[pbs-devel] [RFC proxmox-backup 27/36] client: implement prepare reference method

[Christian Ebner]

Implement a method that prepares the decoder instance to access a
previous snapshots metadata index and payload index in order to
pass it to the pxar archiver. The archiver than can utilize these
to compare the metadata for files to the previous state and gather
reusable chunks.

Signed-off-by: Christian Ebner <c.ebner at proxmox.com>
---
 pbs-client/src/pxar/create.rs     | 13 ++++++
 pbs-client/src/pxar/mod.rs        |  2 +-
 proxmox-backup-client/src/main.rs | 71 ++++++++++++++++++++++++++++++-
 3 files changed, 83 insertions(+), 3 deletions(-)

diff --git a/pbs-client/src/pxar/create.rs b/pbs-client/src/pxar/create.rs
index 9ae84d37..cb0af29e 100644
--- a/pbs-client/src/pxar/create.rs
+++ b/pbs-client/src/pxar/create.rs
@@ -17,6 +17,7 @@ use nix::sys::stat::{FileStat, Mode};
 
 use pathpatterns::{MatchEntry, MatchFlag, MatchList, MatchType, PatternFlag};
 use proxmox_sys::error::SysError;
+use pxar::accessor::aio::Accessor;
 use pxar::encoder::{LinkOffset, SeqWrite};
 use pxar::Metadata;
 
@@ -24,7 +25,9 @@ use proxmox_io::vec;
 use proxmox_lang::c_str;
 use proxmox_sys::fs::{self, acl, xattr};
 
+use crate::RemoteChunkReader;
 use pbs_datastore::catalog::BackupCatalogWriter;
+use pbs_datastore::dynamic_index::{DynamicIndexReader, LocalDynamicReadAt};
 
 use crate::inject_reused_chunks::InjectChunks;
 use crate::pxar::metadata::errno_is_unsupported;
@@ -46,6 +49,16 @@ pub struct PxarCreateOptions {
     pub skip_e2big_xattr: bool,
 }
 
+/// Statefull information of previous backups snapshots for partial backups
+pub struct PxarPrevRef {
+    /// Reference accessor for metadata comparison
+    pub accessor: Accessor<LocalDynamicReadAt<RemoteChunkReader>>,
+    /// Reference index for reusing payload chunks
+    pub payload_index: DynamicIndexReader,
+    /// Reference archive name for partial backups
+    pub archive_name: String,
+}
+
 fn detect_fs_type(fd: RawFd) -> Result<i64, Error> {
     let mut fs_stat = std::mem::MaybeUninit::uninit();
     let res = unsafe { libc::fstatfs(fd, fs_stat.as_mut_ptr()) };
diff --git a/pbs-client/src/pxar/mod.rs b/pbs-client/src/pxar/mod.rs
index 14674b9b..24315f5f 100644
--- a/pbs-client/src/pxar/mod.rs
+++ b/pbs-client/src/pxar/mod.rs
@@ -56,7 +56,7 @@ pub(crate) mod tools;
 mod flags;
 pub use flags::Flags;
 
-pub use create::{create_archive, PxarCreateOptions};
+pub use create::{create_archive, PxarCreateOptions, PxarPrevRef};
 pub use extract::{
     create_tar, create_zip, extract_archive, extract_sub_dir, extract_sub_dir_seq, ErrorHandler,
     OverwriteFlags, PxarExtractContext, PxarExtractOptions,
diff --git a/proxmox-backup-client/src/main.rs b/proxmox-backup-client/src/main.rs
index 290df4a1..2d48ca85 100644
--- a/proxmox-backup-client/src/main.rs
+++ b/proxmox-backup-client/src/main.rs
@@ -21,6 +21,7 @@ use proxmox_router::{cli::*, ApiMethod, RpcEnvironment};
 use proxmox_schema::api;
 use proxmox_sys::fs::{file_get_json, image_size, replace_file, CreateOptions};
 use proxmox_time::{epoch_i64, strftime_local};
+use pxar::accessor::aio::Accessor;
 use pxar::accessor::{MaybeReady, ReadAt, ReadAtOperation};
 
 use pbs_api_types::{
@@ -30,7 +31,7 @@ use pbs_api_types::{
     BACKUP_TYPE_SCHEMA, TRAFFIC_CONTROL_BURST_SCHEMA, TRAFFIC_CONTROL_RATE_SCHEMA,
 };
 use pbs_client::catalog_shell::Shell;
-use pbs_client::pxar::ErrorHandler as PxarErrorHandler;
+use pbs_client::pxar::{ErrorHandler as PxarErrorHandler, PxarPrevRef};
 use pbs_client::tools::{
     complete_archive_name, complete_auth_id, complete_backup_group, complete_backup_snapshot,
     complete_backup_source, complete_chunk_size, complete_group_or_snapshot,
@@ -50,7 +51,7 @@ use pbs_client::{
 };
 use pbs_datastore::catalog::{BackupCatalogWriter, CatalogReader, CatalogWriter};
 use pbs_datastore::chunk_store::verify_chunk_size;
-use pbs_datastore::dynamic_index::{BufferedDynamicReader, DynamicIndexReader};
+use pbs_datastore::dynamic_index::{BufferedDynamicReader, DynamicIndexReader, LocalDynamicReadAt};
 use pbs_datastore::fixed_index::FixedIndexReader;
 use pbs_datastore::index::IndexFile;
 use pbs_datastore::manifest::{
@@ -1181,6 +1182,72 @@ async fn create_backup(
     Ok(Value::Null)
 }
 
+async fn prepare_reference(
+    target_base: &str,
+    extension: &str,
+    manifest: Option<Arc<BackupManifest>>,
+    backup_writer: &BackupWriter,
+    backup_reader: Option<Arc<BackupReader>>,
+    crypt_config: Option<Arc<CryptConfig>>,
+) -> Result<Option<PxarPrevRef>, Error> {
+    let target = format!("{target_base}.meta.{extension}");
+    let payload_target = format!("{target_base}.pld.{extension}");
+
+    let manifest = if let Some(ref manifest) = manifest {
+        manifest
+    } else {
+        return Ok(None);
+    };
+
+    let backup_reader = if let Some(ref reader) = backup_reader {
+        reader
+    } else {
+        return Ok(None);
+    };
+
+    let metadata_ref_index = if let Ok(index) = backup_reader
+        .download_dynamic_index(&manifest, &target)
+        .await
+    {
+        index
+    } else {
+        log::info!("No previous metadata index, fallback to regular encoding");
+        return Ok(None);
+    };
+
+    let known_payload_chunks = Arc::new(Mutex::new(HashSet::new()));
+    let payload_ref_index = if let Ok(index) = backup_writer
+        .download_previous_dynamic_index(&payload_target, &manifest, known_payload_chunks)
+        .await
+    {
+        index
+    } else {
+        log::info!("No previous payload index, fallback to regular encoding");
+        return Ok(None);
+    };
+
+    log::info!("Using previous index as metadata reference for '{target}'");
+
+    let most_used = metadata_ref_index.find_most_used_chunks(8);
+    let file_info = manifest.lookup_file_info(&target)?;
+    let chunk_reader = RemoteChunkReader::new(
+        backup_reader.clone(),
+        crypt_config.clone(),
+        file_info.chunk_crypt_mode(),
+        most_used,
+    );
+    let reader = BufferedDynamicReader::new(metadata_ref_index, chunk_reader);
+    let archive_size = reader.archive_size();
+    let reader = LocalDynamicReadAt::new(reader);
+    let accessor = Accessor::new(reader, archive_size).await?;
+
+    Ok(Some(pbs_client::pxar::PxarPrevRef {
+        accessor,
+        payload_index: payload_ref_index,
+        archive_name: target,
+    }))
+}
+
 async fn dump_image<W: Write>(
     client: Arc<BackupReader>,
     crypt_config: Option<Arc<CryptConfig>>,
-- 
2.39.2