all lists on lists.proxmox.com
 help / color / mirror / Atom feed
From: Christian Ebner <c.ebner@proxmox.com>
To: pbs-devel@lists.proxmox.com
Subject: [pbs-devel] [PATCH proxmox-backup v6 16/37] verify: implement chunk verification for stores with s3 backend
Date: Tue,  8 Jul 2025 19:00:53 +0200	[thread overview]
Message-ID: <20250708170114.1556057-26-c.ebner@proxmox.com> (raw)
In-Reply-To: <20250708170114.1556057-1-c.ebner@proxmox.com>

For datastores backed by an S3 compatible object store, rather than
reading the chunks to be verified from the local filesystem, fetch
them via the s3 client from the configured bucket.

Signed-off-by: Christian Ebner <c.ebner@proxmox.com>
---
 src/backup/verify.rs | 89 ++++++++++++++++++++++++++++++++++++++------
 1 file changed, 77 insertions(+), 12 deletions(-)

diff --git a/src/backup/verify.rs b/src/backup/verify.rs
index dea10f618..3a4a1d0d5 100644
--- a/src/backup/verify.rs
+++ b/src/backup/verify.rs
@@ -5,6 +5,7 @@ use std::sync::{Arc, Mutex};
 use std::time::Instant;
 
 use anyhow::{bail, Error};
+use http_body_util::BodyExt;
 use tracing::{error, info, warn};
 
 use proxmox_worker_task::WorkerTaskContext;
@@ -89,6 +90,38 @@ impl VerifyWorker {
             }
         }
 
+        if let Ok(DatastoreBackend::S3(s3_client)) = datastore.backend() {
+            let suffix = format!(".{}.bad", counter);
+            let target_key =
+                match pbs_datastore::s3::object_key_from_digest_with_suffix(digest, &suffix) {
+                    Ok(target_key) => target_key,
+                    Err(err) => {
+                        info!("could not generate target key for corrupted chunk {path:?} - {err}");
+                        return;
+                    }
+                };
+            let object_key = match pbs_datastore::s3::object_key_from_digest(digest) {
+                Ok(object_key) => object_key,
+                Err(err) => {
+                    info!("could not generate object key for corrupted chunk {path:?} - {err}");
+                    return;
+                }
+            };
+            if proxmox_async::runtime::block_on(
+                s3_client.copy_object(object_key.clone(), target_key),
+            )
+            .is_ok()
+            {
+                if proxmox_async::runtime::block_on(s3_client.delete_object(object_key)).is_err() {
+                    info!("failed to delete corrupt chunk on s3 backend: {digest_str}");
+                }
+            } else {
+                info!("failed to copy corrupt chunk on s3 backend: {digest_str}");
+            }
+        } else {
+            info!("failed to get s3 backend while trying to rename bad chunk: {digest_str}");
+        }
+
         match std::fs::rename(&path, &new_path) {
             Ok(_) => {
                 info!("corrupted chunk renamed to {:?}", &new_path);
@@ -189,18 +222,50 @@ impl VerifyWorker {
                 continue; // already verified or marked corrupt
             }
 
-            match self.datastore.load_chunk(&info.digest) {
-                Err(err) => {
-                    self.corrupt_chunks.lock().unwrap().insert(info.digest);
-                    error!("can't verify chunk, load failed - {err}");
-                    errors.fetch_add(1, Ordering::SeqCst);
-                    Self::rename_corrupted_chunk(self.datastore.clone(), &info.digest);
-                }
-                Ok(chunk) => {
-                    let size = info.size();
-                    read_bytes += chunk.raw_size();
-                    decoder_pool.send((chunk, info.digest, size))?;
-                    decoded_bytes += size;
+            match &self.backend {
+                DatastoreBackend::Filesystem => match self.datastore.load_chunk(&info.digest) {
+                    Err(err) => {
+                        self.corrupt_chunks.lock().unwrap().insert(info.digest);
+                        error!("can't verify chunk, load failed - {err}");
+                        errors.fetch_add(1, Ordering::SeqCst);
+                        Self::rename_corrupted_chunk(self.datastore.clone(), &info.digest);
+                    }
+                    Ok(chunk) => {
+                        let size = info.size();
+                        read_bytes += chunk.raw_size();
+                        decoder_pool.send((chunk, info.digest, size))?;
+                        decoded_bytes += size;
+                    }
+                },
+                DatastoreBackend::S3(s3_client) => {
+                    let object_key = pbs_datastore::s3::object_key_from_digest(&info.digest)?;
+                    match proxmox_async::runtime::block_on(s3_client.get_object(object_key)) {
+                        Ok(Some(response)) => {
+                            let bytes =
+                                proxmox_async::runtime::block_on(response.content.collect())?
+                                    .to_bytes();
+                            let chunk = DataBlob::from_raw(bytes.to_vec())?;
+                            let size = info.size();
+                            read_bytes += chunk.raw_size();
+                            decoder_pool.send((chunk, info.digest, size))?;
+                            decoded_bytes += size;
+                        }
+                        Ok(None) => {
+                            self.corrupt_chunks.lock().unwrap().insert(info.digest);
+                            error!(
+                                "can't verify missing chunk with digest {}",
+                                hex::encode(info.digest)
+                            );
+                            errors.fetch_add(1, Ordering::SeqCst);
+                            Self::rename_corrupted_chunk(self.datastore.clone(), &info.digest);
+                        }
+                        Err(err) => {
+                            self.corrupt_chunks.lock().unwrap().insert(info.digest);
+                            error!("can't verify chunk, load failed - {err}");
+                            errors.fetch_add(1, Ordering::SeqCst);
+                            Self::rename_corrupted_chunk(self.datastore.clone(), &info.digest);
+                        }
+                    }
                 }
             }
         }
-- 
2.47.2



_______________________________________________
pbs-devel mailing list
pbs-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel


  parent reply	other threads:[~2025-07-08 17:01 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-08 17:00 [pbs-devel] [PATCH proxmox{, -backup} v6 00/46] fix #2943: S3 storage backend for datastores Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 1/9] s3 client: add crate for AWS s3 compatible object store client Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 2/9] s3 client: implement AWS signature v4 request authentication Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 3/9] s3 client: add dedicated type for s3 object keys Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 4/9] s3 client: add type for last modified timestamp in responses Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 5/9] s3 client: add helper to parse http date headers Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 6/9] s3 client: implement methods to operate on s3 objects in bucket Christian Ebner
2025-07-09 10:04   ` Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 7/9] s3 client: add example usage for basic operations Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 8/9] pbs-api-types: extend datastore config by backend config enum Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox v6 9/9] pbs-api-types: maintenance: add new maintenance mode S3 refresh Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 01/37] datastore: add helpers for path/digest to s3 object key conversion Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 02/37] config: introduce s3 object store client configuration Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 03/37] api: config: implement endpoints to manipulate and list s3 configs Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 04/37] api: datastore: check s3 backend bucket access on datastore create Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 05/37] api/cli: add endpoint and command to check s3 client connection Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 06/37] datastore: allow to get the backend for a datastore Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 07/37] api: backup: store datastore backend in runtime environment Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 08/37] api: backup: conditionally upload chunks to s3 object store backend Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 09/37] api: backup: conditionally upload blobs " Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 10/37] api: backup: conditionally upload indices " Christian Ebner
2025-07-09  7:55   ` Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 11/37] api: backup: conditionally upload manifest " Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 12/37] sync: pull: conditionally upload content to s3 backend Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 13/37] api: reader: fetch chunks based on datastore backend Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 14/37] datastore: local chunk reader: read chunks based on backend Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 15/37] verify worker: add datastore backed to verify worker Christian Ebner
2025-07-08 17:00 ` Christian Ebner [this message]
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 17/37] datastore: create namespace marker in s3 backend Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 18/37] datastore: create/delete protected marker file on s3 storage backend Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 19/37] datastore: prune groups/snapshots from s3 object store backend Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 20/37] datastore: get and set owner for s3 " Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 21/37] datastore: implement garbage collection for s3 backend Christian Ebner
2025-07-10  6:59   ` Thomas Lamprecht
2025-07-10  7:36     ` Christian Ebner
2025-07-10  9:47     ` Christian Ebner
2025-07-10 11:15       ` Christian Ebner
2025-07-08 17:00 ` [pbs-devel] [PATCH proxmox-backup v6 22/37] ui: add datastore type selector and reorganize component layout Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 23/37] ui: add s3 client edit window for configuration create/edit Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 24/37] ui: add s3 client view for configuration Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 25/37] ui: expose the s3 client view in the navigation tree Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 26/37] ui: add s3 client selector and bucket field for s3 backend setup Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 27/37] tools: lru cache: add removed callback for evicted cache nodes Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 28/37] tools: async lru cache: implement insert, remove and contains methods Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 29/37] datastore: add local datastore cache for network attached storages Christian Ebner
2025-07-10 10:05   ` Thomas Lamprecht
2025-07-10 10:30     ` Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 30/37] api: backup: use local datastore cache on s3 backend chunk upload Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 31/37] api: reader: use local datastore cache on s3 backend chunk fetching Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 32/37] datastore: local chunk reader: get cached chunk from local cache store Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 33/37] api: backup: add no-cache flag to bypass local datastore cache Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 34/37] api/datastore: implement refresh endpoint for stores with s3 backend Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 35/37] cli: add dedicated subcommand for datastore s3 refresh Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 36/37] ui: render s3 refresh as valid maintenance type and task description Christian Ebner
2025-07-08 17:01 ` [pbs-devel] [PATCH proxmox-backup v6 37/37] ui: expose s3 refresh button for datastores backed by object store Christian Ebner
2025-07-10 17:09 ` [pbs-devel] superseded: [PATCH proxmox{, -backup} v6 00/46] fix #2943: S3 storage backend for datastores Christian Ebner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250708170114.1556057-26-c.ebner@proxmox.com \
    --to=c.ebner@proxmox.com \
    --cc=pbs-devel@lists.proxmox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.
Service provided by Proxmox Server Solutions GmbH | Privacy | Legal