[PULL 06/25] migration: Introduce dirty-limit capability

[Juan Quintela <quintela@redhat.com>]

From: Hyman Huang(黄勇) <yong.huang@smartx.com>

Introduce migration dirty-limit capability, which can
be turned on before live migration and limit dirty
page rate durty live migration.

Introduce migrate_dirty_limit function to help check
if dirty-limit capability enabled during live migration.

Meanwhile, refactor vcpu_dirty_rate_stat_collect
so that period can be configured instead of hardcoded.

dirty-limit capability is kind of like auto-converge
but using dirty limit instead of traditional cpu-throttle
to throttle guest down. To enable this feature, turn on
the dirty-limit capability before live migration using
migrate-set-capabilities, and set the parameters
"x-vcpu-dirty-limit-period", "vcpu-dirty-limit" suitably
to speed up convergence.

Signed-off-by: Hyman Huang(黄勇) <yong.huang@smartx.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <168618975839.6361.17407633874747688653-4@git.sr.ht>
Signed-off-by: Juan Quintela <quintela@redhat.com>
---
 qapi/migration.json  | 13 ++++++++++++-
 migration/options.h  |  1 +
 migration/options.c  | 23 ++++++++++++++++++++++-
 softmmu/dirtylimit.c | 18 ++++++++++++++----
 4 files changed, 49 insertions(+), 6 deletions(-)

diff --git a/qapi/migration.json b/qapi/migration.json
index 22104cef08..e094438d74 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -497,6 +497,16 @@
 #     are present.  'return-path' capability must be enabled to use
 #     it.  (since 8.1)
 #
+# @dirty-limit: If enabled, migration will use the dirty-limit algo to
+#               throttle down guest instead of auto-converge algo.
+#               Throttle algo only works when vCPU's dirtyrate greater
+#               than 'vcpu-dirty-limit', read processes in guest os
+#               aren't penalized any more, so this algo can improve
+#               performance of vCPU during live migration. This is an
+#               optional performance feature and should not affect the
+#               correctness of the existing auto-converge algo.
+#               (since 8.1)
+#
 # Features:
 #
 # @unstable: Members @x-colo and @x-ignore-shared are experimental.
@@ -512,7 +522,8 @@
            'dirty-bitmaps', 'postcopy-blocktime', 'late-block-activate',
            { 'name': 'x-ignore-shared', 'features': [ 'unstable' ] },
            'validate-uuid', 'background-snapshot',
-           'zero-copy-send', 'postcopy-preempt', 'switchover-ack'] }
+           'zero-copy-send', 'postcopy-preempt', 'switchover-ack',
+           'dirty-limit'] }
 
 ##
 # @MigrationCapabilityStatus:
diff --git a/migration/options.h b/migration/options.h
index 9aaf363322..045e2a41a2 100644
--- a/migration/options.h
+++ b/migration/options.h
@@ -29,6 +29,7 @@ bool migrate_block(void);
 bool migrate_colo(void);
 bool migrate_compress(void);
 bool migrate_dirty_bitmaps(void);
+bool migrate_dirty_limit(void);
 bool migrate_events(void);
 bool migrate_ignore_shared(void);
 bool migrate_late_block_activate(void);
diff --git a/migration/options.c b/migration/options.c
index 7d2d98830e..7d83f190d6 100644
--- a/migration/options.c
+++ b/migration/options.c
@@ -27,6 +27,7 @@
 #include "qemu-file.h"
 #include "ram.h"
 #include "options.h"
+#include "sysemu/kvm.h"
 
 /* Maximum migrate downtime set to 2000 seconds */
 #define MAX_MIGRATE_DOWNTIME_SECONDS 2000
@@ -196,7 +197,7 @@ Property migration_properties[] = {
 #endif
     DEFINE_PROP_MIG_CAP("x-switchover-ack",
                         MIGRATION_CAPABILITY_SWITCHOVER_ACK),
-
+    DEFINE_PROP_MIG_CAP("x-dirty-limit", MIGRATION_CAPABILITY_DIRTY_LIMIT),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -242,6 +243,13 @@ bool migrate_dirty_bitmaps(void)
     return s->capabilities[MIGRATION_CAPABILITY_DIRTY_BITMAPS];
 }
 
+bool migrate_dirty_limit(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return s->capabilities[MIGRATION_CAPABILITY_DIRTY_LIMIT];
+}
+
 bool migrate_events(void)
 {
     MigrationState *s = migrate_get_current();
@@ -572,6 +580,19 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp)
             return false;
         }
     }
+    if (new_caps[MIGRATION_CAPABILITY_DIRTY_LIMIT]) {
+        if (new_caps[MIGRATION_CAPABILITY_AUTO_CONVERGE]) {
+            error_setg(errp, "dirty-limit conflicts with auto-converge"
+                       " either of then available currently");
+            return false;
+        }
+
+        if (!kvm_enabled() || !kvm_dirty_ring_enabled()) {
+            error_setg(errp, "dirty-limit requires KVM with accelerator"
+                   " property 'dirty-ring-size' set");
+            return false;
+        }
+    }
 
     return true;
 }
diff --git a/softmmu/dirtylimit.c b/softmmu/dirtylimit.c
index e80201097a..942d876523 100644
--- a/softmmu/dirtylimit.c
+++ b/softmmu/dirtylimit.c
@@ -24,6 +24,9 @@
 #include "hw/boards.h"
 #include "sysemu/kvm.h"
 #include "trace.h"
+#include "migration/misc.h"
+#include "migration/migration.h"
+#include "migration/options.h"
 
 /*
  * Dirtylimit stop working if dirty page rate error
@@ -75,14 +78,21 @@ static bool dirtylimit_quit;
 
 static void vcpu_dirty_rate_stat_collect(void)
 {
+    MigrationState *s = migrate_get_current();
     VcpuStat stat;
     int i = 0;
+    int64_t period = DIRTYLIMIT_CALC_TIME_MS;
+
+    if (migrate_dirty_limit() &&
+        migration_is_active(s)) {
+        period = s->parameters.x_vcpu_dirty_limit_period;
+    }
 
     /* calculate vcpu dirtyrate */
-    vcpu_calculate_dirtyrate(DIRTYLIMIT_CALC_TIME_MS,
-                             &stat,
-                             GLOBAL_DIRTY_LIMIT,
-                             false);
+    vcpu_calculate_dirtyrate(period,
+                              &stat,
+                              GLOBAL_DIRTY_LIMIT,
+                              false);
 
     for (i = 0; i < stat.nvcpu; i++) {
         vcpu_dirty_rate_stat->stat.rates[i].id = i;
-- 
2.40.1