From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <pbs-devel-bounces@lists.proxmox.com>
Received: from firstgate.proxmox.com (firstgate.proxmox.com [IPv6:2a01:7e0:0:424::9])
	by lore.proxmox.com (Postfix) with ESMTPS id E057020EC9A
	for <inbox@lore.proxmox.com>; Mon, 29 Apr 2024 14:12:04 +0200 (CEST)
Received: from firstgate.proxmox.com (localhost [127.0.0.1])
	by firstgate.proxmox.com (Proxmox) with ESMTP id 114C6FEC2;
	Mon, 29 Apr 2024 14:12:10 +0200 (CEST)
From: Christian Ebner <c.ebner@proxmox.com>
To: pbs-devel@lists.proxmox.com
Date: Mon, 29 Apr 2024 14:10:48 +0200
Message-Id: <20240429121102.315059-45-c.ebner@proxmox.com>
X-Mailer: git-send-email 2.39.2
In-Reply-To: <20240429121102.315059-1-c.ebner@proxmox.com>
References: <20240429121102.315059-1-c.ebner@proxmox.com>
MIME-Version: 1.0
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 v4 proxmox-backup 44/58] 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
 <pbs-devel.lists.proxmox.com>
List-Unsubscribe: <https://lists.proxmox.com/cgi-bin/mailman/options/pbs-devel>, 
 <mailto:pbs-devel-request@lists.proxmox.com?subject=unsubscribe>
List-Archive: <http://lists.proxmox.com/pipermail/pbs-devel/>
List-Post: <mailto:pbs-devel@lists.proxmox.com>
List-Help: <mailto:pbs-devel-request@lists.proxmox.com?subject=help>
List-Subscribe: <https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel>, 
 <mailto:pbs-devel-request@lists.proxmox.com?subject=subscribe>
Reply-To: Proxmox Backup Server development discussion
 <pbs-devel@lists.proxmox.com>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Errors-To: pbs-devel-bounces@lists.proxmox.com
Sender: "pbs-devel" <pbs-devel-bounces@lists.proxmox.com>

Add method to compare metadata of current file entry against metadata
of the entry looked up in the previous backup snapshot. If the
metadata matched, the start offset pointing to the files payload
header in the payload steam is returned.

This is in preparation for reusing payload chunks for unchanged files.

Signed-off-by: Christian Ebner <c.ebner@proxmox.com>
---
 pbs-client/src/pxar/create.rs | 34 +++++++++++++++++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/pbs-client/src/pxar/create.rs b/pbs-client/src/pxar/create.rs
index 979c7b2a8..bb2a4f42a 100644
--- a/pbs-client/src/pxar/create.rs
+++ b/pbs-client/src/pxar/create.rs
@@ -2,6 +2,7 @@ use std::collections::{HashMap, HashSet};
 use std::ffi::{CStr, CString, OsStr};
 use std::fmt;
 use std::io::{self, Read};
+use std::mem::size_of;
 use std::ops::Range;
 use std::os::unix::ffi::OsStrExt;
 use std::os::unix::io::{AsRawFd, FromRawFd, IntoRawFd, OwnedFd, RawFd};
@@ -20,7 +21,7 @@ use pathpatterns::{MatchEntry, MatchFlag, MatchList, MatchType, PatternFlag};
 use proxmox_sys::error::SysError;
 use pxar::accessor::aio::{Accessor, Directory};
 use pxar::encoder::{LinkOffset, SeqWrite};
-use pxar::Metadata;
+use pxar::{EntryKind, Metadata};
 
 use proxmox_io::vec;
 use proxmox_lang::c_str;
@@ -342,6 +343,37 @@ impl Archiver {
         .boxed()
     }
 
+    async fn is_reusable_entry(
+        &mut self,
+        previous_metadata_accessor: &mut Directory<LocalDynamicReadAt<RemoteChunkReader>>,
+        file_name: &Path,
+        metadata: &Metadata,
+    ) -> Result<Option<Range<u64>>, Error> {
+        if let Some(file_entry) = previous_metadata_accessor.lookup(file_name).await? {
+            if metadata == file_entry.metadata() {
+                if let EntryKind::File {
+                    payload_offset: Some(offset),
+                    size,
+                    ..
+                } = file_entry.entry().kind()
+                {
+                    let range = *offset..*offset + size + size_of::<pxar::format::Header>() as u64;
+                    log::debug!(
+                        "reusable: {file_name:?} at range {range:?} has unchanged metadata."
+                    );
+                    return Ok(Some(range));
+                }
+                log::debug!("reencode: {file_name:?} not a regular file.");
+                return Ok(None);
+            }
+            log::debug!("reencode: {file_name:?} metadata did not match.");
+            return Ok(None);
+        }
+
+        log::debug!("reencode: {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



_______________________________________________
pbs-devel mailing list
pbs-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel