xen:rtds: towards work conserving RTDS

Make RTDS scheduler work conserving without breaking the real-time guarantees.

VCPU model:
Each real-time VCPU is extended to have an extratime flag
and a priority_level field.
When a VCPU's budget is depleted in the current period,
if it has extratime flag set,
its priority_level will increase by 1 and its budget will be refilled;
othewrise, the VCPU will be moved to the depletedq.

Scheduling policy is modified global EDF:
A VCPU v1 has higher priority than another VCPU v2 if
(i) v1 has smaller priority_leve; or
(ii) v1 has the same priority_level but has a smaller deadline

Queue management:
Run queue holds VCPUs with extratime flag set and VCPUs with
remaining budget. Run queue is sorted in increasing order of VCPUs priorities.
Depleted queue holds VCPUs which have extratime flag cleared and depleted budget.
Replenished queue is not modified.

Distribution of spare bandwidth
Spare bandwidth is distributed among all VCPUs with extratime flag set,
proportional to these VCPUs utilizations

Signed-off-by: Meng Xu <mengxu@cis.upenn.edu>
Reviewed-by: Dario Faggioli <raistlin@linux.it>

diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index 5c51cd93c76ca455d512b70a1400efcc7a1d882d..b770287f97de63f299689462fa4bb587c54e85a9 100644 (file)
--- a/xen/common/sched_rt.c
+++ b/xen/common/sched_rt.c
@@ -49,13 +49,15 @@
  * A PCPU is feasible if the VCPU can run on this PCPU and (the PCPU is idle or
  * has a lower-priority VCPU running on it.)
  *
- * Each VCPU has a dedicated period and budget.
+ * Each VCPU has a dedicated period, budget and a extratime flag
  * The deadline of a VCPU is at the end of each period;
  * A VCPU has its budget replenished at the beginning of each period;
  * While scheduled, a VCPU burns its budget.
  * The VCPU needs to finish its budget before its deadline in each period;
  * The VCPU discards its unused budget at the end of each period.
- * If a VCPU runs out of budget in a period, it has to wait until next period.
+ * When a VCPU runs out of budget in a period, if its extratime flag is set,
+ * the VCPU increases its priority_level by 1 and refills its budget; otherwise,
+ * it has to wait until next period.
  *
  * Each VCPU is implemented as a deferable server.
  * When a VCPU has a task running on it, its budget is continuously burned;
@@ -63,7 +65,8 @@
  *
  * Queue scheme:
  * A global runqueue and a global depletedqueue for each CPU pool.
- * The runqueue holds all runnable VCPUs with budget, sorted by deadline;
+ * The runqueue holds all runnable VCPUs with budget,
+ * sorted by priority_level and deadline;
  * The depletedqueue holds all VCPUs without budget, unsorted;
  *
  * Note: cpumask and cpupool is supported.
@@ -150,6 +153,14 @@
 #define __RTDS_depleted     3
 #define RTDS_depleted (1<<__RTDS_depleted)
 
+/*
+ * RTDS_extratime: Can the vcpu run in the time that is
+ * not part of any real-time reservation, and would therefore
+ * be otherwise left idle?
+ */
+#define __RTDS_extratime    4
+#define RTDS_extratime (1<<__RTDS_extratime)
+
 /*
  * rt tracing events ("only" 512 available!). Check
  * include/public/trace.h for more details.
@@ -201,6 +212,8 @@ struct rt_vcpu {
     struct rt_dom *sdom;
     struct vcpu *vcpu;
 
+    unsigned priority_level;
+
     unsigned flags;              /* mark __RTDS_scheduled, etc.. */
 };
 
@@ -245,6 +258,11 @@ static inline struct list_head *rt_replq(const struct scheduler *ops)
     return &rt_priv(ops)->replq;
 }
 
+static inline bool has_extratime(const struct rt_vcpu *svc)
+{
+    return svc->flags & RTDS_extratime;
+}
+
 /*
  * Helper functions for manipulating the runqueue, the depleted queue,
  * and the replenishment events queue.
@@ -273,6 +291,21 @@ vcpu_on_replq(const struct rt_vcpu *svc)
     return !list_empty(&svc->replq_elem);
 }
 
+/*
+ * If v1 priority >= v2 priority, return value > 0
+ * Otherwise, return value < 0
+ */
+static s_time_t
+compare_vcpu_priority(const struct rt_vcpu *v1, const struct rt_vcpu *v2)
+{
+    int prio = v2->priority_level - v1->priority_level;
+
+    if ( prio == 0 )
+        return v2->cur_deadline - v1->cur_deadline;
+
+    return prio;
+}
+
 /*
  * Debug related code, dump vcpu/cpu information
  */
@@ -303,6 +336,7 @@ rt_dump_vcpu(const struct scheduler *ops, const struct rt_vcpu *svc)
     cpulist_scnprintf(keyhandler_scratch, sizeof(keyhandler_scratch), mask);
     printk("[%5d.%-2u] cpu %u, (%"PRI_stime", %"PRI_stime"),"
            " cur_b=%"PRI_stime" cur_d=%"PRI_stime" last_start=%"PRI_stime"\n"
+           " \t\t priority_level=%d has_extratime=%d\n"
            " \t\t onQ=%d runnable=%d flags=%x effective hard_affinity=%s\n",
             svc->vcpu->domain->domain_id,
             svc->vcpu->vcpu_id,
@@ -312,6 +346,8 @@ rt_dump_vcpu(const struct scheduler *ops, const struct rt_vcpu *svc)
             svc->cur_budget,
             svc->cur_deadline,
             svc->last_start,
+            svc->priority_level,
+            has_extratime(svc),
             vcpu_on_q(svc),
             vcpu_runnable(svc->vcpu),
             svc->flags,
@@ -423,15 +459,18 @@ rt_update_deadline(s_time_t now, struct rt_vcpu *svc)
      */
     svc->last_start = now;
     svc->cur_budget = svc->budget;
+    svc->priority_level = 0;
 
     /* TRACE */
     {
         struct __packed {
             unsigned vcpu:16, dom:16;
+            unsigned priority_level;
             uint64_t cur_deadline, cur_budget;
         } d;
         d.dom = svc->vcpu->domain->domain_id;
         d.vcpu = svc->vcpu->vcpu_id;
+        d.priority_level = svc->priority_level;
         d.cur_deadline = (uint64_t) svc->cur_deadline;
         d.cur_budget = (uint64_t) svc->cur_budget;
         trace_var(TRC_RTDS_BUDGET_REPLENISH, 1,
@@ -454,7 +493,7 @@ rt_update_deadline(s_time_t now, struct rt_vcpu *svc)
  * cases, if the vcpu with the earliest deadline is what we
  * are dealing with).
  */
-static inline bool_t
+static inline bool
 deadline_queue_remove(struct list_head *queue, struct list_head *elem)
 {
     int pos = 0;
@@ -466,7 +505,7 @@ deadline_queue_remove(struct list_head *queue, struct list_head *elem)
     return !pos;
 }
 
-static inline bool_t
+static inline bool
 deadline_queue_insert(struct rt_vcpu * (*qelem)(struct list_head *),
                       struct rt_vcpu *svc, struct list_head *elem,
                       struct list_head *queue)
@@ -477,7 +516,7 @@ deadline_queue_insert(struct rt_vcpu * (*qelem)(struct list_head *),
     list_for_each ( iter, queue )
     {
         struct rt_vcpu * iter_svc = (*qelem)(iter);
-        if ( svc->cur_deadline <= iter_svc->cur_deadline )
+        if ( compare_vcpu_priority(svc, iter_svc) > 0 )
             break;
         pos++;
     }
@@ -537,8 +576,9 @@ runq_insert(const struct scheduler *ops, struct rt_vcpu *svc)
     ASSERT( !vcpu_on_q(svc) );
     ASSERT( vcpu_on_replq(svc) );
 
-    /* add svc to runq if svc still has budget */
-    if ( svc->cur_budget > 0 )
+    /* add svc to runq if svc still has budget or its extratime is set */
+    if ( svc->cur_budget > 0 ||
+         has_extratime(svc) )
         deadline_runq_insert(svc, &svc->q_elem, runq);
     else
         list_add(&svc->q_elem, &prv->depletedq);
@@ -857,6 +897,8 @@ rt_alloc_vdata(const struct scheduler *ops, struct vcpu *vc, void *dd)
     svc->vcpu = vc;
     svc->last_start = 0;
 
+    __set_bit(__RTDS_extratime, &svc->flags);
+    svc->priority_level = 0;
     svc->period = RTDS_DEFAULT_PERIOD;
     if ( !is_idle_vcpu(vc) )
         svc->budget = RTDS_DEFAULT_BUDGET;
@@ -966,8 +1008,16 @@ burn_budget(const struct scheduler *ops, struct rt_vcpu *svc, s_time_t now)
 
     if ( svc->cur_budget <= 0 )
     {
-        svc->cur_budget = 0;
-        __set_bit(__RTDS_depleted, &svc->flags);
+        if ( has_extratime(svc) )
+        {
+            svc->priority_level++;
+            svc->cur_budget = svc->budget;
+        }
+        else
+        {
+            svc->cur_budget = 0;
+            __set_bit(__RTDS_depleted, &svc->flags);
+        }
     }
 
     /* TRACE */
@@ -976,11 +1026,15 @@ burn_budget(const struct scheduler *ops, struct rt_vcpu *svc, s_time_t now)
             unsigned vcpu:16, dom:16;
             uint64_t cur_budget;
             int delta;
+            unsigned priority_level;
+            bool has_extratime;
         } d;
         d.dom = svc->vcpu->domain->domain_id;
         d.vcpu = svc->vcpu->vcpu_id;
         d.cur_budget = (uint64_t) svc->cur_budget;
         d.delta = delta;
+        d.priority_level = svc->priority_level;
+        d.has_extratime = svc->flags & RTDS_extratime;
         trace_var(TRC_RTDS_BUDGET_BURN, 1,
                   sizeof(d),
                   (unsigned char *) &d);
@@ -1088,7 +1142,7 @@ rt_schedule(const struct scheduler *ops, s_time_t now, bool_t tasklet_work_sched
              vcpu_runnable(current) &&
              scurr->cur_budget > 0 &&
              ( is_idle_vcpu(snext->vcpu) ||
-               scurr->cur_deadline <= snext->cur_deadline ) )
+               compare_vcpu_priority(scurr, snext) > 0 ) )
             snext = scurr;
     }
 
@@ -1194,7 +1248,7 @@ runq_tickle(const struct scheduler *ops, struct rt_vcpu *new)
         }
         iter_svc = rt_vcpu(iter_vc);
         if ( latest_deadline_vcpu == NULL ||
-             iter_svc->cur_deadline > latest_deadline_vcpu->cur_deadline )
+             compare_vcpu_priority(iter_svc, latest_deadline_vcpu) < 0 )
             latest_deadline_vcpu = iter_svc;
 
         cpumask_clear_cpu(cpu, &not_tickled);
@@ -1203,7 +1257,7 @@ runq_tickle(const struct scheduler *ops, struct rt_vcpu *new)
 
     /* 2) candicate has higher priority, kick out lowest priority vcpu */
     if ( latest_deadline_vcpu != NULL &&
-         new->cur_deadline < latest_deadline_vcpu->cur_deadline )
+         compare_vcpu_priority(latest_deadline_vcpu, new) < 0 )
     {
         SCHED_STAT_CRANK(tickled_busy_cpu);
         cpu_to_tickle = latest_deadline_vcpu->vcpu->processor;
@@ -1394,6 +1448,10 @@ rt_dom_cntl(
                 svc = rt_vcpu(d->vcpu[local_sched.vcpuid]);
                 local_sched.u.rtds.budget = svc->budget / MICROSECS(1);
                 local_sched.u.rtds.period = svc->period / MICROSECS(1);
+                if ( has_extratime(svc) )
+                    local_sched.u.rtds.flags |= XEN_DOMCTL_SCHEDRT_extra;
+                else
+                    local_sched.u.rtds.flags &= ~XEN_DOMCTL_SCHEDRT_extra;
                 spin_unlock_irqrestore(&prv->lock, flags);
 
                 if ( copy_to_guest_offset(op->u.v.vcpus, index,
@@ -1418,6 +1476,10 @@ rt_dom_cntl(
                 svc = rt_vcpu(d->vcpu[local_sched.vcpuid]);
                 svc->period = period;
                 svc->budget = budget;
+                if ( local_sched.u.rtds.flags & XEN_DOMCTL_SCHEDRT_extra )
+                    __set_bit(__RTDS_extratime, &svc->flags);
+                else
+                    __clear_bit(__RTDS_extratime, &svc->flags);
                 spin_unlock_irqrestore(&prv->lock, flags);
             }
             /* Process a most 64 vCPUs without checking for preemptions. */
@@ -1492,7 +1554,7 @@ static void repl_timer_handler(void *data){
         {
             struct rt_vcpu *next_on_runq = q_elem(runq->next);
 
-            if ( svc->cur_deadline > next_on_runq->cur_deadline )
+            if ( compare_vcpu_priority(svc, next_on_runq) < 0 )
                 runq_tickle(ops, next_on_runq);
         }
         else if ( __test_and_clear_bit(__RTDS_depleted, &svc->flags) &&

diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
index 8853445c931acf8e780b16c93a6fab1b2285e696..70027abc005c2ac6caa67e309433f874355d41d4 100644 (file)
--- a/xen/include/public/domctl.h
+++ b/xen/include/public/domctl.h
@@ -342,6 +342,10 @@ struct xen_domctl_sched_credit2 {
 struct xen_domctl_sched_rtds {
     uint32_t period;
     uint32_t budget;
+/* Can this vCPU execute beyond its reserved amount of time? */
+#define _XEN_DOMCTL_SCHEDRT_extra   0
+#define XEN_DOMCTL_SCHEDRT_extra    (1U<<_XEN_DOMCTL_SCHEDRT_extra)
+    uint32_t flags;
 };
 
 typedef struct xen_domctl_schedparam_vcpu {