Merge pull request #5527 from nnethercott/all-cpus-in-import-dump

Use all CPUs during an import dump

crates/meilisearch/src/lib.rs

@@ -37,7 +37,9 @@ use index_scheduler::{IndexScheduler, IndexSchedulerOptions};
 use meilisearch_auth::{open_auth_store_env, AuthController};
 use meilisearch_types::milli::constants::VERSION_MAJOR;
 use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
-use meilisearch_types::milli::update::{IndexDocumentsConfig, IndexDocumentsMethod};
+use meilisearch_types::milli::update::{
+    default_thread_pool_and_threads, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig,
+};
 use meilisearch_types::settings::apply_settings_to_builder;
 use meilisearch_types::tasks::KindWithContent;
 use meilisearch_types::versioning::{
@@ -500,7 +502,19 @@ fn import_dump(
     let network = dump_reader.network()?.cloned().unwrap_or_default();
     index_scheduler.put_network(network)?;
 
-    let indexer_config = index_scheduler.indexer_config();
+    // 3.1 Use all cpus to process dump if `max_indexing_threads` not configured
+    let backup_config;
+    let base_config = index_scheduler.indexer_config();
+
+    let indexer_config = if base_config.max_threads.is_none() {
+        let (thread_pool, _) = default_thread_pool_and_threads();
+
+        let _config = IndexerConfig { thread_pool, ..*base_config };
+        backup_config = _config;
+        &backup_config
+    } else {
+        base_config
+    };
 
     // /!\ The tasks must be imported AFTER importing the indexes or else the scheduler might
     // try to process tasks while we're trying to import the indexes.

crates/meilisearch/src/option.rs

@@ -746,10 +746,12 @@ impl IndexerOpts {
                 max_indexing_memory.to_string(),
             );
         }
-        export_to_env_if_not_present(
-            MEILI_MAX_INDEXING_THREADS,
-            max_indexing_threads.0.to_string(),
-        );
+        if let Some(max_indexing_threads) = max_indexing_threads.0 {
+            export_to_env_if_not_present(
+                MEILI_MAX_INDEXING_THREADS,
+                max_indexing_threads.to_string(),
+            );
+        }
     }
 }
 
@@ -757,15 +759,15 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
     type Error = anyhow::Error;
 
     fn try_from(other: &IndexerOpts) -> Result<Self, Self::Error> {
-        let thread_pool = ThreadPoolNoAbortBuilder::new()
-            .thread_name(|index| format!("indexing-thread:{index}"))
-            .num_threads(*other.max_indexing_threads)
+        let thread_pool = ThreadPoolNoAbortBuilder::new_for_indexing()
+            .num_threads(other.max_indexing_threads.unwrap_or_else(|| num_cpus::get() / 2))
             .build()?;
 
         Ok(Self {
+            thread_pool,
             log_every_n: Some(DEFAULT_LOG_EVERY_N),
             max_memory: other.max_indexing_memory.map(|b| b.as_u64() as usize),
-            thread_pool: Some(thread_pool),
+            max_threads: *other.max_indexing_threads,
             max_positions_per_attributes: None,
             skip_index_budget: other.skip_index_budget,
             ..Default::default()
@@ -828,31 +830,31 @@ fn total_memory_bytes() -> Option<u64> {
     }
 }
 
-#[derive(Debug, Clone, Copy, Deserialize, Serialize)]
-pub struct MaxThreads(usize);
+#[derive(Default, Debug, Clone, Copy, Deserialize, Serialize)]
+pub struct MaxThreads(Option<usize>);
 
 impl FromStr for MaxThreads {
     type Err = ParseIntError;
 
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        usize::from_str(s).map(Self)
-    }
-}
-
-impl Default for MaxThreads {
-    fn default() -> Self {
-        MaxThreads(num_cpus::get() / 2)
+    fn from_str(s: &str) -> Result<MaxThreads, Self::Err> {
+        if s.is_empty() || s == "unlimited" {
+            return Ok(MaxThreads::default());
+        }
+        usize::from_str(s).map(Some).map(MaxThreads)
     }
 }
 
 impl fmt::Display for MaxThreads {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "{}", self.0)
+        match self.0 {
+            Some(threads) => write!(f, "{}", threads),
+            None => write!(f, "unlimited"),
+        }
     }
 }
 
 impl Deref for MaxThreads {
-    type Target = usize;
+    type Target = Option<usize>;
 
     fn deref(&self) -> &Self::Target {
         &self.0