[pbs-devel] [PATCH v3 proxmox-backup 6/6] fix #5331: garbage collection: avoid multiple chunk atime updates

[Christian Ebner]

To reduce the number of atimes updates, keep track of the recently
marked chunks in phase 1 of garbage to avoid multiple atime updates
via expensive utimensat() calls.

Recently touched chunks are tracked by storing the chunk digests in
an LRU cache of fixed capacity. By inserting a digest, the chunk will
be the most recently touched one and if already present in the cache
before insert, the atime update can be skipped.

Fixes: https://bugzilla.proxmox.com/show_bug.cgi?id=5331
Signed-off-by: Christian Ebner <c.ebner at proxmox.com>
---
changes since version 2:
- Switch to LRU cache instead of keeping track of chunks from previous
  snapshot of the same group.

 pbs-datastore/src/datastore.rs | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/pbs-datastore/src/datastore.rs b/pbs-datastore/src/datastore.rs
index c4123f2b7..1f1c3b396 100644
--- a/pbs-datastore/src/datastore.rs
+++ b/pbs-datastore/src/datastore.rs
@@ -7,6 +7,7 @@ use std::sync::{Arc, LazyLock, Mutex};
 
 use anyhow::{bail, format_err, Context, Error};
 use nix::unistd::{unlinkat, UnlinkatFlags};
+use pbs_tools::lru_cache::LruCache;
 use tracing::{info, warn};
 
 use proxmox_human_byte::HumanByte;
@@ -1081,6 +1082,7 @@ impl DataStore {
         &self,
         index: Box<dyn IndexFile>,
         file_name: &Path, // only used for error reporting
+        recently_touched_chunks: &mut LruCache<[u8; 32], ()>,
         status: &mut GarbageCollectionStatus,
         worker: &dyn WorkerTaskContext,
     ) -> Result<(), Error> {
@@ -1091,6 +1093,12 @@ impl DataStore {
             worker.check_abort()?;
             worker.fail_on_shutdown()?;
             let digest = index.index_digest(pos).unwrap();
+
+            // Avoid multiple expensive atime updates by utimensat
+            if recently_touched_chunks.insert(*digest, ()) {
+                continue;
+            }
+
             if !self.inner.chunk_store.cond_touch_chunk(digest, false)? {
                 let hex = hex::encode(digest);
                 warn!(
@@ -1131,6 +1139,8 @@ impl DataStore {
         let mut unprocessed_image_list = self.list_images()?;
         let image_count = unprocessed_image_list.len();
 
+        // Allow up to 32 MiB, as only storing the 32 digest as key
+        let mut recently_touched_chunks = LruCache::new(1024 * 1024);
         let mut processed_images = 0;
         let mut last_percentage: usize = 0;
 
@@ -1157,7 +1167,13 @@ impl DataStore {
                             Some(index) => index,
                             None => continue,
                         };
-                        self.index_mark_used_chunks(index, &path, status, worker)?;
+                        self.index_mark_used_chunks(
+                            index,
+                            &path,
+                            &mut recently_touched_chunks,
+                            status,
+                            worker,
+                        )?;
 
                         unprocessed_image_list.remove(&path);
 
@@ -1184,7 +1200,13 @@ impl DataStore {
                 Some(index) => index,
                 None => continue,
             };
-            self.index_mark_used_chunks(index, &path, status, worker)?;
+            self.index_mark_used_chunks(
+                index,
+                &path,
+                &mut recently_touched_chunks,
+                status,
+                worker,
+            )?;
             warn!(
                 "Marked chunks for unexpected index file at '{}'",
                 path.to_string_lossy()
-- 
2.39.5