Re: [Qemu-devel] [PATCH] Add warmup phase for live migration of large memory apps

[Anthony Liguori <anthony@codemonkey.ws>]

On 05/11/2011 02:58 AM, Shribman, Aidan wrote:
> From: Aidan Shribman<aidan.shribman@sap.com>
>
> [PATCH] Add warmup phase for live migration of large memory apps
>
> By invoking "migrate -w<url>" we initiate a background live-migration
> transferring of dirty pages continuously until invocation of "migrate_end"
> which attempts to complete the live migration operation.
>
> Qemu host: Ubuntu 10.10
>
> Testing: live migration (with/without warmup phase) tested successfully.
>
> Signed-off-by: Benoit Hudzia<benoit.hudzia@sap.com>
> Signed-off-by: Petter Svard<petters@cs.umu.se>
> Signed-off-by: Aidan Shribman<aidan.shribman@sap.com>

If you do:

migrate_set_downtime 0
migrate -d <url>

You'll achieve the same result.  The migration will never converge 
because there's no way QEMU can meet the downtime expectation.

You can then do:

migrate_set_downtime 30ms

To let migration go.  You can even use info migrate to figure out when 
migration has been sufficiently warmed up.

You can also always do migrate_cancel to abort the operation.

Regards,

Anthony Liguori

> ---
>   hmp-commands.hx |   34 +++++++++++++++++++++++++---------
>   migration.c     |   23 ++++++++++++++++++++++-
>   migration.h     |    2 ++
>   qmp-commands.hx |   41 ++++++++++++++++++++++++++++++++++-------
>   savevm.c        |   12 ++++++++++++
>   sysemu.h        |    1 +
>   6 files changed, 96 insertions(+), 17 deletions(-)
>
> diff --git a/hmp-commands.hx b/hmp-commands.hx
> index e5585ba..234a952 100644
> --- a/hmp-commands.hx
> +++ b/hmp-commands.hx
> @@ -717,24 +717,27 @@ ETEXI
>
>       {
>           .name       = "migrate",
> -        .args_type  = "detach:-d,blk:-b,inc:-i,uri:s",
> -        .params     = "[-d] [-b] [-i] uri",
> -        .help       = "migrate to URI (using -d to not wait for completion)"
> -		      "\n\t\t\t -b for migration without shared storage with"
> -		      " full copy of disk\n\t\t\t -i for migration without "
> -		      "shared storage with incremental copy of disk "
> -		      "(base image shared between src and destination)",
> +        .args_type  = "detach:-d,blk:-b,inc:-i,warmup:-w,uri:s",
> +        .params     = "[-d] [-b] [-i] [-w] uri",
> +        .help       = "migrate to URI"
> +                      "\n\t -d to not wait for completion"
> +                      "\n\t -b for migration without shared storage with"
> +                      " full copy of disk"
> +                      "\n\t -i for migration without"
> +                      " shared storage with incremental copy of disk"
> +                      " (base image shared between source and destination)"
> +                      "\n\t -w to enter warmup phase",
>           .user_print = monitor_user_noop,	
>   	.mhandler.cmd_new = do_migrate,
>       },
>
> -
>   STEXI
> -@item migrate [-d] [-b] [-i] @var{uri}
> +@item migrate [-d] [-b] [-i] [-w] @var{uri}
>   @findex migrate
>   Migrate to @var{uri} (using -d to not wait for completion).
>   	-b for migration with full copy of disk
>   	-i for migration with incremental copy of disk (base image is shared)
> +    -w to enter warmup phase
>   ETEXI
>
>       {
> @@ -753,6 +756,19 @@ Cancel the current VM migration.
>   ETEXI
>
>       {
> +        .name       = "migrate_end",
> +        .args_type  = "",
> +        .params     = "",
> +        .help       = "Complete warmup and move to full live migration",
> +        .mhandler.cmd = do_migrate_end,
> +    },
> +
> +STEXI
> +@item migrate_end
> +Complete warmup and move to full live migration.
> +ETEXI
> +
> +    {
>           .name       = "migrate_set_speed",
>           .args_type  = "value:o",
>           .params     = "value",
> diff --git a/migration.c b/migration.c
> index 9ee8b17..7525b47 100644
> --- a/migration.c
> +++ b/migration.c
> @@ -31,6 +31,8 @@
>       do { } while (0)
>   #endif
>
> +static int is_migrate_warmup = 0;
> +
>   /* Migration speed throttling */
>   static uint32_t max_throttle = (32<<  20);
>
> @@ -81,6 +83,11 @@ int do_migrate(Monitor *mon, const QDict *qdict, QObject **ret_data)
>       int blk = qdict_get_try_bool(qdict, "blk", 0);
>       int inc = qdict_get_try_bool(qdict, "inc", 0);
>       const char *uri = qdict_get_str(qdict, "uri");
> +    is_migrate_warmup = qdict_get_try_bool(qdict, "warmup", 0);
> +
> +    if (is_migrate_warmup) {
> +        detach = 1; /* as we need migrate_end to complte */
> +	}
>
>       if (current_migration&&
>           current_migration->get_status(current_migration) == MIG_STATE_ACTIVE) {
> @@ -361,7 +368,9 @@ void migrate_fd_put_ready(void *opaque)
>       }
>
>       DPRINTF("iterate\n");
> -    if (qemu_savevm_state_iterate(s->mon, s->file) == 1) {
> +    if (is_migrate_warmup) {
> +            qemu_savevm_state_warmup(s->mon, s->file);
> +	} else if (qemu_savevm_state_iterate(s->mon, s->file) == 1) {
>           int state;
>           int old_vm_running = vm_running;
>
> @@ -448,3 +457,15 @@ int migrate_fd_close(void *opaque)
>       qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
>       return s->close(s);
>   }
> +
> +void do_migrate_end(Monitor *mon, const QDict *qdict)
> +{
> +    if (!vm_running) {
> +        return;
> +	}
> +    if (!is_migrate_warmup) {
> +        return;
> +	}
> +    is_migrate_warmup = 0;
> +}
> +
> diff --git a/migration.h b/migration.h
> index d13ed4f..6a96b29 100644
> --- a/migration.h
> +++ b/migration.h
> @@ -134,4 +134,6 @@ static inline FdMigrationState *migrate_to_fms(MigrationState *mig_state)
>       return container_of(mig_state, FdMigrationState, mig_state);
>   }
>
> +void do_migrate_end(Monitor *mon, const QDict *qdict);
> +
>   #endif
> diff --git a/qmp-commands.hx b/qmp-commands.hx
> index 793cf1c..58fe696 100644
> --- a/qmp-commands.hx
> +++ b/qmp-commands.hx
> @@ -431,13 +431,16 @@ EQMP
>
>       {
>           .name       = "migrate",
> -        .args_type  = "detach:-d,blk:-b,inc:-i,uri:s",
> -        .params     = "[-d] [-b] [-i] uri",
> -        .help       = "migrate to URI (using -d to not wait for completion)"
> -		      "\n\t\t\t -b for migration without shared storage with"
> -		      " full copy of disk\n\t\t\t -i for migration without "
> -		      "shared storage with incremental copy of disk "
> -		      "(base image shared between src and destination)",
> +        .args_type  = "detach:-d,blk:-b,inc:-i,xbrle:-x,warmup:-w,uri:s",
> +        .params     = "[-d] [-b] [-i] [-w] uri",
> +        .help       = "migrate to URI"
> +                      "\n\t -d to not wait for completion"
> +                      "\n\t -b for migration without shared storage with"
> +                      " full copy of disk"
> +                      "\n\t -i for migration without"
> +                      " shared storage with incremental copy of disk"
> +                      " (base image shared between source and destination)"
> +                      "\n\t -w to enter warmup phase",
>           .user_print = monitor_user_noop,	
>   	.mhandler.cmd_new = do_migrate,
>       },
> @@ -453,6 +456,7 @@ Arguments:
>   - "blk": block migration, full disk copy (json-bool, optional)
>   - "inc": incremental disk copy (json-bool, optional)
>   - "uri": Destination URI (json-string)
> +- "warmup":to enter warmup phasen
>
>   Example:
>
> @@ -494,6 +498,29 @@ Example:
>   EQMP
>
>       {
> +        .name       = "migrate_end",
> +        .args_type  = "",
> +        .params     = "",
> +        .help       = "Complete warmup and move to full live migration",
> +        .mhandler.cmd = do_migrate_end,
> +    },
> +
> +SQMP
> +migrate_end
> +-----------
> +
> +End the current migration warmup.
> +
> +Arguments: None.
> +
> +Example:
> +
> +->  { "execute": "migrate_end" }
> +<- { "return": {} }
> +
> +EQMP
> +
> +    {
>           .name       = "migrate_set_speed",
>           .args_type  = "value:f",
>           .params     = "value",
> diff --git a/savevm.c b/savevm.c
> index 4e49765..521589c 100644
> --- a/savevm.c
> +++ b/savevm.c
> @@ -1471,6 +1471,18 @@ int qemu_savevm_state_begin(Monitor *mon, QEMUFile *f, int blk_enable,
>       return 0;
>   }
>
> +int qemu_savevm_state_warmup(Monitor *mon, QEMUFile *f) {
> +    int ret = 1;
> +
> +    ret = qemu_savevm_state_iterate(mon, f);
> +
> +    if (ret == -EIO) {
> +        return ret;
> +	}
> +
> +    return 0;
> +}
> +
>   int qemu_savevm_state_iterate(Monitor *mon, QEMUFile *f)
>   {
>       SaveStateEntry *se;
> diff --git a/sysemu.h b/sysemu.h
> index b81a70e..74e8a48 100644
> --- a/sysemu.h
> +++ b/sysemu.h
> @@ -76,6 +76,7 @@ void main_loop_wait(int nonblocking);
>   int qemu_savevm_state_begin(Monitor *mon, QEMUFile *f, int blk_enable,
>                               int shared);
>   int qemu_savevm_state_iterate(Monitor *mon, QEMUFile *f);
> +int qemu_savevm_state_warmup(Monitor *mon, QEMUFile *f);
>   int qemu_savevm_state_complete(Monitor *mon, QEMUFile *f);
>   void qemu_savevm_state_cancel(Monitor *mon, QEMUFile *f);
>   int qemu_loadvm_state(QEMUFile *f);