[pbs-devel] [RFC v2 proxmox-backup 16/23] fix #3174: upload stream: impl reused chunk injector

[Christian Ebner]

In order to be included in the backups index file, the reused chunks
which store the payload of skipped files during pxar encoding have to be
inserted after the encoder has written the pxar appendix entry type.

The chunker forces a chunk boundary after this marker and queues the
list of chunks to be uploaded thereafter.
This implements the logic to inject the chunks into the chunk upload
stream after such a boundary is requested, by looping over the queued
chunks and inserting them into the stream.

Signed-off-by: Christian Ebner <c.ebner at proxmox.com>
---
Changes since version 1:
no changes

 pbs-client/src/inject_reused_chunks.rs | 123 +++++++++++++++++++++++++
 pbs-client/src/lib.rs                  |   1 +
 2 files changed, 124 insertions(+)
 create mode 100644 pbs-client/src/inject_reused_chunks.rs

diff --git a/pbs-client/src/inject_reused_chunks.rs b/pbs-client/src/inject_reused_chunks.rs
new file mode 100644
index 00000000..01cb1350
--- /dev/null
+++ b/pbs-client/src/inject_reused_chunks.rs
@@ -0,0 +1,123 @@
+use std::collections::VecDeque;
+use std::pin::Pin;
+use std::sync::atomic::{AtomicUsize, Ordering};
+use std::sync::{Arc, Mutex};
+use std::task::{Context, Poll};
+
+use anyhow::Error;
+use futures::{ready, Stream};
+use pin_project_lite::pin_project;
+
+use pbs_datastore::dynamic_index::DynamicEntry;
+
+pin_project! {
+    pub struct InjectReusedChunksQueue<S> {
+        #[pin]
+        input: S,
+        current: Option<InjectChunks>,
+        injection_queue: Arc<Mutex<VecDeque<InjectChunks>>>,
+        stream_len: Arc<AtomicUsize>,
+        index_csum: Arc<Mutex<Option<openssl::sha::Sha256>>>,
+    }
+}
+
+#[derive(Debug)]
+pub struct InjectChunks {
+    pub boundary: u64,
+    pub chunks: Vec<DynamicEntry>,
+    pub size: usize,
+}
+
+pub enum InjectedChunksInfo {
+    Known(Vec<(u64, [u8; 32])>),
+    Raw((u64, bytes::BytesMut)),
+}
+
+pub trait InjectReusedChunks: Sized {
+    fn inject_reused_chunks(
+        self,
+        injection_queue: Arc<Mutex<VecDeque<InjectChunks>>>,
+        stream_len: Arc<AtomicUsize>,
+        index_csum: Arc<Mutex<Option<openssl::sha::Sha256>>>,
+    ) -> InjectReusedChunksQueue<Self>;
+}
+
+impl<S> InjectReusedChunks for S
+where
+    S: Stream<Item = Result<bytes::BytesMut, Error>>,
+{
+    fn inject_reused_chunks(
+        self,
+        injection_queue: Arc<Mutex<VecDeque<InjectChunks>>>,
+        stream_len: Arc<AtomicUsize>,
+        index_csum: Arc<Mutex<Option<openssl::sha::Sha256>>>,
+    ) -> InjectReusedChunksQueue<Self> {
+        let current = injection_queue.lock().unwrap().pop_front();
+
+        InjectReusedChunksQueue {
+            input: self,
+            current,
+            injection_queue,
+            stream_len,
+            index_csum,
+        }
+    }
+}
+
+impl<S> Stream for InjectReusedChunksQueue<S>
+where
+    S: Stream<Item = Result<bytes::BytesMut, Error>>,
+{
+    type Item = Result<InjectedChunksInfo, Error>;
+
+    fn poll_next(self: Pin<&mut Self>, cx: &mut Context) -> Poll<Option<Self::Item>> {
+        let mut this = self.project();
+        loop {
+            let current = this.current.take();
+            if let Some(current) = current {
+                let mut chunks = Vec::new();
+                let mut guard = this.index_csum.lock().unwrap();
+                let csum = guard.as_mut().unwrap();
+
+                for chunk in current.chunks {
+                    let offset = this
+                        .stream_len
+                        .fetch_add(chunk.end() as usize, Ordering::SeqCst)
+                        as u64;
+                    let digest = chunk.digest();
+                    chunks.push((offset, digest));
+                    // Chunk end is assumed to be normalized to chunk size here
+                    let end_offset = offset + chunk.end();
+                    csum.update(&end_offset.to_le_bytes());
+                    csum.update(&digest);
+                }
+                let chunk_info = InjectedChunksInfo::Known(chunks);
+                return Poll::Ready(Some(Ok(chunk_info)));
+            }
+
+            match ready!(this.input.as_mut().poll_next(cx)) {
+                None => return Poll::Ready(None),
+                Some(Err(err)) => return Poll::Ready(Some(Err(err))),
+                Some(Ok(raw)) => {
+                    let chunk_size = raw.len();
+                    let offset = this.stream_len.fetch_add(chunk_size, Ordering::SeqCst) as u64;
+                    let mut injections = this.injection_queue.lock().unwrap();
+                    if let Some(inject) = injections.pop_front() {
+                        if inject.boundary == offset {
+                            let _ = this.current.insert(inject);
+                            // Should be injected here, directly jump to next loop iteration
+                            continue;
+                        } else if inject.boundary <= offset + chunk_size as u64 {
+                            let _ = this.current.insert(inject);
+                        } else {
+                            injections.push_front(inject);
+                        }
+                    }
+                    let data = InjectedChunksInfo::Raw((offset, raw));
+
+                    return Poll::Ready(Some(Ok(data)));
+                }
+            }
+        }
+    }
+}
diff --git a/pbs-client/src/lib.rs b/pbs-client/src/lib.rs
index 21cf8556..8bf26381 100644
--- a/pbs-client/src/lib.rs
+++ b/pbs-client/src/lib.rs
@@ -8,6 +8,7 @@ pub mod pxar;
 pub mod tools;
 
 mod merge_known_chunks;
+mod inject_reused_chunks;
 pub mod pipe_to_stream;
 
 mod http_client;
-- 
2.39.2