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 A3BCDBC01A for ; Thu, 28 Mar 2024 13:37:40 +0100 (CET) Received: from firstgate.proxmox.com (localhost [127.0.0.1]) by firstgate.proxmox.com (Proxmox) with ESMTP id A248F9D78 for ; Thu, 28 Mar 2024 13:37:38 +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 13:37:36 +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 C2787428E6 for ; Thu, 28 Mar 2024 13:37:36 +0100 (CET) From: Christian Ebner To: pbs-devel@lists.proxmox.com Date: Thu, 28 Mar 2024 13:36:17 +0100 Message-Id: <20240328123707.336951-9-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 0.031 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 pxar 08/58] encoder: add payload reference capability 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 12:37:40 -0000 Allows to encode regular files with a payload reference within a separate payload archive rather than encoding the payload within the regular archive. Following the PXAR_PAYLOAD_REF marked header, the payload offset and size are encoded. Signed-off-by: Christian Ebner --- changes since version 2: - Add additional consistency check for current payload position - Use PayloadRefs `data` for encoding - Fixed incorrect comments src/encoder/aio.rs | 18 ++++++++++++++- src/encoder/mod.rs | 54 +++++++++++++++++++++++++++++++++++++++++++++ src/encoder/sync.rs | 21 +++++++++++++++++- 3 files changed, 91 insertions(+), 2 deletions(-) diff --git a/src/encoder/aio.rs b/src/encoder/aio.rs index 635e550..17ade7d 100644 --- a/src/encoder/aio.rs +++ b/src/encoder/aio.rs @@ -5,7 +5,7 @@ use std::path::Path; use std::pin::Pin; use std::task::{Context, Poll}; -use crate::encoder::{self, LinkOffset, SeqWrite}; +use crate::encoder::{self, LinkOffset, PayloadOffset, SeqWrite}; use crate::format; use crate::Metadata; @@ -103,6 +103,22 @@ impl<'a, T: SeqWrite + 'a> Encoder<'a, T> { // ).await // } + /// Encode a payload reference pointing to given offset in the separate payload output + /// + /// Returns with error if the encoder instance has no separate payload output or encoding + /// failed. + pub async fn add_payload_ref( + &mut self, + metadata: &Metadata, + file_name: &Path, + file_size: u64, + payload_offset: PayloadOffset, + ) -> io::Result<()> { + self.inner + .add_payload_ref(metadata, file_name.as_ref(), file_size, payload_offset) + .await + } + /// Create a new subdirectory. Note that the subdirectory has to be finished by calling the /// `finish()` method, otherwise the entire archive will be in an error state. pub async fn create_directory>( diff --git a/src/encoder/mod.rs b/src/encoder/mod.rs index 31bb0fa..fcd636d 100644 --- a/src/encoder/mod.rs +++ b/src/encoder/mod.rs @@ -38,6 +38,24 @@ impl LinkOffset { } } +/// File reference used to create payload references. +#[derive(Clone, Copy, Debug, Default, Eq, PartialEq, Ord, PartialOrd)] +pub struct PayloadOffset(u64); + +impl PayloadOffset { + /// Get the raw byte offset of this link. + #[inline] + pub fn raw(self) -> u64 { + self.0 + } + + /// Return a new PayloadOffset, positively shifted by offset + #[inline] + pub fn add(&self, offset: u64) -> Self { + Self(self.0 + offset) + } +} + /// Sequential write interface used by the encoder's state machine. /// /// This is our internal writer trait which is available for `std::io::Write` types in the @@ -485,6 +503,42 @@ impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> { Ok(offset) } + /// Encode a payload reference pointing to given offset in the separate payload output + /// + /// Returns with error if the encoder instance has no separate payload output or encoding + /// failed. + pub async fn add_payload_ref( + &mut self, + metadata: &Metadata, + file_name: &Path, + file_size: u64, + payload_offset: PayloadOffset, + ) -> io::Result<()> { + if self.payload_output.as_mut().is_none() { + io_bail!("unable to add payload reference"); + } + + let offset = payload_offset.raw(); + let payload_position = self.state()?.payload_position(); + if offset < payload_position { + io_bail!("offset smaller than current position: {offset} < {payload_position}"); + } + + let payload_ref = PayloadRef { + offset, + size: file_size, + }; + let _this_offset: LinkOffset = self + .add_file_entry( + Some(metadata), + file_name, + Some((format::PXAR_PAYLOAD_REF, &payload_ref.data())), + ) + .await?; + + Ok(()) + } + /// Return a file offset usable with `add_hardlink`. pub async fn add_symlink( &mut self, diff --git a/src/encoder/sync.rs b/src/encoder/sync.rs index d0d62ba..48942b9 100644 --- a/src/encoder/sync.rs +++ b/src/encoder/sync.rs @@ -6,7 +6,7 @@ use std::pin::Pin; use std::task::{Context, Poll}; use crate::decoder::sync::StandardReader; -use crate::encoder::{self, LinkOffset, SeqWrite}; +use crate::encoder::{self, LinkOffset, PayloadOffset, SeqWrite}; use crate::format; use crate::util::poll_result_once; use crate::Metadata; @@ -100,6 +100,25 @@ impl<'a, T: SeqWrite + 'a> Encoder<'a, T> { )) } + /// Encode a payload reference pointing to given offset in the separate payload output + /// + /// Returns with error if the encoder instance has no separate payload output or encoding + /// failed. + pub async fn add_payload_ref( + &mut self, + metadata: &Metadata, + file_name: &Path, + file_size: u64, + payload_offset: PayloadOffset, + ) -> io::Result<()> { + poll_result_once(self.inner.add_payload_ref( + metadata, + file_name.as_ref(), + file_size, + payload_offset, + )) + } + /// Create a new subdirectory. Note that the subdirectory has to be finished by calling the /// `finish()` method, otherwise the entire archive will be in an error state. pub fn create_directory>( -- 2.39.2