[PATCH proxmox-backup v6 03/15] tools: implement buffered logger for concurrent log messages

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

Implements a buffered logger instance which collects messages send
from different sender instances via an async tokio channel and
buffers them. Sender identify by label and provide a log level for
each log line to be buffered and flushed.

On collection, log lines are grouped by label and buffered in
sequence of arrival per label, up to the configured maximum number of
per group lines or periodically with the configured interval. The
interval timeout is reset when contents are flushed. In addition,
senders can request flushing at any given point.

When the timeout set based on the interval is reached, all labels
log buffers are flushed. There is no guarantee on the order of labels
when flushing.

Log output is written based on provided log line level and prefixed
by the label.

Signed-off-by: Christian Ebner <c.ebner@proxmox.com>
---
changes since version 5:
- not present in previous version

 pbs-tools/Cargo.toml             |   2 +
 pbs-tools/src/buffered_logger.rs | 216 +++++++++++++++++++++++++++++++
 pbs-tools/src/lib.rs             |   1 +
 3 files changed, 219 insertions(+)
 create mode 100644 pbs-tools/src/buffered_logger.rs

diff --git a/pbs-tools/Cargo.toml b/pbs-tools/Cargo.toml
index 998e3077e..6b1d92fa6 100644
--- a/pbs-tools/Cargo.toml
+++ b/pbs-tools/Cargo.toml
@@ -17,10 +17,12 @@ openssl.workspace = true
 serde_json.workspace = true
 # rt-multi-thread is required for block_in_place
 tokio = { workspace = true, features = [ "fs", "io-util", "rt", "rt-multi-thread", "sync" ] }
+tracing.workspace = true
 
 proxmox-async.workspace = true
 proxmox-io = { workspace = true, features = [ "tokio" ] }
 proxmox-human-byte.workspace = true
+proxmox-log.workspace = true
 proxmox-sys.workspace = true
 proxmox-time.workspace = true
 
diff --git a/pbs-tools/src/buffered_logger.rs b/pbs-tools/src/buffered_logger.rs
new file mode 100644
index 000000000..39cf068cd
--- /dev/null
+++ b/pbs-tools/src/buffered_logger.rs
@@ -0,0 +1,216 @@
+//! Log aggregator to collect and group messages send from concurrent tasks via
+//! a tokio channel.
+
+use std::collections::hash_map::Entry;
+use std::collections::HashMap;
+use std::time::Duration;
+
+use anyhow::Error;
+use tokio::sync::mpsc;
+use tokio::time::{self, Instant};
+use tracing::{debug, error, info, trace, warn, Level};
+
+use proxmox_log::LogContext;
+
+/// Label to be used to group currently buffered messages when flushing.
+pub type SenderLabel = String;
+
+/// Requested action for the log collection task
+enum SenderRequest {
+    // new log line to be buffered
+    Message(LogLine),
+    // flush currently buffered log lines associated by sender label
+    Flush(SenderLabel),
+}
+
+/// Logger instance to buffer and group log output to keep concurrent logs readable
+///
+/// Receives the logs from an async input channel, buffers them grouped by input
+/// channel and flushes them after either reaching a timeout or capacity limit.
+pub struct BufferedLogger {
+    // buffer to aggregate log lines based on sender label
+    buffer_map: HashMap<SenderLabel, Vec<LogLine>>,
+    // maximum number of received lines for an individual sender instance before
+    // flushing
+    max_buffered_lines: usize,
+    // maximum aggregation duration of received lines for an individual sender
+    // instance before flushing
+    max_aggregation_time: Duration,
+    // channel to receive log messages
+    receiver: mpsc::Receiver<SenderRequest>,
+}
+
+/// Instance to create new sender instances by cloning the channel sender
+pub struct LogLineSenderBuilder {
+    // to clone new senders if requested
+    _sender: mpsc::Sender<SenderRequest>,
+}
+
+impl LogLineSenderBuilder {
+    /// Create new sender instance to send log messages, to be grouped by given label
+    ///
+    /// Label is not checked to be unique (no other instance with same label exists),
+    /// it is the callers responsibility to check so if required.
+    pub fn sender_with_label(&self, label: SenderLabel) -> LogLineSender {
+        LogLineSender {
+            label,
+            sender: self._sender.clone(),
+        }
+    }
+}
+
+/// Sender to publish new log messages to buffered log aggregator
+pub struct LogLineSender {
+    // label used to group log lines
+    label: SenderLabel,
+    // sender to publish new log lines to buffered log aggregator task
+    sender: mpsc::Sender<SenderRequest>,
+}
+
+impl LogLineSender {
+    /// Send a new log message with given level to the buffered logger task
+    pub async fn log(&self, level: Level, message: String) -> Result<(), Error> {
+        let line = LogLine {
+            label: self.label.clone(),
+            level,
+            message,
+        };
+        self.sender.send(SenderRequest::Message(line)).await?;
+        Ok(())
+    }
+
+    /// Flush all messages with sender's label
+    pub async fn flush(&self) -> Result<(), Error> {
+        self.sender
+            .send(SenderRequest::Flush(self.label.clone()))
+            .await?;
+        Ok(())
+    }
+}
+
+/// Log message entity
+struct LogLine {
+    /// label indentifiying the sender
+    label: SenderLabel,
+    /// Log level to use during flushing
+    level: Level,
+    /// log line to be buffered and flushed
+    message: String,
+}
+
+impl BufferedLogger {
+    /// New instance of a buffered logger
+    pub fn new(
+        max_buffered_lines: usize,
+        max_aggregation_time: Duration,
+    ) -> (Self, LogLineSenderBuilder) {
+        let (_sender, receiver) = mpsc::channel(100);
+
+        (
+            Self {
+                buffer_map: HashMap::new(),
+                max_buffered_lines,
+                max_aggregation_time,
+                receiver,
+            },
+            LogLineSenderBuilder { _sender },
+        )
+    }
+
+    /// Starts the collection loop spawned on a new tokio task
+    /// Finishes when all sender belonging to the channel have been dropped.
+    pub fn run_log_collection(mut self) {
+        let future = async move {
+            loop {
+                let deadline = Instant::now() + self.max_aggregation_time;
+                match time::timeout_at(deadline, self.receive_log_line()).await {
+                    Ok(finished) => {
+                        if finished {
+                            break;
+                        }
+                    }
+                    Err(_timeout) => self.flush_all_buffered(),
+                }
+            }
+        };
+        match LogContext::current() {
+            None => tokio::spawn(future),
+            Some(context) => tokio::spawn(context.scope(future)),
+        };
+    }
+
+    /// Collects new log lines, buffers and flushes them if max lines limit exceeded.
+    ///
+    /// Returns `true` if all the senders have been dropped and the task should no
+    /// longer wait for new messages and finish.
+    async fn receive_log_line(&mut self) -> bool {
+        if let Some(request) = self.receiver.recv().await {
+            match request {
+                SenderRequest::Flush(label) => {
+                    if let Some(log_lines) = self.buffer_map.get_mut(&label) {
+                        Self::log_with_label(&label, log_lines);
+                        log_lines.clear();
+                    }
+                }
+                SenderRequest::Message(log_line) => {
+                    if self.max_buffered_lines == 0
+                        || self.max_aggregation_time < Duration::from_secs(0)
+                    {
+                        // shortcut if no buffering should happen
+                        Self::log_by_level(&log_line.label, &log_line);
+                    }
+
+                    match self.buffer_map.entry(log_line.label.clone()) {
+                        Entry::Occupied(mut occupied) => {
+                            let log_lines = occupied.get_mut();
+                            if log_lines.len() + 1 > self.max_buffered_lines {
+                                // reached limit for this label,
+                                // flush all buffered and new log line
+                                Self::log_with_label(&log_line.label, log_lines);
+                                log_lines.clear();
+                                Self::log_by_level(&log_line.label, &log_line);
+                            } else {
+                                // below limit, push to buffer to flush later
+                                log_lines.push(log_line);
+                            }
+                        }
+                        Entry::Vacant(vacant) => {
+                            vacant.insert(vec![log_line]);
+                        }
+                    }
+                }
+            }
+            return false;
+        }
+
+        // no more senders, all LogLineSender's and LogLineSenderBuilder have been dropped
+        self.flush_all_buffered();
+        true
+    }
+
+    /// Flush all currently buffered contents without ordering, but grouped by label
+    fn flush_all_buffered(&mut self) {
+        for (label, log_lines) in self.buffer_map.iter() {
+            Self::log_with_label(label, log_lines);
+        }
+        self.buffer_map.clear();
+    }
+
+    /// Log given log lines prefixed by label
+    fn log_with_label(label: &str, log_lines: &[LogLine]) {
+        for log_line in log_lines {
+            Self::log_by_level(label, log_line);
+        }
+    }
+
+    /// Write the given log line prefixed by label
+    fn log_by_level(label: &str, log_line: &LogLine) {
+        match log_line.level {
+            Level::ERROR => error!("[{label}]: {}", log_line.message),
+            Level::WARN => warn!("[{label}]: {}", log_line.message),
+            Level::INFO => info!("[{label}]: {}", log_line.message),
+            Level::DEBUG => debug!("[{label}]: {}", log_line.message),
+            Level::TRACE => trace!("[{label}]: {}", log_line.message),
+        }
+    }
+}
diff --git a/pbs-tools/src/lib.rs b/pbs-tools/src/lib.rs
index f41aef6df..1e3972c92 100644
--- a/pbs-tools/src/lib.rs
+++ b/pbs-tools/src/lib.rs
@@ -1,4 +1,5 @@
 pub mod async_lru_cache;
+pub mod buffered_logger;
 pub mod cert;
 pub mod crypt_config;
 pub mod format;
-- 
2.47.3