xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Dario Faggioli <dario.faggioli@citrix.com>
To: xen-devel@lists.xenproject.org
Cc: George Dunlap <dunlapg@umich.edu>, Justin Weaver <jtweaver@hawaii.edu>
Subject: [PATCH 16/16] xen: sched: implement vcpu hard affinity in Credit2
Date: Fri, 18 Mar 2016 20:06:12 +0100	[thread overview]
Message-ID: <20160318190612.8117.79354.stgit@Solace.station> (raw)
In-Reply-To: <20160318185524.8117.74837.stgit@Solace.station>

From: Justin Weaver <jtweaver@hawaii.edu>

as it was still missing.

Note that this patch "only" implements hard affinity,
i.e., the possibility of specifying on what pCPUs a
certain vCPU can run. Soft affinity (which express a
preference for vCPUs to run on certain pCPUs) is still
not supported by Credit2, even after this patch.

Signed-off-by: Justin Weaver <jtweaver@hawaii.edu>
Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
---
Cc: George Dunlap <dunlapg@umich.edu>
---
 xen/common/sched_credit2.c |  131 ++++++++++++++++++++++++++++++++++----------
 1 file changed, 102 insertions(+), 29 deletions(-)

diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index a650216..3190eb3 100644
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -327,6 +327,36 @@ struct csched2_dom {
     uint16_t nr_vcpus;
 };
 
+/*
+ * When a hard affinity change occurs, we may not be able to check some
+ * (any!) of the other runqueues, when looking for the best new processor
+ * for svc (as trylock-s in choose_cpu() can fail). If that happens, we
+ * pick, in order of decreasing preference:
+ *  - svc's current pcpu;
+ *  - another pcpu from svc's current runq;
+ *  - any cpu.
+ */
+static int get_fallback_cpu(struct csched2_vcpu *svc)
+{
+    int cpu;
+
+    if ( likely(cpumask_test_cpu(svc->vcpu->processor,
+                                 svc->vcpu->cpu_hard_affinity)) )
+        return svc->vcpu->processor;
+
+    cpumask_and(cpumask_scratch, svc->vcpu->cpu_hard_affinity,
+                &svc->rqd->active);
+    cpu = cpumask_first(cpumask_scratch);
+    if ( likely(cpu < nr_cpu_ids) )
+        return cpu;
+
+    cpumask_and(cpumask_scratch, svc->vcpu->cpu_hard_affinity,
+                cpupool_domain_cpumask(svc->vcpu->domain));
+
+    ASSERT(!cpumask_empty(cpumask_scratch));
+
+    return cpumask_first(cpumask_scratch);
+}
 
 /*
  * Time-to-credit, credit-to-time.
@@ -560,8 +590,9 @@ runq_tickle(const struct scheduler *ops, unsigned int cpu, struct csched2_vcpu *
         goto tickle;
     }
     
-    /* Get a mask of idle, but not tickled */
+    /* Get a mask of idle, but not tickled, that new is allowed to run on. */
     cpumask_andnot(&mask, &rqd->idle, &rqd->tickled);
+    cpumask_and(&mask, &mask, new->vcpu->cpu_hard_affinity);
     
     /* If it's not empty, choose one */
     i = cpumask_cycle(cpu, &mask);
@@ -572,9 +603,11 @@ runq_tickle(const struct scheduler *ops, unsigned int cpu, struct csched2_vcpu *
     }
 
     /* Otherwise, look for the non-idle cpu with the lowest credit,
-     * skipping cpus which have been tickled but not scheduled yet */
+     * skipping cpus which have been tickled but not scheduled yet,
+     * that new is allowed to run on. */
     cpumask_andnot(&mask, &rqd->active, &rqd->idle);
     cpumask_andnot(&mask, &mask, &rqd->tickled);
+    cpumask_and(&mask, &mask, new->vcpu->cpu_hard_affinity);
 
     for_each_cpu(i, &mask)
     {
@@ -1124,9 +1157,8 @@ choose_cpu(const struct scheduler *ops, struct vcpu *vc)
             d2printk("%pv -\n", svc->vcpu);
             clear_bit(__CSFLAG_runq_migrate_request, &svc->flags);
         }
-        /* Leave it where it is for now.  When we actually pay attention
-         * to affinity we'll have to figure something out... */
-        return vc->processor;
+
+        return get_fallback_cpu(svc);
     }
 
     /* First check to see if we're here because someone else suggested a place
@@ -1137,45 +1169,56 @@ choose_cpu(const struct scheduler *ops, struct vcpu *vc)
         {
             printk("%s: Runqueue migrate aborted because target runqueue disappeared!\n",
                    __func__);
-            /* Fall-through to normal cpu pick */
         }
         else
         {
-            d2printk("%pv +\n", svc->vcpu);
-            new_cpu = cpumask_cycle(vc->processor, &svc->migrate_rqd->active);
-            goto out_up;
+            cpumask_and(cpumask_scratch, vc->cpu_hard_affinity,
+                        &svc->migrate_rqd->active);
+            new_cpu = cpumask_any(cpumask_scratch);
+            if ( new_cpu < nr_cpu_ids )
+            {
+                d2printk("%pv +\n", svc->vcpu);
+                goto out_up;
+            }
         }
+        /* Fall-through to normal cpu pick */
     }
 
-    /* FIXME: Pay attention to cpu affinity */                                                                                      
-
     min_avgload = MAX_LOAD;
 
     /* Find the runqueue with the lowest instantaneous load */
     for_each_cpu(i, &prv->active_queues)
     {
         struct csched2_runqueue_data *rqd;
-        s_time_t rqd_avgload;
+        s_time_t rqd_avgload = MAX_LOAD;
 
         rqd = prv->rqd + i;
 
-        /* If checking a different runqueue, grab the lock,
-         * read the avg, and then release the lock.
+        /*
+         * If checking a different runqueue, grab the lock, check hard
+         * affinity, read the avg, and then release the lock.
          *
          * If on our own runqueue, don't grab or release the lock;
          * but subtract our own load from the runqueue load to simulate
-         * impartiality */
+         * impartiality.
+         *
+         * Note that, if svc's hard affinity has changed, this is the
+         * first time when we see such change, so it is indeed possible
+         * that none of the cpus in svc's current runqueue is in our
+         * (new) hard affinity!
+         */
         if ( rqd == svc->rqd )
         {
-            rqd_avgload = rqd->b_avgload - svc->avgload;
+            if ( cpumask_intersects(vc->cpu_hard_affinity, &rqd->active) )
+                rqd_avgload = rqd->b_avgload - svc->avgload;
         }
         else if ( spin_trylock(&rqd->lock) )
         {
-            rqd_avgload = rqd->b_avgload;
+            if ( cpumask_intersects(vc->cpu_hard_affinity, &rqd->active) )
+                rqd_avgload = rqd->b_avgload;
+
             spin_unlock(&rqd->lock);
         }
-        else
-            continue;
 
         if ( rqd_avgload < min_avgload )
         {
@@ -1184,12 +1227,14 @@ choose_cpu(const struct scheduler *ops, struct vcpu *vc)
         }
     }
 
-    /* We didn't find anyone (most likely because of spinlock contention); leave it where it is */
+    /* We didn't find anyone (most likely because of spinlock contention). */
     if ( min_rqi == -1 )
-        new_cpu = vc->processor;
+        new_cpu = get_fallback_cpu(svc);
     else
     {
-        new_cpu = cpumask_cycle(vc->processor, &prv->rqd[min_rqi].active);
+        cpumask_and(cpumask_scratch, vc->cpu_hard_affinity,
+                    &prv->rqd[min_rqi].active);
+        new_cpu = cpumask_any(cpumask_scratch);
         BUG_ON(new_cpu >= nr_cpu_ids);
     }
 
@@ -1269,7 +1314,12 @@ static void migrate(const struct scheduler *ops,
             on_runq=1;
         }
         __runq_deassign(svc);
-        svc->vcpu->processor = cpumask_any(&trqd->active);
+
+        cpumask_and(cpumask_scratch, svc->vcpu->cpu_hard_affinity,
+                    &trqd->active);
+        svc->vcpu->processor = cpumask_any(cpumask_scratch);
+        BUG_ON(svc->vcpu->processor >= nr_cpu_ids);
+
         __runq_assign(svc, trqd);
         if ( on_runq )
         {
@@ -1283,6 +1333,17 @@ static void migrate(const struct scheduler *ops,
     }
 }
 
+/*
+ * It makes sense considering migrating svc to rqd, if:
+ *  - svc is not already flagged to migrate,
+ *  - if svc is allowed to run on at least one of the pcpus of rqd.
+ */
+static bool_t vcpu_is_migrateable(struct csched2_vcpu *svc,
+                                  struct csched2_runqueue_data *rqd)
+{
+    return !(svc->flags & CSFLAG_runq_migrate_request) &&
+           cpumask_intersects(svc->vcpu->cpu_hard_affinity, &rqd->active);
+}
 
 static void balance_load(const struct scheduler *ops, int cpu, s_time_t now)
 {
@@ -1391,8 +1452,7 @@ retry:
 
         __update_svc_load(ops, push_svc, 0, now);
 
-        /* Skip this one if it's already been flagged to migrate */
-        if ( push_svc->flags & CSFLAG_runq_migrate_request )
+        if ( !vcpu_is_migrateable(push_svc, st.orqd) )
             continue;
 
         list_for_each( pull_iter, &st.orqd->svc )
@@ -1404,8 +1464,7 @@ retry:
                 __update_svc_load(ops, pull_svc, 0, now);
             }
         
-            /* Skip this one if it's already been flagged to migrate */
-            if ( pull_svc->flags & CSFLAG_runq_migrate_request )
+            if ( !vcpu_is_migrateable(pull_svc, st.lrqd) )
                 continue;
 
             consider(&st, push_svc, pull_svc);
@@ -1421,8 +1480,7 @@ retry:
     {
         struct csched2_vcpu * pull_svc = list_entry(pull_iter, struct csched2_vcpu, rqd_elem);
         
-        /* Skip this one if it's already been flagged to migrate */
-        if ( pull_svc->flags & CSFLAG_runq_migrate_request )
+        if ( !vcpu_is_migrateable(pull_svc, st.lrqd) )
             continue;
 
         /* Consider pull only */
@@ -1461,11 +1519,22 @@ csched2_vcpu_migrate(
 
     /* Check if new_cpu is valid */
     BUG_ON(!cpumask_test_cpu(new_cpu, &CSCHED2_PRIV(ops)->initialized));
+    ASSERT(cpumask_test_cpu(new_cpu, vc->cpu_hard_affinity));
 
     trqd = RQD(ops, new_cpu);
 
+    /*
+     * Do the actual movement toward new_cpu, and update vc->processor.
+     * If we are changing runqueue, migrate() takes care of everything.
+     * If we are not changing runqueue, we need to update vc->processor
+     * here. In fact, if, for instance, we are here because the vcpu's
+     * hard affinity changed, we don't want to risk leaving vc->processor
+     * pointing to a pcpu where we can't run any longer.
+     */
     if ( trqd != svc->rqd )
         migrate(ops, svc, trqd, NOW());
+    else
+        vc->processor = new_cpu;
 }
 
 static int
@@ -1685,6 +1754,10 @@ runq_candidate(struct csched2_runqueue_data *rqd,
     {
         struct csched2_vcpu * svc = list_entry(iter, struct csched2_vcpu, runq_elem);
 
+        /* Only consider vcpus that are allowed to run on this processor. */
+        if ( !cpumask_test_cpu(cpu, svc->vcpu->cpu_hard_affinity) )
+            continue;
+
         /* If this is on a different processor, don't pull it unless
          * its credit is at least CSCHED2_MIGRATE_RESIST higher. */
         if ( svc->vcpu->processor != cpu


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel

  parent reply	other threads:[~2016-03-18 19:06 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-18 19:03 [PATCH 00/16] Fixes and improvement (including hard affinity!) for Credit2 Dario Faggioli
2016-03-18 19:04 ` [PATCH 01/16] xen: sched: fix locking when allocating an RTDS pCPU Dario Faggioli
2016-03-19  2:22   ` Meng Xu
2016-03-23 15:37   ` George Dunlap
2016-03-18 19:04 ` [PATCH 02/16] xen: sched: add .init_pdata hook to the scheduler interface Dario Faggioli
2016-03-22  8:08   ` Juergen Gross
2016-03-23 17:32   ` George Dunlap
2016-03-18 19:04 ` [PATCH 03/16] xen: sched: make implementing .alloc_pdata optional Dario Faggioli
2016-03-19  2:23   ` Meng Xu
2016-03-21 14:22   ` Jan Beulich
2016-03-23 17:36     ` George Dunlap
2016-03-24  9:43       ` Jan Beulich
2016-03-24 13:14         ` Dario Faggioli
2016-03-21 14:48   ` Juergen Gross
2016-03-21 15:07     ` Jan Beulich
2016-04-01 17:01       ` Dario Faggioli
2016-04-04  4:21         ` Juergen Gross
2016-04-04  6:13         ` Jan Beulich
2016-04-05 16:01           ` Dario Faggioli
2016-03-23 17:38   ` George Dunlap
2016-03-18 19:04 ` [PATCH 04/16] xen: sched: implement .init_pdata in all schedulers Dario Faggioli
2016-03-19  2:24   ` Meng Xu
2016-03-22  8:03   ` Juergen Gross
2016-03-23 17:46     ` George Dunlap
2016-03-18 19:04 ` [PATCH 05/16] xen: sched: move pCPU initialization in an helper Dario Faggioli
2016-03-23 17:51   ` George Dunlap
2016-03-23 18:09     ` George Dunlap
2016-03-24 13:21     ` Dario Faggioli
2016-03-18 19:04 ` [PATCH 06/16] xen: sched: prepare a .switch_sched hook for Credit1 Dario Faggioli
2016-03-18 19:04 ` [PATCH 07/16] xen: sched: prepare a .switch_sched hook for Credit2 Dario Faggioli
2016-03-18 19:04 ` [PATCH 08/16] " Dario Faggioli
2016-03-19  2:24   ` Meng Xu
2016-03-21 14:25   ` Jan Beulich
2016-03-18 19:05 ` [PATCH 09/16] xen: sched: close potential races when switching scheduler to CPUs Dario Faggioli
2016-03-19  2:25   ` Meng Xu
2016-03-23 19:05   ` George Dunlap
2016-04-05 16:26     ` Dario Faggioli
2016-04-06 15:51       ` Dario Faggioli
2016-03-24 12:14   ` George Dunlap
2016-04-05 17:37     ` Dario Faggioli
2016-04-06 16:21       ` Dario Faggioli
2016-03-18 19:05 ` [PATCH 10/16] xen: sched: improve credit2 bootparams' scope, placement and signedness Dario Faggioli
2016-03-21 14:51   ` Juergen Gross
2016-03-24 12:20   ` George Dunlap
2016-03-18 19:05 ` [PATCH 11/16] xen: sched: on Credit2, don't reprogram the timer if idle Dario Faggioli
2016-03-24 15:03   ` George Dunlap
2016-03-18 19:05 ` [PATCH 12/16] xen: sched: fix per-socket runqueue creation in credit2 Dario Faggioli
2016-03-24 12:24   ` George Dunlap
2016-03-18 19:05 ` [PATCH 13/16] xen: sched: allow for choosing credit2 runqueues configuration at boot Dario Faggioli
2016-03-22  7:46   ` Juergen Gross
2016-03-24 12:36   ` George Dunlap
2016-03-18 19:05 ` [PATCH 14/16] xen: sched: per-core runqueues as default in credit2 Dario Faggioli
2016-03-24 12:37   ` George Dunlap
2016-03-18 19:06 ` [PATCH 15/16] xen: sched: scratch space for cpumasks on Credit2 Dario Faggioli
2016-03-18 19:27   ` Andrew Cooper
2016-03-24 12:44     ` George Dunlap
2016-03-24 12:56       ` Andrew Cooper
2016-03-24 13:10       ` Dario Faggioli
2016-03-18 19:06 ` Dario Faggioli [this message]
2016-03-24 15:42   ` [PATCH 16/16] xen: sched: implement vcpu hard affinity in Credit2 George Dunlap
2016-04-05 16:50     ` Dario Faggioli

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160318190612.8117.79354.stgit@Solace.station \
    --to=dario.faggioli@citrix.com \
    --cc=dunlapg@umich.edu \
    --cc=jtweaver@hawaii.edu \
    --cc=xen-devel@lists.xenproject.org \
    --subject='Re: [PATCH 16/16] xen: sched: implement vcpu hard affinity in Credit2' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).