From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from firstgate.proxmox.com (firstgate.proxmox.com [212.224.123.68]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits)) (No client certificate requested) by lists.proxmox.com (Postfix) with ESMTPS id 95F31BC06A for ; Thu, 28 Mar 2024 13:38:06 +0100 (CET) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id 63A349FEF for ; Thu, 28 Mar 2024 13:37:48 +0100 (CET) Received: from proxmox-new.maurer-it.com (proxmox-new.maurer-it.com [94.136.29.106]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits)) (No client certificate requested) by firstgate.proxmox.com (Proxmox) with ESMTPS for ; Thu, 28 Mar 2024 13:37:46 +0100 (CET) Received: from proxmox-new.maurer-it.com (localhost.localdomain [127.0.0.1]) by proxmox-new.maurer-it.com (Proxmox) with ESMTP id 3853942A77 for ; Thu, 28 Mar 2024 13:37:46 +0100 (CET) From: Christian Ebner To: pbs-devel@lists.proxmox.com Date: Thu, 28 Mar 2024 13:36:54 +0100 Message-Id: <20240328123707.336951-46-c.ebner@proxmox.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20240328123707.336951-1-c.ebner@proxmox.com> References: <20240328123707.336951-1-c.ebner@proxmox.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-SPAM-LEVEL: Spam detection results: 0 AWL 0.029 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 v3 proxmox-backup 45/58] client: pxar: add method for metadata comparison 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: , X-List-Received-Date: Thu, 28 Mar 2024 12:38:06 -0000 Adds a method to compare the metadata of the current file entry against the metadata of the entry looked up in the previous backup snapshot. If the metadata matched, the start offset for the payload stream is returned. This is in preparation for reusing payload chunks for unchanged files. Signed-off-by: Christian Ebner --- changes since version 2: - refactored to new padding based threshold pbs-client/src/pxar/create.rs | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) diff --git a/pbs-client/src/pxar/create.rs b/pbs-client/src/pxar/create.rs index 79925bba2..c64084a74 100644 --- a/pbs-client/src/pxar/create.rs +++ b/pbs-client/src/pxar/create.rs @@ -21,7 +21,7 @@ use pbs_datastore::index::IndexFile; use proxmox_sys::error::SysError; use pxar::accessor::aio::{Accessor, Directory}; use pxar::encoder::{LinkOffset, PayloadOffset, SeqWrite}; -use pxar::Metadata; +use pxar::{EntryKind, Metadata}; use proxmox_io::vec; use proxmox_lang::c_str; @@ -466,6 +466,35 @@ impl Archiver { .boxed() } + async fn is_reusable_entry( + &mut self, + previous_metadata_accessor: &mut Directory>, + file_name: &Path, + stat: &FileStat, + metadata: &Metadata, + ) -> Result, Error> { + if stat.st_nlink > 1 { + log::debug!("re-encode: {file_name:?} has hardlinks."); + return Ok(None); + } + + if let Some(file_entry) = previous_metadata_accessor.lookup(file_name).await? { + if metadata == file_entry.metadata() { + if let EntryKind::File { payload_offset, .. } = file_entry.entry().kind() { + log::debug!("possible re-use: {file_name:?} at offset {payload_offset:?} has unchanged metadata."); + return Ok(*payload_offset); + } + log::debug!("re-encode: {file_name:?} not a regular file."); + return Ok(None); + } + log::debug!("re-encode: {file_name:?} metadata did not match."); + return Ok(None); + } + + log::debug!("re-encode: {file_name:?} not found in previous archive."); + Ok(None) + } + /// openat() wrapper which allows but logs `EACCES` and turns `ENOENT` into `None`. /// /// The `existed` flag is set when iterating through a directory to note that we know the file -- 2.39.2