xen: sched: allow for choosing credit2 runqueues configuration at boot

In fact, credit2 uses CPU topology to decide how to arrange
its internal runqueues. Before this change, only 'one runqueue
per socket' was allowed. However, experiments have shown that,
for instance, having one runqueue per physical core improves
performance, especially in case hyperthreading is available.

In general, it makes sense to allow users to pick one runqueue
arrangement at boot time, so that:
 - more experiments can be easily performed to even better
   assess and improve performance;
 - one can select the best configuration for his specific
   use case and/or hardware.

This patch enables the above.

Note that, for correctly arranging runqueues to be per-core,
just checking cpu_to_core() on the host CPUs is not enough.
In fact, cores (and hyperthreads) on different sockets, can
have the same core (and thread) IDs! We, therefore, need to
check whether the full topology of two CPUs matches, for
them to be put in the same runqueue.

Note also that the default (although not functional) for
credit2, since now, has been per-socket runqueue. This patch
leaves things that way, to avoid mixing policy and technical
changes.

Finally, it would be a nice feature to be able to select
a particular runqueue arrangement, even when creating a
Credit2 cpupool. This is left as future work.

Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Signed-off-by: Uma Sharma <uma.sharma523@gmail.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: George Dunlap <george.dunlap@citrix.com>

diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
index ca77e3bcc36b0161aba8a1e460cebdc060887c3c..0047f94f525060a472a46c61ee7e9e5bf21d483f 100644 (file)
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -469,6 +469,25 @@ combination with the `low_crashinfo` command line option.
 ### credit2\_load\_window\_shift
 > `= <integer>`
 
+### credit2\_runqueue
+> `= core | socket | node | all`
+
+> Default: `socket`
+
+Specify how host CPUs are arranged in runqueues. Runqueues are kept
+balanced with respect to the load generated by the vCPUs running on
+them. Smaller runqueues (as in with `core`) means more accurate load
+balancing (for instance, it will deal better with hyperthreading),
+but also more overhead.
+
+Available alternatives, with their meaning, are:
+* `core`: one runqueue per each physical core of the host;
+* `socket`: one runqueue per each physical socket (which often,
+            but not always, matches a NUMA node) of the host;
+* `node`: one runqueue per each NUMA node of the host;
+* `all`: just one runqueue shared by all the logical pCPUs of
+         the host
+
 ### dbgp
 > `= ehci[ <integer> | @pci<bus>:<slot>.<func> ]`
 

diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index a61a45a223c4e5c403da096616f3a3f1ac663b9a..d43f67ac97c6f03e9341a86fbcdd5c0009ae3cb6 100644 (file)
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -81,10 +81,6 @@
  * Credits are "reset" when the next vcpu in the runqueue is less than
  * or equal to zero.  At that point, everyone's credits are "clipped"
  * to a small value, and a fixed credit is added to everyone.
- *
- * The plan is for all cores that share an L2 will share the same
- * runqueue.  At the moment, there is one global runqueue for all
- * cores.
  */
 
 /*
@@ -192,6 +188,63 @@ integer_param("credit2_balance_under", opt_underload_balance_tolerance);
 static int __read_mostly opt_overload_balance_tolerance = -3;
 integer_param("credit2_balance_over", opt_overload_balance_tolerance);
 
+/*
+ * Runqueue organization.
+ *
+ * The various cpus are to be assigned each one to a runqueue, and we
+ * want that to happen basing on topology. At the moment, it is possible
+ * to choose to arrange runqueues to be:
+ *
+ * - per-core: meaning that there will be one runqueue per each physical
+ *             core of the host. This will happen if the opt_runqueue
+ *             parameter is set to 'core';
+ *
+ * - per-socket: meaning that there will be one runqueue per each physical
+ *               socket (AKA package, which often, but not always, also
+ *               matches a NUMA node) of the host; This will happen if
+ *               the opt_runqueue parameter is set to 'socket';
+ *
+ * - per-node: meaning that there will be one runqueue per each physical
+ *             NUMA node of the host. This will happen if the opt_runqueue
+ *             parameter is set to 'node';
+ *
+ * - global: meaning that there will be only one runqueue to which all the
+ *           (logical) processors of the host belong. This will happen if
+ *           the opt_runqueue parameter is set to 'all'.
+ *
+ * Depending on the value of opt_runqueue, therefore, cpus that are part of
+ * either the same physical core, the same physical socket, the same NUMA
+ * node, or just all of them, will be put together to form runqueues.
+ */
+#define OPT_RUNQUEUE_CORE   0
+#define OPT_RUNQUEUE_SOCKET 1
+#define OPT_RUNQUEUE_NODE   2
+#define OPT_RUNQUEUE_ALL    3
+static const char *const opt_runqueue_str[] = {
+    [OPT_RUNQUEUE_CORE] = "core",
+    [OPT_RUNQUEUE_SOCKET] = "socket",
+    [OPT_RUNQUEUE_NODE] = "node",
+    [OPT_RUNQUEUE_ALL] = "all"
+};
+static int __read_mostly opt_runqueue = OPT_RUNQUEUE_SOCKET;
+
+static void parse_credit2_runqueue(const char *s)
+{
+    unsigned int i;
+
+    for ( i = 0; i < ARRAY_SIZE(opt_runqueue_str); i++ )
+    {
+        if ( !strcmp(s, opt_runqueue_str[i]) )
+        {
+            opt_runqueue = i;
+            return;
+        }
+    }
+
+    printk("WARNING, unrecognized value of credit2_runqueue option!\n");
+}
+custom_param("credit2_runqueue", parse_credit2_runqueue);
+
 /*
  * Per-runqueue data
  */
@@ -1974,6 +2027,22 @@ static void deactivate_runqueue(struct csched2_private *prv, int rqi)
     cpumask_clear_cpu(rqi, &prv->active_queues);
 }
 
+static inline bool_t same_node(unsigned int cpua, unsigned int cpub)
+{
+    return cpu_to_node(cpua) == cpu_to_node(cpub);
+}
+
+static inline bool_t same_socket(unsigned int cpua, unsigned int cpub)
+{
+    return cpu_to_socket(cpua) == cpu_to_socket(cpub);
+}
+
+static inline bool_t same_core(unsigned int cpua, unsigned int cpub)
+{
+    return same_socket(cpua, cpub) &&
+           cpu_to_core(cpua) == cpu_to_core(cpub);
+}
+
 static unsigned int
 cpu_to_runqueue(struct csched2_private *prv, unsigned int cpu)
 {
@@ -2006,7 +2075,10 @@ cpu_to_runqueue(struct csched2_private *prv, unsigned int cpu)
         BUG_ON(cpu_to_socket(cpu) == XEN_INVALID_SOCKET_ID ||
                cpu_to_socket(peer_cpu) == XEN_INVALID_SOCKET_ID);
 
-        if ( cpu_to_socket(cpumask_first(&rqd->active)) == cpu_to_socket(cpu) )
+        if ( opt_runqueue == OPT_RUNQUEUE_ALL ||
+             (opt_runqueue == OPT_RUNQUEUE_CORE && same_core(peer_cpu, cpu)) ||
+             (opt_runqueue == OPT_RUNQUEUE_SOCKET && same_socket(peer_cpu, cpu)) ||
+             (opt_runqueue == OPT_RUNQUEUE_NODE && same_node(peer_cpu, cpu)) )
             break;
     }
 
@@ -2170,6 +2242,7 @@ csched2_init(struct scheduler *ops)
     printk(" load_window_shift: %d\n", opt_load_window_shift);
     printk(" underload_balance_tolerance: %d\n", opt_underload_balance_tolerance);
     printk(" overload_balance_tolerance: %d\n", opt_overload_balance_tolerance);
+    printk(" runqueues arrangement: %s\n", opt_runqueue_str[opt_runqueue]);
 
     if ( opt_load_window_shift < LOADAVG_WINDOW_SHIFT_MIN )
     {