public inbox for pbs-devel@lists.proxmox.com
 help / color / mirror / Atom feed
From: Christian Ebner <c.ebner@proxmox.com>
To: pbs-devel@lists.proxmox.com
Subject: [pbs-devel] [PATCH v9 proxmox-backup 03/58] client: pxar: optionally split metadata and payload streams
Date: Wed,  5 Jun 2024 12:53:21 +0200	[thread overview]
Message-ID: <20240605105416.278748-4-c.ebner@proxmox.com> (raw)
In-Reply-To: <20240605105416.278748-1-c.ebner@proxmox.com>

... and attach the split payload writer variant to the pxar archive
creation. By this, metadata and payload data will create different
dynamic indexes, allowing to lookup and reuse payload chunks without
the additional overhead of the pxar archive's metadata.

For now this functionality remains disabled and will be enabled in a
later patch once the logic for reusing the payload chunks is in
place.

Signed-off-by: Christian Ebner <c.ebner@proxmox.com>
---
changes since version 8:
- no changes

 pbs-client/src/pxar_backup_stream.rs | 51 ++++++++++++++-----
 proxmox-backup-client/src/main.rs    | 75 +++++++++++++++++++++++++---
 2 files changed, 105 insertions(+), 21 deletions(-)

diff --git a/pbs-client/src/pxar_backup_stream.rs b/pbs-client/src/pxar_backup_stream.rs
index 8dc3fd088..3541eddb5 100644
--- a/pbs-client/src/pxar_backup_stream.rs
+++ b/pbs-client/src/pxar_backup_stream.rs
@@ -42,21 +42,37 @@ impl PxarBackupStream {
         dir: Dir,
         catalog: Arc<Mutex<CatalogWriter<W>>>,
         options: crate::pxar::PxarCreateOptions,
-    ) -> Result<Self, Error> {
-        let (tx, rx) = std::sync::mpsc::sync_channel(10);
-
+        separate_payload_stream: bool,
+    ) -> Result<(Self, Option<Self>), Error> {
         let buffer_size = 256 * 1024;
 
-        let error = Arc::new(Mutex::new(None));
-        let error2 = Arc::clone(&error);
-        let handler = async move {
-            let writer = TokioWriterAdapter::new(std::io::BufWriter::with_capacity(
+        let (tx, rx) = std::sync::mpsc::sync_channel(10);
+        let writer = TokioWriterAdapter::new(std::io::BufWriter::with_capacity(
+            buffer_size,
+            StdChannelWriter::new(tx),
+        ));
+        let writer = pxar::encoder::sync::StandardWriter::new(writer);
+
+        let (writer, payload_rx) = if separate_payload_stream {
+            let (tx, rx) = std::sync::mpsc::sync_channel(10);
+            let payload_writer = TokioWriterAdapter::new(std::io::BufWriter::with_capacity(
                 buffer_size,
                 StdChannelWriter::new(tx),
             ));
+            (
+                pxar::PxarVariant::Split(
+                    writer,
+                    pxar::encoder::sync::StandardWriter::new(payload_writer),
+                ),
+                Some(rx),
+            )
+        } else {
+            (pxar::PxarVariant::Unified(writer), None)
+        };
 
-            let writer =
-                pxar::PxarVariant::Unified(pxar::encoder::sync::StandardWriter::new(writer));
+        let error = Arc::new(Mutex::new(None));
+        let error2 = Arc::clone(&error);
+        let handler = async move {
             if let Err(err) = crate::pxar::create_archive(
                 dir,
                 PxarWriters::new(writer, Some(catalog)),
@@ -78,21 +94,30 @@ impl PxarBackupStream {
         let future = Abortable::new(handler, registration);
         tokio::spawn(future);
 
-        Ok(Self {
+        let backup_stream = Self {
+            rx: Some(rx),
+            handle: Some(handle.clone()),
+            error: Arc::clone(&error),
+        };
+
+        let backup_payload_stream = payload_rx.map(|rx| Self {
             rx: Some(rx),
             handle: Some(handle),
             error,
-        })
+        });
+
+        Ok((backup_stream, backup_payload_stream))
     }
 
     pub fn open<W: Write + Send + 'static>(
         dirname: &Path,
         catalog: Arc<Mutex<CatalogWriter<W>>>,
         options: crate::pxar::PxarCreateOptions,
-    ) -> Result<Self, Error> {
+        separate_payload_stream: bool,
+    ) -> Result<(Self, Option<Self>), Error> {
         let dir = nix::dir::Dir::open(dirname, OFlag::O_DIRECTORY, Mode::empty())?;
 
-        Self::new(dir, catalog, options)
+        Self::new(dir, catalog, options, separate_payload_stream)
     }
 }
 
diff --git a/proxmox-backup-client/src/main.rs b/proxmox-backup-client/src/main.rs
index ad2bc5a66..25556d672 100644
--- a/proxmox-backup-client/src/main.rs
+++ b/proxmox-backup-client/src/main.rs
@@ -187,18 +187,24 @@ async fn backup_directory<P: AsRef<Path>>(
     client: &BackupWriter,
     dir_path: P,
     archive_name: &str,
+    payload_target: Option<&str>,
     chunk_size: Option<usize>,
     catalog: Arc<Mutex<CatalogWriter<TokioWriterAdapter<StdChannelWriter<Error>>>>>,
     pxar_create_options: pbs_client::pxar::PxarCreateOptions,
     upload_options: UploadOptions,
-) -> Result<BackupStats, Error> {
+) -> Result<(BackupStats, Option<BackupStats>), Error> {
     if upload_options.fixed_size.is_some() {
         bail!("cannot backup directory with fixed chunk size!");
     }
 
-    let pxar_stream = PxarBackupStream::open(dir_path.as_ref(), catalog, pxar_create_options)?;
-    let mut chunk_stream = ChunkStream::new(pxar_stream, chunk_size);
+    let (pxar_stream, payload_stream) = PxarBackupStream::open(
+        dir_path.as_ref(),
+        catalog,
+        pxar_create_options,
+        payload_target.is_some(),
+    )?;
 
+    let mut chunk_stream = ChunkStream::new(pxar_stream, chunk_size);
     let (tx, rx) = mpsc::channel(10); // allow to buffer 10 chunks
 
     let stream = ReceiverStream::new(rx).map_err(Error::from);
@@ -210,11 +216,36 @@ async fn backup_directory<P: AsRef<Path>>(
         }
     });
 
-    let stats = client
-        .upload_stream(archive_name, stream, upload_options)
-        .await?;
+    let stats = client.upload_stream(archive_name, stream, upload_options.clone());
 
-    Ok(stats)
+    if let Some(payload_stream) = payload_stream {
+        let payload_target = payload_target
+            .ok_or_else(|| format_err!("got payload stream, but no target archive name"))?;
+
+        let mut payload_chunk_stream = ChunkStream::new(payload_stream, chunk_size);
+        let (payload_tx, payload_rx) = mpsc::channel(10); // allow to buffer 10 chunks
+        let stream = ReceiverStream::new(payload_rx).map_err(Error::from);
+
+        // spawn payload chunker inside a separate task so that it can run parallel
+        tokio::spawn(async move {
+            while let Some(v) = payload_chunk_stream.next().await {
+                let _ = payload_tx.send(v).await;
+            }
+        });
+
+        let payload_stats = client.upload_stream(&payload_target, stream, upload_options);
+
+        match futures::join!(stats, payload_stats) {
+            (Ok(stats), Ok(payload_stats)) => Ok((stats, Some(payload_stats))),
+            (Err(err), Ok(_)) => Err(format_err!("upload failed: {err}")),
+            (Ok(_), Err(err)) => Err(format_err!("upload failed: {err}")),
+            (Err(err), Err(payload_err)) => {
+                Err(format_err!("upload failed: {err} - {payload_err}"))
+            }
+        }
+    } else {
+        Ok((stats.await?, None))
+    }
 }
 
 async fn backup_image<P: AsRef<Path>>(
@@ -985,6 +1016,23 @@ async fn create_backup(
                 manifest.add_file(target, stats.size, stats.csum, crypto.mode)?;
             }
             (BackupSpecificationType::PXAR, false) => {
+                let metadata_mode = false; // Until enabled via param
+
+                let target_base = if let Some(base) = target_base.strip_suffix(".pxar") {
+                    base.to_string()
+                } else {
+                    bail!("unexpected suffix in target: {target_base}");
+                };
+
+                let (target, payload_target) = if metadata_mode {
+                    (
+                        format!("{target_base}.mpxar.{extension}"),
+                        Some(format!("{target_base}.ppxar.{extension}")),
+                    )
+                } else {
+                    (target, None)
+                };
+
                 // start catalog upload on first use
                 if catalog.is_none() {
                     let catalog_upload_res =
@@ -1015,16 +1063,27 @@ async fn create_backup(
                     ..UploadOptions::default()
                 };
 
-                let stats = backup_directory(
+                let (stats, payload_stats) = backup_directory(
                     &client,
                     &filename,
                     &target,
+                    payload_target.as_deref(),
                     chunk_size_opt,
                     catalog.clone(),
                     pxar_options,
                     upload_options,
                 )
                 .await?;
+
+                if let Some(payload_stats) = payload_stats {
+                    manifest.add_file(
+                        payload_target
+                            .ok_or_else(|| format_err!("missing payload target archive"))?,
+                        payload_stats.size,
+                        payload_stats.csum,
+                        crypto.mode,
+                    )?;
+                }
                 manifest.add_file(target, stats.size, stats.csum, crypto.mode)?;
                 catalog.lock().unwrap().end_directory()?;
             }
-- 
2.39.2



_______________________________________________
pbs-devel mailing list
pbs-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel


  parent reply	other threads:[~2024-06-05 10:54 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-05 10:53 [pbs-devel] [PATCH v9 proxmox-backup 00/58] fix #3174: improve file-level backup Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 01/58] client: pxar: switch to stack based encoder state Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 02/58] client: pxar: combine writers into struct Christian Ebner
2024-06-05 10:53 ` Christian Ebner [this message]
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 04/58] client: helper: add helpers for creating reader instances Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 05/58] client: helper: add method for split archive name mapping Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 06/58] client: tools: helper to check pxar filename extensions Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 07/58] client: restore: read payload from dedicated index Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 08/58] client: tools: cover extension for split pxar archives Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 09/58] client: mount: make split pxar archives mountable Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 10/58] api: datastore: attach split archive payload chunk reader Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 11/58] catalog: shell: make split pxar archives accessible Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 12/58] www: cover metadata extension for pxar archives Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 13/58] file restore: cover extension for split " Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 14/58] file restore: factor out getting pxar reader Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 15/58] file restore: cover split metadata and payload archives Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 16/58] file restore: show more error context when extraction fails Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 17/58] pxar: bin: add optional payload input for archive restore Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 18/58] pxar: bin: cover listing for split archives Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 19/58] pxar: bin: add more context to extraction error Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 20/58] client: pxar: include payload offset in entry listing Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 21/58] client: pxar: helper for lookup of reusable dynamic entries Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 22/58] upload stream: implement reused chunk injector Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 23/58] client: chunk stream: add struct to hold injection state Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 24/58] chunker: add method to reset chunker state Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 25/58] client: streams: add channels for dynamic entry injection Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 26/58] specs: add backup detection mode specification Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 27/58] client: implement prepare reference method Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 28/58] client: pxar: add method for metadata comparison Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 29/58] pxar: caching: add look-ahead cache Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 30/58] client: pxar: refactor catalog encoding for directories Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 31/58] fix #3174: client: pxar: enable caching and meta comparison Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 32/58] client: backup writer: add injected chunk count to stats Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 33/58] pxar: create: keep track of reused chunks and files Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 34/58] pxar: create: show chunk injection stats info output Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 35/58] client: backup writer: make backup info output more concise Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 36/58] client: pxar: add helper to handle optional preludes Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 37/58] client: pxar: opt encode cli exclude patterns as Prelude Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 38/58] client: pxar: allow to restore prelude to optional path Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 39/58] pxar: bin: show padding in debug output on archive list Christian Ebner
2024-06-05 10:53 ` [pbs-devel] [PATCH v9 proxmox-backup 40/58] pxar: bin: ignore version and prelude entries in listing Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 42/58] pxar: bin: support creation of split pxar archives via cli Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 43/58] pxar: add optional payload input to mount archive Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 44/58] datastore: chunker: add Chunker trait Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 45/58] datastore: chunker: implement chunker for payload stream Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 46/58] chunker: tests: add regression tests for payload chunker Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 47/58] chunk stream: " Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 48/58] client: chunk stream: switch payload stream chunker Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 49/58] client: pxar: add archive creation with reference test Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 50/58] client: tools: add helper to raise nofile rlimit Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 51/58] client: pxar: set cache limit based on " Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 52/58] api: datastore: add endpoint to lookup entries via pxar archive Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 53/58] api: datastore: add optional archive-name to file-restore Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 54/58] www: content: lookup via metadata archive instead of catalog Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 55/58] docs: file formats: describe split pxar archive file layout Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 56/58] docs: add section describing change detection mode Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 57/58] test-suite: add detection mode change benchmark Christian Ebner
2024-06-05 10:54 ` [pbs-devel] [PATCH v9 proxmox-backup 58/58] test-suite: Makefile: add debian package and related files Christian Ebner
2024-06-06  6:47 ` [pbs-devel] partially-applied: [PATCH v9 proxmox-backup 00/58] fix #3174: improve file-level backup Fabian Grünbichler

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240605105416.278748-4-c.ebner@proxmox.com \
    --to=c.ebner@proxmox.com \
    --cc=pbs-devel@lists.proxmox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Service provided by Proxmox Server Solutions GmbH | Privacy | Legal