feat(pageserver): support dry-run for gc-compaction, add statistics (#…

…8557)

Add dry-run mode that does not produce any image layer + delta layer. I
will use this code to do some experiments and see how much space we can
reclaim for tenants on staging. Part of
#8002

* Add dry-run mode that runs the full compaction process without
updating the layer map. (We never call finish on the writers and the
files will be removed before exiting the function).
* Add compaction statistics and print them at the end of compaction.

---------

Signed-off-by: Alex Chi Z <[email protected]>

pageserver/src/tenant.rs

@@ -6899,7 +6899,10 @@ mod tests {
         }
 
         let cancel = CancellationToken::new();
-        tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
 
         for (idx, expected) in expected_result.iter().enumerate() {
             assert_eq!(
@@ -6993,7 +6996,10 @@ mod tests {
             guard.cutoffs.time = Lsn(0x40);
             guard.cutoffs.space = Lsn(0x40);
         }
-        tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
 
         Ok(())
     }
@@ -7327,7 +7333,10 @@ mod tests {
         }
 
         let cancel = CancellationToken::new();
-        tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
 
         for idx in 0..10 {
             assert_eq!(
@@ -7353,7 +7362,10 @@ mod tests {
             guard.cutoffs.time = Lsn(0x40);
             guard.cutoffs.space = Lsn(0x40);
         }
-        tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
 
         Ok(())
     }
@@ -7898,11 +7910,28 @@ mod tests {
         verify_result().await;
 
         let cancel = CancellationToken::new();
-        tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        let mut dryrun_flags = EnumSet::new();
+        dryrun_flags.insert(CompactFlags::DryRun);
+
+        tline
+            .compact_with_gc(&cancel, dryrun_flags, &ctx)
+            .await
+            .unwrap();
+        // We expect layer map to be the same b/c the dry run flag, but we don't know whether there will be other background jobs
+        // cleaning things up, and therefore, we don't do sanity checks on the layer map during unit tests.
+        verify_result().await;
+
+        tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
         verify_result().await;
 
         // compact again
-        tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
         verify_result().await;
 
         // increase GC horizon and compact again
@@ -7912,11 +7941,17 @@ mod tests {
             guard.cutoffs.time = Lsn(0x38);
             guard.cutoffs.space = Lsn(0x38);
         }
-        tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
         verify_result().await; // no wals between 0x30 and 0x38, so we should obtain the same result
 
         // not increasing the GC horizon and compact again
-        tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
         verify_result().await;
 
         Ok(())
@@ -8097,7 +8132,10 @@ mod tests {
         verify_result().await;
 
         let cancel = CancellationToken::new();
-        branch_tline.compact_with_gc(&cancel, &ctx).await.unwrap();
+        branch_tline
+            .compact_with_gc(&cancel, EnumSet::new(), &ctx)
+            .await
+            .unwrap();
 
         verify_result().await;
 

pageserver/src/tenant/storage_layer/image_layer.rs

@@ -753,6 +753,10 @@ struct ImageLayerWriterInner {
 }
 
 impl ImageLayerWriterInner {
+    fn size(&self) -> u64 {
+        self.tree.borrow_writer().size() + self.blob_writer.size()
+    }
+
     ///
     /// Start building a new image layer.
     ///
@@ -1044,6 +1048,10 @@ impl ImageLayerWriter {
             .finish(timeline, ctx, Some(end_key))
             .await
     }
+
+    pub(crate) fn size(&self) -> u64 {
+        self.inner.as_ref().unwrap().size()
+    }
 }
 
 impl Drop for ImageLayerWriter {

pageserver/src/tenant/timeline.rs

@@ -704,6 +704,7 @@ pub(crate) enum CompactFlags {
     ForceRepartition,
     ForceImageLayerCreation,
     EnhancedGcBottomMostCompaction,
+    DryRun,
 }
 
 impl std::fmt::Debug for Timeline {