bees: add -G/--thread-min option for minimum thread count

The -g option limits the number of worker threads when the target load
average is exceeded.  On some systems the load normally runs high, and
continuous bees operation is required to avoid running out of disk space.

Add a -G/--thread-min option to force at least some threads to continue
running.

Signed-off-by: Zygo Blaxell <bees@furryterror.org>

README.md

@@ -545,8 +545,11 @@ Command Line Options
 * --loadavg-target (-g) LOADAVG
   * Specify load average target for dynamic worker threads.
     Threads will be started or stopped subject to the upper limit imposed
-    by thread-factor and thread-count until the load average is within
-    +/- 0.5 of LOADAVG.
+    by thread-factor, thread-min and thread-count until the load average
+    is within +/- 0.5 of LOADAVG.
+* --thread-min (-G) COUNT
+  * Specify minimum number of worker threads for scanning.
+    Ignored unless -g option is used to specify a target load.
 
 * --scan-mode (-m) MODE
   * Specify extent scanning algorithm.  Default mode is 0.

include/crucible/task.h

@@ -58,6 +58,9 @@ namespace crucible {
 		// Blocks until the running thread count reaches this number
 		static void set_thread_count(size_t threads);
 
+		// Sets minimum thread count when load average tracking enabled
+		static void set_thread_min_count(size_t min_threads);
+
 		// Calls set_thread_count with default
 		static void set_thread_count();
 

lib/task.cc

@@ -43,6 +43,7 @@ namespace crucible {
 		condition_variable 			m_condvar;
 		list<shared_ptr<TaskState>>		m_queue;
 		size_t					m_thread_max;
+		size_t					m_thread_min = 0;
 		set<shared_ptr<TaskConsumer>>		m_threads;
 		shared_ptr<thread>			m_load_tracking_thread;
 		double					m_load_target = 0;
@@ -56,6 +57,7 @@ namespace crucible {
 		void start_threads_nolock();
 		void start_stop_threads();
 		void set_thread_count(size_t thread_max);
+		void set_thread_min_count(size_t thread_min);
 		void adjust_thread_count();
 		size_t calculate_thread_count_nolock();
 		void set_loadavg_target(double target);
@@ -269,7 +271,7 @@ namespace crucible {
 		m_thread_target = min(max(0.0, m_thread_target), double(m_configured_thread_max));
 
 		// Convert to integer but keep within range
-		const size_t rv = min(size_t(ceil(m_thread_target)), m_configured_thread_max);
+		const size_t rv = max(m_thread_min, min(size_t(ceil(m_thread_target)), m_configured_thread_max));
 
 		return rv;
 	}
@@ -306,6 +308,22 @@ namespace crucible {
 		s_tms->set_thread_count(thread_max);
 	}
 
+	void
+	TaskMasterState::set_thread_min_count(size_t thread_min)
+	{
+		unique_lock<mutex> lock(m_mutex);
+		m_thread_min = thread_min;
+		lock.unlock();
+		adjust_thread_count();
+		start_stop_threads();
+	}
+
+	void
+	TaskMaster::set_thread_min_count(size_t thread_min)
+	{
+		s_tms->set_thread_min_count(thread_min);
+	}
+
 	void
 	TaskMasterState::loadavg_thread_fn()
 	{

src/bees.cc

@@ -45,6 +45,7 @@ do_cmd_help(char *argv[])
 		"\t-h, --help\t\tShow this help\n"
 		"\t-c, --thread-count\tWorker thread count (default CPU count * factor)\n"
 		"\t-C, --thread-factor\tWorker thread factor (default " << BEES_DEFAULT_THREAD_FACTOR << ")\n"
+		"\t-G, --thread-min\t\tMinimum worker thread count with load average target (default 0)\n"
 		"\t-g, --loadavg-target\t\tTarget load average for worker threads (default is no target)\n"
 		"\t-m, --scan-mode\t\tScanning mode (0..2, default 0)\n"
 		"\t-t, --timestamps\tShow timestamps in log output (default)\n"
@@ -653,6 +654,7 @@ bees_main(int argc, char *argv[])
 	bool chatter_prefix_timestamp = true;
 	double thread_factor = 0;
 	unsigned thread_count = 0;
+	unsigned thread_min = 0;
 	double load_target = 0;
 
 	// Parse options
@@ -661,18 +663,19 @@ bees_main(int argc, char *argv[])
 		int option_index = 0;
 		static const struct option long_options[] = {
 			{ "thread-factor",  required_argument, NULL, 'C' },
+			{ "thread-min",     required_argument, NULL, 'G' },
 			{ "strip-paths",    no_argument,       NULL, 'P' },
 			{ "no-timestamps",  no_argument,       NULL, 'T' },
 			{ "thread-count",   required_argument, NULL, 'c' },
-			{ "help",           no_argument,       NULL, 'h' },
 			{ "loadavg-target", required_argument, NULL, 'g' },
+			{ "help",           no_argument,       NULL, 'h' },
 			{ "scan-mode", 	    required_argument, NULL, 'm' },
 			{ "absolute-paths", no_argument,       NULL, 'p' },
 			{ "timestamps",     no_argument,       NULL, 't' },
 			{ "verbose",        required_argument, NULL, 'v' },
 		};
 
-		c = getopt_long(argc, argv, "C:PTc:hg:m:ptv:", long_options, &option_index);
+		c = getopt_long(argc, argv, "C:G:PTc:hg:m:ptv:", long_options, &option_index);
 		if (-1 == c) {
 			break;
 		}
@@ -682,6 +685,9 @@ bees_main(int argc, char *argv[])
 			case 'C':
 				thread_factor = stod(optarg);
 				break;
+			case 'G':
+				thread_min = stoul(optarg);
+				break;
 			case 'P':
 				crucible::set_relative_path(cwd);
 				break;
@@ -748,10 +754,12 @@ bees_main(int argc, char *argv[])
 
 	if (load_target != 0) {
 		BEESLOGNOTICE("setting load average target to " << load_target);
+		BEESLOGNOTICE("setting worker thread pool minimum size to " << thread_min);
+		TaskMaster::set_thread_min_count(thread_min);
 	}
 	TaskMaster::set_loadavg_target(load_target);
 
-	BEESLOGNOTICE("setting worker thread pool maximum size to " << load_target);
+	BEESLOGNOTICE("setting worker thread pool maximum size to " << thread_count);
 	TaskMaster::set_thread_count(thread_count);
 
 	// Create a context and start crawlers