From mboxrd@z Thu Jan 1 00:00:00 1970
Return-Path: <d.csapak@proxmox.com>
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 1437CCA7E
for <pbs-devel@lists.proxmox.com>; Tue, 12 Apr 2022 13:04:22 +0200 (CEST)
Received: from firstgate.proxmox.com (localhost [127.0.0.1])
by firstgate.proxmox.com (Proxmox) with ESMTP id 12439DC4D
for <pbs-devel@lists.proxmox.com>; Tue, 12 Apr 2022 13:04:22 +0200 (CEST)
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 id 674D1DC1C
for <pbs-devel@lists.proxmox.com>; Tue, 12 Apr 2022 13:04:19 +0200 (CEST)
Received: from proxmox-new.maurer-it.com (localhost.localdomain [127.0.0.1])
by proxmox-new.maurer-it.com (Proxmox) with ESMTP id 3FF55413F8
for <pbs-devel@lists.proxmox.com>; Tue, 12 Apr 2022 13:04:19 +0200 (CEST)
From: Dominik Csapak <d.csapak@proxmox.com>
To: pbs-devel@lists.proxmox.com
Date: Tue, 12 Apr 2022 13:04:14 +0200
Message-Id: <20220412110418.3360746-3-d.csapak@proxmox.com>
X-Mailer: git-send-email 2.30.2
In-Reply-To: <20220412110418.3360746-1-d.csapak@proxmox.com>
References: <20220412110418.3360746-1-d.csapak@proxmox.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
X-SPAM-LEVEL: Spam detection results: 0
AWL 0.139 Adjusted score from AWL reputation of From: address
BAYES_00 -1.9 Bayes spam probability is 0 to 1%
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
T_SCC_BODY_TEXT_LINE -0.01 -
URIBL_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to URIBL was blocked. See
http://wiki.apache.org/spamassassin/DnsBlocklists#dnsbl-block for more
information. [zstd.rs, lib.rs]
Subject: [pbs-devel] [PATCH proxmox 2/2] proxmox-compression: add streaming
zstd encoder
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>
X-List-Received-Date: Tue, 12 Apr 2022 11:04:22 -0000
similar to our DeflateEncoder, takes a Stream and implements it itself,
so that we can use it as an adapter for async api calls
Signed-off-by: Dominik Csapak <d.csapak@proxmox.com>
---
proxmox-compression/Cargo.toml | 1 +
proxmox-compression/src/lib.rs | 1 +
proxmox-compression/src/zstd.rs | 126 ++++++++++++++++++++++++++++++++
3 files changed, 128 insertions(+)
create mode 100644 proxmox-compression/src/zstd.rs
diff --git a/proxmox-compression/Cargo.toml b/proxmox-compression/Cargo.toml
index c3f7f49..5ca67b2 100644
--- a/proxmox-compression/Cargo.toml
+++ b/proxmox-compression/Cargo.toml
@@ -18,6 +18,7 @@ futures = "0.3"
tokio = { version = "1.6", features = [ "fs", "io-util"] }
walkdir = "2"
tar = "0.4"
+zstd = { version = "0.6", features = []}
proxmox-time = { path = "../proxmox-time", version = "1" }
proxmox-io = { path = "../proxmox-io", version = "1", features = [ "tokio" ] }
diff --git a/proxmox-compression/src/lib.rs b/proxmox-compression/src/lib.rs
index e9dd113..1fcfb97 100644
--- a/proxmox-compression/src/lib.rs
+++ b/proxmox-compression/src/lib.rs
@@ -3,3 +3,4 @@ pub use compression::*;
pub mod tar;
pub mod zip;
+pub mod zstd;
diff --git a/proxmox-compression/src/zstd.rs b/proxmox-compression/src/zstd.rs
new file mode 100644
index 0000000..0b480f6
--- /dev/null
+++ b/proxmox-compression/src/zstd.rs
@@ -0,0 +1,126 @@
+//! zstd helper
+use std::io;
+use std::pin::Pin;
+use std::task::{Context, Poll};
+
+use anyhow::{format_err, Error};
+use bytes::Bytes;
+use futures::ready;
+use futures::stream::Stream;
+use zstd::stream::raw::{Encoder, Operation, OutBuffer};
+
+use proxmox_io::ByteBuffer;
+
+const BUFFER_SIZE: usize = 8192;
+
+#[derive(Eq, PartialEq)]
+enum EncoderState {
+ Reading,
+ Writing,
+ Finishing,
+ Finished,
+}
+
+/// An async ZstdEncoder that implements [Stream] for another [Stream]
+///
+/// Useful for on-the-fly zstd compression in streaming api calls
+pub struct ZstdEncoder<'a, T> {
+ inner: T,
+ compressor: Encoder<'a>,
+ buffer: ByteBuffer,
+ input_buffer: Bytes,
+ state: EncoderState,
+}
+
+impl<'a, T> ZstdEncoder<'a, T> {
+ /// Returns a new [ZstdEncoder] with default level 3
+ pub fn new(inner: T) -> Result<Self, io::Error> {
+ Self::with_quality(inner, 3)
+ }
+
+ /// Returns a new [ZstdEncoder] with the given level
+ pub fn with_quality(inner: T, level: i32) -> Result<Self, io::Error> {
+ Ok(Self {
+ inner,
+ compressor: Encoder::new(level)?,
+ buffer: ByteBuffer::with_capacity(BUFFER_SIZE),
+ input_buffer: Bytes::new(),
+ state: EncoderState::Reading,
+ })
+ }
+
+ /// Returns the wrapped [Stream]
+ pub fn into_inner(self) -> T {
+ self.inner
+ }
+
+ fn encode(&mut self, inbuf: &[u8]) -> Result<zstd::stream::raw::Status, io::Error> {
+ let res = self
+ .compressor
+ .run_on_buffers(inbuf, self.buffer.get_free_mut_slice())?;
+ self.buffer.add_size(res.bytes_written);
+
+ Ok(res)
+ }
+
+ fn finish(&mut self) -> Result<usize, io::Error> {
+ let mut outbuf = OutBuffer::around(self.buffer.get_free_mut_slice());
+ let res = self.compressor.finish(&mut outbuf, true);
+ let size = outbuf.pos;
+ drop(outbuf);
+ self.buffer.add_size(size);
+ res
+ }
+}
+
+impl<'a, T, O> Stream for ZstdEncoder<'a, T>
+where
+ T: Stream<Item = Result<O, Error>> + Unpin,
+ O: Into<Bytes>,
+{
+ type Item = Result<Bytes, Error>;
+
+ fn poll_next(self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Option<Self::Item>> {
+ let this = self.get_mut();
+
+ loop {
+ match this.state {
+ EncoderState::Reading => {
+ if let Some(res) = ready!(Pin::new(&mut this.inner).poll_next(cx)) {
+ let buf = res?;
+ this.input_buffer = buf.into();
+ this.state = EncoderState::Writing;
+ } else {
+ this.state = EncoderState::Finishing;
+ }
+ }
+ EncoderState::Writing => {
+ if this.input_buffer.is_empty() {
+ return Poll::Ready(Some(Err(format_err!("empty input during write"))));
+ }
+ let mut buf = this.input_buffer.split_off(0);
+ let status = this.encode(&buf[..])?;
+ this.input_buffer = buf.split_off(status.bytes_read);
+ if this.input_buffer.is_empty() {
+ this.state = EncoderState::Reading;
+ }
+ if this.buffer.is_full() {
+ let bytes = this.buffer.remove_data(this.buffer.len()).to_vec();
+ return Poll::Ready(Some(Ok(bytes.into())));
+ }
+ }
+ EncoderState::Finishing => {
+ let remaining = this.finish()?;
+ if remaining == 0 {
+ this.state = EncoderState::Finished;
+ }
+ if !this.buffer.is_empty() {
+ let bytes = this.buffer.remove_data(this.buffer.len()).to_vec();
+ return Poll::Ready(Some(Ok(bytes.into())));
+ }
+ }
+ EncoderState::Finished => return Poll::Ready(None),
+ }
+ }
+ }
+}
--
2.30.2