Merge #2098

2098: feat(dump): Provide the same cli options as the snapshots r=MarinPostma a=irevoire

Add two cli options for the dump:
- `--ignore-missing-dump`
- `--ignore-dump-if-db-exists`

Fix #2087

Co-authored-by: Tamo <tamo@meilisearch.com>

meilisearch-http/src/lib.rs

@@ -30,11 +30,15 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<MeiliSearch> {
     meilisearch
         .set_max_index_size(opt.max_index_size.get_bytes() as usize)
         .set_max_task_store_size(opt.max_task_db_size.get_bytes() as usize)
+        // snapshot
         .set_ignore_missing_snapshot(opt.ignore_missing_snapshot)
         .set_ignore_snapshot_if_db_exists(opt.ignore_snapshot_if_db_exists)
-        .set_dump_dst(opt.dumps_dir.clone())
         .set_snapshot_interval(Duration::from_secs(opt.snapshot_interval_sec))
-        .set_snapshot_dir(opt.snapshot_dir.clone());
+        .set_snapshot_dir(opt.snapshot_dir.clone())
+        // dump
+        .set_ignore_missing_dump(opt.ignore_missing_dump)
+        .set_ignore_dump_if_db_exists(opt.ignore_dump_if_db_exists)
+        .set_dump_dst(opt.dumps_dir.clone());
 
     if let Some(ref path) = opt.import_snapshot {
         meilisearch.set_import_snapshot(path.clone());

meilisearch-http/src/option.rs

@@ -124,14 +124,22 @@ pub struct Opt {
     #[clap(long, env = "MEILI_SNAPSHOT_INTERVAL_SEC", default_value = "86400")] // 24h
     pub snapshot_interval_sec: u64,
 
-    /// Folder where dumps are created when the dump route is called.
-    #[clap(long, env = "MEILI_DUMPS_DIR", default_value = "dumps/")]
-    pub dumps_dir: PathBuf,
-
     /// Import a dump from the specified path, must be a `.dump` file.
     #[clap(long, conflicts_with = "import-snapshot")]
     pub import_dump: Option<PathBuf>,
 
+    /// If the dump doesn't exists, load or create the database specified by `db-path` instead.
+    #[clap(long, requires = "import-dump")]
+    pub ignore_missing_dump: bool,
+
+    /// Ignore the dump if a database already exists, and load that database instead.
+    #[clap(long, requires = "import-dump")]
+    pub ignore_dump_if_db_exists: bool,
+
+    /// Folder where dumps are created when the dump route is called.
+    #[clap(long, env = "MEILI_DUMPS_DIR", default_value = "dumps/")]
+    pub dumps_dir: PathBuf,
+
     /// Set the log level
     #[clap(long, env = "MEILI_LOG_LEVEL", default_value = "info")]
     pub log_level: String,

meilisearch-http/tests/common/server.rs

@@ -148,6 +148,8 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
         schedule_snapshot: false,
         snapshot_interval_sec: 0,
         import_dump: None,
+        ignore_missing_dump: false,
+        ignore_dump_if_db_exists: false,
         indexer_options: IndexerOpts {
             // memory has to be unlimited because several meilisearch are running in test context.
             max_memory: MaxMemory::unlimited(),

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

@@ -1,14 +1,16 @@
 use std::fs::File;
 use std::path::{Path, PathBuf};
 
+use anyhow::bail;
 use chrono::{DateTime, Utc};
-use log::{info, trace, warn};
+use log::{info, trace};
 use serde::{Deserialize, Serialize};
 
 pub use actor::DumpActor;
 pub use handle_impl::*;
 use meilisearch_auth::AuthController;
 pub use message::DumpMsg;
+use tempfile::TempDir;
 use tokio::fs::create_dir_all;
 use tokio::sync::oneshot;
 
@@ -79,6 +81,47 @@ pub enum MetadataVersion {
 }
 
 impl MetadataVersion {
+    pub fn load_dump(
+        self,
+        src: impl AsRef<Path>,
+        dst: impl AsRef<Path>,
+        index_db_size: usize,
+        meta_env_size: usize,
+        indexing_options: &IndexerOpts,
+    ) -> anyhow::Result<()> {
+        match self {
+            MetadataVersion::V1(_meta) => {
+                anyhow::bail!("The version 1 of the dumps is not supported anymore. You can re-export your dump from a version between 0.21 and 0.24, or start fresh from a version 0.25 onwards.")
+            }
+            MetadataVersion::V2(meta) => v2::load_dump(
+                meta,
+                src,
+                dst,
+                index_db_size,
+                meta_env_size,
+                indexing_options,
+            )?,
+            MetadataVersion::V3(meta) => v3::load_dump(
+                meta,
+                src,
+                dst,
+                index_db_size,
+                meta_env_size,
+                indexing_options,
+            )?,
+            MetadataVersion::V4(meta) => v4::load_dump(
+                meta,
+                src,
+                dst,
+                index_db_size,
+                meta_env_size,
+                indexing_options,
+            )?,
+        }
+
+        Ok(())
+    }
+
     pub fn new_v4(index_db_size: usize, update_db_size: usize) -> Self {
         let meta = Metadata::new(index_db_size, update_db_size);
         Self::V4(meta)
@@ -160,10 +203,46 @@ impl DumpInfo {
 pub fn load_dump(
     dst_path: impl AsRef<Path>,
     src_path: impl AsRef<Path>,
+    ignore_dump_if_db_exists: bool,
+    ignore_missing_dump: bool,
     index_db_size: usize,
     update_db_size: usize,
     indexer_opts: &IndexerOpts,
 ) -> anyhow::Result<()> {
+    let empty_db = crate::is_empty_db(&dst_path);
+    let src_path_exists = src_path.as_ref().exists();
+
+    if empty_db && src_path_exists {
+        let (tmp_src, tmp_dst, meta) = extract_dump(&dst_path, &src_path)?;
+        meta.load_dump(
+            tmp_src.path(),
+            tmp_dst.path(),
+            index_db_size,
+            update_db_size,
+            indexer_opts,
+        )?;
+        persist_dump(&dst_path, tmp_dst)?;
+        Ok(())
+    } else if !empty_db && !ignore_dump_if_db_exists {
+        bail!(
+            "database already exists at {:?}, try to delete it or rename it",
+            dst_path
+                .as_ref()
+                .canonicalize()
+                .unwrap_or_else(|_| dst_path.as_ref().to_owned())
+        )
+    } else if !src_path_exists && !ignore_missing_dump {
+        bail!("dump doesn't exist at {:?}", src_path.as_ref())
+    } else {
+        // there is nothing to do
+        Ok(())
+    }
+}
+
+fn extract_dump(
+    dst_path: impl AsRef<Path>,
+    src_path: impl AsRef<Path>,
+) -> anyhow::Result<(TempDir, TempDir, MetadataVersion)> {
     // Setup a temp directory path in the same path as the database, to prevent cross devices
     // references.
     let temp_path = dst_path
@@ -201,40 +280,14 @@ pub fn load_dump(
         meta.version()
     );
 
-    match meta {
-        MetadataVersion::V1(_meta) => {
-            anyhow::bail!("The version 1 of the dumps is not supported anymore. You can re-export your dump from a version between 0.21 and 0.24, or start fresh from a version 0.25 onwards.")
-        }
-        MetadataVersion::V2(meta) => v2::load_dump(
-            meta,
-            &tmp_src_path,
-            tmp_dst.path(),
-            index_db_size,
-            update_db_size,
-            indexer_opts,
-        )?,
-        MetadataVersion::V3(meta) => v3::load_dump(
-            meta,
-            &tmp_src_path,
-            tmp_dst.path(),
-            index_db_size,
-            update_db_size,
-            indexer_opts,
-        )?,
-        MetadataVersion::V4(meta) => v4::load_dump(
-            meta,
-            &tmp_src_path,
-            tmp_dst.path(),
-            index_db_size,
-            update_db_size,
-            indexer_opts,
-        )?,
+    Ok((tmp_src, tmp_dst, meta))
 }
+
+fn persist_dump(dst_path: impl AsRef<Path>, tmp_dst: TempDir) -> anyhow::Result<()> {
     let persisted_dump = tmp_dst.into_path();
 
     // Delete everything in the `data.ms` except the tempdir.
     if dst_path.as_ref().exists() {
-        warn!("Overwriting database at {}", dst_path.as_ref().display());
         for file in dst_path.as_ref().read_dir().unwrap() {
             let file = file.unwrap().path();
             if file.file_name() == persisted_dump.file_name() {

meilisearch-lib/src/index_controller/mod.rs

@@ -150,6 +150,8 @@ pub struct IndexControllerBuilder {
     schedule_snapshot: bool,
     dump_src: Option<PathBuf>,
     dump_dst: Option<PathBuf>,
+    ignore_dump_if_db_exists: bool,
+    ignore_missing_dump: bool,
 }
 
 impl IndexControllerBuilder {
@@ -186,6 +188,8 @@ impl IndexControllerBuilder {
             load_dump(
                 db_path.as_ref(),
                 src_path,
+                self.ignore_dump_if_db_exists,
+                self.ignore_missing_dump,
                 index_size,
                 task_store_size,
                 &indexer_options,
@@ -296,18 +300,6 @@ impl IndexControllerBuilder {
         self
     }
 
-    /// Set the index controller builder's dump src.
-    pub fn set_dump_src(&mut self, dump_src: PathBuf) -> &mut Self {
-        self.dump_src.replace(dump_src);
-        self
-    }
-
-    /// Set the index controller builder's dump dst.
-    pub fn set_dump_dst(&mut self, dump_dst: PathBuf) -> &mut Self {
-        self.dump_dst.replace(dump_dst);
-        self
-    }
-
     /// Set the index controller builder's import snapshot.
     pub fn set_import_snapshot(&mut self, import_snapshot: PathBuf) -> &mut Self {
         self.import_snapshot.replace(import_snapshot);
@@ -325,6 +317,30 @@ impl IndexControllerBuilder {
         self.schedule_snapshot = true;
         self
     }
+
+    /// Set the index controller builder's dump src.
+    pub fn set_dump_src(&mut self, dump_src: PathBuf) -> &mut Self {
+        self.dump_src.replace(dump_src);
+        self
+    }
+
+    /// Set the index controller builder's dump dst.
+    pub fn set_dump_dst(&mut self, dump_dst: PathBuf) -> &mut Self {
+        self.dump_dst.replace(dump_dst);
+        self
+    }
+
+    /// Set the index controller builder's ignore dump if db exists.
+    pub fn set_ignore_dump_if_db_exists(&mut self, ignore_dump_if_db_exists: bool) -> &mut Self {
+        self.ignore_dump_if_db_exists = ignore_dump_if_db_exists;
+        self
+    }
+
+    /// Set the index controller builder's ignore missing dump.
+    pub fn set_ignore_missing_dump(&mut self, ignore_missing_dump: bool) -> &mut Self {
+        self.ignore_missing_dump = ignore_missing_dump;
+        self
+    }
 }
 
 impl<U, I> IndexController<U, I>

meilisearch-lib/src/lib.rs

@@ -10,6 +10,8 @@ mod snapshot;
 pub mod tasks;
 mod update_file_store;
 
+use std::path::Path;
+
 pub use index_controller::MeiliSearch;
 
 pub use milli;
@@ -33,3 +35,19 @@ impl EnvSizer for heed::Env {
             .fold(0, |acc, m| acc + m.len())
     }
 }
+
+/// Check if a db is empty. It does not provide any information on the
+/// validity of the data in it.
+/// We consider a database as non empty when it's a non empty directory.
+pub fn is_empty_db(db_path: impl AsRef<Path>) -> bool {
+    let db_path = db_path.as_ref();
+
+    if !db_path.exists() {
+        true
+    // if we encounter an error or if the db is a file we consider the db non empty
+    } else if let Ok(dir) = db_path.read_dir() {
+        dir.count() == 0
+    } else {
+        true
+    }
+}

meilisearch-lib/src/snapshot.rs

@@ -49,7 +49,10 @@ pub fn load_snapshot(
     ignore_snapshot_if_db_exists: bool,
     ignore_missing_snapshot: bool,
 ) -> anyhow::Result<()> {
-    if !db_path.as_ref().exists() && snapshot_path.as_ref().exists() {
+    let empty_db = crate::is_empty_db(&db_path);
+    let snapshot_path_exists = snapshot_path.as_ref().exists();
+
+    if empty_db && snapshot_path_exists {
         match from_tar_gz(snapshot_path, &db_path) {
             Ok(()) => Ok(()),
             Err(e) => {
@@ -58,7 +61,7 @@ pub fn load_snapshot(
                 Err(e)
             }
         }
-    } else if db_path.as_ref().exists() && !ignore_snapshot_if_db_exists {
+    } else if !empty_db && !ignore_snapshot_if_db_exists {
         bail!(
             "database already exists at {:?}, try to delete it or rename it",
             db_path
@@ -66,14 +69,8 @@ pub fn load_snapshot(
                 .canonicalize()
                 .unwrap_or_else(|_| db_path.as_ref().to_owned())
         )
-    } else if !snapshot_path.as_ref().exists() && !ignore_missing_snapshot {
-        bail!(
-            "snapshot doesn't exist at {:?}",
-            snapshot_path
-                .as_ref()
-                .canonicalize()
-                .unwrap_or_else(|_| snapshot_path.as_ref().to_owned())
-        )
+    } else if !snapshot_path_exists && !ignore_missing_snapshot {
+        bail!("snapshot doesn't exist at {:?}", snapshot_path.as_ref())
     } else {
         Ok(())
     }