[Qemu-devel] [PATCH v7 0/3] Throttle-down guest to help with live migration convergence

[Qemu-devel] [PATCH v7 0/3] Throttle-down guest to help with live migration convergence

[Chegu Vinod]

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.

If a user chooses to force convergence of their migration via a new
migration capability "auto-converge" then this change will auto-detect
lack of convergence scenario and trigger a slow down of the workload
by explicitly disallowing the VCPUs from spending much time in the VM
context.

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. end up entering
stage 3 (downtime phase) soon after that. No external trigger is
required.

Thanks to Juan and Paolo for their useful suggestions.

---
Changes from v6:
- incorporated feedback from Paolo.
- rebased to latest qemu.git and removing RFC

Changes from v5:
- incorporated feedback from Paolo & Igor.
- rebased to latest qemu.git

Changes from v4:
- incorporated feedback from Paolo.
- split into 3 patches.

Changes from v3:
- incorporated feedback from Paolo and Eric
- rebased to latest qemu.git

Changes from v2:
- incorporated feedback from Orit, Juan and Eric
- stop the throttling thread at the start of stage 3
- rebased to latest qemu.git

Changes from v1:
- rebased to latest qemu.git
- added auto-converge capability(default off) - suggested by Anthony Liguori &
                                                Eric Blake.

Signed-off-by: Chegu Vinod <chegu_vinod@hp.com>
---

Chegu Vinod (3):
  Introduce async_run_on_cpu()
  Add 'auto-converge' migration capability
  Force auto-convegence of live migration

 arch_init.c                   |   85 +++++++++++++++++++++++++++++++++++++++++
 cpus.c                        |   29 ++++++++++++++
 include/migration/migration.h |    2 +
 include/qemu-common.h         |    1 +
 include/qom/cpu.h             |   10 +++++
 migration.c                   |    9 ++++
 qapi-schema.json              |    5 ++-
 7 files changed, 140 insertions(+), 1 deletions(-)

[Qemu-devel] [PATCH v7 1/3] Introduce async_run_on_cpu()

[Chegu Vinod]

Introduce an asynchronous version of run_on_cpu() i.e. the caller
doesn't have to block till the call back routine finishes execution
on the target vcpu.

Signed-off-by: Chegu Vinod <chegu_vinod@hp.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 cpus.c                |   29 +++++++++++++++++++++++++++++
 include/qemu-common.h |    1 +
 include/qom/cpu.h     |   10 ++++++++++
 3 files changed, 40 insertions(+), 0 deletions(-)

diff --git a/cpus.c b/cpus.c
index c8bc8ad..c7c90d0 100644
--- a/cpus.c
+++ b/cpus.c
@@ -653,6 +653,7 @@ void run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data)
 
     wi.func = func;
     wi.data = data;
+    wi.free = false;
     if (cpu->queued_work_first == NULL) {
         cpu->queued_work_first = &wi;
     } else {
@@ -671,6 +672,31 @@ void run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data)
     }
 }
 
+void async_run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data)
+{
+    struct qemu_work_item *wi;
+
+    if (qemu_cpu_is_self(cpu)) {
+        func(data);
+        return;
+    }
+
+    wi = g_malloc0(sizeof(struct qemu_work_item));
+    wi->func = func;
+    wi->data = data;
+    wi->free = true;
+    if (cpu->queued_work_first == NULL) {
+        cpu->queued_work_first = wi;
+    } else {
+        cpu->queued_work_last->next = wi;
+    }
+    cpu->queued_work_last = wi;
+    wi->next = NULL;
+    wi->done = false;
+
+    qemu_cpu_kick(cpu);
+}
+
 static void flush_queued_work(CPUState *cpu)
 {
     struct qemu_work_item *wi;
@@ -683,6 +709,9 @@ static void flush_queued_work(CPUState *cpu)
         cpu->queued_work_first = wi->next;
         wi->func(wi->data);
         wi->done = true;
+        if (wi->free) {
+            g_free(wi);
+        }
     }
     cpu->queued_work_last = NULL;
     qemu_cond_broadcast(&qemu_work_cond);
diff --git a/include/qemu-common.h b/include/qemu-common.h
index 3c91375..9834dcb 100644
--- a/include/qemu-common.h
+++ b/include/qemu-common.h
@@ -291,6 +291,7 @@ struct qemu_work_item {
     void (*func)(void *data);
     void *data;
     int done;
+    bool free;
 };
 
 #ifdef CONFIG_USER_ONLY
diff --git a/include/qom/cpu.h b/include/qom/cpu.h
index a5bb515..b555c22 100644
--- a/include/qom/cpu.h
+++ b/include/qom/cpu.h
@@ -288,6 +288,16 @@ bool cpu_is_stopped(CPUState *cpu);
 void run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data);
 
 /**
+ * async_run_on_cpu:
+ * @cpu: The vCPU to run on.
+ * @func: The function to be executed.
+ * @data: Data to pass to the function.
+ *
+ * Schedules the function @func for execution on the vCPU @cpu asynchronously.
+ */
+void async_run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data);
+
+/**
  * qemu_for_each_cpu:
  * @func: The function to be executed.
  * @data: Data to pass to the function.
-- 
1.7.1

[Qemu-devel] [PATCH v7 2/3] Add 'auto-converge' migration capability

[Chegu Vinod]

The auto-converge migration capability allows the user to specify if they
choose live migration seqeunce to automatically detect and force convergence.

Signed-off-by: Chegu Vinod <chegu_vinod@hp.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
---
 include/migration/migration.h |    2 ++
 migration.c                   |    9 +++++++++
 qapi-schema.json              |    5 ++++-
 3 files changed, 15 insertions(+), 1 deletions(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index e2acec6..ace91b0 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -127,4 +127,6 @@ int migrate_use_xbzrle(void);
 int64_t migrate_xbzrle_cache_size(void);
 
 int64_t xbzrle_cache_resize(int64_t new_size);
+
+bool migrate_auto_converge(void);
 #endif
diff --git a/migration.c b/migration.c
index 058f9e6..d0759c1 100644
--- a/migration.c
+++ b/migration.c
@@ -473,6 +473,15 @@ void qmp_migrate_set_downtime(double value, Error **errp)
     max_downtime = (uint64_t)value;
 }
 
+bool migrate_auto_converge(void)
+{
+    MigrationState *s;
+
+    s = migrate_get_current();
+
+    return s->enabled_capabilities[MIGRATION_CAPABILITY_AUTO_CONVERGE];
+}
+
 int migrate_use_xbzrle(void)
 {
     MigrationState *s;
diff --git a/qapi-schema.json b/qapi-schema.json
index a80ee40..c019fec 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -605,10 +605,13 @@
 #          This feature allows us to minimize migration traffic for certain work
 #          loads, by sending compressed difference of the pages
 #
+# @auto-converge: If enabled, QEMU will automatically throttle down the guest
+#          to speed up convergence of RAM migration. (since 1.6)
+#
 # Since: 1.2
 ##
 { 'enum': 'MigrationCapability',
-  'data': ['xbzrle'] }
+  'data': ['xbzrle', 'auto-converge'] }
 
 ##
 # @MigrationCapabilityStatus
-- 
1.7.1

[Qemu-devel] [PATCH v7 2/3] Add 'auto-converge' migration capability

[Chegu Vinod]

If a user chooses to turn on the auto-converge migration capability
these changes detect the lack of convergence and throttle down the
guest. i.e. force the VCPUs out of the guest for some duration
and let the migration thread catchup and help converge.

Verified the convergence using the following :
 - Java Warehouse workload running on a 20VCPU/256G guest(~80% busy)
 - OLTP like workload running on a 80VCPU/512G guest (~80% busy)

Sample results with Java warehouse workload : (migrate speed set to 20Gb and
migrate downtime set to 4seconds).

 (qemu) info migrate
 capabilities: xbzrle: off auto-converge: off  <----
 Migration status: active
 total time: 1487503 milliseconds
 expected downtime: 519 milliseconds
 transferred ram: 383749347 kbytes
 remaining ram: 2753372 kbytes
 total ram: 268444224 kbytes
 duplicate: 65461532 pages
 skipped: 64901568 pages
 normal: 95750218 pages
 normal bytes: 383000872 kbytes
 dirty pages rate: 67551 pages

 ---

 (qemu) info migrate
 capabilities: xbzrle: off auto-converge: on   <----
 Migration status: completed
 total time: 241161 milliseconds
 downtime: 6373 milliseconds
 transferred ram: 28235307 kbytes
 remaining ram: 0 kbytes
 total ram: 268444224 kbytes
 duplicate: 64946416 pages
 skipped: 64903523 pages
 normal: 7044971 pages
 normal bytes: 28179884 kbytes

Signed-off-by: Chegu Vinod <chegu_vinod@hp.com>
---
 arch_init.c |   79 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 79 insertions(+), 0 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index a8b91ee..e7ca3b1 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -104,6 +104,9 @@ int graphic_depth = 15;
 #endif
 
 const uint32_t arch_type = QEMU_ARCH;
+static bool mig_throttle_on;
+static int dirty_rate_high_cnt;
+static void check_guest_throttling(void);
 
 /***********************************************************/
 /* ram save/restore */
@@ -378,8 +381,14 @@ static void migration_bitmap_sync(void)
     uint64_t num_dirty_pages_init = migration_dirty_pages;
     MigrationState *s = migrate_get_current();
     static int64_t start_time;
+    static int64_t bytes_xfer_prev;
     static int64_t num_dirty_pages_period;
     int64_t end_time;
+    int64_t bytes_xfer_now;
+
+    if (!bytes_xfer_prev) {
+        bytes_xfer_prev = ram_bytes_transferred();
+    }
 
     if (!start_time) {
         start_time = qemu_get_clock_ms(rt_clock);
@@ -404,6 +413,23 @@ static void migration_bitmap_sync(void)
 
     /* more than 1 second = 1000 millisecons */
     if (end_time > start_time + 1000) {
+        if (migrate_auto_converge()) {
+            /* 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==4)
+               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) &&
+               (dirty_rate_high_cnt++ > 4)) {
+                    trace_migration_throttle();
+                    mig_throttle_on = true;
+                    dirty_rate_high_cnt = 0;
+             }
+             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;
@@ -566,6 +592,8 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     migration_bitmap = bitmap_new(ram_pages);
     bitmap_set(migration_bitmap, 0, ram_pages);
     migration_dirty_pages = ram_pages;
+    mig_throttle_on = false;
+    dirty_rate_high_cnt = 0;
 
     if (migrate_use_xbzrle()) {
         XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
@@ -628,6 +656,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
         }
         total_sent += bytes_sent;
         acct_info.iterations++;
+        check_guest_throttling();
         /* we want to check in the 1st loop, just in case it was the 1st time
            and we had to sync the dirty bitmap.
            qemu_get_clock_ns() is a bit expensive, so we only check each some
@@ -1097,3 +1126,53 @@ TargetInfo *qmp_query_target(Error **errp)
 
     return info;
 }
+
+/* Stub function that's gets run on the vcpu when its brought out of the
+   VM to run inside qemu via async_run_on_cpu()*/
+static void mig_sleep_cpu(void *opq)
+{
+    qemu_mutex_unlock_iothread();
+    g_usleep(30*1000);
+    qemu_mutex_lock_iothread();
+}
+
+/* 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 performance drop.
+*/
+static void mig_throttle_cpu_down(CPUState *cpu, void *data)
+{
+    async_run_on_cpu(cpu, mig_sleep_cpu, NULL);
+}
+
+static void mig_throttle_guest_down(void)
+{
+    qemu_mutex_lock_iothread();
+    qemu_for_each_cpu(mig_throttle_cpu_down, NULL);
+    qemu_mutex_unlock_iothread();
+}
+
+static void check_guest_throttling(void)
+{
+    static int64_t t0;
+    int64_t        t1;
+
+    if (!mig_throttle_on) {
+        return;
+    }
+
+    if (!t0)  {
+        t0 = qemu_get_clock_ns(rt_clock);
+        return;
+    }
+
+    t1 = qemu_get_clock_ns(rt_clock);
+
+    /* If it has been more than 40 ms since the last time the guest
+     * was throttled then do it again.
+     */
+    if (40 < (t1-t0)/1000000) {
+        mig_throttle_guest_down();
+        t0 = t1;
+    }
+}
-- 
1.7.1

Re: [Qemu-devel] [PATCH v7 2/3] Add 'auto-converge' migration capability

[Chegu Vinod]

Oops!  A minor glitch on my side (pl. ignore the subject line of 
this...as this is actually patch 3/3 and not patch 2/3).   I just resent 
this as patch 3/3 with the correct subject line.

Thx
Vinod

On 6/23/2013 1:05 PM, Chegu Vinod wrote:
> If a user chooses to turn on the auto-converge migration capability
> these changes detect the lack of convergence and throttle down the
> guest. i.e. force the VCPUs out of the guest for some duration
> and let the migration thread catchup and help converge.
>
> Verified the convergence using the following :
>   - Java Warehouse workload running on a 20VCPU/256G guest(~80% busy)
>   - OLTP like workload running on a 80VCPU/512G guest (~80% busy)
>
> Sample results with Java warehouse workload : (migrate speed set to 20Gb and
> migrate downtime set to 4seconds).
>
>   (qemu) info migrate
>   capabilities: xbzrle: off auto-converge: off  <----
>   Migration status: active
>   total time: 1487503 milliseconds
>   expected downtime: 519 milliseconds
>   transferred ram: 383749347 kbytes
>   remaining ram: 2753372 kbytes
>   total ram: 268444224 kbytes
>   duplicate: 65461532 pages
>   skipped: 64901568 pages
>   normal: 95750218 pages
>   normal bytes: 383000872 kbytes
>   dirty pages rate: 67551 pages
>
>   ---
>
>   (qemu) info migrate
>   capabilities: xbzrle: off auto-converge: on   <----
>   Migration status: completed
>   total time: 241161 milliseconds
>   downtime: 6373 milliseconds
>   transferred ram: 28235307 kbytes
>   remaining ram: 0 kbytes
>   total ram: 268444224 kbytes
>   duplicate: 64946416 pages
>   skipped: 64903523 pages
>   normal: 7044971 pages
>   normal bytes: 28179884 kbytes
>
> Signed-off-by: Chegu Vinod <chegu_vinod@hp.com>
> ---
>   arch_init.c |   79 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>   1 files changed, 79 insertions(+), 0 deletions(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index a8b91ee..e7ca3b1 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -104,6 +104,9 @@ int graphic_depth = 15;
>   #endif
>   
>   const uint32_t arch_type = QEMU_ARCH;
> +static bool mig_throttle_on;
> +static int dirty_rate_high_cnt;
> +static void check_guest_throttling(void);
>   
>   /***********************************************************/
>   /* ram save/restore */
> @@ -378,8 +381,14 @@ static void migration_bitmap_sync(void)
>       uint64_t num_dirty_pages_init = migration_dirty_pages;
>       MigrationState *s = migrate_get_current();
>       static int64_t start_time;
> +    static int64_t bytes_xfer_prev;
>       static int64_t num_dirty_pages_period;
>       int64_t end_time;
> +    int64_t bytes_xfer_now;
> +
> +    if (!bytes_xfer_prev) {
> +        bytes_xfer_prev = ram_bytes_transferred();
> +    }
>   
>       if (!start_time) {
>           start_time = qemu_get_clock_ms(rt_clock);
> @@ -404,6 +413,23 @@ static void migration_bitmap_sync(void)
>   
>       /* more than 1 second = 1000 millisecons */
>       if (end_time > start_time + 1000) {
> +        if (migrate_auto_converge()) {
> +            /* 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==4)
> +               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) &&
> +               (dirty_rate_high_cnt++ > 4)) {
> +                    trace_migration_throttle();
> +                    mig_throttle_on = true;
> +                    dirty_rate_high_cnt = 0;
> +             }
> +             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;
> @@ -566,6 +592,8 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
>       migration_bitmap = bitmap_new(ram_pages);
>       bitmap_set(migration_bitmap, 0, ram_pages);
>       migration_dirty_pages = ram_pages;
> +    mig_throttle_on = false;
> +    dirty_rate_high_cnt = 0;
>   
>       if (migrate_use_xbzrle()) {
>           XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
> @@ -628,6 +656,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
>           }
>           total_sent += bytes_sent;
>           acct_info.iterations++;
> +        check_guest_throttling();
>           /* we want to check in the 1st loop, just in case it was the 1st time
>              and we had to sync the dirty bitmap.
>              qemu_get_clock_ns() is a bit expensive, so we only check each some
> @@ -1097,3 +1126,53 @@ TargetInfo *qmp_query_target(Error **errp)
>   
>       return info;
>   }
> +
> +/* Stub function that's gets run on the vcpu when its brought out of the
> +   VM to run inside qemu via async_run_on_cpu()*/
> +static void mig_sleep_cpu(void *opq)
> +{
> +    qemu_mutex_unlock_iothread();
> +    g_usleep(30*1000);
> +    qemu_mutex_lock_iothread();
> +}
> +
> +/* 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 performance drop.
> +*/
> +static void mig_throttle_cpu_down(CPUState *cpu, void *data)
> +{
> +    async_run_on_cpu(cpu, mig_sleep_cpu, NULL);
> +}
> +
> +static void mig_throttle_guest_down(void)
> +{
> +    qemu_mutex_lock_iothread();
> +    qemu_for_each_cpu(mig_throttle_cpu_down, NULL);
> +    qemu_mutex_unlock_iothread();
> +}
> +
> +static void check_guest_throttling(void)
> +{
> +    static int64_t t0;
> +    int64_t        t1;
> +
> +    if (!mig_throttle_on) {
> +        return;
> +    }
> +
> +    if (!t0)  {
> +        t0 = qemu_get_clock_ns(rt_clock);
> +        return;
> +    }
> +
> +    t1 = qemu_get_clock_ns(rt_clock);
> +
> +    /* If it has been more than 40 ms since the last time the guest
> +     * was throttled then do it again.
> +     */
> +    if (40 < (t1-t0)/1000000) {
> +        mig_throttle_guest_down();
> +        t0 = t1;
> +    }
> +}