------------------------
### Status:
enqueued [2,3,]
succeeded [4,]
failed []
----------------------------------------------------------------------
### Kind:
"indexCreation" [2,3,]
"taskDeletion" [4,]
----------------------------------------------------------------------
### Index Tasks:
doggo [2,3,]
----------------------------------------------------------------------
### Index Mapper:
doggo: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [2,]
[timestamp] [3,]
[timestamp] [4,]
----------------------------------------------------------------------
### Started At:
[timestamp] [4,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [4,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------
[
{
"uid": 2,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 3,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 4,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"TaskDeletion": {
"matched_tasks": 2,
"deleted_tasks": 2,
"original_filter": "[filter]"
}
},
"status": "succeeded",
"kind": {
"taskDeletion": {
"query": "[query]",
"tasks": [
58,
48,
0,
0,
1,
0,
0,
0,
0,
0,
1,
0,
16,
0,
0,
0,
0,
0,
1,
0
]
}
}
}
]

90
index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/task_queue_is_full.snap Normal file
View File

@ -0,0 +1,90 @@
---
source: index-scheduler/src/lib.rs
---
[
{
"uid": 0,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "succeeded",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 1,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": {
"message": "Index `doggo` already exists.",
"code": "index_already_exists",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#index_already_exists"
},
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "failed",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 2,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 3,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
}
]