[pbs-devel] [PATCH proxmox-backup v7 33/38] datastore: local chunk reader: get cached chunk from local cache store

[Christian Ebner]

Check if a chunk is contained in the local cache and if so prefer
fetching it from the cache instead of pulling it via the S3 api. This
improves performance and reduces number of requests to the backend.

Basic restore performance tests:

Restored a snapshot containing the linux git repository (on-disk size
5.069 GiB, compressed 3.718 GiB) from an AWS S3 backed datastore, with
and without cached contents:
non cached: 691.95 s
all cached:  74.89 s

Signed-off-by: Christian Ebner <c.ebner at proxmox.com>
---
changes since version 6:
- added basic restore preformace results to the commit message

 pbs-datastore/src/local_chunk_reader.rs | 31 +++++++++++++++++++++----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/pbs-datastore/src/local_chunk_reader.rs b/pbs-datastore/src/local_chunk_reader.rs
index f5aa217ae..7ad44c4fa 100644
--- a/pbs-datastore/src/local_chunk_reader.rs
+++ b/pbs-datastore/src/local_chunk_reader.rs
@@ -2,7 +2,7 @@ use std::future::Future;
 use std::pin::Pin;
 use std::sync::Arc;
 
-use anyhow::{bail, Error};
+use anyhow::{bail, format_err, Error};
 use http_body_util::BodyExt;
 
 use pbs_api_types::CryptMode;
@@ -68,9 +68,18 @@ impl ReadChunk for LocalChunkReader {
     fn read_raw_chunk(&self, digest: &[u8; 32]) -> Result<DataBlob, Error> {
         let chunk = match &self.backend {
             DatastoreBackend::Filesystem => self.store.load_chunk(digest)?,
-            DatastoreBackend::S3(s3_client) => {
-                proxmox_async::runtime::block_on(fetch(s3_client.clone(), digest))?
-            }
+            DatastoreBackend::S3(s3_client) => match self.store.cache() {
+                None => proxmox_async::runtime::block_on(fetch(s3_client.clone(), digest))?,
+                Some(cache) => {
+                    let mut cacher = self
+                        .store
+                        .cacher()?
+                        .ok_or(format_err!("no cacher for datastore"))?;
+                    proxmox_async::runtime::block_on(cache.access(digest, &mut cacher))?.ok_or(
+                        format_err!("unable to access chunk with digest {}", hex::encode(digest)),
+                    )?
+                }
+            },
         };
         self.ensure_crypt_mode(chunk.crypt_mode()?)?;
 
@@ -98,7 +107,19 @@ impl AsyncReadChunk for LocalChunkReader {
                     let raw_data = tokio::fs::read(&path).await?;
                     DataBlob::load_from_reader(&mut &raw_data[..])?
                 }
-                DatastoreBackend::S3(s3_client) => fetch(s3_client.clone(), digest).await?,
+                DatastoreBackend::S3(s3_client) => match self.store.cache() {
+                    None => fetch(s3_client.clone(), digest).await?,
+                    Some(cache) => {
+                        let mut cacher = self
+                            .store
+                            .cacher()?
+                            .ok_or(format_err!("no cacher for datastore"))?;
+                        cache.access(digest, &mut cacher).await?.ok_or(format_err!(
+                            "unable to access chunk with digest {}",
+                            hex::encode(digest)
+                        ))?
+                    }
+                },
             };
             self.ensure_crypt_mode(chunk.crypt_mode()?)?;
 
-- 
2.47.2