[pbs-devel] [PATCH v3 proxmox-backup 08/33] client: backup writer: allow push uploading index and chunks

Christian Ebner c.ebner at proxmox.com
Thu Sep 12 16:32:57 CEST 2024


Add a method `upload_index_chunk_info` to be used for uploading an
existing index and the corresponding chunk stream.
Instead of taking an input stream of raw bytes as the
`upload_stream`, this takes a stream of `ChunkInfo` object provided
by the local chunk reader of the sync jobs source.

Signed-off-by: Christian Ebner <c.ebner at proxmox.com>
---
changes since version 2:
- no changes

 pbs-client/src/backup_writer.rs | 106 ++++++++++++++++++++++++++++++++
 1 file changed, 106 insertions(+)

diff --git a/pbs-client/src/backup_writer.rs b/pbs-client/src/backup_writer.rs
index b71157164..dbb7db0e8 100644
--- a/pbs-client/src/backup_writer.rs
+++ b/pbs-client/src/backup_writer.rs
@@ -288,6 +288,112 @@ impl BackupWriter {
             .await
     }
 
+    /// Upload chunks and index
+    pub async fn upload_index_chunk_info(
+        &self,
+        archive_name: &str,
+        stream: impl Stream<Item = Result<ChunkInfo, Error>>,
+        options: UploadOptions,
+        known_chunks: Arc<Mutex<HashSet<[u8; 32]>>>,
+    ) -> Result<BackupStats, Error> {
+        let mut param = json!({ "archive-name": archive_name });
+        let prefix = if let Some(size) = options.fixed_size {
+            param["size"] = size.into();
+            "fixed"
+        } else {
+            "dynamic"
+        };
+
+        if options.encrypt && self.crypt_config.is_none() {
+            bail!("requested encryption without a crypt config");
+        }
+
+        let wid = self
+            .h2
+            .post(&format!("{prefix}_index"), Some(param))
+            .await?
+            .as_u64()
+            .unwrap();
+
+        let total_chunks = Arc::new(AtomicUsize::new(0));
+        let known_chunk_count = Arc::new(AtomicUsize::new(0));
+
+        let stream_len = Arc::new(AtomicUsize::new(0));
+        let compressed_stream_len = Arc::new(AtomicU64::new(0));
+        let reused_len = Arc::new(AtomicUsize::new(0));
+
+        let counters = UploadStatsCounters {
+            injected_chunk_count: Arc::new(AtomicUsize::new(0)),
+            known_chunk_count: known_chunk_count.clone(),
+            total_chunks: total_chunks.clone(),
+            compressed_stream_len: compressed_stream_len.clone(),
+            injected_len: Arc::new(AtomicUsize::new(0)),
+            reused_len: reused_len.clone(),
+            stream_len: stream_len.clone(),
+        };
+
+        let is_fixed_chunk_size = prefix == "fixed";
+
+        let index_csum = Arc::new(Mutex::new(Some(Sha256::new())));
+        let index_csum_2 = index_csum.clone();
+
+        let stream = stream
+            .and_then(move |chunk_info| {
+                total_chunks.fetch_add(1, Ordering::SeqCst);
+                reused_len.fetch_add(chunk_info.chunk_len as usize, Ordering::SeqCst);
+                let offset = stream_len.fetch_add(chunk_info.chunk_len as usize, Ordering::SeqCst);
+
+                let end_offset = offset as u64 + chunk_info.chunk_len;
+                let mut guard = index_csum.lock().unwrap();
+                let csum = guard.as_mut().unwrap();
+                if !is_fixed_chunk_size {
+                    csum.update(&end_offset.to_le_bytes());
+                }
+                csum.update(&chunk_info.digest);
+
+                let mut known_chunks = known_chunks.lock().unwrap();
+                if known_chunks.contains(&chunk_info.digest) {
+                    known_chunk_count.fetch_add(1, Ordering::SeqCst);
+                    future::ok(MergedChunkInfo::Known(vec![(
+                        chunk_info.offset,
+                        chunk_info.digest,
+                    )]))
+                } else {
+                    known_chunks.insert(chunk_info.digest);
+                    future::ok(MergedChunkInfo::New(chunk_info))
+                }
+            })
+            .merge_known_chunks();
+
+        let upload_stats = Self::upload_merged_chunk_stream(
+            self.h2.clone(),
+            wid,
+            prefix,
+            stream,
+            index_csum_2,
+            counters,
+        )
+        .await?;
+
+        let param = json!({
+            "wid": wid ,
+            "chunk-count": upload_stats.chunk_count,
+            "size": upload_stats.size,
+            "csum": hex::encode(upload_stats.csum),
+        });
+        let _value = self
+            .h2
+            .post(&format!("{prefix}_close"), Some(param))
+            .await?;
+
+        Ok(BackupStats {
+            size: upload_stats.size as u64,
+            csum: upload_stats.csum,
+            duration: upload_stats.duration,
+            chunk_count: upload_stats.chunk_count as u64,
+        })
+    }
+
     pub async fn upload_stream(
         &self,
         archive_name: &str,
-- 
2.39.2





More information about the pbs-devel mailing list