[RFC 10/31] mars: add new module lib_limiter

[Thomas Schoebel-Theuer]

Signed-off-by: Thomas Schoebel-Theuer <tst@xxxxxxxxxxxxxxxxxx>
---
 drivers/staging/mars/lib/lib_limiter.c | 129 +++++++++++++++++++++++++++++++++
 include/linux/brick/lib_limiter.h      |  49 +++++++++++++
 2 files changed, 178 insertions(+)
 create mode 100644 drivers/staging/mars/lib/lib_limiter.c
 create mode 100644 include/linux/brick/lib_limiter.h

diff --git a/drivers/staging/mars/lib/lib_limiter.c b/drivers/staging/mars/lib/lib_limiter.c
new file mode 100644
index 0000000..12ac8de
--- /dev/null
+++ b/drivers/staging/mars/lib/lib_limiter.c
@@ -0,0 +1,129 @@
+/*
+ * MARS Long Distance Replication Software
+ *
+ * Copyright (C) 2010-2014 Thomas Schoebel-Theuer
+ * Copyright (C) 2011-2014 1&1 Internet AG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/brick/lib_limiter.h>
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/sched.h>
+
+#define LIMITER_TIME_RESOLUTION		NSEC_PER_SEC
+
+int rate_limit(struct rate_limiter *lim, int amount)
+{
+	int delay = 0;
+	long long now;
+
+	now = cpu_clock(raw_smp_processor_id());
+
+	/* Compute the maximum delay along the path
+	 * down to the root of the hierarchy tree.
+	 */
+	while (lim != NULL) {
+		long long window = now - lim->lim_stamp;
+
+		/* Sometimes, raw CPU clocks may do weired things...
+		 * Smaller windows in the denominator than 1s could fake unrealistic rates.
+		 */
+		if (unlikely(lim->lim_min_window <= 0))
+			lim->lim_min_window = 1000;
+		if (unlikely(lim->lim_max_window <= lim->lim_min_window))
+			lim->lim_max_window = lim->lim_min_window + 8000;
+		if (unlikely(window < (long long)lim->lim_min_window * (LIMITER_TIME_RESOLUTION / 1000)))
+			window = (long long)lim->lim_min_window * (LIMITER_TIME_RESOLUTION / 1000);
+
+		/* Update total statistics.
+		 * They will intentionally wrap around.
+		 * Userspace must take care of that.
+		 */
+		lim->lim_total_ops++;
+		lim->lim_total_sum += amount;
+
+		/* Only use incremental accumulation at repeated calls, but
+		 * never after longer pauses.
+		 */
+		if (likely(lim->lim_stamp &&
+			   window < (long long)lim->lim_max_window * (LIMITER_TIME_RESOLUTION / 1000))) {
+			long long rate_raw;
+			int rate;
+
+			/* Races are possible, but taken into account.
+			 * There is no real harm from rarely lost updates.
+			 */
+			if (likely(amount > 0)) {
+				lim->lim_accu += amount;
+				lim->lim_cumul += amount;
+				lim->lim_count++;
+			}
+
+			rate_raw = lim->lim_accu * LIMITER_TIME_RESOLUTION / window;
+			rate = rate_raw;
+			if (unlikely(rate_raw > INT_MAX))
+				rate = INT_MAX;
+			lim->lim_rate = rate;
+
+			/*  limit exceeded? */
+			if (lim->lim_max_rate > 0 && rate > lim->lim_max_rate) {
+				int this_delay = (window * rate / lim->lim_max_rate - window) / (LIMITER_TIME_RESOLUTION / 1000);
+
+				/*  compute maximum */
+				if (this_delay > delay && this_delay > 0)
+					delay = this_delay;
+			}
+
+			/* Try to keep the next window below min_window
+			 */
+			window -= lim->lim_min_window * (LIMITER_TIME_RESOLUTION / 1000);
+			if (window > 0) {
+				long long used_up = (long long)lim->lim_rate * window / LIMITER_TIME_RESOLUTION;
+
+				if (used_up > 0) {
+					lim->lim_stamp += window;
+					lim->lim_accu -= used_up;
+					if (unlikely(lim->lim_accu < 0))
+						lim->lim_accu = 0;
+				}
+			}
+		} else { /*  reset, start over with new measurement cycle */
+			if (unlikely(amount < 0))
+				amount = 0;
+			lim->lim_accu = amount;
+			lim->lim_stamp = now - lim->lim_min_window * (LIMITER_TIME_RESOLUTION / 1000);
+			lim->lim_rate = 0;
+		}
+		lim = lim->lim_father;
+	}
+	return delay;
+}
+
+void rate_limit_sleep(struct rate_limiter *lim, int amount)
+{
+	int sleep = rate_limit(lim, amount);
+
+	if (sleep > 0) {
+		unsigned long timeout;
+
+		if (unlikely(lim->lim_max_delay <= 0))
+			lim->lim_max_delay = 1000;
+		if (sleep > lim->lim_max_delay)
+			sleep = lim->lim_max_delay;
+		timeout = msecs_to_jiffies(sleep);
+		while ((long)timeout > 0)
+			timeout = schedule_timeout_uninterruptible(timeout);
+	}
+}
diff --git a/include/linux/brick/lib_limiter.h b/include/linux/brick/lib_limiter.h
new file mode 100644
index 0000000..e14fa7e
--- /dev/null
+++ b/include/linux/brick/lib_limiter.h
@@ -0,0 +1,49 @@
+/*
+ * MARS Long Distance Replication Software
+ *
+ * Copyright (C) 2010-2014 Thomas Schoebel-Theuer
+ * Copyright (C) 2011-2014 1&1 Internet AG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef LIB_LIMITER_H
+#define LIB_LIMITER_H
+
+#include <linux/utsname.h>
+
+struct rate_limiter {
+	/* hierarchy tree */
+	struct rate_limiter *lim_father;
+
+	/* tunables */
+	int lim_max_rate;
+	int lim_max_delay;
+	int lim_min_window;
+	int lim_max_window;
+
+	/* readable */
+	int lim_rate;
+	int lim_cumul;
+	int lim_count;
+	int lim_total_ops;
+	int lim_total_sum;
+	long long lim_stamp;
+
+	/* internal */
+	long long lim_accu;
+};
+
+extern int rate_limit(struct rate_limiter *lim, int amount);
+
+extern void rate_limit_sleep(struct rate_limiter *lim, int amount);
+
+#endif
-- 
2.6.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/