qmp: Support for querying stats

Gathering statistics is important for development, for monitoring and
for performance measurement.  There are tools such as kvm_stat that do
this and they rely on the _user_ knowing the interesting data points
rather than the tool (which can treat them as opaque).

The commands introduced in this commit introduce QMP support for
querying stats; the goal is to take the capabilities of these tools
and making them available throughout the whole virtualization stack,
so that one can observe, monitor and measure virtual machines without
having shell access + root on the host that runs them.

query-stats returns a list of all stats per target type (only VM
and vCPU to start); future commits add extra options for specifying
stat names, vCPU qom paths, and providers.  All these are used by the
HMP command "info stats".  Because of the development usecases around
statistics, a good HMP interface is important.

query-stats-schemas returns a list of stats included in each target
type, with an option for specifying the provider.  The concepts in the
schema are based on the KVM binary stats' own introspection data, just
translated to QAPI.

There are two reasons to have a separate schema that is not tied to
the QAPI schema.  The first is the contents of the schemas: the new
introspection data provides different information than the QAPI data,
namely unit of measurement, how the numbers are gathered and change
(peak/instant/cumulative/histogram), and histogram bucket sizes.
There's really no reason to have this kind of metadata in the QAPI
introspection schema (except possibly for the unit of measure, but
there's a very weak justification).

Another reason is the dynamicity of the schema.  The QAPI introspection
data is very much static; and while QOM is somewhat more dynamic,
generally we consider that to be a bug rather than a feature these days.
On the other hand, the statistics that are exposed by QEMU might be
passed through from another source, such as KVM, and the disadvantages of
manually updating the QAPI schema for outweight the benefits from vetting
the statistics and filtering out anything that seems "too unstable".
Running old QEMU with new kernel is a supported usecase; if old QEMU
cannot expose statistics from a new kernel, or if a kernel developer
needs to change QEMU before gathering new info from the new kernel,
then that is a poor user interface.

The framework provides a method to register callbacks for these QMP
commands.  Most of the work in fact is done by the callbacks, and a
large majority of this patch is new QAPI structs and commands.

Examples (with KVM stats):

- Query all VM stats:

{ "execute": "query-stats", "arguments" : { "target": "vm" } }

{ "return": [
     { "provider": "kvm",
       "stats": [
          { "name": "max_mmu_page_hash_collisions", "value": 0 },
          { "name": "max_mmu_rmap_size", "value": 0 },
          { "name": "nx_lpage_splits", "value": 148 },
          ... ] },
     { "provider": "xyz",
       "stats": [ ... ] }
] }

- Query all vCPU stats:

{ "execute": "query-stats", "arguments" : { "target": "vcpu" } }

{ "return": [
     { "provider": "kvm",
       "qom_path": "/machine/unattached/device[0]"
       "stats": [
          { "name": "guest_mode", "value": 0 },
          { "name": "directed_yield_successful", "value": 0 },
          { "name": "directed_yield_attempted", "value": 106 },
          ... ] },
     { "provider": "kvm",
       "qom_path": "/machine/unattached/device[1]"
       "stats": [
          { "name": "guest_mode", "value": 0 },
          { "name": "directed_yield_successful", "value": 0 },
          { "name": "directed_yield_attempted", "value": 106 },
          ... ] },
] }

- Retrieve the schemas:

{ "execute": "query-stats-schemas" }

{ "return": [
    { "provider": "kvm",
      "target": "vcpu",
      "stats": [
         { "name": "guest_mode",
           "unit": "none",
           "base": 10,
           "exponent": 0,
           "type": "instant" },
        { "name": "directed_yield_successful",
           "unit": "none",
           "base": 10,
           "exponent": 0,
           "type": "cumulative" },
        ... ]
    },
    { "provider": "kvm",
      "target": "vm",
      "stats": [
        { "name": "max_mmu_page_hash_collisions",
           "unit": "none",
           "base": 10,
           "exponent": 0,
           "type": "peak" },
        ... ]
    },
    { "provider": "xyz",
      "target": "vm",
      "stats": [ ... ]
    }
] }

Signed-off-by: Mark Kanda <mark.kanda@oracle.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 95 insertions, 0 deletions

diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c
index 1ebb89f46c..a6ac8d7473 100644
--- a/monitor/qmp-cmds.c
+++ b/monitor/qmp-cmds.c
@@ -35,6 +35,7 @@
 #include "qapi/qapi-commands-control.h"
 #include "qapi/qapi-commands-machine.h"
 #include "qapi/qapi-commands-misc.h"
+#include "qapi/qapi-commands-stats.h"
 #include "qapi/qapi-commands-ui.h"
 #include "qapi/type-helpers.h"
 #include "qapi/qmp/qerror.h"
@@ -43,6 +44,7 @@
 #include "hw/acpi/acpi_dev_interface.h"
 #include "hw/intc/intc.h"
 #include "hw/rdma/rdma.h"
+#include "monitor/stats.h"
 
 NameInfo *qmp_query_name(Error **errp)
 {
@@ -441,3 +443,96 @@ HumanReadableText *qmp_x_query_irq(Error **errp)
 
     return human_readable_text_from_str(buf);
 }
+
+typedef struct StatsCallbacks {
+    StatRetrieveFunc *stats_cb;
+    SchemaRetrieveFunc *schemas_cb;
+    QTAILQ_ENTRY(StatsCallbacks) next;
+} StatsCallbacks;
+
+static QTAILQ_HEAD(, StatsCallbacks) stats_callbacks =
+    QTAILQ_HEAD_INITIALIZER(stats_callbacks);
+
+void add_stats_callbacks(StatRetrieveFunc *stats_fn,
+                         SchemaRetrieveFunc *schemas_fn)
+{
+    StatsCallbacks *entry = g_new(StatsCallbacks, 1);
+    entry->stats_cb = stats_fn;
+    entry->schemas_cb = schemas_fn;
+
+    QTAILQ_INSERT_TAIL(&stats_callbacks, entry, next);
+}
+
+static bool invoke_stats_cb(StatsCallbacks *entry,
+                            StatsResultList **stats_results,
+                            StatsFilter *filter,
+                            Error **errp)
+{
+    ERRP_GUARD();
+
+    entry->stats_cb(stats_results, filter->target, errp);
+    if (*errp) {
+        qapi_free_StatsResultList(*stats_results);
+        *stats_results = NULL;
+        return false;
+    }
+    return true;
+}
+
+StatsResultList *qmp_query_stats(StatsFilter *filter, Error **errp)
+{
+    StatsResultList *stats_results = NULL;
+    StatsCallbacks *entry;
+
+    QTAILQ_FOREACH(entry, &stats_callbacks, next) {
+        if (!invoke_stats_cb(entry, &stats_results, filter, errp)) {
+            break;
+        }
+    }
+
+    return stats_results;
+}
+
+StatsSchemaList *qmp_query_stats_schemas(Error **errp)
+{
+    StatsSchemaList *stats_results = NULL;
+    StatsCallbacks *entry;
+    ERRP_GUARD();
+
+    QTAILQ_FOREACH(entry, &stats_callbacks, next) {
+        entry->schemas_cb(&stats_results, errp);
+        if (*errp) {
+            qapi_free_StatsSchemaList(stats_results);
+            return NULL;
+        }
+    }
+
+    return stats_results;
+}
+
+void add_stats_entry(StatsResultList **stats_results, StatsProvider provider,
+                     const char *qom_path, StatsList *stats_list)
+{
+    StatsResult *entry = g_new0(StatsResult, 1);
+
+    entry->provider = provider;
+    if (qom_path) {
+        entry->has_qom_path = true;
+        entry->qom_path = g_strdup(qom_path);
+    }
+    entry->stats = stats_list;
+
+    QAPI_LIST_PREPEND(*stats_results, entry);
+}
+
+void add_stats_schema(StatsSchemaList **schema_results,
+                      StatsProvider provider, StatsTarget target,
+                      StatsSchemaValueList *stats_list)
+{
+    StatsSchema *entry = g_new0(StatsSchema, 1);
+
+    entry->provider = provider;
+    entry->target = target;
+    entry->stats = stats_list;
+    QAPI_LIST_PREPEND(*schema_results, entry);
+}