[pbs-devel] [RFC PATCH proxmox-backup 2/3] verify: move chunk loading into parallel handler

[Dominik Csapak]

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.

In my local tests I measured the following speed difference:
verified a single snapshot with ~64 GiB (4x the RAM size) with 12 cores

current:    ~550MiB/s
this patch: ~950MiB/s

Obviously it increased the IO and CPU load in line with the throughput.

Signed-off-by: Dominik Csapak <d.csapak at proxmox.com>
---
 src/backup/verify.rs | 48 +++++++++++++++++++++++---------------------
 1 file changed, 25 insertions(+), 23 deletions(-)

diff --git a/src/backup/verify.rs b/src/backup/verify.rs
index ba4ca4d2f..83dd0d9a3 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;
 
@@ -17,7 +17,7 @@ use pbs_api_types::{
 use pbs_datastore::backup_info::{BackupDir, BackupGroup, BackupInfo};
 use pbs_datastore::index::IndexFile;
 use pbs_datastore::manifest::{BackupManifest, FileInfo};
-use pbs_datastore::{DataBlob, DataStore, StoreProgress};
+use pbs_datastore::{DataStore, StoreProgress};
 
 use crate::tools::parallel_handler::ParallelHandler;
 
@@ -106,16 +106,32 @@ fn verify_index_chunks(
 
     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 decoder_pool = ParallelHandler::new("verify chunk decoder", 4, {
         let datastore = Arc::clone(&verify_worker.datastore);
         let corrupt_chunks = Arc::clone(&verify_worker.corrupt_chunks);
         let verified_chunks = Arc::clone(&verify_worker.verified_chunks);
         let errors = Arc::clone(&errors);
+        let read_bytes = Arc::clone(&read_bytes);
+        let decoded_bytes = Arc::clone(&decoded_bytes);
 
-        move |(chunk, digest, size): (DataBlob, [u8; 32], u64)| {
+        move |(digest, size): ([u8; 32], u64)| {
+            let chunk = match datastore.load_chunk(&digest) {
+                Err(err) => {
+                    corrupt_chunks.lock().unwrap().insert(digest);
+                    error!("can't verify chunk, load failed - {err}");
+                    errors.fetch_add(1, Ordering::SeqCst);
+                    rename_corrupted_chunk(datastore.clone(), &digest);
+                    return Ok(());
+                }
+                Ok(chunk) => {
+                    read_bytes.fetch_add(chunk.raw_size(), Ordering::SeqCst);
+                    decoded_bytes.fetch_add(size, Ordering::SeqCst);
+                    chunk
+                }
+            };
             let chunk_crypt_mode = match chunk.crypt_mode() {
                 Err(err) => {
                     corrupt_chunks.lock().unwrap().insert(digest);
@@ -193,30 +209,16 @@ fn verify_index_chunks(
             continue; // already verified or marked corrupt
         }
 
-        match verify_worker.datastore.load_chunk(&info.digest) {
-            Err(err) => {
-                verify_worker
-                    .corrupt_chunks
-                    .lock()
-                    .unwrap()
-                    .insert(info.digest);
-                error!("can't verify chunk, load failed - {err}");
-                errors.fetch_add(1, Ordering::SeqCst);
-                rename_corrupted_chunk(verify_worker.datastore.clone(), &info.digest);
-            }
-            Ok(chunk) => {
-                let size = info.size();
-                read_bytes += chunk.raw_size();
-                decoder_pool.send((chunk, info.digest, size))?;
-                decoded_bytes += size;
-            }
-        }
+        decoder_pool.send((info.digest, info.size()))?;
     }
 
     decoder_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);
 
-- 
2.39.5