diff -urpN -X /home/fletch/.diff.exclude 105-numameminfo/Documentation/filesystems/proc.txt 114-sched_tunables/Documentation/filesystems/proc.txt
--- 105-numameminfo/Documentation/filesystems/proc.txt Sat Jun 14 18:37:23 2003
+++ 114-sched_tunables/Documentation/filesystems/proc.txt Wed Aug 13 20:27:51 2003
@@ -37,6 +37,7 @@ Table of Contents
2.8 /proc/sys/net/ipv4 - IPV4 settings
2.9 Appletalk
2.10 IPX
+ 2.11 /proc/sys/sched - scheduler tunables
------------------------------------------------------------------------------
Preface
@@ -1751,6 +1752,104 @@ IPX.
The /proc/net/ipx_route table holds a list of IPX routes. For each route it
gives the destination network, the router node (or Directly) and the network
address of the router (or Connected) for internal networks.
+
+2.11 /proc/sys/sched - scheduler tunables
+-----------------------------------------
+
+Useful knobs for tuning the scheduler live in /proc/sys/sched.
+
+child_penalty
+-------------
+
+Percentage of the parent's sleep_avg that children inherit. sleep_avg is
+a running average of the time a process spends sleeping. Tasks with high
+sleep_avg values are considered interactive and given a higher dynamic
+priority and a larger timeslice. You typically want this some value just
+under 100.
+
+exit_weight
+-----------
+
+When a CPU hog task exits, its parent's sleep_avg is reduced by a factor of
+exit_weight against the exiting task's sleep_avg.
+
+interactive_delta
+-----------------
+
+If a task is "interactive" it is reinserted into the active array after it
+has expired its timeslice, instead of being inserted into the expired array.
+How "interactive" a task must be in order to be deemed interactive is a
+function of its nice value. This interactive limit is scaled linearly by nice
+value and is offset by the interactive_delta.
+
+max_sleep_avg
+-------------
+
+max_sleep_avg is the largest value (in ms) stored for a task's running sleep
+average. The larger this value, the longer a task needs to sleep to be
+considered interactive (maximum interactive bonus is a function of
+max_sleep_avg).
+
+max_timeslice
+-------------
+
+Maximum timeslice, in milliseconds. This is the value given to tasks of the
+highest dynamic priority.
+
+min_timeslice
+-------------
+
+Minimum timeslice, in milliseconds. This is the value given to tasks of the
+lowest dynamic priority. Every task gets at least this slice of the processor
+per array switch.
+
+parent_penalty
+--------------
+
+Percentage of the parent's sleep_avg that it retains across a fork().
+sleep_avg is a running average of the time a process spends sleeping. Tasks
+with high sleep_avg values are considered interactive and given a higher
+dynamic priority and a larger timeslice. Normally, this value is 100 and thus
+task's retain their sleep_avg on fork. If you want to punish interactive
+tasks for forking, set this below 100.
+
+prio_bonus_ratio
+----------------
+
+Middle percentage of the priority range that tasks can receive as a dynamic
+priority. The default value of 25% ensures that nice values at the
+extremes are still enforced. For example, nice +19 interactive tasks will
+never be able to preempt a nice 0 CPU hog. Setting this higher will increase
+the size of the priority range the tasks can receive as a bonus. Setting
+this lower will decrease this range, making the interactivity bonus less
+apparent and user nice values more applicable.
+
+starvation_limit
+----------------
+
+Sufficiently interactive tasks are reinserted into the active array when they
+run out of timeslice. Normally, tasks are inserted into the expired array.
+Reinserting interactive tasks into the active array allows them to remain
+runnable, which is important to interactive performance. This could starve
+expired tasks, however, since the interactive task could prevent the array
+switch. To prevent starving the tasks on the expired array for too long. the
+starvation_limit is the longest (in ms) we will let the expired array starve
+at the expense of reinserting interactive tasks back into active. Higher
+values here give more preferance to running interactive tasks, at the expense
+of expired tasks. Lower values provide more fair scheduling behavior, at the
+expense of interactivity. The units are in milliseconds.
+
+idle_node_rebalance_ratio
+-------------------------
+
+On NUMA machines, we normally rebalance within nodes, but we also rebalance
+globally every N idle rebalance ticks, where N = idle_node_rebalance_ratio.
+
+busy_node_rebalance_ratio
+-------------------------
+
+On NUMA machines, we normally rebalance within nodes, but we also rebalance
+globally every N busy rebalance ticks, where N = busy_node_rebalance_ratio.
------------------------------------------------------------------------------
Summary
diff -urpN -X /home/fletch/.diff.exclude 105-numameminfo/include/linux/sysctl.h 114-sched_tunables/include/linux/sysctl.h
--- 105-numameminfo/include/linux/sysctl.h Tue Aug 5 20:01:43 2003
+++ 114-sched_tunables/include/linux/sysctl.h Wed Aug 13 20:27:51 2003
@@ -60,7 +60,8 @@ enum
CTL_DEV=7, /* Devices */
CTL_BUS=8, /* Busses */
CTL_ABI=9, /* Binary emulation */
- CTL_CPU=10 /* CPU stuff (speed scaling, etc) */
+ CTL_CPU=10, /* CPU stuff (speed scaling, etc) */
+ CTL_SCHED=11, /* scheduler tunables */
};
/* CTL_BUS names: */
@@ -155,6 +156,21 @@ enum
VM_MIN_FREE_KBYTES=21, /* Minimum free kilobytes to maintain */
};
+/* Tunable scheduler parameters in /proc/sys/sched/ */
+enum {
+ SCHED_MIN_TIMESLICE=1, /* minimum process timeslice */
+ SCHED_MAX_TIMESLICE=2, /* maximum process timeslice */
+ SCHED_CHILD_PENALTY=3, /* penalty on fork to child */
+ SCHED_PARENT_PENALTY=4, /* penalty on fork to parent */
+ SCHED_EXIT_WEIGHT=5, /* penalty to parent of CPU hog child */
+ SCHED_PRIO_BONUS_RATIO=6, /* percent of max prio given as bonus */
+ SCHED_INTERACTIVE_DELTA=7, /* delta used to scale interactivity */
+ SCHED_MAX_SLEEP_AVG=8, /* maximum sleep avg attainable */
+ SCHED_STARVATION_LIMIT=9, /* no re-active if expired is starved */
+ SCHED_NODE_THRESHOLD=10, /* NUMA node rebalance threshold */
+ SCHED_IDLE_NODE_REBALANCE_RATIO=11, /* how often to global balance */
+ SCHED_BUSY_NODE_REBALANCE_RATIO=12, /* how often to global balance */
+};
/* CTL_NET names: */
enum
diff -urpN -X /home/fletch/.diff.exclude 105-numameminfo/kernel/sched.c 114-sched_tunables/kernel/sched.c
--- 105-numameminfo/kernel/sched.c Tue Aug 5 20:01:56 2003
+++ 114-sched_tunables/kernel/sched.c Wed Aug 13 20:27:52 2003
@@ -66,16 +66,27 @@
* maximum timeslice is 200 msecs. Timeslices get refilled after
* they expire.
*/
-#define MIN_TIMESLICE ( 10 * HZ / 1000)
-#define MAX_TIMESLICE (200 * HZ / 1000)
-#define CHILD_PENALTY 50
-#define PARENT_PENALTY 100
-#define EXIT_WEIGHT 3
-#define PRIO_BONUS_RATIO 25
-#define INTERACTIVE_DELTA 2
-#define MAX_SLEEP_AVG (10*HZ)
-#define STARVATION_LIMIT (10*HZ)
-#define NODE_THRESHOLD 125
+int min_timeslice = (10 * HZ) / 1000;
+int max_timeslice = (200 * HZ) / 1000;
+int child_penalty = 50;
+int parent_penalty = 100;
+int exit_weight = 3;
+int prio_bonus_ratio = 25;
+int interactive_delta = 2;
+int max_sleep_avg = 10 * HZ;
+int starvation_limit = 10 * HZ;
+int node_threshold = 125;
+
+#define MIN_TIMESLICE (min_timeslice)
+#define MAX_TIMESLICE (max_timeslice)
+#define CHILD_PENALTY (child_penalty)
+#define PARENT_PENALTY (parent_penalty)
+#define EXIT_WEIGHT (exit_weight)
+#define PRIO_BONUS_RATIO (prio_bonus_ratio)
+#define INTERACTIVE_DELTA (interactive_delta)
+#define MAX_SLEEP_AVG (max_sleep_avg)
+#define STARVATION_LIMIT (starvation_limit)
+#define NODE_THRESHOLD (node_threshold)
/*
* If a task is 'interactive' then we reinsert it in the active
@@ -858,6 +869,9 @@ static int find_busiest_node(int this_no
#endif /* CONFIG_NUMA */
+int idle_node_rebalance_ratio = 10;
+int busy_node_rebalance_ratio = 2;
+
#ifdef CONFIG_SMP
/*
@@ -1085,8 +1099,8 @@ out:
*/
#define IDLE_REBALANCE_TICK (HZ/1000 ?: 1)
#define BUSY_REBALANCE_TICK (HZ/5 ?: 1)
-#define IDLE_NODE_REBALANCE_TICK (IDLE_REBALANCE_TICK * 5)
-#define BUSY_NODE_REBALANCE_TICK (BUSY_REBALANCE_TICK * 2)
+#define IDLE_NODE_REBALANCE_TICK (IDLE_REBALANCE_TICK * idle_node_rebalance_ratio)
+#define BUSY_NODE_REBALANCE_TICK (BUSY_REBALANCE_TICK * busy_node_rebalance_ratio)
#ifdef CONFIG_NUMA
static void balance_node(runqueue_t *this_rq, int idle, int this_cpu)
diff -urpN -X /home/fletch/.diff.exclude 105-numameminfo/kernel/sysctl.c 114-sched_tunables/kernel/sysctl.c
--- 105-numameminfo/kernel/sysctl.c Wed Aug 13 20:24:33 2003
+++ 114-sched_tunables/kernel/sysctl.c Wed Aug 13 20:28:58 2003
@@ -58,6 +58,18 @@ extern int cad_pid;
extern int pid_max;
extern int sysctl_lower_zone_protection;
extern int min_free_kbytes;
+extern int min_timeslice;
+extern int max_timeslice;
+extern int child_penalty;
+extern int parent_penalty;
+extern int exit_weight;
+extern int prio_bonus_ratio;
+extern int interactive_delta;
+extern int max_sleep_avg;
+extern int starvation_limit;
+extern int node_threshold;
+extern int idle_node_rebalance_ratio;
+extern int busy_node_rebalance_ratio;
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
static int maxolduid = 65535;
@@ -120,6 +132,7 @@ static struct ctl_table_header root_tabl
static ctl_table kern_table[];
static ctl_table vm_table[];
+static ctl_table sched_table[];
#ifdef CONFIG_NET
extern ctl_table net_table[];
#endif
@@ -199,6 +212,12 @@ static ctl_table root_table[] = {
.mode = 0555,
.child = dev_table,
},
+ {
+ .ctl_name = CTL_SCHED,
+ .procname = "sched",
+ .mode = 0555,
+ .child = sched_table,
+ },
{ .ctl_name = 0 }
};
@@ -586,6 +605,7 @@ static ctl_table kern_table[] = {
/* Constants for minimum and maximum testing in vm_table.
We use these as one-element integer vectors. */
static int zero;
+static int one = 1;
static int one_hundred = 100;
@@ -805,6 +825,48 @@ static ctl_table debug_table[] = {
static ctl_table dev_table[] = {
{ .ctl_name = 0 }
};
+
+static ctl_table sched_table[] = {
+ {SCHED_MAX_TIMESLICE, "max_timeslice", &max_timeslice,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &one, NULL},
+ {SCHED_MIN_TIMESLICE, "min_timeslice", &min_timeslice,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &one, NULL},
+ {SCHED_CHILD_PENALTY, "child_penalty", &child_penalty,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &zero, NULL},
+ {SCHED_PARENT_PENALTY, "parent_penalty", &parent_penalty,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &zero, NULL},
+ {SCHED_EXIT_WEIGHT, "exit_weight", &exit_weight,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &zero, NULL},
+ {SCHED_PRIO_BONUS_RATIO, "prio_bonus_ratio", &prio_bonus_ratio,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &zero, NULL},
+ {SCHED_INTERACTIVE_DELTA, "interactive_delta", &interactive_delta,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &zero, NULL},
+ {SCHED_MAX_SLEEP_AVG, "max_sleep_avg", &max_sleep_avg,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &one, NULL},
+ {SCHED_STARVATION_LIMIT, "starvation_limit", &starvation_limit,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &zero, NULL},
+ {SCHED_NODE_THRESHOLD, "node_threshold", &node_threshold,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ sysctl_intvec, NULL, &one, NULL},
+ {SCHED_IDLE_NODE_REBALANCE_RATIO, "idle_node_rebalance_ratio",
+ &idle_node_rebalance_ratio,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &zero, NULL},
+ {SCHED_BUSY_NODE_REBALANCE_RATIO, "busy_node_rebalance_ratio",
+ &busy_node_rebalance_ratio,
+ sizeof(int), 0644, NULL, &proc_dointvec_minmax,
+ &sysctl_intvec, NULL, &zero, NULL},
+ {0}
+};
extern void init_irq_proc (void);