Merge #2523

2523: Improve the tasks error reporting when processed in batches r=irevoire a=Kerollmops

This fixes #2478 by changing the behavior of the task handler when there is an error in a batch of document addition or update.

What changes is that when there is a user error in a task in a batch we now report this task as failed with the right error message but we continue to process the other tasks. A user error can be when a geo field is invalid, a document id is invalid, or missing.

fixes #2582, #2478

Co-authored-by: Kerollmops <clement@meilisearch.com>
Co-authored-by: ManyTheFish <many@meilisearch.com>

meilisearch-http/src/helpers/env.rs

@@ -1,17 +0,0 @@
-use meilisearch_lib::heed::Env;
-use walkdir::WalkDir;
-
-pub trait EnvSizer {
-    fn size(&self) -> u64;
-}
-
-impl EnvSizer for Env {
-    fn size(&self) -> u64 {
-        WalkDir::new(self.path())
-            .into_iter()
-            .filter_map(|entry| entry.ok())
-            .filter_map(|entry| entry.metadata().ok())
-            .filter(|metadata| metadata.is_file())
-            .fold(0, |acc, m| acc + m.len())
-    }
-}

meilisearch-http/src/helpers/mod.rs

@@ -1,3 +0,0 @@
-mod env;
-
-pub use env::EnvSizer;

meilisearch-http/src/lib.rs

@@ -5,7 +5,6 @@ pub mod analytics;
 pub mod task;
 #[macro_use]
 pub mod extractors;
-pub mod helpers;
 pub mod option;
 pub mod routes;
 
@@ -30,9 +29,9 @@ pub static AUTOBATCHING_ENABLED: AtomicBool = AtomicBool::new(false);
 pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<MeiliSearch> {
     let mut meilisearch = MeiliSearch::builder();
 
-    // enable autobatching?
+    // disable autobatching?
     AUTOBATCHING_ENABLED.store(
-        opt.scheduler_options.enable_auto_batching,
+        !opt.scheduler_options.disable_auto_batching,
         std::sync::atomic::Ordering::Relaxed,
     );
 

meilisearch-http/src/task.rs

@@ -231,7 +231,7 @@ pub struct TaskView {
     #[serde(serialize_with = "time::serde::rfc3339::option::serialize")]
     finished_at: Option<OffsetDateTime>,
     #[serde(skip_serializing_if = "Option::is_none")]
-    batch_uid: Option<Option<BatchId>>,
+    batch_uid: Option<BatchId>,
 }
 
 impl From<Task> for TaskView {
@@ -380,15 +380,15 @@ impl From<Task> for TaskView {
 
         let duration = finished_at.zip(started_at).map(|(tf, ts)| (tf - ts));
 
-        let batch_uid = if AUTOBATCHING_ENABLED.load(std::sync::atomic::Ordering::Relaxed) {
-            let id = events.iter().find_map(|e| match e {
-                TaskEvent::Batched { batch_id, .. } => Some(*batch_id),
-                _ => None,
-            });
-            Some(id)
-        } else {
-            None
-        };
+        let batch_uid = AUTOBATCHING_ENABLED
+            .load(std::sync::atomic::Ordering::Relaxed)
+            .then(|| {
+                events.iter().find_map(|e| match e {
+                    TaskEvent::Batched { batch_id, .. } => Some(*batch_id),
+                    _ => None,
+                })
+            })
+            .flatten();
 
         Self {
             uid: id,