foundation: restore SegmentComponent::TempStore (revert #2815)

Index sorting streams documents to a temporary store before resorting
them into the final Store. Upstream #2815 ("Remove temp file") removed
SegmentComponent::TempStore as part of the index-sorting removal
cleanup; this restores it (the upstream-original mechanism, including
the include_temp_doc_store garbage-collection tracking).

This also subsumes paradedb/tantivy #104 ("Index sort test in CI"),
whose fix was re-adding TempStore to the component iterator and the
list_files GC handling.

src/directory/mmap_directory/mod.rs

@@ -676,7 +676,7 @@ mod tests {
             let num_segments = reader.searcher().segment_readers().len();
             assert!(num_segments <= 4);
             let num_components_except_deletes_and_tempstore =
-                crate::index::SegmentComponent::iterator().len() - 1;
+                crate::index::SegmentComponent::iterator().len() - 2;
             let max_num_mmapped = num_components_except_deletes_and_tempstore * num_segments;
             assert_eventually(|| {
                 let num_mmapped = mmap_directory.get_cache_info().mmapped.len();

src/index/index_meta.rs

@@ -1,6 +1,8 @@
 use std::collections::HashSet;
 use std::fmt;
 use std::path::PathBuf;
+use std::sync::atomic::AtomicBool;
+use std::sync::Arc;
 
 use serde::{Deserialize, Serialize};
 
@@ -35,6 +37,7 @@ impl SegmentMetaInventory {
         let inner = InnerSegmentMeta {
             segment_id,
             max_doc,
+            include_temp_doc_store: Arc::new(AtomicBool::new(true)),
             deletes: None,
         };
         SegmentMeta::from(self.inventory.track(inner))
@@ -82,6 +85,15 @@ impl SegmentMeta {
         self.tracked.segment_id
     }
 
+    /// Removes the Component::TempStore from the alive list and
+    /// therefore marks the temp docstore file to be deleted by
+    /// the garbage collection.
+    pub fn untrack_temp_docstore(&self) {
+        self.tracked
+            .include_temp_doc_store
+            .store(false, std::sync::atomic::Ordering::Relaxed);
+    }
+
     /// Returns the number of deleted documents.
     pub fn num_deleted_docs(&self) -> u32 {
         self.tracked
@@ -99,9 +111,20 @@ impl SegmentMeta {
     /// is by removing all files that have been created by tantivy
     /// and are not used by any segment anymore.
     pub fn list_files(&self) -> HashSet<PathBuf> {
-        SegmentComponent::iterator()
-            .map(|component| self.relative_path(*component))
-            .collect::<HashSet<PathBuf>>()
+        if self
+            .tracked
+            .include_temp_doc_store
+            .load(std::sync::atomic::Ordering::Relaxed)
+        {
+            SegmentComponent::iterator()
+                .map(|component| self.relative_path(*component))
+                .collect::<HashSet<PathBuf>>()
+        } else {
+            SegmentComponent::iterator()
+                .filter(|comp| *comp != &SegmentComponent::TempStore)
+                .map(|component| self.relative_path(*component))
+                .collect::<HashSet<PathBuf>>()
+        }
     }
 
     /// Returns the relative path of a component of our segment.
@@ -115,6 +138,7 @@ impl SegmentMeta {
             SegmentComponent::Positions => ".pos".to_string(),
             SegmentComponent::Terms => ".term".to_string(),
             SegmentComponent::Store => ".store".to_string(),
+            SegmentComponent::TempStore => ".store.temp".to_string(),
             SegmentComponent::FastFields => ".fast".to_string(),
             SegmentComponent::FieldNorms => ".fieldnorm".to_string(),
             SegmentComponent::Delete => format!(".{}.del", self.delete_opstamp().unwrap_or(0)),
@@ -159,6 +183,7 @@ impl SegmentMeta {
             segment_id: inner_meta.segment_id,
             max_doc,
             deletes: None,
+            include_temp_doc_store: Arc::new(AtomicBool::new(true)),
         });
         SegmentMeta { tracked }
     }
@@ -177,6 +202,7 @@ impl SegmentMeta {
         let tracked = self.tracked.map(move |inner_meta| InnerSegmentMeta {
             segment_id: inner_meta.segment_id,
             max_doc: inner_meta.max_doc,
+            include_temp_doc_store: Arc::new(AtomicBool::new(true)),
             deletes: Some(delete_meta),
         });
         SegmentMeta { tracked }
@@ -188,6 +214,14 @@ struct InnerSegmentMeta {
     segment_id: SegmentId,
     max_doc: u32,
     pub deletes: Option<DeleteMeta>,
+    /// If you want to avoid the SegmentComponent::TempStore file to be covered by
+    /// garbage collection and deleted, set this to true. This is used during merge.
+    #[serde(skip)]
+    #[serde(default = "default_temp_store")]
+    pub(crate) include_temp_doc_store: Arc<AtomicBool>,
+}
+fn default_temp_store() -> Arc<AtomicBool> {
+    Arc::new(AtomicBool::new(false))
 }
 
 impl InnerSegmentMeta {

src/index/segment_component.rs

@@ -23,6 +23,8 @@ pub enum SegmentComponent {
     /// Accessing a document from the store is relatively slow, as it
     /// requires to decompress the entire block it belongs to.
     Store,
+    /// Temporary storage of the documents, before streamed to `Store`.
+    TempStore,
     /// Bitset describing which document of the segment is alive.
     /// (It was representing deleted docs but changed to represent alive docs from v0.17)
     Delete,
@@ -31,13 +33,14 @@ pub enum SegmentComponent {
 impl SegmentComponent {
     /// Iterates through the components.
     pub fn iterator() -> slice::Iter<'static, SegmentComponent> {
-        static SEGMENT_COMPONENTS: [SegmentComponent; 7] = [
+        static SEGMENT_COMPONENTS: [SegmentComponent; 8] = [
             SegmentComponent::Postings,
             SegmentComponent::Positions,
             SegmentComponent::FastFields,
             SegmentComponent::FieldNorms,
             SegmentComponent::Terms,
             SegmentComponent::Store,
+            SegmentComponent::TempStore,
             SegmentComponent::Delete,
         ];
         SEGMENT_COMPONENTS.iter()

src/indexer/index_writer.rs

@@ -218,7 +218,7 @@ fn index_documents<D: Document>(
     let alive_bitset_opt = apply_deletes(&segment_with_max_doc, &mut delete_cursor, &doc_opstamps)?;
 
     let meta = segment_with_max_doc.meta().clone();
-
+    meta.untrack_temp_docstore();
     // update segment_updater inventory to remove tempstore
     let segment_entry = SegmentEntry::new(meta, delete_cursor, alive_bitset_opt);
     segment_updater.schedule_add_segment(segment_entry).wait()?;

src/space_usage/mod.rs

@@ -124,6 +124,7 @@ impl SegmentSpaceUsage {
             FieldNorms => PerField(self.fieldnorms().clone()),
             Terms => PerField(self.termdict().clone()),
             SegmentComponent::Store => ComponentSpaceUsage::Store(self.store().clone()),
+            SegmentComponent::TempStore => ComponentSpaceUsage::Store(self.store().clone()),
             Delete => Basic(self.deletes()),
         }
     }