all lists on lists.proxmox.com
 help / color / mirror / Atom feed
From: Shan Shaji <s.shaji@proxmox.com>
To: pbs-devel@lists.proxmox.com
Subject: [RFC PATCH proxmox-backup 1/4] datastore: factor out s3 chunk objects pagination into a helper
Date: Tue, 15 Sep 2026 17:59:32 +0200	[thread overview]
Message-ID: <20260915155935.135460-2-s.shaji@proxmox.com> (raw)
In-Reply-To: <20260915155935.135460-1-s.shaji@proxmox.com>

This is in preparation to re-use the chunk iteration logic for creating
empty marker files during s3 refresh.

Signed-off-by: Shan Shaji <s.shaji@proxmox.com>
---
 pbs-datastore/src/datastore.rs | 85 ++++++++++++++++++++++------------
 1 file changed, 56 insertions(+), 29 deletions(-)

diff --git a/pbs-datastore/src/datastore.rs b/pbs-datastore/src/datastore.rs
index c3db52269..f3eab8a28 100644
--- a/pbs-datastore/src/datastore.rs
+++ b/pbs-datastore/src/datastore.rs
@@ -2382,6 +2382,47 @@ impl DataStore {
         }
     }
 
+    /// Fetch chunk objects in batches of max 1000 per request.
+    /// For each objects listed, the `callback` will be invoked with its
+    /// S3 object key and size.
+    fn paginate_s3_chunk_objects<F>(
+        &self,
+        worker: &dyn WorkerTaskContext,
+        s3_client: &S3Client,
+        mut callback: F,
+    ) -> Result<(), Error>
+    where
+        F: FnMut(S3ObjectKey, u64) -> Result<(), Error>,
+    {
+        let prefix = S3PathPrefix::Some(".chunks/".to_string());
+        let mut list_bucket_result =
+            proxmox_async::runtime::block_on(s3_client.list_objects_v2(&prefix, None))
+                .context("failed to list chunk in s3 object store")?;
+
+        loop {
+            for content in list_bucket_result.contents {
+                worker.check_abort()?;
+                worker.fail_on_shutdown()?;
+
+                callback(content.key, content.size)?;
+            }
+
+            // Process next batch of chunks if there are more.
+            if list_bucket_result.is_truncated {
+                list_bucket_result = proxmox_async::runtime::block_on(s3_client.list_objects_v2(
+                    &prefix,
+                    list_bucket_result.next_continuation_token.as_deref(),
+                ))?;
+
+                continue;
+            }
+
+            break;
+        }
+
+        Ok(())
+    }
+
     fn garbage_collection_impl(
         &self,
         worker: &dyn WorkerTaskContext,
@@ -2473,28 +2514,23 @@ impl DataStore {
 
         if let Some(ref s3_client) = s3_client {
             let mut chunk_count = 0;
-            let prefix = S3PathPrefix::Some(".chunks/".to_string());
-            // Operates in batches of 1000 objects max per request
-            let mut list_bucket_result =
-                proxmox_async::runtime::block_on(s3_client.list_objects_v2(&prefix, None))
-                    .context("failed to list chunk in s3 object store")?;
-
             let mut delete_list =
                 S3DeleteList::with_thresholds(S3_DELETE_BATCH_LIMIT, S3_DELETE_DEFER_LIMIT_SECONDS);
-            loop {
-                for content in list_bucket_result.contents {
-                    worker.check_abort()?;
-                    worker.fail_on_shutdown()?;
+
+            self.paginate_s3_chunk_objects(
+                worker,
+                s3_client,
+                |object_key, size| -> Result<(), Error> {
                     let (chunk_path, digest, bad) =
-                        match self.chunk_path_from_object_key(&content.key) {
+                        match self.chunk_path_from_object_key(&object_key) {
                             Some(path) => path,
-                            None => continue,
+                            None => return Ok(()),
                         };
 
                     let timeout = std::time::Duration::from_secs(0);
                     let _chunk_guard = match self.inner.chunk_store.lock_chunk(&digest, timeout) {
                         Ok(guard) => guard,
-                        Err(_) => continue,
+                        Err(_) => return Ok(()),
                     };
                     let _guard = self.inner.chunk_store.mutex().lock().unwrap();
 
@@ -2526,7 +2562,7 @@ impl DataStore {
                                 atime,
                                 min_atime,
                                 oldest_writer,
-                                content.size,
+                                size,
                                 bad,
                                 &mut gc_status,
                                 || {
@@ -2537,15 +2573,15 @@ impl DataStore {
                                             std::fs::remove_file(chunk_path)?;
                                         }
                                     }
-                                    delete_list.push(content.key, _chunk_guard);
+                                    delete_list.push(object_key, _chunk_guard);
                                     Ok(())
                                 },
                             )?;
                         }
                     } else {
                         gc_status.removed_chunks += 1;
-                        gc_status.removed_bytes += content.size;
-                        delete_list.push(content.key, _chunk_guard);
+                        gc_status.removed_bytes += size;
+                        delete_list.push(object_key, _chunk_guard);
                     }
 
                     chunk_count += 1;
@@ -2555,19 +2591,10 @@ impl DataStore {
 
                     // limit pending deletes to avoid holding too many chunk flocks
                     delete_list.conditional_delete_and_drop_locks(s3_client)?;
-                }
-                // Process next batch of chunks if there is more
-                if list_bucket_result.is_truncated {
-                    list_bucket_result =
-                        proxmox_async::runtime::block_on(s3_client.list_objects_v2(
-                            &prefix,
-                            list_bucket_result.next_continuation_token.as_deref(),
-                        ))?;
-                    continue;
-                }
 
-                break;
-            }
+                    Ok(())
+                },
+            )?;
 
             // delete the last batch of objects, if there are any remaining
             delete_list.delete_and_drop_locks(s3_client)?;
-- 
2.47.3





  reply	other threads:[~2026-09-15 16:00 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-15 15:59 [RFC PATCH proxmox-backup 0/4] fix #7903: rebuild local S3 chunk markers Shan Shaji
2026-09-15 15:59 ` Shan Shaji [this message]
2026-09-15 15:59 ` [RFC PATCH proxmox-backup 2/4] fix #7908: datastore: create zero-byte markers when re-using datastore Shan Shaji
2026-09-15 15:59 ` [RFC PATCH proxmox-backup 3/4] datastore: api: add option to rebuild S3 chunk markers Shan Shaji
2026-09-15 15:59 ` [RFC PATCH proxmox-backup 4/4] datastore: backup-manager: expose option to rebuild s3 " Shan Shaji
2026-09-15 16:04 ` [RFC PATCH proxmox-backup 0/4] fix #7903: rebuild local S3 " Shan Shaji

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=20260915155935.135460-2-s.shaji@proxmox.com \
    --to=s.shaji@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