[libvirt] [PATCH v3 03/14] qemu: Handle postcopy-active migration state
Jiri Denemark
jdenemar at redhat.com
Wed Mar 2 11:42:24 UTC 2016
Migration enters "postcopy-active" state after QEMU switches to
post-copy and pauses guest CPUs. From libvirt's point of view this state
is similar to "completed" because we need to transfer guest execution to
the destination host.
Signed-off-by: Jiri Denemark <jdenemar at redhat.com>
---
Notes:
Version 3:
- remove completed stats for incoming post-copy migration
Version 2:
- no change
src/qemu/qemu_migration.c | 103 +++++++++++++++++++++++++++++++++++++------
src/qemu/qemu_monitor.c | 2 +-
src/qemu/qemu_monitor.h | 1 +
src/qemu/qemu_monitor_json.c | 1 +
src/qemu/qemu_process.c | 10 ++++-
5 files changed, 101 insertions(+), 16 deletions(-)
diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c
index 38fa81c..fdd95c5 100644
--- a/src/qemu/qemu_migration.c
+++ b/src/qemu/qemu_migration.c
@@ -2460,6 +2460,7 @@ qemuMigrationUpdateJobType(qemuDomainJobInfoPtr jobInfo)
case QEMU_MONITOR_MIGRATION_STATUS_SETUP:
case QEMU_MONITOR_MIGRATION_STATUS_ACTIVE:
+ case QEMU_MONITOR_MIGRATION_STATUS_POSTCOPY:
case QEMU_MONITOR_MIGRATION_STATUS_CANCELLING:
case QEMU_MONITOR_MIGRATION_STATUS_LAST:
break;
@@ -2577,6 +2578,7 @@ enum qemuMigrationCompletedFlags {
QEMU_MIGRATION_COMPLETED_ABORT_ON_ERROR = (1 << 0),
QEMU_MIGRATION_COMPLETED_CHECK_STORAGE = (1 << 1),
QEMU_MIGRATION_COMPLETED_UPDATE_STATS = (1 << 2),
+ QEMU_MIGRATION_COMPLETED_POSTCOPY = (1 << 3),
};
/**
@@ -2618,6 +2620,20 @@ qemuMigrationCompleted(virQEMUDriverPtr driver,
goto error;
}
+ /* In case of postcopy the source considers migration completed at the
+ * moment it switched from active to postcopy-active state. The destination
+ * will continue waiting until the migrate state changes to completed.
+ */
+ if (flags & QEMU_MIGRATION_COMPLETED_POSTCOPY &&
+ jobInfo->type == VIR_DOMAIN_JOB_UNBOUNDED &&
+ jobInfo->stats.status == QEMU_MONITOR_MIGRATION_STATUS_POSTCOPY) {
+ VIR_DEBUG("Migration switched to post-copy");
+ if (updateStats &&
+ qemuMigrationUpdateJobStatus(driver, vm, asyncJob) < 0)
+ goto error;
+ return 1;
+ }
+
if (jobInfo->type == VIR_DOMAIN_JOB_COMPLETED)
return 1;
else
@@ -2651,9 +2667,11 @@ qemuMigrationWaitForCompletion(virQEMUDriverPtr driver,
qemuDomainObjPrivatePtr priv = vm->privateData;
qemuDomainJobInfoPtr jobInfo = priv->job.current;
bool events = virQEMUCapsGet(priv->qemuCaps, QEMU_CAPS_MIGRATION_EVENT);
- unsigned int flags = QEMU_MIGRATION_COMPLETED_UPDATE_STATS;
+ unsigned int flags;
int rv;
+ flags = QEMU_MIGRATION_COMPLETED_UPDATE_STATS |
+ QEMU_MIGRATION_COMPLETED_POSTCOPY;
if (abort_on_error)
flags |= QEMU_MIGRATION_COMPLETED_ABORT_ON_ERROR;
if (storage)
@@ -2692,9 +2710,11 @@ qemuMigrationWaitForCompletion(virQEMUDriverPtr driver,
static int
qemuMigrationWaitForDestCompletion(virQEMUDriverPtr driver,
virDomainObjPtr vm,
- qemuDomainAsyncJob asyncJob)
+ qemuDomainAsyncJob asyncJob,
+ bool postcopy)
{
qemuDomainObjPrivatePtr priv = vm->privateData;
+ unsigned int flags = 0;
int rv;
if (!virQEMUCapsGet(priv->qemuCaps, QEMU_CAPS_MIGRATION_EVENT))
@@ -2702,7 +2722,11 @@ qemuMigrationWaitForDestCompletion(virQEMUDriverPtr driver,
VIR_DEBUG("Waiting for incoming migration to complete");
- while ((rv = qemuMigrationCompleted(driver, vm, asyncJob, NULL, 0)) != 1) {
+ if (postcopy)
+ flags = QEMU_MIGRATION_COMPLETED_POSTCOPY;
+
+ while ((rv = qemuMigrationCompleted(driver, vm, asyncJob,
+ NULL, flags)) != 1) {
if (rv < 0 || virDomainObjWait(vm) < 0)
return -1;
}
@@ -2904,7 +2928,7 @@ qemuMigrationRunIncoming(virQEMUDriverPtr driver,
goto cleanup;
}
- if (qemuMigrationWaitForDestCompletion(driver, vm, asyncJob) < 0)
+ if (qemuMigrationWaitForDestCompletion(driver, vm, asyncJob, false) < 0)
goto cleanup;
ret = 0;
@@ -3895,6 +3919,19 @@ qemuMigrationConfirmPhase(virQEMUDriverPtr driver,
/* Update times with the values sent by the destination daemon */
if (mig->jobInfo && jobInfo) {
+ int reason;
+
+ /* We need to refresh migration statistics after a completed post-copy
+ * migration since priv->job.completed contains obsolete data from the
+ * time we switched to post-copy mode.
+ */
+ if (virDomainObjGetState(vm, &reason) == VIR_DOMAIN_PAUSED &&
+ reason == VIR_DOMAIN_PAUSED_POSTCOPY &&
+ qemuMigrationFetchJobStatus(driver, vm,
+ QEMU_ASYNC_JOB_MIGRATION_OUT,
+ jobInfo) < 0)
+ VIR_WARN("Could not refresh migration statistics");
+
qemuDomainJobInfoUpdateTime(jobInfo);
jobInfo->timeDeltaSet = mig->jobInfo->timeDeltaSet;
jobInfo->timeDelta = mig->jobInfo->timeDelta;
@@ -4305,6 +4342,7 @@ qemuMigrationRun(virQEMUDriverPtr driver,
unsigned int cookieFlags = 0;
bool abort_on_error = !!(flags & VIR_MIGRATE_ABORT_ON_ERROR);
bool events = virQEMUCapsGet(priv->qemuCaps, QEMU_CAPS_MIGRATION_EVENT);
+ bool inPostCopy = false;
int rc;
VIR_DEBUG("driver=%p, vm=%p, cookiein=%s, cookieinlen=%d, "
@@ -4493,6 +4531,9 @@ qemuMigrationRun(virQEMUDriverPtr driver,
else if (rc == -1)
goto cleanup;
+ if (priv->job.current->stats.status == QEMU_MONITOR_MIGRATION_STATUS_POSTCOPY)
+ inPostCopy = true;
+
/* When migration completed, QEMU will have paused the CPUs for us.
* Wait for the STOP event to be processed or explicitly stop CPUs
* (for old QEMU which does not send events) to release the lock state.
@@ -4502,15 +4543,12 @@ qemuMigrationRun(virQEMUDriverPtr driver,
priv->signalStop = true;
rc = virDomainObjWait(vm);
priv->signalStop = false;
- if (rc < 0) {
- priv->job.current->type = VIR_DOMAIN_JOB_FAILED;
- goto cleanup;
- }
+ if (rc < 0)
+ goto cancelPostCopy;
}
} else if (virDomainObjGetState(vm, NULL) == VIR_DOMAIN_RUNNING &&
qemuMigrationSetOffline(driver, vm) < 0) {
- priv->job.current->type = VIR_DOMAIN_JOB_FAILED;
- goto cleanup;
+ goto cancelPostCopy;
}
if (priv->job.completed)
priv->job.completed->stopped = priv->job.current->stopped;
@@ -4541,7 +4579,7 @@ qemuMigrationRun(virQEMUDriverPtr driver,
ignore_value(virTimeMillisNow(&priv->job.completed->sent));
}
- if (priv->job.current->type == VIR_DOMAIN_JOB_UNBOUNDED)
+ if (priv->job.current->type == VIR_DOMAIN_JOB_UNBOUNDED && !inPostCopy)
priv->job.current->type = VIR_DOMAIN_JOB_FAILED;
cookieFlags |= QEMU_MIGRATION_COOKIE_NETWORK |
@@ -4581,6 +4619,13 @@ qemuMigrationRun(virQEMUDriverPtr driver,
}
}
goto cleanup;
+
+ cancelPostCopy:
+ priv->job.current->type = VIR_DOMAIN_JOB_FAILED;
+ if (inPostCopy)
+ goto cancel;
+ else
+ goto cleanup;
}
/* Perform migration using QEMU's native migrate support,
@@ -5736,6 +5781,7 @@ qemuMigrationFinish(virQEMUDriverPtr driver,
virObjectEventPtr event;
int rc;
qemuDomainJobInfoPtr jobInfo = NULL;
+ bool inPostCopy = false;
VIR_DEBUG("driver=%p, dconn=%p, vm=%p, cookiein=%s, cookieinlen=%d, "
"cookieout=%p, cookieoutlen=%p, flags=%lx, retcode=%d",
@@ -5841,7 +5887,8 @@ qemuMigrationFinish(virQEMUDriverPtr driver,
* before starting guest CPUs.
*/
if (qemuMigrationWaitForDestCompletion(driver, vm,
- QEMU_ASYNC_JOB_MIGRATION_IN) < 0) {
+ QEMU_ASYNC_JOB_MIGRATION_IN,
+ !!(flags & VIR_MIGRATE_POSTCOPY)) < 0) {
/* There's not much we can do for v2 protocol since the
* original domain on the source host is already gone.
*/
@@ -5849,13 +5896,17 @@ qemuMigrationFinish(virQEMUDriverPtr driver,
goto endjob;
}
+ if (priv->job.current->stats.status == QEMU_MONITOR_MIGRATION_STATUS_POSTCOPY)
+ inPostCopy = true;
+
if (!(flags & VIR_MIGRATE_PAUSED)) {
/* run 'cont' on the destination, which allows migration on qemu
* >= 0.10.6 to work properly. This isn't strictly necessary on
* older qemu's, but it also doesn't hurt anything there
*/
if (qemuProcessStartCPUs(driver, vm, dconn,
- VIR_DOMAIN_RUNNING_MIGRATED,
+ inPostCopy ? VIR_DOMAIN_RUNNING_POSTCOPY
+ : VIR_DOMAIN_RUNNING_MIGRATED,
QEMU_ASYNC_JOB_MIGRATION_IN) < 0) {
if (virGetLastError() == NULL)
virReportError(VIR_ERR_INTERNAL_ERROR,
@@ -5876,6 +5927,13 @@ qemuMigrationFinish(virQEMUDriverPtr driver,
if (v3proto)
goto endjob;
}
+
+ if (inPostCopy) {
+ event = virDomainEventLifecycleNewFromObj(vm,
+ VIR_DOMAIN_EVENT_RESUMED,
+ VIR_DOMAIN_EVENT_RESUMED_POSTCOPY);
+ qemuDomainEventQueue(driver, event);
+ }
}
if (mig->jobInfo) {
@@ -5891,6 +5949,19 @@ qemuMigrationFinish(virQEMUDriverPtr driver,
qemuDomainJobInfoUpdateDowntime(jobInfo);
}
+ if (inPostCopy) {
+ if (qemuMigrationWaitForDestCompletion(driver, vm,
+ QEMU_ASYNC_JOB_MIGRATION_IN,
+ false) < 0) {
+ goto endjob;
+ }
+ if (virDomainObjGetState(vm, NULL) == VIR_DOMAIN_RUNNING) {
+ virDomainObjSetState(vm,
+ VIR_DOMAIN_RUNNING,
+ VIR_DOMAIN_RUNNING_MIGRATED);
+ }
+ }
+
dom = virGetDomain(dconn, vm->def->name, vm->def->uuid);
event = virDomainEventLifecycleNewFromObj(vm,
@@ -5933,6 +6004,12 @@ qemuMigrationFinish(virQEMUDriverPtr driver,
if (qemuMigrationBakeCookie(mig, driver, vm, cookieout, cookieoutlen,
QEMU_MIGRATION_COOKIE_STATS) < 0)
VIR_WARN("Unable to encode migration cookie");
+
+ /* Remove completed stats for post-copy, everything but timing fields
+ * is obsolete anyway.
+ */
+ if (inPostCopy)
+ VIR_FREE(priv->job.completed);
}
qemuMigrationJobFinish(driver, vm);
diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c
index ace3bb4..e831834 100644
--- a/src/qemu/qemu_monitor.c
+++ b/src/qemu/qemu_monitor.c
@@ -161,7 +161,7 @@ VIR_ONCE_GLOBAL_INIT(qemuMonitor)
VIR_ENUM_IMPL(qemuMonitorMigrationStatus,
QEMU_MONITOR_MIGRATION_STATUS_LAST,
"inactive", "setup",
- "active",
+ "active", "postcopy-active",
"completed", "failed",
"cancelling", "cancelled")
diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h
index 4467a41..9331dab 100644
--- a/src/qemu/qemu_monitor.h
+++ b/src/qemu/qemu_monitor.h
@@ -473,6 +473,7 @@ typedef enum {
QEMU_MONITOR_MIGRATION_STATUS_INACTIVE,
QEMU_MONITOR_MIGRATION_STATUS_SETUP,
QEMU_MONITOR_MIGRATION_STATUS_ACTIVE,
+ QEMU_MONITOR_MIGRATION_STATUS_POSTCOPY,
QEMU_MONITOR_MIGRATION_STATUS_COMPLETED,
QEMU_MONITOR_MIGRATION_STATUS_ERROR,
QEMU_MONITOR_MIGRATION_STATUS_CANCELLING,
diff --git a/src/qemu/qemu_monitor_json.c b/src/qemu/qemu_monitor_json.c
index 8352e53..8a2aed7 100644
--- a/src/qemu/qemu_monitor_json.c
+++ b/src/qemu/qemu_monitor_json.c
@@ -2548,6 +2548,7 @@ qemuMonitorJSONGetMigrationStatsReply(virJSONValuePtr reply,
break;
case QEMU_MONITOR_MIGRATION_STATUS_ACTIVE:
+ case QEMU_MONITOR_MIGRATION_STATUS_POSTCOPY:
case QEMU_MONITOR_MIGRATION_STATUS_COMPLETED:
case QEMU_MONITOR_MIGRATION_STATUS_CANCELLING:
ram = virJSONValueObjectGetObject(ret, "ram");
diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c
index cd7861e..3757a53 100644
--- a/src/qemu/qemu_process.c
+++ b/src/qemu/qemu_process.c
@@ -711,8 +711,14 @@ qemuProcessHandleStop(qemuMonitorPtr mon ATTRIBUTE_UNUSED,
}
if (priv->job.asyncJob == QEMU_ASYNC_JOB_MIGRATION_OUT) {
- reason = VIR_DOMAIN_PAUSED_MIGRATION;
- detail = VIR_DOMAIN_EVENT_SUSPENDED_MIGRATED;
+ if (priv->job.current->stats.status ==
+ QEMU_MONITOR_MIGRATION_STATUS_POSTCOPY) {
+ reason = VIR_DOMAIN_PAUSED_POSTCOPY;
+ detail = VIR_DOMAIN_EVENT_SUSPENDED_POSTCOPY;
+ } else {
+ reason = VIR_DOMAIN_PAUSED_MIGRATION;
+ detail = VIR_DOMAIN_EVENT_SUSPENDED_MIGRATED;
+ }
}
VIR_DEBUG("Transitioned guest %s to paused state, reason %s",
--
2.7.2
More information about the libvir-list
mailing list