implement the upgrade from v1.10 to v1.11 in meilitool

Cargo.lock

@@ -404,6 +404,25 @@ dependencies = [
  "thiserror",
 ]
 
+[[package]]
+name = "arroy"
+version = "0.5.0"
+source = "git+https://github.com/meilisearch/arroy/?rev=3908c9e#3908c9edfba77ba18cc50bda41c88166ba5ebd37"
+dependencies = [
+ "bytemuck",
+ "byteorder",
+ "heed",
+ "log",
+ "memmap2",
+ "nohash",
+ "ordered-float",
+ "rand",
+ "rayon",
+ "roaring",
+ "tempfile",
+ "thiserror",
+]
+
 [[package]]
 name = "assert-json-diff"
 version = "2.0.2"
@@ -707,9 +726,9 @@ checksum = "2c676a478f63e9fa2dd5368a42f28bba0d6c560b775f38583c8bbaa7fcd67c9c"
 
 [[package]]
 name = "bytemuck"
-version = "1.16.1"
+version = "1.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b236fc92302c97ed75b38da1f4917b5cdda4984745740f153a5d3059e48d725e"
+checksum = "8334215b81e418a0a7bdb8ef0849474f40bb10c8b71f1c4ed315cff49f32494d"
 dependencies = [
  "bytemuck_derive",
 ]
@@ -2556,7 +2575,7 @@ name = "index-scheduler"
 version = "1.11.0"
 dependencies = [
  "anyhow",
- "arroy",
+ "arroy 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "big_s",
  "bincode",
  "crossbeam",
@@ -3517,6 +3536,7 @@ name = "meilitool"
 version = "1.11.0"
 dependencies = [
  "anyhow",
+ "arroy 0.5.0 (git+https://github.com/meilisearch/arroy/?rev=3908c9e)",
  "clap",
  "dump",
  "file-store",
@@ -3547,7 +3567,7 @@ dependencies = [
 name = "milli"
 version = "1.11.0"
 dependencies = [
- "arroy",
+ "arroy 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "big_s",
  "bimap",
  "bincode",

crates/meilitool/Cargo.toml

@@ -18,3 +18,5 @@ meilisearch-types = { path = "../meilisearch-types" }
 serde = { version = "1.0.209", features = ["derive"] }
 time = { version = "0.3.36", features = ["formatting"] }
 uuid = { version = "1.10.0", features = ["v4"], default-features = false }
+arroy_v04_to_v05 = { package = "arroy", git = "https://github.com/meilisearch/arroy/", rev = "3908c9e" }
+

crates/milli/Cargo.toml

@@ -15,7 +15,7 @@ license.workspace = true
 bimap = { version = "0.6.3", features = ["serde"] }
 bincode = "1.3.3"
 bstr = "1.9.1"
-bytemuck = { version = "1.16.1", features = ["extern_crate_alloc"] }
+bytemuck = { version = "1.18.0", features = ["extern_crate_alloc"] }
 byteorder = "1.5.0"
 charabia = { version = "0.9.1", default-features = false }
 concat-arrays = "0.1.2"

meilitool/src/upgrade/mod.rs

@@ -1,13 +1,16 @@
 mod v1_10;
+mod v1_11;
 mod v1_9;
 
-use std::path::PathBuf;
+use std::path::{Path, PathBuf};
 
 use anyhow::{bail, Context};
 use meilisearch_types::versioning::create_version_file;
 
 use v1_10::v1_9_to_v1_10;
 
+use crate::upgrade::v1_11::v1_10_to_v1_11;
+
 pub struct OfflineUpgrade {
     pub db_path: PathBuf,
     pub current_version: (String, String, String),
@@ -16,28 +19,49 @@ pub struct OfflineUpgrade {
 
 impl OfflineUpgrade {
     pub fn upgrade(self) -> anyhow::Result<()> {
+        let upgrade_list = [
+            (v1_9_to_v1_10 as fn(&Path) -> Result<(), anyhow::Error>, "1", "10", "0"),
+            (v1_10_to_v1_11, "1", "11", "0"),
+        ];
+
         let (current_major, current_minor, current_patch) = &self.current_version;
+
+        let start_at = match (
+            current_major.as_str(),
+            current_minor.as_str(),
+            current_patch.as_str(),
+        ) {
+            ("1", "9", _) => 0,
+            ("1", "10", _) => 1,
+            _ => {
+                bail!("Unsupported current version {current_major}.{current_minor}.{current_patch}. Can only upgrade from v1.9")
+            }
+        };
+
         let (target_major, target_minor, target_patch) = &self.target_version;
 
-        println!("Upgrading from {current_major}.{current_minor}.{current_patch} to {target_major}.{target_minor}.{target_patch}");
-
-        match (
-            (current_major.as_str(), current_minor.as_str(), current_patch.as_str()),
-            (target_major.as_str(), target_minor.as_str(), target_patch.as_str()),
-        ) {
-            (("1", "9", _), ("1", "10", _)) => v1_9_to_v1_10(&self.db_path)?,
-            ((major, minor, _), _) if major != "1" && minor != "9" =>
-                bail!("Unsupported current version {current_major}.{current_minor}.{current_patch}. Can only upgrade from v1.9"),
-            (_, (major, minor, _)) if major != "1" && minor != "10" =>
-                bail!("Unsupported target version {target_major}.{target_minor}.{target_patch}. Can only upgrade to v1.10"),
-            _ => 
-                bail!("Unsupported upgrade from {current_major}.{current_minor}.{current_patch} to {target_major}.{target_minor}.{target_patch}. Can only upgrade from v1.9 to v1.10"),
+        let ends_at = match (target_major.as_str(), target_minor.as_str(), target_patch.as_str()) {
+            ("v1", "10", _) => 0,
+            ("v1", "11", _) => 1,
+            _ => {
+                bail!("Unsupported target version {target_major}.{target_minor}.{target_patch}. Can only upgrade to v1.11")
             }
+        };
 
+        println!("Starting the upgrade from {current_major}.{current_minor}.{current_patch} to {target_major}.{target_minor}.{target_patch}");
+
+        #[allow(clippy::needless_range_loop)]
+        for index in start_at..=ends_at {
+            let (func, major, minor, patch) = upgrade_list[index];
+            (func)(&self.db_path)?;
+            println!("Done");
+            // We're writing the version file just in case an issue arise _while_ upgrading.
+            // We don't want the DB to fail in an unknown state.
             println!("Writing VERSION file");
 
-        create_version_file(&self.db_path, target_major, target_minor, target_patch)
+            create_version_file(&self.db_path, major, minor, patch)
                 .context("while writing VERSION file after the upgrade")?;
+        }
 
         println!("Success");
 

meilitool/src/upgrade/v1_10.rs

@@ -79,7 +79,8 @@ fn update_index_stats(
     let stats: Option<v1_9::IndexStats> = index_stats
         .remap_data_type::<SerdeJson<v1_9::IndexStats>>()
         .get(sched_wtxn, &index_uuid)
-        .with_context(ctx)?;
+        .with_context(ctx)
+        .with_context(|| "While reading value")?;
 
     if let Some(stats) = stats {
         let stats: self::IndexStats = stats.into();
@@ -87,7 +88,8 @@ fn update_index_stats(
         index_stats
             .remap_data_type::<SerdeJson<self::IndexStats>>()
             .put(sched_wtxn, &index_uuid, &stats)
-            .with_context(ctx)?;
+            .with_context(ctx)
+            .with_context(|| "While writing value")?;
     }
 
     Ok(())
@@ -155,6 +157,7 @@ fn date_round_trip(
 }
 
 pub fn v1_9_to_v1_10(db_path: &Path) -> anyhow::Result<()> {
+    println!("Upgrading from v1.9.0 to v1.10.0");
     // 2 changes here
 
     // 1. date format. needs to be done before opening the Index

meilitool/src/upgrade/v1_11.rs

@@ -0,0 +1,76 @@
+//! The breaking changes that happened between the v1.10 and the v1.11 are:
+//! - Arroy went from the v0.4.0 to the v0.5.0, see this release note to get the whole context: https://github.com/meilisearch/arroy/releases/tag/v0.5.0
+//!   - The `angular` distance has been renamed to `cosine` => We only need to update the string in the metadata.
+//!   - Reorganize the `NodeId` to make the appending of vectors work => We'll have to update the keys of almost all items in the DB.
+//!   - Store the list of updated IDs directly in LMDB instead of a roaring bitmap => This shouldn't be an issue since we are never supposed to commit this roaring bitmap, but it's not forbidden by arroy so ensuring it works is probably better than anything.
+
+use std::path::Path;
+
+use anyhow::Context;
+use meilisearch_types::{
+    heed::{types::Str, Database, EnvOpenOptions},
+    milli::index::db_name,
+};
+
+use crate::{try_opening_database, try_opening_poly_database, uuid_codec::UuidCodec};
+
+pub fn v1_10_to_v1_11(db_path: &Path) -> anyhow::Result<()> {
+    println!("Upgrading from v1.10.0 to v1.11.0");
+
+    let index_scheduler_path = db_path.join("tasks");
+    let env = unsafe { EnvOpenOptions::new().max_dbs(100).open(&index_scheduler_path) }
+        .with_context(|| format!("While trying to open {:?}", index_scheduler_path.display()))?;
+
+    let sched_rtxn = env.read_txn()?;
+
+    let index_mapping: Database<Str, UuidCodec> =
+        try_opening_database(&env, &sched_rtxn, "index-mapping")?;
+
+    let index_count =
+        index_mapping.len(&sched_rtxn).context("while reading the number of indexes")?;
+
+    let indexes: Vec<_> = index_mapping
+        .iter(&sched_rtxn)?
+        .map(|res| res.map(|(uid, uuid)| (uid.to_owned(), uuid)))
+        .collect();
+
+    // check that update can take place
+    for (index_index, result) in indexes.into_iter().enumerate() {
+        let (uid, uuid) = result?;
+        let index_path = db_path.join("indexes").join(uuid.to_string());
+
+        println!(
+            "[{}/{index_count}]Checking that update can take place for  `{uid}` at `{}`",
+            index_index + 1,
+            index_path.display()
+        );
+
+        let index_env = unsafe {
+            EnvOpenOptions::new().max_dbs(25).open(&index_path).with_context(|| {
+                format!("while opening index {uid} at '{}'", index_path.display())
+            })?
+        };
+
+        let index_rtxn = index_env.read_txn().with_context(|| {
+            format!(
+                "while obtaining a read transaction for index {uid} at {}",
+                index_path.display()
+            )
+        })?;
+        let mut index_wtxn = index_env.write_txn().with_context(|| {
+            format!(
+                "while obtaining a write transaction for index {uid} at {}",
+                index_path.display()
+            )
+        })?;
+
+        let database = try_opening_poly_database(&index_env, &index_rtxn, db_name::VECTOR_ARROY)
+            .with_context(|| format!("while updating date format for index `{uid}`"))?;
+
+        arroy_v04_to_v05::ugrade_from_prev_version(&index_rtxn, &mut index_wtxn, database)?;
+
+        index_wtxn.commit()?;
+    }
+
+    Ok(())
+}