dql: Dynamic queue limits

Implementation of dynamic queue limits (dql).  This is a libary which
allows a queue limit to be dynamically managed.  The goal of dql is
to set the queue limit, number of objects to the queue, to be minimized
without allowing the queue to be starved.

dql would be used with a queue which has these properties:

1) Objects are queued up to some limit which can be expressed as a
   count of objects.
2) Periodically a completion process executes which retires consumed
   objects.
3) Starvation occurs when limit has been reached, all queued data has
   actually been consumed but completion processing has not yet run,
   so queuing new data is blocked.
4) Minimizing the amount of queued data is desirable.

A canonical example of such a queue would be a NIC HW transmit queue.

The queue limit is dynamic, it will increase or decrease over time
depending on the workload.  The queue limit is recalculated each time
completion processing is done.  Increases occur when the queue is
starved and can exponentially increase over successive intervals.
Decreases occur when more data is being maintained in the queue than
needed to prevent starvation.  The number of extra objects, or "slack",
is measured over successive intervals, and to avoid hysteresis the
limit is only reduced by the miminum slack seen over a configurable
time period.

dql API provides routines to manage the queue:
- dql_init is called to intialize the dql structure
- dql_reset is called to reset dynamic values
- dql_queued called when objects are being enqueued
- dql_avail returns availability in the queue
- dql_completed is called when objects have be consumed in the queue

Configuration consists of:
- max_limit, maximum limit
- min_limit, minimum limit
- slack_hold_time, time to measure instances of slack before reducing
  queue limit

Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 97 insertions, 0 deletions

diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
new file mode 100644
index 0000000..5621547
--- /dev/null
+++ b/include/linux/dynamic_queue_limits.h
@@ -0,0 +1,97 @@
+/*
+ * Dynamic queue limits (dql) - Definitions
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ *
+ * This header file contains the definitions for dynamic queue limits (dql).
+ * dql would be used in conjunction with a producer/consumer type queue
+ * (possibly a HW queue).  Such a queue would have these general properties:
+ *
+ *   1) Objects are queued up to some limit specified as number of objects.
+ *   2) Periodically a completion process executes which retires consumed
+ *      objects.
+ *   3) Starvation occurs when limit has been reached, all queued data has
+ *      actually been consumed, but completion processing has not yet run
+ *      so queuing new data is blocked.
+ *   4) Minimizing the amount of queued data is desirable.
+ *
+ * The goal of dql is to calculate the limit as the minimum number of objects
+ * needed to prevent starvation.
+ *
+ * The primary functions of dql are:
+ *    dql_queued - called when objects are enqueued to record number of objects
+ *    dql_avail - returns how many objects are available to be queued based
+ *      on the object limit and how many objects are already enqueued
+ *    dql_completed - called at completion time to indicate how many objects
+ *      were retired from the queue
+ *
+ * The dql implementation does not implement any locking for the dql data
+ * structures, the higher layer should provide this.  dql_queued should
+ * be serialized to prevent concurrent execution of the function; this
+ * is also true for  dql_completed.  However, dql_queued and dlq_completed  can
+ * be executed concurrently (i.e. they can be protected by different locks).
+ */
+
+#ifndef _LINUX_DQL_H
+#define _LINUX_DQL_H
+
+#ifdef __KERNEL__
+
+struct dql {
+	/* Fields accessed in enqueue path (dql_queued) */
+	unsigned int	num_queued;		/* Total ever queued */
+	unsigned int	adj_limit;		/* limit + num_completed */
+	unsigned int	last_obj_cnt;		/* Count at last queuing */
+
+	/* Fields accessed only by completion path (dql_completed) */
+
+	unsigned int	limit ____cacheline_aligned_in_smp; /* Current limit */
+	unsigned int	num_completed;		/* Total ever completed */
+
+	unsigned int	prev_ovlimit;		/* Previous over limit */
+	unsigned int	prev_num_queued;	/* Previous queue total */
+	unsigned int	prev_last_obj_cnt;	/* Previous queuing cnt */
+
+	unsigned int	lowest_slack;		/* Lowest slack found */
+	unsigned long	slack_start_time;	/* Time slacks seen */
+
+	/* Configuration */
+	unsigned int	max_limit;		/* Max limit */
+	unsigned int	min_limit;		/* Minimum limit */
+	unsigned int	slack_hold_time;	/* Time to measure slack */
+};
+
+/* Set some static maximums */
+#define DQL_MAX_OBJECT (UINT_MAX / 16)
+#define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT)
+
+/*
+ * Record number of objects queued. Assumes that caller has already checked
+ * availability in the queue with dql_avail.
+ */
+static inline void dql_queued(struct dql *dql, unsigned int count)
+{
+	BUG_ON(count > DQL_MAX_OBJECT);
+
+	dql->num_queued += count;
+	dql->last_obj_cnt = count;
+}
+
+/* Returns how many objects can be queued, < 0 indicates over limit. */
+static inline int dql_avail(const struct dql *dql)
+{
+	return dql->adj_limit - dql->num_queued;
+}
+
+/* Record number of completed objects and recalculate the limit. */
+void dql_completed(struct dql *dql, unsigned int count);
+
+/* Reset dql state */
+void dql_reset(struct dql *dql);
+
+/* Initialize dql state */
+int dql_init(struct dql *dql, unsigned hold_time);
+
+#endif /* _KERNEL_ */
+
+#endif /* _LINUX_DQL_H */