From mboxrd@z Thu Jan 1 00:00:00 1970
Return-Path: <w.bumiller@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 4CD3575058;
Fri, 4 Jun 2021 14:22:41 +0200 (CEST)
Received: from firstgate.proxmox.com (localhost [127.0.0.1])
by firstgate.proxmox.com (Proxmox) with ESMTP id 3DE3C1C96F;
Fri, 4 Jun 2021 14:22:11 +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 1A70E1C964;
Fri, 4 Jun 2021 14:22:07 +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 E01E646717;
Fri, 4 Jun 2021 14:22:06 +0200 (CEST)
Date: Fri, 4 Jun 2021 14:22:05 +0200
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
To: Stefan Reiter <s.reiter@proxmox.com>
Cc: pve-devel@lists.proxmox.com, pbs-devel@lists.proxmox.com
Message-ID: <20210604122205.ivembuqsue7osqah@olga.proxmox.com>
References: <20210602143833.4423-1-s.reiter@proxmox.com>
<20210602143833.4423-4-s.reiter@proxmox.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20210602143833.4423-4-s.reiter@proxmox.com>
User-Agent: NeoMutt/20180716
X-SPAM-LEVEL: Spam detection results: 0
AWL 0.016 Adjusted score from AWL reputation of From: address
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
URIBL_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to URIBL was blocked. See
http://wiki.apache.org/spamassassin/DnsBlocklists#dnsbl-block for more
information. [backup.rs]
Subject: Re: [pve-devel] [pbs-devel] [PATCH proxmox-backup 3/9] backup: add
CachedChunkReader utilizing AsyncLruCache
X-BeenThere: pve-devel@lists.proxmox.com
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Proxmox VE development discussion <pve-devel.lists.proxmox.com>
List-Unsubscribe: <https://lists.proxmox.com/cgi-bin/mailman/options/pve-devel>,
<mailto:pve-devel-request@lists.proxmox.com?subject=unsubscribe>
List-Archive: <http://lists.proxmox.com/pipermail/pve-devel/>
List-Post: <mailto:pve-devel@lists.proxmox.com>
List-Help: <mailto:pve-devel-request@lists.proxmox.com?subject=help>
List-Subscribe: <https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel>,
<mailto:pve-devel-request@lists.proxmox.com?subject=subscribe>
X-List-Received-Date: Fri, 04 Jun 2021 12:22:41 -0000
On Wed, Jun 02, 2021 at 04:38:27PM +0200, Stefan Reiter wrote:
> Provides a fast cache read implementation with full async and
> concurrency support.
>
> Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
> ---
>
> This is technically all that's needed for proxmox-backup-qemu to build and
> function as intended, but I decided to also use this IMHO cleaner implementation
> to replace the AsyncIndexReader with the following patches.
>
> src/backup.rs | 3 ++
> src/backup/cached_chunk_reader.rs | 87 +++++++++++++++++++++++++++++++
> 2 files changed, 90 insertions(+)
> create mode 100644 src/backup/cached_chunk_reader.rs
>
> diff --git a/src/backup.rs b/src/backup.rs
> index ae937be0..5e1147b4 100644
> --- a/src/backup.rs
> +++ b/src/backup.rs
> @@ -259,3 +259,6 @@ pub use catalog_shell::*;
>
> mod async_index_reader;
> pub use async_index_reader::*;
> +
> +mod cached_chunk_reader;
> +pub use cached_chunk_reader::*;
> diff --git a/src/backup/cached_chunk_reader.rs b/src/backup/cached_chunk_reader.rs
> new file mode 100644
> index 00000000..fd5a049f
> --- /dev/null
> +++ b/src/backup/cached_chunk_reader.rs
> @@ -0,0 +1,87 @@
> +//! An async and concurrency safe data reader backed by a local LRU cache.
> +
> +use anyhow::Error;
> +
> +use std::future::Future;
> +use std::sync::Arc;
> +
> +use crate::backup::{AsyncReadChunk, IndexFile};
> +use crate::tools::async_lru_cache::{AsyncCacher, AsyncLruCache};
> +
> +struct AsyncChunkCacher<T> {
> + reader: Arc<T>,
> +}
> +
> +impl<T: AsyncReadChunk + Send + Sync + 'static> AsyncCacher<[u8; 32], Arc<Vec<u8>>>
> + for AsyncChunkCacher<T>
> +{
> + fn fetch(
> + &self,
> + key: [u8; 32],
> + ) -> Box<dyn Future<Output = Result<Option<Arc<Vec<u8>>>, Error>> + Send> {
> + let reader = Arc::clone(&self.reader);
> + Box::new(async move {
> + AsyncReadChunk::read_chunk(reader.as_ref(), &key)
> + .await
> + .map(|x| Some(Arc::new(x)))
> + })
> + }
> +}
> +
> +/// Represents an AsyncLruCache used for storing data chunks.
> +pub type ChunkCache = Arc<AsyncLruCache<[u8; 32], Arc<Vec<u8>>>>;
Given that you now use this type in an external crate but still have to
*instantiate* it via `Arc::new(AsyncLruCache::new(...))` I wonder if
this should just be a struct prividing a `new`, `clone` and
`Deref<Target = AsyncLruCache>`?
> +
> +/// Allows arbitrary data reads from an Index via an AsyncReadChunk implementation, using an LRU
> +/// cache internally to cache chunks and provide support for multiple concurrent reads (potentially
> +/// to the same chunk).
> +pub struct CachedChunkReader<I: IndexFile, R: AsyncReadChunk + Send + Sync + 'static> {
> + cache: ChunkCache,
> + cacher: AsyncChunkCacher<R>,
> + index: I,
> +}
> +
> +impl<I: IndexFile, R: AsyncReadChunk + Send + Sync + 'static> CachedChunkReader<I, R> {
> + /// Create a new reader with a local LRU cache containing 'capacity' chunks.
> + pub fn new(reader: R, index: I, capacity: usize) -> Self {
> + let cache = Arc::new(AsyncLruCache::new(capacity));
> + Self::new_with_cache(reader, index, cache)
> + }
> +
> + /// Create a new reader with a custom LRU cache. Use this to share a cache between multiple
> + /// readers.
> + pub fn new_with_cache(reader: R, index: I, cache: ChunkCache) -> Self {
> + Self {
> + cache,
> + cacher: AsyncChunkCacher {
> + reader: Arc::new(reader),
> + },
> + index,
> + }
> + }
> +
> + /// Read data at a given byte offset into a variable size buffer. Returns the amount of bytes
> + /// read, which will always be the size of the buffer except when reaching EOF.
> + pub async fn read_at(&self, buf: &mut [u8], offset: u64) -> Result<usize, Error> {
> + let size = buf.len();
> + let mut read: usize = 0;
> + while read < size {
> + let cur_offset = offset + read as u64;
> + if let Some(chunk) = self.index.chunk_from_offset(cur_offset) {
> + let info = self.index.chunk_info(chunk.0).unwrap();
> +
> + // will never be None, see AsyncChunkCacher
Why comment on this unwrap but not on the one above? ;-)
> + let data = self.cache.access(info.digest, &self.cacher).await?.unwrap();
> +
> + let want_bytes = ((info.range.end - cur_offset) as usize).min(size - read);
> + let slice = &mut buf[read..(read + want_bytes)];
> + let intra_chunk = chunk.1 as usize;
> + slice.copy_from_slice(&data[intra_chunk..(intra_chunk + want_bytes)]);
> + read += want_bytes;
> + } else {
> + // EOF
> + break;
> + }
> + }
> + Ok(read)
> + }
> +}
> --
> 2.30.2