rust-nodemap: accounting for dead blocks
authorGeorges Racinet <georges.racinet@octobus.net>
Tue, 18 Feb 2020 19:11:17 +0100
changeset 44389 6329ce04c69f
parent 44388 5ac1eecc9c64
child 44390 d518994384a4
rust-nodemap: accounting for dead blocks By the very append-only nature of the `NodeTree`, inserting new blocks has the effect of making some of the older ones useless as they become unreachable. Therefore some automatic housekeeping will need to be provided. This is standard procedure in the word of databases, under names such as "repack" or "vacuum". The new `masked_readonly_blocks()` will provide callers with useful information to decide if the nodetree is ripe for repacking, but all the `NodeTree` can provide is how many blocks have been masked in the currently mutable part. Analysing the readonly part would be way too long to do it for each transaction and defeat the whole purpose of nodemap persistence. Serializing callers (from the Python layer) will get this figure before each extraction and maintain an aggregate counter of unreachable blocks separately. Note: at this point, the most efficient repacking is just to restart afresh with a full rescan. Differential Revision: https://phab.mercurial-scm.org/D8097
rust/hg-core/src/revlog/nodemap.rs
--- a/rust/hg-core/src/revlog/nodemap.rs	Tue Feb 18 19:11:17 2020 +0100
+++ b/rust/hg-core/src/revlog/nodemap.rs	Tue Feb 18 19:11:17 2020 +0100
@@ -274,6 +274,7 @@
     readonly: Box<dyn Deref<Target = [Block]> + Send>,
     growable: Vec<Block>,
     root: Block,
+    masked_inner_blocks: usize,
 }
 
 impl Index<usize> for NodeTree {
@@ -350,6 +351,7 @@
             readonly: readonly,
             growable: Vec::new(),
             root: root,
+            masked_inner_blocks: 0,
         }
     }
 
@@ -483,6 +485,7 @@
         let ro_len = ro_blocks.len();
         let glen = self.growable.len();
         if idx < ro_len {
+            self.masked_inner_blocks += 1;
             // TODO OPTIM I think this makes two copies
             self.growable.push(ro_blocks[idx].clone());
             (glen + ro_len, &mut self.growable[glen], glen + 1)
@@ -571,6 +574,22 @@
         }
         Ok(())
     }
+
+    /// Return the number of blocks in the readonly part that are currently
+    /// masked in the mutable part.
+    ///
+    /// The `NodeTree` structure has no efficient way to know how many blocks
+    /// are already unreachable in the readonly part.
+    pub fn masked_readonly_blocks(&self) -> usize {
+        if let Some(readonly_root) = self.readonly.last() {
+            if readonly_root == &self.root {
+                return 0;
+            }
+        } else {
+            return 0;
+        }
+        self.masked_inner_blocks + 1
+    }
 }
 
 pub struct NodeTreeBytes {
@@ -853,6 +872,7 @@
             readonly: sample_nodetree().readonly,
             growable: vec![block![0: Rev(1), 5: Rev(3)]],
             root: block![0: Block(1), 1:Block(3), 12: Rev(2)],
+            masked_inner_blocks: 1,
         };
         assert_eq!(nt.find_hex(&idx, "10")?, Some(1));
         assert_eq!(nt.find_hex(&idx, "c")?, Some(2));
@@ -861,6 +881,7 @@
         assert_eq!(nt.find_hex(&idx, "000")?, Some(NULL_REVISION));
         assert_eq!(nt.unique_prefix_len_hex(&idx, "000")?, Some(3));
         assert_eq!(nt.find_hex(&idx, "01")?, Some(9));
+        assert_eq!(nt.masked_readonly_blocks(), 2);
         Ok(())
     }
 
@@ -950,6 +971,8 @@
         assert_eq!(idx.find_hex("1a345")?, Some(3));
         assert_eq!(idx.find_hex("1a341")?, None);
 
+        // there's no readonly block to mask
+        assert_eq!(idx.nt.masked_readonly_blocks(), 0);
         Ok(())
     }
 
@@ -1011,6 +1034,8 @@
         assert_eq!(idx.find_hex("1235")?, Some(1));
         assert_eq!(idx.find_hex("131")?, Some(2));
         assert_eq!(idx.find_hex("cafe")?, Some(3));
+        // we did not add anything since init from readonly
+        assert_eq!(idx.nt.masked_readonly_blocks(), 0);
 
         idx.insert(4, "123A")?;
         assert_eq!(idx.find_hex("1234")?, Some(0));
@@ -1018,12 +1043,18 @@
         assert_eq!(idx.find_hex("131")?, Some(2));
         assert_eq!(idx.find_hex("cafe")?, Some(3));
         assert_eq!(idx.find_hex("123A")?, Some(4));
+        // we masked blocks for all prefixes of "123", including the root
+        assert_eq!(idx.nt.masked_readonly_blocks(), 4);
 
+        eprintln!("{:?}", idx.nt);
         idx.insert(5, "c0")?;
         assert_eq!(idx.find_hex("cafe")?, Some(3));
         assert_eq!(idx.find_hex("c0")?, Some(5));
         assert_eq!(idx.find_hex("c1")?, None);
         assert_eq!(idx.find_hex("1234")?, Some(0));
+        // inserting "c0" is just splitting the 'c' slot of the mutable root,
+        // it doesn't mask anything
+        assert_eq!(idx.nt.masked_readonly_blocks(), 4);
 
         Ok(())
     }