Re: [Qemu-devel] [PATCH v5 11/45] Return path: Send responses from destination to source

[Dr. David Alan Gilbert]

* David Gibson (address@hidden) wrote:
> On Wed, Feb 25, 2015 at 04:51:34PM +0000, Dr. David Alan Gilbert (git) wrote:
> > From: "Dr. David Alan Gilbert" <address@hidden>
> > 
> > Add migrate_send_rp_message to send a message from destination to source 
> > along the return path.
> >   (It uses a mutex to let it be called from multiple threads)
> > Add migrate_send_rp_shut to send a 'shut' message to indicate
> >   the destination is finished with the RP.
> > Add migrate_send_rp_ack to send a 'PONG' message in response to a PING
> >   Use it in the CMD_PING handler
> > 
> > Signed-off-by: Dr. David Alan Gilbert <address@hidden>
> > ---
> >  include/migration/migration.h | 17 ++++++++++++++++
> >  migration/migration.c         | 45 
> > +++++++++++++++++++++++++++++++++++++++++++
> >  savevm.c                      |  2 +-
> >  trace-events                  |  1 +
> >  4 files changed, 64 insertions(+), 1 deletion(-)
> > 
> > diff --git a/include/migration/migration.h b/include/migration/migration.h
> > index c514dd4..6775747 100644
> > --- a/include/migration/migration.h
> > +++ b/include/migration/migration.h
> > @@ -41,6 +41,13 @@ struct MigrationParams {
> >      bool shared;
> >  };
> >  
> > +/* Commands sent on the return path from destination to source*/
> > +enum mig_rpcomm_cmd {
> 
> "command" doesn't seem like quite the right description for these rp
> messages.

Would you prefer 'message' ?

> > +    MIG_RP_CMD_INVALID = 0,  /* Must be 0 */
> > +    MIG_RP_CMD_SHUT,         /* sibling will not send any more RP messages 
> > */
> > +    MIG_RP_CMD_PONG,         /* Response to a PING; data (seq: be32 ) */
> > +};
> > +
> >  typedef struct MigrationState MigrationState;
> >  
> >  /* State for the incoming migration */
> > @@ -48,6 +55,7 @@ struct MigrationIncomingState {
> >      QEMUFile *file;
> >  
> >      QEMUFile *return_path;
> > +    QemuMutex      rp_mutex;    /* We send replies from multiple threads */
> >  };
> >  
> >  MigrationIncomingState *migration_incoming_get_current(void);
> > @@ -169,6 +177,15 @@ int64_t migrate_xbzrle_cache_size(void);
> >  
> >  int64_t xbzrle_cache_resize(int64_t new_size);
> >  
> > +/* Sending on the return path - generic and then for each message type */
> > +void migrate_send_rp_message(MigrationIncomingState *mis,
> > +                             enum mig_rpcomm_cmd cmd,
> > +                             uint16_t len, uint8_t *data);
> > +void migrate_send_rp_shut(MigrationIncomingState *mis,
> > +                          uint32_t value);
> > +void migrate_send_rp_pong(MigrationIncomingState *mis,
> > +                          uint32_t value);
> > +
> >  void ram_control_before_iterate(QEMUFile *f, uint64_t flags);
> >  void ram_control_after_iterate(QEMUFile *f, uint64_t flags);
> >  void ram_control_load_hook(QEMUFile *f, uint64_t flags);
> > diff --git a/migration/migration.c b/migration/migration.c
> > index a36ea65..80d234c 100644
> > --- a/migration/migration.c
> > +++ b/migration/migration.c
> > @@ -78,6 +78,7 @@ MigrationIncomingState 
> > *migration_incoming_state_new(QEMUFile* f)
> >  {
> >      mis_current = g_malloc0(sizeof(MigrationIncomingState));
> >      mis_current->file = f;
> > +    qemu_mutex_init(&mis_current->rp_mutex);
> >  
> >      return mis_current;
> >  }
> > @@ -88,6 +89,50 @@ void migration_incoming_state_destroy(void)
> >      mis_current = NULL;
> >  }
> >  
> > +/*
> > + * Send a message on the return channel back to the source
> > + * of the migration.
> > + */
> > +void migrate_send_rp_message(MigrationIncomingState *mis,
> > +                             enum mig_rpcomm_cmd cmd,
> > +                             uint16_t len, uint8_t *data)
> 
> Using (void *) for data would avoid casts in a bunch of the callers.

Fixed; thanks.

> > +{
> > +    trace_migrate_send_rp_message((int)cmd, len);
> > +    qemu_mutex_lock(&mis->rp_mutex);
> > +    qemu_put_be16(mis->return_path, (unsigned int)cmd);
> > +    qemu_put_be16(mis->return_path, len);
> > +    qemu_put_buffer(mis->return_path, data, len);
> > +    qemu_fflush(mis->return_path);
> > +    qemu_mutex_unlock(&mis->rp_mutex);
> > +}
> > +
> > +/*
> > + * Send a 'SHUT' message on the return channel with the given value
> > + * to indicate that we've finished with the RP.  None-0 value indicates
> > + * error.
> > + */
> > +void migrate_send_rp_shut(MigrationIncomingState *mis,
> > +                          uint32_t value)
> > +{
> > +    uint32_t buf;
> > +
> > +    buf = cpu_to_be32(value);
> > +    migrate_send_rp_message(mis, MIG_RP_CMD_SHUT, 4, (uint8_t *)&buf);
> 
>                                                      ^ sizeof(buf)
>                                                    would be safer

Done.

> > +}
> > +
> > +/*
> > + * Send a 'PONG' message on the return channel with the given value
> > + * (normally in response to a 'PING')
> > + */
> > +void migrate_send_rp_pong(MigrationIncomingState *mis,
> > +                          uint32_t value)
> > +{
> > +    uint32_t buf;
> > +
> > +    buf = cpu_to_be32(value);
> > +    migrate_send_rp_message(mis, MIG_RP_CMD_PONG, 4, (uint8_t *)&buf);
> 
> It occurs to me that you could define PONG as returning the whole
> buffer that PING sends, instead of just 4-bytes.  Might allow for some
> more testing of variable sized messages.

Yes; although it would complicate things a lot if I made it fully generic
because I'd have to worry about allocating a buffer etc and I'm not
making vast use of the 4 bytes I've already got.

Dave

> 
> > +}
> > +
> >  void qemu_start_incoming_migration(const char *uri, Error **errp)
> >  {
> >      const char *p;
> > diff --git a/savevm.c b/savevm.c
> > index d082738..7084d07 100644
> > --- a/savevm.c
> > +++ b/savevm.c
> > @@ -1008,7 +1008,7 @@ static int loadvm_process_command(QEMUFile *f)
> >                           tmp32);
> >              return -1;
> >          }
> > -        /* migrate_send_rp_pong(mis, tmp32); TODO: gets added later */
> > +        migrate_send_rp_pong(mis, tmp32);
> >          break;
> >  
> >      default:
> > diff --git a/trace-events b/trace-events
> > index 99e00b5..4f3eff8 100644
> > --- a/trace-events
> > +++ b/trace-events
> > @@ -1379,6 +1379,7 @@ migrate_fd_cleanup(void) ""
> >  migrate_fd_error(void) ""
> >  migrate_fd_cancel(void) ""
> >  migrate_pending(uint64_t size, uint64_t max) "pending size %" PRIu64 " max 
> > %" PRIu64
> > +migrate_send_rp_message(int cmd, uint16_t len) "cmd=%d, len=%d"
> >  migrate_transferred(uint64_t tranferred, uint64_t time_spent, double 
> > bandwidth, uint64_t size) "transferred %" PRIu64 " time_spent %" PRIu64 " 
> > bandwidth %g max_size %" PRId64
> >  
> >  # migration/rdma.c
> 
> -- 
> David Gibson                  | I'll have my music baroque, and my code
> david AT gibson.dropbear.id.au        | minimalist, thank you.  NOT _the_ 
> _other_
>                               | _way_ _around_!
> http://www.ozlabs.org/~dgibson


--
Dr. David Alan Gilbert / address@hidden / Manchester, UK