[pbs-devel] [PATCH proxmox-backup 1/4] api: verify: move chunk loading into parallel handler

[Nicolas Frey <n.frey@proxmox.com>]

This way, the chunks will be loaded in parallel in addition to being
checked in parallel.

Depending on the underlying storage, this can speed up reading chunks
from disk, especially when the underlying storage is IO depth
dependent, and the CPU is faster than the storage.

Originally-by: Dominik Csapak <d.csapak@proxmox.com>
Signed-off-by: Nicolas Frey <n.frey@proxmox.com>
---
 src/backup/verify.rs | 120 +++++++++++++++++++++++++++----------------
 1 file changed, 75 insertions(+), 45 deletions(-)

diff --git a/src/backup/verify.rs b/src/backup/verify.rs
index e33fdf50..7f91f38c 100644
--- a/src/backup/verify.rs
+++ b/src/backup/verify.rs
@@ -1,6 +1,6 @@
 use pbs_config::BackupLockGuard;
 use std::collections::HashSet;
-use std::sync::atomic::{AtomicUsize, Ordering};
+use std::sync::atomic::{AtomicU64, AtomicUsize, Ordering};
 use std::sync::{Arc, Mutex};
 use std::time::Instant;
 
@@ -20,7 +20,7 @@ use pbs_datastore::index::{ChunkReadInfo, IndexFile};
 use pbs_datastore::manifest::{BackupManifest, FileInfo};
 use pbs_datastore::{DataBlob, DataStore, DatastoreBackend, StoreProgress};
 
-use crate::tools::parallel_handler::ParallelHandler;
+use crate::tools::parallel_handler::{ParallelHandler, SendHandle};
 
 use crate::backup::hierarchy::ListAccessibleBackupGroups;
 
@@ -156,23 +156,20 @@ impl VerifyWorker {
 
         let start_time = Instant::now();
 
-        let mut read_bytes = 0;
-        let mut decoded_bytes = 0;
+        let read_bytes = Arc::new(AtomicU64::new(0));
+        let decoded_bytes = Arc::new(AtomicU64::new(0));
 
-        let datastore2 = Arc::clone(&self.datastore);
-        let corrupt_chunks2 = Arc::clone(&self.corrupt_chunks);
-        let verified_chunks2 = Arc::clone(&self.verified_chunks);
-        let errors2 = Arc::clone(&errors);
-
-        let decoder_pool = ParallelHandler::new(
-            "verify chunk decoder",
-            4,
+        let decoder_pool = ParallelHandler::new("verify chunk decoder", 4, {
+            let datastore = Arc::clone(&self.datastore);
+            let corrupt_chunks = Arc::clone(&self.corrupt_chunks);
+            let verified_chunks = Arc::clone(&self.verified_chunks);
+            let errors = Arc::clone(&errors);
             move |(chunk, digest, size): (DataBlob, [u8; 32], u64)| {
                 let chunk_crypt_mode = match chunk.crypt_mode() {
                     Err(err) => {
-                        corrupt_chunks2.lock().unwrap().insert(digest);
+                        corrupt_chunks.lock().unwrap().insert(digest);
                         info!("can't verify chunk, unknown CryptMode - {err}");
-                        errors2.fetch_add(1, Ordering::SeqCst);
+                        errors.fetch_add(1, Ordering::SeqCst);
                         return Ok(());
                     }
                     Ok(mode) => mode,
@@ -182,21 +179,21 @@ impl VerifyWorker {
                     info!(
                     "chunk CryptMode {chunk_crypt_mode:?} does not match index CryptMode {crypt_mode:?}"
                 );
-                    errors2.fetch_add(1, Ordering::SeqCst);
+                    errors.fetch_add(1, Ordering::SeqCst);
                 }
 
                 if let Err(err) = chunk.verify_unencrypted(size as usize, &digest) {
-                    corrupt_chunks2.lock().unwrap().insert(digest);
+                    corrupt_chunks.lock().unwrap().insert(digest);
                     info!("{err}");
-                    errors2.fetch_add(1, Ordering::SeqCst);
-                    Self::rename_corrupted_chunk(datastore2.clone(), &digest);
+                    errors.fetch_add(1, Ordering::SeqCst);
+                    Self::rename_corrupted_chunk(datastore.clone(), &digest);
                 } else {
-                    verified_chunks2.lock().unwrap().insert(digest);
+                    verified_chunks.lock().unwrap().insert(digest);
                 }
 
                 Ok(())
-            },
-        );
+            }
+        });
 
         let skip_chunk = |digest: &[u8; 32]| -> bool {
             if self.verified_chunks.lock().unwrap().contains(digest) {
@@ -223,6 +220,29 @@ impl VerifyWorker {
             .datastore
             .get_chunks_in_order(&*index, skip_chunk, check_abort)?;
 
+        let reader_pool = ParallelHandler::new("read chunks", 4, {
+            let decoder_pool = decoder_pool.channel();
+            let datastore = Arc::clone(&self.datastore);
+            let corrupt_chunks = Arc::clone(&self.corrupt_chunks);
+            let read_bytes = Arc::clone(&read_bytes);
+            let decoded_bytes = Arc::clone(&decoded_bytes);
+            let errors = Arc::clone(&errors);
+            let backend = self.backend.clone();
+
+            move |info: ChunkReadInfo| {
+                Self::verify_chunk_by_backend(
+                    &backend,
+                    Arc::clone(&datastore),
+                    Arc::clone(&corrupt_chunks),
+                    Arc::clone(&read_bytes),
+                    Arc::clone(&decoded_bytes),
+                    Arc::clone(&errors),
+                    &decoder_pool,
+                    &info,
+                )
+            }
+        });
+
         for (pos, _) in chunk_list {
             self.worker.check_abort()?;
             self.worker.fail_on_shutdown()?;
@@ -234,19 +254,16 @@ impl VerifyWorker {
                 continue; // already verified or marked corrupt
             }
 
-            self.verify_chunk_by_backend(
-                &info,
-                &mut read_bytes,
-                &mut decoded_bytes,
-                Arc::clone(&errors),
-                &decoder_pool,
-            )?;
+            reader_pool.send(info)?;
         }
 
-        decoder_pool.complete()?;
+        reader_pool.complete()?;
 
         let elapsed = start_time.elapsed().as_secs_f64();
 
+        let read_bytes = read_bytes.load(Ordering::SeqCst);
+        let decoded_bytes = decoded_bytes.load(Ordering::SeqCst);
+
         let read_bytes_mib = (read_bytes as f64) / (1024.0 * 1024.0);
         let decoded_bytes_mib = (decoded_bytes as f64) / (1024.0 * 1024.0);
 
@@ -266,26 +283,31 @@ impl VerifyWorker {
         Ok(())
     }
 
+    #[allow(clippy::too_many_arguments)]
     fn verify_chunk_by_backend(
-        &self,
-        info: &ChunkReadInfo,
-        read_bytes: &mut u64,
-        decoded_bytes: &mut u64,
+        backend: &DatastoreBackend,
+        datastore: Arc<DataStore>,
+        corrupt_chunks: Arc<Mutex<HashSet<[u8; 32]>>>,
+        read_bytes: Arc<AtomicU64>,
+        decoded_bytes: Arc<AtomicU64>,
         errors: Arc<AtomicUsize>,
-        decoder_pool: &ParallelHandler<(DataBlob, [u8; 32], u64)>,
+        decoder_pool: &SendHandle<(DataBlob, [u8; 32], u64)>,
+        info: &ChunkReadInfo,
     ) -> Result<(), Error> {
-        match &self.backend {
-            DatastoreBackend::Filesystem => match self.datastore.load_chunk(&info.digest) {
-                Err(err) => self.add_corrupt_chunk(
+        match backend {
+            DatastoreBackend::Filesystem => match datastore.load_chunk(&info.digest) {
+                Err(err) => Self::add_corrupt_chunk(
+                    datastore,
+                    corrupt_chunks,
                     info.digest,
                     errors,
                     &format!("can't verify chunk, load failed - {err}"),
                 ),
                 Ok(chunk) => {
                     let size = info.size();
-                    *read_bytes += chunk.raw_size();
+                    read_bytes.fetch_add(chunk.raw_size(), Ordering::SeqCst);
                     decoder_pool.send((chunk, info.digest, size))?;
-                    *decoded_bytes += size;
+                    decoded_bytes.fetch_add(size, Ordering::SeqCst);
                 }
             },
             DatastoreBackend::S3(s3_client) => {
@@ -302,9 +324,9 @@ impl VerifyWorker {
                         match chunk_result {
                             Ok(chunk) => {
                                 let size = info.size();
-                                *read_bytes += chunk.raw_size();
+                                read_bytes.fetch_add(chunk.raw_size(), Ordering::SeqCst);
                                 decoder_pool.send((chunk, info.digest, size))?;
-                                *decoded_bytes += size;
+                                decoded_bytes.fetch_add(size, Ordering::SeqCst);
                             }
                             Err(err) => {
                                 errors.fetch_add(1, Ordering::SeqCst);
@@ -312,7 +334,9 @@ impl VerifyWorker {
                             }
                         }
                     }
-                    Ok(None) => self.add_corrupt_chunk(
+                    Ok(None) => Self::add_corrupt_chunk(
+                        datastore,
+                        corrupt_chunks,
                         info.digest,
                         errors,
                         &format!(
@@ -330,13 +354,19 @@ impl VerifyWorker {
         Ok(())
     }
 
-    fn add_corrupt_chunk(&self, digest: [u8; 32], errors: Arc<AtomicUsize>, message: &str) {
+    fn add_corrupt_chunk(
+        datastore: Arc<DataStore>,
+        corrupt_chunks: Arc<Mutex<HashSet<[u8; 32]>>>,
+        digest: [u8; 32],
+        errors: Arc<AtomicUsize>,
+        message: &str,
+    ) {
         // Panic on poisoned mutex
-        let mut corrupt_chunks = self.corrupt_chunks.lock().unwrap();
+        let mut corrupt_chunks = corrupt_chunks.lock().unwrap();
         corrupt_chunks.insert(digest);
         error!(message);
         errors.fetch_add(1, Ordering::SeqCst);
-        Self::rename_corrupted_chunk(self.datastore.clone(), &digest);
+        Self::rename_corrupted_chunk(datastore.clone(), &digest);
     }
 
     fn verify_fixed_index(&self, backup_dir: &BackupDir, info: &FileInfo) -> Result<(), Error> {
-- 
2.47.3


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