Provides a fast cache read implementation with full async and concurrency support.
Signed-off-by: Stefan Reiter <s.rei...@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>>>>; + +/// 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 + 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 _______________________________________________ pve-devel mailing list pve-devel@lists.proxmox.com https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel