Merge #1824

1824: Fix indexation perfomances on mounted disk r=ManyTheFish a=ManyTheFish

We were creating all of our tempfiles in data.ms directory, but when the database directory is stored in a mounted disk, tempfiles I/O throughput decreases, impacting the indexation time.

Now, only the persisting tempfiles will be created in the database directory. Other tempfiles will stay in the default tmpdir.

Co-authored-by: many <maxime@meilisearch.com>

meilisearch-http/src/lib.rs

@@ -8,7 +8,6 @@ pub mod analytics;
 pub mod helpers;
 pub mod option;
 pub mod routes;
-use std::path::Path;
 use std::time::Duration;
 
 use crate::error::MeilisearchHttpError;
@@ -75,27 +74,6 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<MeiliSearch> {
     meilisearch.build(opt.db_path.clone(), opt.indexer_options.clone())
 }
 
-/// Cleans and setup the temporary file folder in the database directory. This must be done after
-/// the meilisearch instance has been created, to not interfere with the snapshot and dump loading.
-pub fn setup_temp_dir(db_path: impl AsRef<Path>) -> anyhow::Result<()> {
-    // Set the tempfile directory in the current db path, to avoid cross device references. Also
-    // remove the previous outstanding files found there
-    //
-    // TODO: if two processes open the same db, one might delete the other tmpdir. Need to make
-    // sure that no one is using it before deleting it.
-    let temp_path = db_path.as_ref().join("tmp");
-    // Ignore error if tempdir doesn't exist
-    let _ = std::fs::remove_dir_all(&temp_path);
-    std::fs::create_dir_all(&temp_path)?;
-    if cfg!(windows) {
-        std::env::set_var("TMP", temp_path);
-    } else {
-        std::env::set_var("TMPDIR", temp_path);
-    }
-
-    Ok(())
-}
-
 pub fn configure_data(config: &mut web::ServiceConfig, data: MeiliSearch, opt: &Opt) {
     let http_payload_size_limit = opt.http_payload_size_limit.get_bytes() as usize;
     config

meilisearch-http/src/main.rs

@@ -46,10 +46,6 @@ async fn main() -> anyhow::Result<()> {
 
     let meilisearch = setup_meilisearch(&opt)?;
 
-    // Setup the temp directory to be in the db folder. This is important, since temporary file
-    // don't support to be persisted accross filesystem boundaries.
-    meilisearch_http::setup_temp_dir(&opt.db_path)?;
-
     #[cfg(all(not(debug_assertions), feature = "analytics"))]
     if !opt.no_analytics {
         let analytics_data = meilisearch.clone();

meilisearch-lib/src/index_controller/dump_actor/loaders/v2.rs

@@ -43,8 +43,9 @@ pub fn load_dump(
         patch_settings(settings_path)?;
     }
 
-    let update_path = src.as_ref().join("updates/data.jsonl");
+    let update_dir = src.as_ref().join("updates");
-    patch_updates(update_path)?;
+    let update_path = update_dir.join("data.jsonl");
+    patch_updates(update_dir, update_path)?;
 
     v3::load_dump(
         meta,
@@ -69,7 +70,7 @@ fn patch_settings(path: impl AsRef<Path>) -> anyhow::Result<()> {
     // We first deserialize the dump meta into a serde_json::Value and change
     // the custom ranking rules settings from the old format to the new format.
     if let Some(ranking_rules) = meta.pointer_mut("/settings/rankingRules") {
-        patch_custon_ranking_rules(ranking_rules);
+        patch_custom_ranking_rules(ranking_rules);
     }
 
     let mut meta_file = OpenOptions::new().truncate(true).write(true).open(path)?;
@@ -79,8 +80,8 @@ fn patch_settings(path: impl AsRef<Path>) -> anyhow::Result<()> {
     Ok(())
 }
 
-fn patch_updates(path: impl AsRef<Path>) -> anyhow::Result<()> {
+fn patch_updates(dir: impl AsRef<Path>, path: impl AsRef<Path>) -> anyhow::Result<()> {
-    let mut output_update_file = NamedTempFile::new()?;
+    let mut output_update_file = NamedTempFile::new_in(&dir)?;
     let update_file = File::open(&path)?;
 
     let stream = Deserializer::from_reader(update_file).into_iter::<compat::UpdateEntry>();
@@ -104,7 +105,7 @@ fn patch_updates(path: impl AsRef<Path>) -> anyhow::Result<()> {
 ///
 /// This is done for compatibility reasons, and to avoid a new dump version,
 /// since the new syntax was introduced soon after the new dump version.
-fn patch_custon_ranking_rules(ranking_rules: &mut Value) {
+fn patch_custom_ranking_rules(ranking_rules: &mut Value) {
     *ranking_rules = match ranking_rules.take() {
         Value::Array(values) => values
             .into_iter()

meilisearch-lib/src/index_controller/dump_actor/mod.rs

@@ -253,7 +253,7 @@ where
         UpdateMsg::dump(&self.update_sender, uuids, temp_dump_path.clone()).await?;
 
         let dump_path = tokio::task::spawn_blocking(move || -> Result<PathBuf> {
-            let temp_dump_file = tempfile::NamedTempFile::new()?;
+            let temp_dump_file = tempfile::NamedTempFile::new_in(&self.path)?;
             to_tar_gz(temp_dump_path, temp_dump_file.path())
                 .map_err(|e| DumpActorError::Internal(e.into()))?;
 

meilisearch-lib/src/index_controller/snapshot.rs

@@ -81,7 +81,7 @@ where
             .snapshot_path
             .join(format!("{}.snapshot", self.db_name));
         let snapshot_path = spawn_blocking(move || -> anyhow::Result<PathBuf> {
-            let temp_snapshot_file = tempfile::NamedTempFile::new()?;
+            let temp_snapshot_file = tempfile::NamedTempFile::new_in(&snapshot_dir)?;
             let temp_snapshot_file_path = temp_snapshot_file.path().to_owned();
             crate::compression::to_tar_gz(temp_snapshot_path, temp_snapshot_file_path)?;
             temp_snapshot_file.persist(&snapshot_path)?;

meilisearch-lib/src/index_controller/update_file_store.rs

@@ -107,7 +107,7 @@ impl UpdateFileStore {
     ///
     /// A call to `persist` is needed to persist the file in the database.
     pub fn new_update(&self) -> Result<(Uuid, UpdateFile)> {
-        let file = NamedTempFile::new()?;
+        let file = NamedTempFile::new_in(&self.path)?;
         let uuid = Uuid::new_v4();
         let path = self.path.join(uuid.to_string());
         let update_file = UpdateFile { file, path };
@@ -141,7 +141,7 @@ impl UpdateFileStore {
         dst.push(&uuid_string);
 
         let update_file = File::open(update_file_path)?;
-        let mut dst_file = NamedTempFile::new()?;
+        let mut dst_file = NamedTempFile::new_in(&dump_path)?;
         let mut document_reader = DocumentBatchReader::from_reader(update_file)?;
 
         let mut document_buffer = Map::new();

meilisearch-lib/src/index_controller/updates/store/dump.rs

@@ -52,7 +52,7 @@ impl UpdateStore {
         uuids: &HashSet<Uuid>,
         path: impl AsRef<Path>,
     ) -> Result<()> {
-        let mut dump_data_file = NamedTempFile::new()?;
+        let mut dump_data_file = NamedTempFile::new_in(&path)?;
 
         self.dump_pending(txn, uuids, &mut dump_data_file, &path)?;
         self.dump_completed(txn, uuids, &mut dump_data_file)?;