[PATCH proxmox-backup v7 3/9] tools: add bounded join set to run concurrent tasks bound by limit

[Christian Ebner <c.ebner@proxmox.com>]

The BoundedJoinSet allows to run tasks concurrently via a JoinSet,
but constrains the number of concurrent tasks by an upper limit.

In contrast to the ParallelHandler implementation, which is a purely
sync implementation and does not provide easy handling for returned
results, this allows to execute tasks in an async context with straight
forward handling of results, as required for e.g. pulling/pushing of
backup groups in parallel for sync jobs. Also, log context is easily
preserved, which is of importance for task logging.

Signed-off-by: Christian Ebner <c.ebner@proxmox.com>
---
 pbs-tools/src/bounded_join_set.rs | 74 +++++++++++++++++++++++++++++++
 pbs-tools/src/lib.rs              |  1 +
 2 files changed, 75 insertions(+)
 create mode 100644 pbs-tools/src/bounded_join_set.rs

diff --git a/pbs-tools/src/bounded_join_set.rs b/pbs-tools/src/bounded_join_set.rs
new file mode 100644
index 000000000..2c8b56299
--- /dev/null
+++ b/pbs-tools/src/bounded_join_set.rs
@@ -0,0 +1,74 @@
+//! JoinSet with an upper bound of concurrent tasks.
+//!
+//! Allows to run up to the configured number of tasks concurrently in an async
+//! context.
+
+use std::future::Future;
+
+use tokio::task::{JoinError, JoinSet};
+
+use proxmox_log::LogContext;
+
+/// Run up to preconfigured number of futures concurrently on tokio tasks.
+pub struct BoundedJoinSet<T> {
+    /// Upper bound for concurrent task execution
+    max_tasks: usize,
+    /// Handles to currently spawned tasks
+    workers: JoinSet<T>,
+}
+
+impl<T: Send + 'static> BoundedJoinSet<T> {
+    /// Create a new join set with up to `max_task` concurrently executed tasks.
+    pub fn new(max_tasks: usize) -> Self {
+        Self {
+            max_tasks,
+            workers: JoinSet::new(),
+        }
+    }
+
+    /// Spawn the given task on the workers, waiting until there is capacity to do so.
+    ///
+    /// If there is no capacity, this will await until there is so, returning the results
+    /// for the finished task(s) providing the now free running slot in order of completion
+    /// or a `JoinError` if joining failed.
+    pub async fn spawn_task<F>(&mut self, task: F) -> Result<Vec<T>, JoinError>
+    where
+        F: Future<Output = T>,
+        F: Send + 'static,
+    {
+        let mut results = Vec::with_capacity(self.workers.len());
+
+        // Collect already finished task results if there are some
+        while let Some(result) = self.workers.try_join_next() {
+            results.push(result?);
+        }
+
+        while self.workers.len() >= self.max_tasks {
+            // capacity reached, wait for an active task to complete
+            if let Some(result) = self.workers.join_next().await {
+                results.push(result?);
+            }
+        }
+
+        match LogContext::current() {
+            Some(context) => self.workers.spawn(context.scope(task)),
+            None => self.workers.spawn(task),
+        };
+
+        Ok(results)
+    }
+
+    /// Wait on all spawned tasks to run to completion.
+    ///
+    /// Returns the results for each task in order of completion or a `JoinError`
+    /// if joining failed.
+    pub async fn join_spawned_tasks(&mut self) -> Result<Vec<T>, JoinError> {
+        let mut results = Vec::with_capacity(self.workers.len());
+
+        while let Some(result) = self.workers.join_next().await {
+            results.push(result?);
+        }
+
+        Ok(results)
+    }
+}
diff --git a/pbs-tools/src/lib.rs b/pbs-tools/src/lib.rs
index 1e3972c92..dc55366b6 100644
--- a/pbs-tools/src/lib.rs
+++ b/pbs-tools/src/lib.rs
@@ -1,4 +1,5 @@
 pub mod async_lru_cache;
+pub mod bounded_join_set;
 pub mod buffered_logger;
 pub mod cert;
 pub mod crypt_config;
-- 
2.47.3