Re: [libvirt] [RFC PATCH] libvirt support to force convergence of live guest migration

Chegu Vinod wrote: > 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 RFC patch includes the libvirt support needed to trigger this > feature. (Testing is still in progress) > Vinod, What is the status of this patch? I see there were a few comments, but don't see (or perhaps missed) a V2.

> Signed-off-by: Chegu Vinod <chegu_vinod(a)hp.com&gt; > --- > include/libvirt/libvirt.h.in | 1 + > src/qemu/qemu_migration.c | 44 ++++++++++++++++++++++++++++++++++++++++++ > src/qemu/qemu_migration.h | 1 + > src/qemu/qemu_monitor.c | 2 +- > src/qemu/qemu_monitor.h | 1 + > tools/virsh-domain.c | 7 ++++++ > 6 files changed, 55 insertions(+), 1 deletions(-) > > diff --git a/include/libvirt/libvirt.h.in b/include/libvirt/libvirt.h.in > index 146a59b..13b0bfc 100644 > --- a/include/libvirt/libvirt.h.in > +++ b/include/libvirt/libvirt.h.in > @@ -1192,6 +1192,7 @@ 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 auto-convergence during during migration */ > } virDomainMigrateFlags; > > > diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c > index e87ea85..8cc0c56 100644 > --- a/src/qemu/qemu_migration.c > +++ b/src/qemu/qemu_migration.c > @@ -1565,6 +1565,40 @@ cleanup: > } > > 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 migration 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) > { > @@ -2389,6 +2423,11 @@ qemuMigrationPrepareAny(virQEMUDriverPtr driver, > QEMU_ASYNC_JOB_MIGRATION_IN) < 0) > goto stop; > > + if (flags & VIR_MIGRATE_AUTO_CONVERGE && > + qemuMigrationSetAutoConverge(driver, vm, > + QEMU_ASYNC_JOB_MIGRATION_IN) < 0) > + goto stop; > + > if (mig->lockState) { > VIR_DEBUG("Received lockstate %s", mig->lockState); > VIR_FREE(priv->lockState); > @@ -3181,6 +3220,11 @@ 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; > diff --git a/src/qemu/qemu_migration.h b/src/qemu/qemu_migration.h > index cafa2a2..c4258a1 100644 > --- a/src/qemu/qemu_migration.h > +++ b/src/qemu/qemu_migration.h > @@ -39,6 +39,7 @@ > VIR_MIGRATE_UNSAFE | \ > VIR_MIGRATE_OFFLINE | \ > VIR_MIGRATE_COMPRESSED | \ > + VIR_MIGRATE_AUTO_CONVERGE | \ > VIR_MIGRATE_ABORT_ON_ERROR) > > /* All supported migration parameters and their types. */ > diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c > index 1514715..780a29a 100644 > --- a/src/qemu/qemu_monitor.c > +++ b/src/qemu/qemu_monitor.c > @@ -118,7 +118,7 @@ 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, > diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h > index eabf000..95e70ab 100644 > --- a/src/qemu/qemu_monitor.h > +++ b/src/qemu/qemu_monitor.h > @@ -440,6 +440,7 @@ int qemuMonitorGetSpiceMigrationStatus(qemuMonitorPtr mon, > > typedef enum { > QEMU_MONITOR_MIGRATION_CAPS_XBZRLE, > + QEMU_MONITOR_MIGRATION_CAPS_AUTO_CONVERGE, > > QEMU_MONITOR_MIGRATION_CAPS_LAST > } qemuMonitorMigrationCaps; > diff --git a/tools/virsh-domain.c b/tools/virsh-domain.c > index 1fe138c..d94a81b 100644 > --- a/tools/virsh-domain.c > +++ b/tools/virsh-domain.c > @@ -8532,6 +8532,10 @@ 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 auto convergence during live migration") > + }, > {.name = "abort-on-error", > .type = VSH_OT_BOOL, > .help = N_("abort on soft errors during migration") > @@ -8676,6 +8680,9 @@ 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; > } > virsh.pod needs updated too. Do you have time to continue working on this patch? If not, I could find some cycles to help out. Thanks!

Regards, Jim .