On Wed, Apr 24, 2013 at 6:42 PM, Chegu Vinod <chegu_vi...@hp.com> 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 does NOT converge.
>
> A few options that were discussed/being-pursued to help with
> the convergence issue include:
>
> 1) Slow down guest considerably via cgroup's CPU controls - requires
> libvirt client support to detect & trigger action, but conceptually
> similar to this RFC change.
>
> 2) Speed up transfer rate:
> - RDMA based Pre-copy - lower overhead and fast (Unfortunately
> has a few restrictions and some customers still choose not
> to deploy RDMA :-( ).
> - Add parallelism to improve transfer rate and use multiple 10Gig
> connections (bonded). - could add some overhead on the host.
>
> 3) Post-copy (preferably with RDMA) or a Pre+Post copy hybrid - Sounds
> promising but need to consider & handle newer failure scenarios.
>
> The following [RFC] change attempts to auto-detect lack of convergence
> situation and trigger a slowdown of the workload by explicitly
> disallowing the VCPUs from spending much time in the VM context.
> No exernal trigger is required (unlike option 1) and it can co-exist
> with enhancements being pursued as part of Option 2 (e.g. RDMA).
>
> The migration thread tries to catchup and this eventually leads
> to convergence in some "deterministic" amount of time. Yes it does
> impact the performance of all the VCPUs but in my observation that
> lasts only for a short duration of time. i.e. we end up entering
> stage 3 (downtime phase) soon after that.
>
This is a reasonable idea and approach but it cannot be unconditional.
Sacrificing VCPU performance to encourage convergence is a management
decision. In some cases, VCPU performance is far more important than
migration convergence.
Regards,
Anthony Liguori
> Verified the convergence using the following:
> - SpecJbb2005 workload running on a 20VCPU/128G guest(~80% busy)
> - OLTP like workload running on a 80VCPU/512G guest (~80% busy)
>
> Thanks to Juan and Paolo for some useful suggestions. More
> refinment is needed (e.g. smarter way to detect & variable
> throttling based on need etc). For now I was hoping to get
> some feedback or hear about other more refined ideas.
>
> Signed-off-by: Chegu Vinod <chegu_vi...@hp.com>
> ---
> arch_init.c | 37 +++++++++++++++++++++++++++++++
> cpus.c | 12 ++++++++++
> include/migration/migration.h | 9 +++++++
> include/qemu/main-loop.h | 3 ++
> kvm-all.c | 49
> +++++++++++++++++++++++++++++++++++++++++
> migration.c | 6 +++++
> 6 files changed, 116 insertions(+), 0 deletions(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index 92de1bd..a06ff81 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -104,6 +104,7 @@ int graphic_depth = 15;
> #endif
>
> const uint32_t arch_type = QEMU_ARCH;
> +static uint64_t mig_throttle_on;
>
> /***********************************************************/
> /* ram save/restore */
> @@ -379,12 +380,19 @@ static void migration_bitmap_sync(void)
> MigrationState *s = migrate_get_current();
> static int64_t start_time;
> static int64_t num_dirty_pages_period;
> + static int64_t bytes_xfer_prev;
> int64_t end_time;
> + int64_t bytes_xfer_now;
> + static int dirty_rate_high_cnt;
>
> if (!start_time) {
> start_time = qemu_get_clock_ms(rt_clock);
> }
>
> + if (!bytes_xfer_prev) {
> + bytes_xfer_prev = ram_bytes_transferred();
> + }
> +
> trace_migration_bitmap_sync_start();
> memory_global_sync_dirty_bitmap(get_system_memory());
>
> @@ -404,6 +412,23 @@ static void migration_bitmap_sync(void)
>
> /* more than 1 second = 1000 millisecons */
> if (end_time > start_time + 1000) {
> + /* The following detection logic can be refined later. For now:
> + Check to see if the dirtied bytes is 50% more than the approx.
> + amount of bytes that just got transferred since the last time we
> + were in this routine. If that happens N times (for now N==5)
> + we turn on the throttle down logic */
> + bytes_xfer_now = ram_bytes_transferred();
> + if (s->dirty_pages_rate &&
> + ((num_dirty_pages_period*TARGET_PAGE_SIZE) >
> + ((bytes_xfer_now - bytes_xfer_prev)/2))) {
> + if (dirty_rate_high_cnt++ > 5) {
> + DPRINTF("Unable to converge. Throtting down guest\n");
> + mig_throttle_on = 1;
> + }
> + }
> + bytes_xfer_prev = bytes_xfer_now;
> +
> s->dirty_pages_rate = num_dirty_pages_period * 1000
> / (end_time - start_time);
> s->dirty_bytes_rate = s->dirty_pages_rate * TARGET_PAGE_SIZE;
> @@ -496,6 +521,18 @@ static int ram_save_block(QEMUFile *f, bool
> last_stage)
> return bytes_sent;
> }
>
> +bool throttling_needed(void)
> +{
> + bool value;
> +
> + qemu_mutex_lock_mig_throttle();
> + value = mig_throttle_on;
> + qemu_mutex_unlock_mig_throttle();
> +
> + if (value) {
> + return true;
> + }
> + return false;
> +}
> +
> static uint64_t bytes_transferred;
>
> static ram_addr_t ram_save_remaining(void)
> diff --git a/cpus.c b/cpus.c
> index 5a98a37..eea6601 100644
> --- a/cpus.c
> +++ b/cpus.c
> @@ -616,6 +616,7 @@ static void qemu_tcg_init_cpu_signals(void)
> #endif /* _WIN32 */
>
> static QemuMutex qemu_global_mutex;
> +static QemuMutex qemu_mig_throttle_mutex;
> static QemuCond qemu_io_proceeded_cond;
> static bool iothread_requesting_mutex;
>
> @@ -638,6 +639,7 @@ void qemu_init_cpu_loop(void)
> qemu_cond_init(&qemu_work_cond);
> qemu_cond_init(&qemu_io_proceeded_cond);
> qemu_mutex_init(&qemu_global_mutex);
> + qemu_mutex_init(&qemu_mig_throttle_mutex);
>
> qemu_thread_get_self(&io_thread);
> }
> @@ -923,6 +925,16 @@ static bool qemu_in_vcpu_thread(void)
> return cpu_single_env &&
> qemu_cpu_is_self(ENV_GET_CPU(cpu_single_env));
> }
>
> +void qemu_mutex_lock_mig_throttle(void)
> +{
> + qemu_mutex_lock(&qemu_mig_throttle_mutex);
> +}
> +
> +void qemu_mutex_unlock_mig_throttle(void)
> +{
> + qemu_mutex_unlock(&qemu_mig_throttle_mutex);
> +}
> +
> void qemu_mutex_lock_iothread(void)
> {
> if (!tcg_enabled()) {
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index e2acec6..cccee91 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -92,6 +92,15 @@ uint64_t ram_bytes_remaining(void);
> uint64_t ram_bytes_transferred(void);
> uint64_t ram_bytes_total(void);
>
> +#ifndef _QEMU_MIG_THROTTLE
> +#define _QEMU_MIG_THROTTLE
> +
> +bool throttling_needed(void);
> +bool throttling_now(void);
> +void *migration_throttle_down(void *);
> +
> +#endif
> +
> extern SaveVMHandlers savevm_ram_handlers;
>
> uint64_t dup_mig_bytes_transferred(void);
> diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h
> index 6f0200a..9a3886d 100644
> --- a/include/qemu/main-loop.h
> +++ b/include/qemu/main-loop.h
> @@ -299,6 +299,9 @@ void qemu_mutex_lock_iothread(void);
> */
> void qemu_mutex_unlock_iothread(void);
>
> +void qemu_mutex_lock_mig_throttle(void);
> +void qemu_mutex_unlock_mig_throttle(void);
> +
> /* internal interfaces */
>
> void qemu_fd_register(int fd);
> diff --git a/kvm-all.c b/kvm-all.c
> index 2d92721..95010ce 100644
> --- a/kvm-all.c
> +++ b/kvm-all.c
> @@ -33,6 +33,8 @@
> #include "exec/memory.h"
> #include "exec/address-spaces.h"
> #include "qemu/event_notifier.h"
> +#include "sysemu/cpus.h"
> +#include "migration/migration.h"
>
> /* This check must be after config-host.h is included */
> #ifdef CONFIG_EVENTFD
> @@ -116,6 +118,8 @@ static const KVMCapabilityInfo
> kvm_required_capabilites[] = {
> KVM_CAP_LAST_INFO
> };
>
> +static void mig_delay_vcpu(void);
> +
> static KVMSlot *kvm_alloc_slot(KVMState *s)
> {
> int i;
> @@ -1609,6 +1613,10 @@ int kvm_cpu_exec(CPUArchState *env)
> }
> qemu_mutex_unlock_iothread();
>
> + if (throttling_needed()) {
> + mig_delay_vcpu();
> + }
> +
> run_ret = kvm_vcpu_ioctl(cpu, KVM_RUN, 0);
>
> qemu_mutex_lock_iothread();
> @@ -2032,3 +2040,44 @@ int kvm_on_sigbus(int code, void *addr)
> {
> return kvm_arch_on_sigbus(code, addr);
> }
> +
> +static bool throttling;
> +bool throttling_now(void)
> +{
> + if (throttling) {
> + return true;
> + }
> + return false;
> +}
> +
> +static void mig_delay_vcpu(void)
> +{
> + g_usleep(50*1000);
> +}
> +
> +/* Stub used for getting the vcpu out of VM and into qemu via
> + run_on_cpu()*/
> +static void mig_kick_cpu(void *opq)
> +{
> + return;
> +}
> +
> +/* To reduce the dirty rate explicitly disallow the VCPUs from spending
> + much time in the VM. The migration thread will try to catchup.
> + Workload will experience a greater performance drop but for a shorter
> + duration.
> +*/
> +void *migration_throttle_down(void *opaque)
> +{
> + throttling = true;
> + while (throttling_needed()) {
> + CPUArchState *penv = first_cpu;
> + while (penv) {
> + qemu_mutex_lock_iothread();
> + run_on_cpu(ENV_GET_CPU(penv), mig_kick_cpu, NULL);
> + qemu_mutex_unlock_iothread();
> + penv = penv->next_cpu;
> + }
> + g_usleep(25*1000);
> + }
> + throttling = false;
> + return NULL;
> +}
> diff --git a/migration.c b/migration.c
> index 3eb0fad..a464afc 100644
> --- a/migration.c
> +++ b/migration.c
> @@ -24,6 +24,7 @@
> #include "qemu/thread.h"
> #include "qmp-commands.h"
> #include "trace.h"
> +#include "sysemu/cpus.h"
>
> //#define DEBUG_MIGRATION
>
> @@ -503,6 +504,7 @@ static void *migration_thread(void *opaque)
> int64_t max_size = 0;
> int64_t start_time = initial_time;
> bool old_vm_running = false;
> + QemuThread thread;
>
> DPRINTF("beginning savevm\n");
> qemu_savevm_state_begin(s->file, &s->params);
> @@ -517,6 +519,10 @@ static void *migration_thread(void *opaque)
> DPRINTF("pending size %lu max %lu\n", pending_size, max_size);
> if (pending_size && pending_size >= max_size) {
> qemu_savevm_state_iterate(s->file);
> + if (throttling_needed() && !throttling_now()) {
> + qemu_thread_create(&thread, migration_throttle_down,
> + NULL, QEMU_THREAD_DETACHED);
> + }
> } else {
> DPRINTF("done iterating\n");
> qemu_mutex_lock_iothread();
> --
> 1.7.1
>
>
>
