From: Christian Ebner <c.ebner@proxmox.com>
To: pbs-devel@lists.proxmox.com
Subject: [pbs-devel] [PATCH proxmox-backup 08/17] verify/datastore: make rename corrupt chunk a datastore helper method
Date: Mon,  3 Nov 2025 12:31:11 +0100	[thread overview]
Message-ID: <20251103113120.239455-9-c.ebner@proxmox.com> (raw)
In-Reply-To: <20251103113120.239455-1-c.ebner@proxmox.com>
By making the rename a helper of the datastore, within this method it
will become possible to access the inner chunk store for locking.
That will be required to correctly lock the store to avoid concurrent
chunk inserts and garbage collection operations during the rename, to
guarantee consistency on datastores with s3 backend.
This is a preparatory patch, no functional changes intended.
Signed-off-by: Christian Ebner <c.ebner@proxmox.com>
---
 pbs-datastore/src/datastore.rs | 70 +++++++++++++++++++++++++++++++
 src/backup/verify.rs           | 75 +---------------------------------
 2 files changed, 72 insertions(+), 73 deletions(-)
diff --git a/pbs-datastore/src/datastore.rs b/pbs-datastore/src/datastore.rs
index 9008d8fc6..ebfbf5229 100644
--- a/pbs-datastore/src/datastore.rs
+++ b/pbs-datastore/src/datastore.rs
@@ -2567,4 +2567,74 @@ impl DataStore {
             .map_err(|err| format_err!("unable to update manifest blob - {err}"))?;
         Ok(())
     }
+
+    pub fn rename_corrupt_chunk(&self, digest: &[u8; 32]) {
+        let (path, digest_str) = self.chunk_path(digest);
+
+        let mut counter = 0;
+        let mut new_path = path.clone();
+        loop {
+            new_path.set_file_name(format!("{}.{}.bad", digest_str, counter));
+            if new_path.exists() && counter < 9 {
+                counter += 1;
+            } else {
+                break;
+            }
+        }
+
+        let backend = match self.backend() {
+            Ok(backend) => backend,
+            Err(err) => {
+                info!(
+                    "failed to get backend while trying to rename bad chunk: {digest_str} - {err}"
+                );
+                return;
+            }
+        };
+
+        if let DatastoreBackend::S3(s3_client) = backend {
+            let suffix = format!(".{}.bad", counter);
+            let target_key = match crate::s3::object_key_from_digest_with_suffix(digest, &suffix) {
+                Ok(target_key) => target_key,
+                Err(err) => {
+                    info!("could not generate target key for corrupt chunk {path:?} - {err}");
+                    return;
+                }
+            };
+            let object_key = match crate::s3::object_key_from_digest(digest) {
+                Ok(object_key) => object_key,
+                Err(err) => {
+                    info!("could not generate object key for corrupt chunk {path:?} - {err}");
+                    return;
+                }
+            };
+            if proxmox_async::runtime::block_on(
+                s3_client.copy_object(object_key.clone(), target_key),
+            )
+            .is_ok()
+            {
+                if proxmox_async::runtime::block_on(s3_client.delete_object(object_key)).is_err() {
+                    info!("failed to delete corrupt chunk on s3 backend: {digest_str}");
+                }
+            } else {
+                info!("failed to copy corrupt chunk on s3 backend: {digest_str}");
+                // Early return to leave the potentially locally cached chunk in the same state as
+                // on the object store. Verification might have failed because of connection issue
+                // after all.
+                return;
+            }
+        }
+
+        match std::fs::rename(&path, &new_path) {
+            Ok(_) => {
+                info!("corrupt chunk renamed to {:?}", &new_path);
+            }
+            Err(err) => {
+                match err.kind() {
+                    std::io::ErrorKind::NotFound => { /* ignored */ }
+                    _ => info!("could not rename corrupt chunk {:?} - {err}", &path),
+                }
+            }
+        };
+    }
 }
diff --git a/src/backup/verify.rs b/src/backup/verify.rs
index df77d177b..7fac46e18 100644
--- a/src/backup/verify.rs
+++ b/src/backup/verify.rs
@@ -76,77 +76,6 @@ impl VerifyWorker {
         }
     }
 
-    fn rename_corrupt_chunk(datastore: Arc<DataStore>, digest: &[u8; 32]) {
-        let (path, digest_str) = datastore.chunk_path(digest);
-
-        let mut counter = 0;
-        let mut new_path = path.clone();
-        loop {
-            new_path.set_file_name(format!("{digest_str}.{counter}.bad"));
-            if new_path.exists() && counter < 9 {
-                counter += 1;
-            } else {
-                break;
-            }
-        }
-
-        let backend = match datastore.backend() {
-            Ok(backend) => backend,
-            Err(err) => {
-                info!(
-                    "failed to get backend while trying to rename bad chunk: {digest_str} - {err}"
-                );
-                return;
-            }
-        };
-
-        if let DatastoreBackend::S3(s3_client) = backend {
-            let suffix = format!(".{counter}.bad");
-            let target_key =
-                match pbs_datastore::s3::object_key_from_digest_with_suffix(digest, &suffix) {
-                    Ok(target_key) => target_key,
-                    Err(err) => {
-                        info!("could not generate target key for corrupt chunk {path:?} - {err}");
-                        return;
-                    }
-                };
-            let object_key = match pbs_datastore::s3::object_key_from_digest(digest) {
-                Ok(object_key) => object_key,
-                Err(err) => {
-                    info!("could not generate object key for corrupt chunk {path:?} - {err}");
-                    return;
-                }
-            };
-            if proxmox_async::runtime::block_on(
-                s3_client.copy_object(object_key.clone(), target_key),
-            )
-            .is_ok()
-            {
-                if proxmox_async::runtime::block_on(s3_client.delete_object(object_key)).is_err() {
-                    info!("failed to delete corrupt chunk on s3 backend: {digest_str}");
-                }
-            } else {
-                info!("failed to copy corrupt chunk on s3 backend: {digest_str}");
-                // Early return to leave the potentially locally cached chunk in the same state as
-                // on the object store. Verification might have failed because of connection issue
-                // after all.
-                return;
-            }
-        }
-
-        match std::fs::rename(&path, &new_path) {
-            Ok(_) => {
-                info!("corrupt chunk renamed to {:?}", &new_path);
-            }
-            Err(err) => {
-                match err.kind() {
-                    std::io::ErrorKind::NotFound => { /* ignored */ }
-                    _ => info!("could not rename corrupt chunk {:?} - {err}", &path),
-                }
-            }
-        };
-    }
-
     fn verify_index_chunks(
         &self,
         index: Box<dyn IndexFile + Send>,
@@ -189,7 +118,7 @@ impl VerifyWorker {
                     corrupt_chunks2.lock().unwrap().insert(digest);
                     info!("{err}");
                     errors2.fetch_add(1, Ordering::SeqCst);
-                    Self::rename_corrupt_chunk(datastore2.clone(), &digest);
+                    datastore2.rename_corrupt_chunk(&digest);
                 } else {
                     verified_chunks2.lock().unwrap().insert(digest);
                 }
@@ -336,7 +265,7 @@ impl VerifyWorker {
         corrupt_chunks.insert(digest);
         error!(message);
         errors.fetch_add(1, Ordering::SeqCst);
-        Self::rename_corrupt_chunk(self.datastore.clone(), &digest);
+        self.datastore.rename_corrupt_chunk(&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
next prev parent reply	other threads:[~2025-11-03 11:31 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-03 11:31 [pbs-devel] [PATCH proxmox-backup 00/17] fix chunk upload/insert, rename corrupt chunks and GC race conditions for s3 backend Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 01/17] sync: pull: instantiate backend only once per sync job Christian Ebner
2025-11-03 14:51   ` Fabian Grünbichler
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 02/17] api/datastore: move group notes setting to the datastore Christian Ebner
2025-11-03 14:51   ` Fabian Grünbichler
2025-11-04  8:51     ` Christian Ebner
2025-11-04  9:13       ` Fabian Grünbichler
2025-11-04  9:37         ` Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 03/17] api/datastore: move snapshot deletion into dedicated datastore helper Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 04/17] api/datastore: move backup log upload by implementing " Christian Ebner
2025-11-03 14:51   ` Fabian Grünbichler
2025-11-04  8:47     ` Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 05/17] api/datastore: add dedicated datastore helper to set snapshot notes Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 06/17] datastore: refactor chunk insert based on backend Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 07/17] verify: rename corrupted to corrupt in log output and function names Christian Ebner
2025-11-03 11:31 ` Christian Ebner [this message]
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 09/17] datastore: refactor rename_corrupt_chunk error handling Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 10/17] datastore: implement per-chunk file locking helper for s3 backend Christian Ebner
2025-11-03 14:51   ` Fabian Grünbichler
2025-11-04  8:45     ` Christian Ebner
2025-11-04  9:01       ` Fabian Grünbichler
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 11/17] datastore: acquire chunk store mutex lock when renaming corrupt chunk Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 12/17] datastore: get per-chunk file lock for chunk rename on s3 backend Christian Ebner
2025-11-03 14:51   ` Fabian Grünbichler
2025-11-04  8:33     ` Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 13/17] fix #6961: datastore: verify: evict corrupt chunks from in-memory LRU cache Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 14/17] datastore: add locking to protect against races on chunk insert for s3 Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 15/17] GC: fix race with chunk upload/insert on s3 backends Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 16/17] GC: lock chunk marker before cleanup in phase 3 " Christian Ebner
2025-11-03 11:31 ` [pbs-devel] [PATCH proxmox-backup 17/17] datastore: GC: drop overly verbose info message during s3 chunk sweep Christian Ebner
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=20251103113120.239455-9-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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.