From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from firstgate.proxmox.com (firstgate.proxmox.com [IPv6:2a01:7e0:0:424::9]) by lore.proxmox.com (Postfix) with ESMTPS id DC1E61FF17E for ; Thu, 16 Oct 2025 15:18:29 +0200 (CEST) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id EC55813C0D; Thu, 16 Oct 2025 15:18:42 +0200 (CEST) From: Christian Ebner To: pbs-devel@lists.proxmox.com Date: Thu, 16 Oct 2025 15:18:14 +0200 Message-ID: <20251016131819.349049-2-c.ebner@proxmox.com> X-Mailer: git-send-email 2.47.3 In-Reply-To: <20251016131819.349049-1-c.ebner@proxmox.com> References: <20251016131819.349049-1-c.ebner@proxmox.com> MIME-Version: 1.0 X-Bm-Milter-Handled: 55990f41-d878-4baa-be0a-ee34c49e34d2 X-Bm-Transport-Timestamp: 1760620713940 X-SPAM-LEVEL: Spam detection results: 0 AWL 0.042 Adjusted score from AWL reputation of From: address BAYES_00 -1.9 Bayes spam probability is 0 to 1% DMARC_MISSING 0.1 Missing DMARC policy KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment SPF_HELO_NONE 0.001 SPF: HELO does not publish an SPF Record SPF_PASS -0.001 SPF: sender matches SPF record Subject: [pbs-devel] [PATCH proxmox-backup 1/6] verify/datastore: make rename corrupt chunk a datastore helper method X-BeenThere: pbs-devel@lists.proxmox.com X-Mailman-Version: 2.1.29 Precedence: list List-Id: Proxmox Backup Server development discussion List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: Proxmox Backup Server development discussion Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: pbs-devel-bounces@lists.proxmox.com Sender: "pbs-devel" By making this a helper of the datastore, within this method it will become possible to access the inner chunk store for locking ecc. 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. Signed-off-by: Christian Ebner --- 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 038306166..802a39536 100644 --- a/pbs-datastore/src/datastore.rs +++ b/pbs-datastore/src/datastore.rs @@ -2418,4 +2418,74 @@ impl DataStore { .map_err(|err| format_err!("{err:#}"))?; Ok((backend_type, Some(s3_client))) } + + pub fn rename_corrupted_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 corrupted 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 corrupted 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!("corrupted chunk renamed to {:?}", &new_path); + } + Err(err) => { + match err.kind() { + std::io::ErrorKind::NotFound => { /* ignored */ } + _ => info!("could not rename corrupted chunk {:?} - {err}", &path), + } + } + }; + } } diff --git a/src/backup/verify.rs b/src/backup/verify.rs index bdbe3148b..92d3d9c49 100644 --- a/src/backup/verify.rs +++ b/src/backup/verify.rs @@ -76,77 +76,6 @@ impl VerifyWorker { } } - fn rename_corrupted_chunk(datastore: Arc, 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!("{}.{}.bad", digest_str, counter)); - 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!(".{}.bad", counter); - 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 corrupted 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 corrupted 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!("corrupted chunk renamed to {:?}", &new_path); - } - Err(err) => { - match err.kind() { - std::io::ErrorKind::NotFound => { /* ignored */ } - _ => info!("could not rename corrupted chunk {:?} - {err}", &path), - } - } - }; - } - fn verify_index_chunks( &self, index: Box, @@ -189,7 +118,7 @@ impl VerifyWorker { corrupt_chunks2.lock().unwrap().insert(digest); info!("{err}"); errors2.fetch_add(1, Ordering::SeqCst); - Self::rename_corrupted_chunk(datastore2.clone(), &digest); + datastore2.rename_corrupted_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_corrupted_chunk(self.datastore.clone(), &digest); + self.datastore.rename_corrupted_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