libvirt support to force convergence of live guest migration

Busy enterprise workloads hosted on large sized VM's tend to dirty
memory faster than the transfer rate achieved via live guest migration.
Despite some good recent improvements (& using dedicated 10Gig NICs
between hosts) the live migration may NOT converge.

Recently support was added in qemu (version 1.6) to allow a user to
choose if they wish to force convergence of their migration via a
new migration capability : "auto-converge". This feature allows for qemu
to auto-detect lack of convergence and trigger a throttle-down of the
VCPUs.

This patch includes the libvirt support needed to trigger this
feature. (Testing is in progress)
Signed-off-by: NChegu Vinod <chegu_vinod@hp.com>
Signed-off-by: NJiri Denemark <jdenemar@redhat.com>

include/libvirt/libvirt.h.in

@@ -1200,6 +1200,7 @@ typedef enum {
     VIR_MIGRATE_OFFLINE           = (1 << 10), /* offline migrate */
     VIR_MIGRATE_COMPRESSED        = (1 << 11), /* compress data during migration */
     VIR_MIGRATE_ABORT_ON_ERROR    = (1 << 12), /* abort migration on I/O errors happened during migration */
+    VIR_MIGRATE_AUTO_CONVERGE     = (1 << 13), /* force convergence */
 } virDomainMigrateFlags;
 
 

src/libvirt.c

@@ -4408,7 +4408,8 @@ virDomainMigrateVersion1(virDomainPtr domain,
     if (ret == 0 && info.state == VIR_DOMAIN_PAUSED)
         flags |= VIR_MIGRATE_PAUSED;
 
-    destflags = flags & ~VIR_MIGRATE_ABORT_ON_ERROR;
+    destflags = flags & ~(VIR_MIGRATE_ABORT_ON_ERROR |
+                          VIR_MIGRATE_AUTO_CONVERGE);
 
     /* Prepare the migration.
      *
@@ -4538,7 +4539,8 @@ virDomainMigrateVersion2(virDomainPtr domain,
     if (ret == 0 && info.state == VIR_DOMAIN_PAUSED)
         flags |= VIR_MIGRATE_PAUSED;
 
-    destflags = flags & ~VIR_MIGRATE_ABORT_ON_ERROR;
+    destflags = flags & ~(VIR_MIGRATE_ABORT_ON_ERROR |
+                          VIR_MIGRATE_AUTO_CONVERGE);
 
     VIR_DEBUG("Prepare2 %p flags=%lx", dconn, destflags);
     ret = dconn->driver->domainMigratePrepare2
@@ -4710,7 +4712,8 @@ virDomainMigrateVersion3Full(virDomainPtr domain,
     if (ret == 0 && state == VIR_DOMAIN_PAUSED)
         flags |= VIR_MIGRATE_PAUSED;
 
-    destflags = flags & ~VIR_MIGRATE_ABORT_ON_ERROR;
+    destflags = flags & ~(VIR_MIGRATE_ABORT_ON_ERROR |
+                          VIR_MIGRATE_AUTO_CONVERGE);
 
     VIR_DEBUG("Prepare3 %p flags=%x", dconn, destflags);
     cookiein = cookieout;

src/qemu/qemu_migration.c

@@ -1621,6 +1621,41 @@ cleanup:
     return ret;
 }
 
+static int
+qemuMigrationSetAutoConverge(virQEMUDriverPtr driver,
+                             virDomainObjPtr vm,
+                             enum qemuDomainAsyncJob job)
+{
+    qemuDomainObjPrivatePtr priv = vm->privateData;
+    int ret;
+
+    if (qemuDomainObjEnterMonitorAsync(driver, vm, job) < 0)
+        return -1;
+
+    ret = qemuMonitorGetMigrationCapability(
+                priv->mon,
+                QEMU_MONITOR_MIGRATION_CAPS_AUTO_CONVERGE);
+
+    if (ret < 0) {
+        goto cleanup;
+    } else if (ret == 0) {
+        virReportError(VIR_ERR_ARGUMENT_UNSUPPORTED, "%s",
+                       _("Auto-Converge is not supported by "
+                         "QEMU binary"));
+        ret = -1;
+        goto cleanup;
+    }
+
+    ret = qemuMonitorSetMigrationCapability(
+                priv->mon,
+                QEMU_MONITOR_MIGRATION_CAPS_AUTO_CONVERGE);
+
+cleanup:
+    qemuDomainObjExitMonitor(driver, vm);
+    return ret;
+}
+
+
 static int
 qemuMigrationWaitForSpice(virQEMUDriverPtr driver,
                           virDomainObjPtr vm)
@@ -3234,6 +3269,11 @@ qemuMigrationRun(virQEMUDriverPtr driver,
                                     QEMU_ASYNC_JOB_MIGRATION_OUT) < 0)
         goto cleanup;
 
+    if (flags & VIR_MIGRATE_AUTO_CONVERGE &&
+        qemuMigrationSetAutoConverge(driver, vm,
+                                     QEMU_ASYNC_JOB_MIGRATION_OUT) < 0)
+        goto cleanup;
+
     if (qemuDomainObjEnterMonitorAsync(driver, vm,
                                        QEMU_ASYNC_JOB_MIGRATION_OUT) < 0)
         goto cleanup;
@@ -3587,7 +3627,8 @@ static int doPeer2PeerMigrate2(virQEMUDriverPtr driver,
     if (virDomainObjGetState(vm, NULL) == VIR_DOMAIN_PAUSED)
         flags |= VIR_MIGRATE_PAUSED;
 
-    destflags = flags & ~VIR_MIGRATE_ABORT_ON_ERROR;
+    destflags = flags & ~(VIR_MIGRATE_ABORT_ON_ERROR |
+                          VIR_MIGRATE_AUTO_CONVERGE);
 
     VIR_DEBUG("Prepare2 %p", dconn);
     if (flags & VIR_MIGRATE_TUNNELLED) {
@@ -3780,7 +3821,8 @@ doPeer2PeerMigrate3(virQEMUDriverPtr driver,
     if (virDomainObjGetState(vm, NULL) == VIR_DOMAIN_PAUSED)
         flags |= VIR_MIGRATE_PAUSED;
 
-    destflags = flags & ~VIR_MIGRATE_ABORT_ON_ERROR;
+    destflags = flags & ~(VIR_MIGRATE_ABORT_ON_ERROR |
+                          VIR_MIGRATE_AUTO_CONVERGE);
 
     VIR_DEBUG("Prepare3 %p", dconn);
     cookiein = cookieout;

src/qemu/qemu_migration.h

@@ -39,7 +39,8 @@
      VIR_MIGRATE_UNSAFE |                       \
      VIR_MIGRATE_OFFLINE |                      \
      VIR_MIGRATE_COMPRESSED |                   \
-     VIR_MIGRATE_ABORT_ON_ERROR)
+     VIR_MIGRATE_ABORT_ON_ERROR |               \
+     VIR_MIGRATE_AUTO_CONVERGE)
 
 /* All supported migration parameters and their types. */
 # define QEMU_MIGRATION_PARAMETERS                              \

src/qemu/qemu_monitor.c

@@ -121,7 +121,7 @@ VIR_ENUM_IMPL(qemuMonitorMigrationStatus,
 
 VIR_ENUM_IMPL(qemuMonitorMigrationCaps,
               QEMU_MONITOR_MIGRATION_CAPS_LAST,
-              "xbzrle")
+              "xbzrle", "auto-converge")
 
 VIR_ENUM_IMPL(qemuMonitorVMStatus,
               QEMU_MONITOR_VM_STATUS_LAST,

src/qemu/qemu_monitor.h

@@ -451,6 +451,7 @@ int qemuMonitorGetSpiceMigrationStatus(qemuMonitorPtr mon,
 
 typedef enum {
     QEMU_MONITOR_MIGRATION_CAPS_XBZRLE,
+    QEMU_MONITOR_MIGRATION_CAPS_AUTO_CONVERGE,
 
     QEMU_MONITOR_MIGRATION_CAPS_LAST
 } qemuMonitorMigrationCaps;

tools/virsh-domain.c

@@ -8757,6 +8757,10 @@ static const vshCmdOptDef opts_migrate[] = {
      .type = VSH_OT_BOOL,
      .help = N_("compress repeated pages during live migration")
     },
+    {.name = "auto-converge",
+     .type = VSH_OT_BOOL,
+     .help = N_("force convergence during live migration")
+    },
     {.name = "abort-on-error",
      .type = VSH_OT_BOOL,
      .help = N_("abort on soft errors during migration")
@@ -8901,6 +8905,9 @@ doMigrate(void *opaque)
     if (vshCommandOptBool(cmd, "compressed"))
         flags |= VIR_MIGRATE_COMPRESSED;
 
+    if (vshCommandOptBool(cmd, "auto-converge"))
+        flags |= VIR_MIGRATE_AUTO_CONVERGE;
+
     if (vshCommandOptBool(cmd, "offline")) {
         flags |= VIR_MIGRATE_OFFLINE;
     }