[Qemu-devel] [PATCH V5 8/9] migration: add postcopy total blocktime into query-migrate

Alexey Perevalov posted 9 patches 8 years, 9 months ago
There is a newer version of this series
[Qemu-devel] [PATCH V5 8/9] migration: add postcopy total blocktime into query-migrate
Posted by Alexey Perevalov 8 years, 9 months ago
Postcopy total blocktime is available on destination side only.
But query-migrate was possible only for source. This patch
adds ability to call query-migrate on destination. To distinguish
src/dst, state of the MigrationState is using, query-migrate prepares
MigrationInfo for source machine only in case of migration's state is different
than MIGRATION_STATUS_NONE.

To be able to see postcopy blocktime, need to request postcopy-blocktime
capability.

The query-migrate command will show following sample result:
{"return":
    "postcopy_vcpu_blocktime": [115, 100],
    "status": "completed",
    "postcopy_blocktime": 100
}}

postcopy_vcpu_blocktime contains list, where the first item is the first
vCPU in QEMU.

Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>
---
 include/migration/migration.h |  4 +++
 migration/migration.c         | 47 ++++++++++++++++++++++++++--
 migration/postcopy-ram.c      | 73 +++++++++++++++++++++++++++++++++++++++++++
 migration/trace-events        |  1 +
 qapi-schema.json              |  6 +++-
 5 files changed, 127 insertions(+), 4 deletions(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 7e69a2d..aba0535 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -135,6 +135,10 @@ struct MigrationIncomingState {
 
 MigrationIncomingState *migration_incoming_get_current(void);
 void migration_incoming_state_destroy(void);
+/*
+ * Functions to work with blocktime context
+ */
+void fill_destination_postcopy_migration_info(MigrationInfo *info);
 
 struct MigrationState
 {
diff --git a/migration/migration.c b/migration/migration.c
index c0443ce..7a4f33f 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -666,9 +666,15 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
     }
 }
 
-MigrationInfo *qmp_query_migrate(Error **errp)
+/* TODO improve this assumption */
+static bool is_source_migration(void)
+{
+    MigrationState *ms = migrate_get_current();
+    return ms->state != MIGRATION_STATUS_NONE;
+}
+
+static void fill_source_migration_info(MigrationInfo *info)
 {
-    MigrationInfo *info = g_malloc0(sizeof(*info));
     MigrationState *s = migrate_get_current();
 
     switch (s->state) {
@@ -759,10 +765,45 @@ MigrationInfo *qmp_query_migrate(Error **errp)
         break;
     }
     info->status = s->state;
+}
+
+static void fill_destination_migration_info(MigrationInfo *info)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
 
-    return info;
+    switch (mis->state) {
+    case MIGRATION_STATUS_NONE:
+        break;
+    case MIGRATION_STATUS_SETUP:
+    case MIGRATION_STATUS_CANCELLING:
+    case MIGRATION_STATUS_CANCELLED:
+    case MIGRATION_STATUS_ACTIVE:
+    case MIGRATION_STATUS_POSTCOPY_ACTIVE:
+    case MIGRATION_STATUS_FAILED:
+    case MIGRATION_STATUS_COLO:
+        info->has_status = true;
+        break;
+    case MIGRATION_STATUS_COMPLETED:
+        info->has_status = true;
+        fill_destination_postcopy_migration_info(info);
+        break;
+    }
+    info->status = mis->state;
 }
 
+MigrationInfo *qmp_query_migrate(Error **errp)
+{
+    MigrationInfo *info = g_malloc0(sizeof(*info));
+
+    if (is_source_migration()) {
+        fill_source_migration_info(info);
+    } else {
+        fill_destination_migration_info(info);
+    }
+
+     return info;
+ }
+
 void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
                                   Error **errp)
 {
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index e2660ae..fe047c8 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -129,6 +129,71 @@ static struct PostcopyBlocktimeContext *blocktime_context_new(void)
     return ctx;
 }
 
+static int64List *get_vcpu_blocktime_list(PostcopyBlocktimeContext *ctx)
+{
+    int64List *list = NULL, *entry = NULL;
+    int i;
+
+    for (i = smp_cpus - 1; i >= 0; i--) {
+            entry = g_new0(int64List, 1);
+            entry->value = ctx->vcpu_blocktime[i];
+            entry->next = list;
+            list = entry;
+    }
+
+    return list;
+}
+
+/*
+ * This function just provide calculated blocktime per cpu and trace it.
+ * Total blocktime is calculated in mark_postcopy_blocktime_end.
+ *
+ *
+ * Assume we have 3 CPU
+ *
+ *      S1        E1           S1               E1
+ * -----***********------------xxx***************------------------------> CPU1
+ *
+ *             S2                E2
+ * ------------****************xxx---------------------------------------> CPU2
+ *
+ *                         S3            E3
+ * ------------------------****xxx********-------------------------------> CPU3
+ *
+ * We have sequence S1,S2,E1,S3,S1,E2,E3,E1
+ * S2,E1 - doesn't match condition due to sequence S1,S2,E1 doesn't include CPU3
+ * S3,S1,E2 - sequence includes all CPUs, in this case overlap will be S1,E2 -
+ *            it's a part of total blocktime.
+ * S1 - here is last_begin
+ * Legend of the picture is following:
+ *              * - means blocktime per vCPU
+ *              x - means overlapped blocktime (total blocktime)
+ */
+void fill_destination_postcopy_migration_info(MigrationInfo *info)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+
+    if (!mis->blocktime_ctx) {
+        return;
+    }
+
+    info->has_postcopy_blocktime = true;
+    info->postcopy_blocktime = mis->blocktime_ctx->total_blocktime;
+    info->has_postcopy_vcpu_blocktime = true;
+    info->postcopy_vcpu_blocktime = get_vcpu_blocktime_list(mis->blocktime_ctx);
+}
+
+static uint64_t get_postcopy_total_blocktime(void)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+
+    if (!mis->blocktime_ctx) {
+        return 0;
+    }
+
+    return mis->blocktime_ctx->total_blocktime;
+}
+
 /*
  * Check userfault fd features, to request only supported features in
  * future.
@@ -462,6 +527,9 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
     }
 
     postcopy_state_set(POSTCOPY_INCOMING_END);
+    /* here should be blocktime receiving back operation */
+    trace_postcopy_ram_incoming_cleanup_blocktime(
+            get_postcopy_total_blocktime());
     migrate_send_rp_shut(mis, qemu_file_get_error(mis->from_src_file) != 0);
 
     if (mis->postcopy_tmp_page) {
@@ -876,6 +944,11 @@ void *postcopy_get_tmp_page(MigrationIncomingState *mis)
 
 #else
 /* No target OS support, stubs just fail */
+void fill_destination_postcopy_migration_info(MigrationInfo *info)
+{
+    error_report("%s: No OS support", __func__);
+}
+
 bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
 {
     error_report("%s: No OS support", __func__);
diff --git a/migration/trace-events b/migration/trace-events
index 9424e3e..bdaca1d 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -193,6 +193,7 @@ postcopy_ram_incoming_cleanup_closeuf(void) ""
 postcopy_ram_incoming_cleanup_entry(void) ""
 postcopy_ram_incoming_cleanup_exit(void) ""
 postcopy_ram_incoming_cleanup_join(void) ""
+postcopy_ram_incoming_cleanup_blocktime(uint64_t total) "total blocktime %" PRIu64
 save_xbzrle_page_skipping(void) ""
 save_xbzrle_page_overflow(void) ""
 ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRIu64 " milliseconds, %d iterations"
diff --git a/qapi-schema.json b/qapi-schema.json
index fde6d63..e11c5f2 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -712,6 +712,8 @@
 #              @status is 'failed'. Clients should not attempt to parse the
 #              error strings. (Since 2.7)
 #
+# @postcopy_vcpu_blocktime: list of the postcopy blocktime per vCPU (Since 2.9)
+#
 # Since: 0.14.0
 ##
 { 'struct': 'MigrationInfo',
@@ -723,7 +725,9 @@
            '*downtime': 'int',
            '*setup-time': 'int',
            '*cpu-throttle-percentage': 'int',
-           '*error-desc': 'str'} }
+           '*error-desc': 'str',
+           '*postcopy_blocktime' : 'int64',
+           '*postcopy_vcpu_blocktime': ['int64']} }
 
 ##
 # @query-migrate:
-- 
1.9.1


Re: [Qemu-devel] [PATCH V5 8/9] migration: add postcopy total blocktime into query-migrate
Posted by Dr. David Alan Gilbert 8 years, 8 months ago
* Alexey Perevalov (a.perevalov@samsung.com) wrote:
> Postcopy total blocktime is available on destination side only.
> But query-migrate was possible only for source. This patch
> adds ability to call query-migrate on destination. To distinguish
> src/dst, state of the MigrationState is using, query-migrate prepares
> MigrationInfo for source machine only in case of migration's state is different
> than MIGRATION_STATUS_NONE.
> 
> To be able to see postcopy blocktime, need to request postcopy-blocktime
> capability.
> 
> The query-migrate command will show following sample result:
> {"return":
>     "postcopy_vcpu_blocktime": [115, 100],
>     "status": "completed",
>     "postcopy_blocktime": 100
> }}
> 
> postcopy_vcpu_blocktime contains list, where the first item is the first
> vCPU in QEMU.

Lets just check Eric is happy with the qapi side.
Please also update hmp.c:hmp_info_migrate.

A few comments below.

> Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>
> ---
>  include/migration/migration.h |  4 +++
>  migration/migration.c         | 47 ++++++++++++++++++++++++++--
>  migration/postcopy-ram.c      | 73 +++++++++++++++++++++++++++++++++++++++++++
>  migration/trace-events        |  1 +
>  qapi-schema.json              |  6 +++-
>  5 files changed, 127 insertions(+), 4 deletions(-)
> 
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index 7e69a2d..aba0535 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -135,6 +135,10 @@ struct MigrationIncomingState {
>  
>  MigrationIncomingState *migration_incoming_get_current(void);
>  void migration_incoming_state_destroy(void);
> +/*
> + * Functions to work with blocktime context
> + */
> +void fill_destination_postcopy_migration_info(MigrationInfo *info);
>  
>  struct MigrationState
>  {
> diff --git a/migration/migration.c b/migration/migration.c
> index c0443ce..7a4f33f 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -666,9 +666,15 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
>      }
>  }
>  
> -MigrationInfo *qmp_query_migrate(Error **errp)
> +/* TODO improve this assumption */
> +static bool is_source_migration(void)
> +{
> +    MigrationState *ms = migrate_get_current();
> +    return ms->state != MIGRATION_STATUS_NONE;
> +}
> +
> +static void fill_source_migration_info(MigrationInfo *info)
>  {
> -    MigrationInfo *info = g_malloc0(sizeof(*info));
>      MigrationState *s = migrate_get_current();
>  
>      switch (s->state) {
> @@ -759,10 +765,45 @@ MigrationInfo *qmp_query_migrate(Error **errp)
>          break;
>      }
>      info->status = s->state;
> +}
> +
> +static void fill_destination_migration_info(MigrationInfo *info)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
>  
> -    return info;
> +    switch (mis->state) {
> +    case MIGRATION_STATUS_NONE:
> +        break;
> +    case MIGRATION_STATUS_SETUP:
> +    case MIGRATION_STATUS_CANCELLING:
> +    case MIGRATION_STATUS_CANCELLED:
> +    case MIGRATION_STATUS_ACTIVE:
> +    case MIGRATION_STATUS_POSTCOPY_ACTIVE:
> +    case MIGRATION_STATUS_FAILED:
> +    case MIGRATION_STATUS_COLO:
> +        info->has_status = true;
> +        break;
> +    case MIGRATION_STATUS_COMPLETED:
> +        info->has_status = true;
> +        fill_destination_postcopy_migration_info(info);
> +        break;
> +    }
> +    info->status = mis->state;
>  }
>  
> +MigrationInfo *qmp_query_migrate(Error **errp)
> +{
> +    MigrationInfo *info = g_malloc0(sizeof(*info));
> +
> +    if (is_source_migration()) {
> +        fill_source_migration_info(info);
> +    } else {
> +        fill_destination_migration_info(info);
> +    }

A VM that was migated in can then later get migrated out;
so I think you need to give both sets of data.
Which probably means you need a second status field
since existing stuff might get confused if it's watching
an outbound migration after an inbound one.

Dave
 
> +
> +     return info;
> + }
> +
>  void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
>                                    Error **errp)
>  {
> diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
> index e2660ae..fe047c8 100644
> --- a/migration/postcopy-ram.c
> +++ b/migration/postcopy-ram.c
> @@ -129,6 +129,71 @@ static struct PostcopyBlocktimeContext *blocktime_context_new(void)
>      return ctx;
>  }
>  
> +static int64List *get_vcpu_blocktime_list(PostcopyBlocktimeContext *ctx)
> +{
> +    int64List *list = NULL, *entry = NULL;
> +    int i;
> +
> +    for (i = smp_cpus - 1; i >= 0; i--) {
> +            entry = g_new0(int64List, 1);
> +            entry->value = ctx->vcpu_blocktime[i];
> +            entry->next = list;
> +            list = entry;
> +    }
> +
> +    return list;
> +}
> +
> +/*
> + * This function just provide calculated blocktime per cpu and trace it.
> + * Total blocktime is calculated in mark_postcopy_blocktime_end.
> + *
> + *
> + * Assume we have 3 CPU
> + *
> + *      S1        E1           S1               E1
> + * -----***********------------xxx***************------------------------> CPU1
> + *
> + *             S2                E2
> + * ------------****************xxx---------------------------------------> CPU2
> + *
> + *                         S3            E3
> + * ------------------------****xxx********-------------------------------> CPU3
> + *
> + * We have sequence S1,S2,E1,S3,S1,E2,E3,E1
> + * S2,E1 - doesn't match condition due to sequence S1,S2,E1 doesn't include CPU3
> + * S3,S1,E2 - sequence includes all CPUs, in this case overlap will be S1,E2 -
> + *            it's a part of total blocktime.
> + * S1 - here is last_begin
> + * Legend of the picture is following:
> + *              * - means blocktime per vCPU
> + *              x - means overlapped blocktime (total blocktime)
> + */
> +void fill_destination_postcopy_migration_info(MigrationInfo *info)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
> +
> +    if (!mis->blocktime_ctx) {
> +        return;
> +    }
> +
> +    info->has_postcopy_blocktime = true;
> +    info->postcopy_blocktime = mis->blocktime_ctx->total_blocktime;
> +    info->has_postcopy_vcpu_blocktime = true;
> +    info->postcopy_vcpu_blocktime = get_vcpu_blocktime_list(mis->blocktime_ctx);
> +}
> +
> +static uint64_t get_postcopy_total_blocktime(void)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
> +
> +    if (!mis->blocktime_ctx) {
> +        return 0;
> +    }
> +
> +    return mis->blocktime_ctx->total_blocktime;
> +}
> +
>  /*
>   * Check userfault fd features, to request only supported features in
>   * future.
> @@ -462,6 +527,9 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
>      }
>  
>      postcopy_state_set(POSTCOPY_INCOMING_END);
> +    /* here should be blocktime receiving back operation */
> +    trace_postcopy_ram_incoming_cleanup_blocktime(
> +            get_postcopy_total_blocktime());
>      migrate_send_rp_shut(mis, qemu_file_get_error(mis->from_src_file) != 0);
>  
>      if (mis->postcopy_tmp_page) {
> @@ -876,6 +944,11 @@ void *postcopy_get_tmp_page(MigrationIncomingState *mis)
>  
>  #else
>  /* No target OS support, stubs just fail */
> +void fill_destination_postcopy_migration_info(MigrationInfo *info)
> +{
> +    error_report("%s: No OS support", __func__);
> +}
> +
>  bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
>  {
>      error_report("%s: No OS support", __func__);
> diff --git a/migration/trace-events b/migration/trace-events
> index 9424e3e..bdaca1d 100644
> --- a/migration/trace-events
> +++ b/migration/trace-events
> @@ -193,6 +193,7 @@ postcopy_ram_incoming_cleanup_closeuf(void) ""
>  postcopy_ram_incoming_cleanup_entry(void) ""
>  postcopy_ram_incoming_cleanup_exit(void) ""
>  postcopy_ram_incoming_cleanup_join(void) ""
> +postcopy_ram_incoming_cleanup_blocktime(uint64_t total) "total blocktime %" PRIu64
>  save_xbzrle_page_skipping(void) ""
>  save_xbzrle_page_overflow(void) ""
>  ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRIu64 " milliseconds, %d iterations"
> diff --git a/qapi-schema.json b/qapi-schema.json
> index fde6d63..e11c5f2 100644
> --- a/qapi-schema.json
> +++ b/qapi-schema.json
> @@ -712,6 +712,8 @@
>  #              @status is 'failed'. Clients should not attempt to parse the
>  #              error strings. (Since 2.7)
>  #
> +# @postcopy_vcpu_blocktime: list of the postcopy blocktime per vCPU (Since 2.9)
> +#
>  # Since: 0.14.0
>  ##
>  { 'struct': 'MigrationInfo',
> @@ -723,7 +725,9 @@
>             '*downtime': 'int',
>             '*setup-time': 'int',
>             '*cpu-throttle-percentage': 'int',
> -           '*error-desc': 'str'} }
> +           '*error-desc': 'str',
> +           '*postcopy_blocktime' : 'int64',
> +           '*postcopy_vcpu_blocktime': ['int64']} }
>  
>  ##
>  # @query-migrate:
> -- 
> 1.9.1
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK

Re: [Qemu-devel] [PATCH V5 8/9] migration: add postcopy total blocktime into query-migrate
Posted by Eric Blake 8 years, 8 months ago
On 05/19/2017 02:23 PM, Dr. David Alan Gilbert wrote:
> * Alexey Perevalov (a.perevalov@samsung.com) wrote:
>> Postcopy total blocktime is available on destination side only.
>> But query-migrate was possible only for source. This patch
>> adds ability to call query-migrate on destination. To distinguish
>> src/dst, state of the MigrationState is using, query-migrate prepares
>> MigrationInfo for source machine only in case of migration's state is different
>> than MIGRATION_STATUS_NONE.
>>

> 
> Lets just check Eric is happy with the qapi side.

I pointed out a couple of things that need to be fixed.

-- 
Eric Blake, Principal Software Engineer
Red Hat, Inc.           +1-919-301-3266
Virtualization:  qemu.org | libvirt.org

Re: [Qemu-devel] [PATCH V5 8/9] migration: add postcopy total blocktime into query-migrate
Posted by Eric Blake 8 years, 8 months ago
On 05/12/2017 08:31 AM, Alexey Perevalov wrote:
> Postcopy total blocktime is available on destination side only.
> But query-migrate was possible only for source. This patch
> adds ability to call query-migrate on destination. To distinguish
> src/dst, state of the MigrationState is using, query-migrate prepares
> MigrationInfo for source machine only in case of migration's state is different
> than MIGRATION_STATUS_NONE.
> 
> To be able to see postcopy blocktime, need to request postcopy-blocktime
> capability.
> 
> The query-migrate command will show following sample result:
> {"return":
>     "postcopy_vcpu_blocktime": [115, 100],
>     "status": "completed",
>     "postcopy_blocktime": 100
> }}
> 
> postcopy_vcpu_blocktime contains list, where the first item is the first
> vCPU in QEMU.
> 
> Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>
> ---

> +++ b/qapi-schema.json
> @@ -712,6 +712,8 @@
>  #              @status is 'failed'. Clients should not attempt to parse the
>  #              error strings. (Since 2.7)
>  #
> +# @postcopy_vcpu_blocktime: list of the postcopy blocktime per vCPU (Since 2.9)

You've missed 2.9; this should be 2.10.

> +#
>  # Since: 0.14.0
>  ##
>  { 'struct': 'MigrationInfo',
> @@ -723,7 +725,9 @@
>             '*downtime': 'int',
>             '*setup-time': 'int',
>             '*cpu-throttle-percentage': 'int',
> -           '*error-desc': 'str'} }
> +           '*error-desc': 'str',
> +           '*postcopy_blocktime' : 'int64',
> +           '*postcopy_vcpu_blocktime': ['int64']} }

You're adding two fields, but only documented one of them
(postcopy_blocktime needs mention).

New fields should favor names with '-', not '_'; especially when part of
a struct that is already using '-' names.  So these should be
'postcopy-blocktime' and 'postcopy-vcpu-blocktime'.

-- 
Eric Blake, Principal Software Engineer
Red Hat, Inc.           +1-919-301-3266
Virtualization:  qemu.org | libvirt.org