[pbs-devel] [PATCH v7 proxmox-backup 47/69] client: pxar: add method for metadata comparison

[Christian Ebner]

Add method to compare metadata of current file entry against metadata
of the entry looked up in the previous backup snapshot. If the
metadata matched, the start offset pointing to the files payload
header in the payload steam is returned.

This is in preparation for reusing payload chunks for unchanged files.

Signed-off-by: Christian Ebner <c.ebner at proxmox.com>
---
changes since version 6:
- move check if previous metadata accessor to within the
  is_reusable_entry

 pbs-client/src/pxar/create.rs     | 37 ++++++++++++++++++++++++++++++-
 proxmox-backup-client/src/main.rs |  3 ++-
 2 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/pbs-client/src/pxar/create.rs b/pbs-client/src/pxar/create.rs
index 678ad768f..ac8827bb2 100644
--- a/pbs-client/src/pxar/create.rs
+++ b/pbs-client/src/pxar/create.rs
@@ -2,6 +2,7 @@ use std::collections::{HashMap, HashSet};
 use std::ffi::{CStr, CString, OsStr};
 use std::fmt;
 use std::io::{self, Read};
+use std::mem::size_of;
 use std::ops::Range;
 use std::os::unix::ffi::OsStrExt;
 use std::os::unix::io::{AsRawFd, FromRawFd, IntoRawFd, OwnedFd, RawFd};
@@ -21,7 +22,7 @@ use proxmox_sys::error::SysError;
 use pxar::accessor::aio::{Accessor, Directory};
 use pxar::accessor::ReadAt;
 use pxar::encoder::{LinkOffset, SeqWrite};
-use pxar::{Metadata, PxarVariant};
+use pxar::{EntryKind, Metadata, PxarVariant};
 
 use proxmox_io::vec;
 use proxmox_lang::c_str;
@@ -333,6 +334,40 @@ impl Archiver {
         .boxed()
     }
 
+    async fn is_reusable_entry(
+        &mut self,
+        previous_metadata_accessor: &Option<Directory<MetadataArchiveReader>>,
+        file_name: &Path,
+        metadata: &Metadata,
+    ) -> Result<Option<Range<u64>>, Error> {
+        if let Some(previous_metadata_accessor) = previous_metadata_accessor {
+            if let Some(file_entry) = previous_metadata_accessor.lookup(file_name).await? {
+                if metadata == file_entry.metadata() {
+                    if let EntryKind::File {
+                        payload_offset: Some(offset),
+                        size,
+                        ..
+                    } = file_entry.entry().kind()
+                    {
+                        let range =
+                            *offset..*offset + size + size_of::<pxar::format::Header>() as u64;
+                        log::debug!(
+                            "reusable: {file_name:?} at range {range:?} has unchanged metadata."
+                        );
+                        return Ok(Some(range));
+                    }
+                    log::debug!("reencode: {file_name:?} not a regular file.");
+                    return Ok(None);
+                }
+                log::debug!("reencode: {file_name:?} metadata did not match.");
+                return Ok(None);
+            }
+            log::debug!("reencode: {file_name:?} not found in previous archive.");
+        }
+
+        Ok(None)
+    }
+
     /// openat() wrapper which allows but logs `EACCES` and turns `ENOENT` into `None`.
     ///
     /// The `existed` flag is set when iterating through a directory to note that we know the file
diff --git a/proxmox-backup-client/src/main.rs b/proxmox-backup-client/src/main.rs
index fcce13430..32e5f9b81 100644
--- a/proxmox-backup-client/src/main.rs
+++ b/proxmox-backup-client/src/main.rs
@@ -1256,7 +1256,8 @@ async fn prepare_reference(
     let reader = BufferedDynamicReader::new(metadata_ref_index, chunk_reader);
     let archive_size = reader.archive_size();
     let reader: MetadataArchiveReader = Arc::new(LocalDynamicReadAt::new(reader));
-    let accessor = Accessor::new(reader, archive_size, None).await?;
+    // only care about the metadata, therefore do not attach payload reader
+    let accessor = Accessor::new(pxar::PxarVariant::Unified(reader), archive_size).await?;
 
     Ok(Some(pbs_client::pxar::PxarPrevRef {
         accessor,
-- 
2.39.2