Re: [Qemu-devel] [PATCH RFC] migration: set cpu throttle value by workload

[Cao jin <caoj.fnst@cn.fujitsu.com>]

Hi,
We have been waiting for a long time on this topic，we have interests in
improving the migration performance, and we think this could benefit in
certain condition like heavy work load, the throttle value is a dynamic
value than fixed increment. Your comments would be important to us,
thanks in advance.

-- 
Sincerely,
Cao jin

On 12/29/2016 05:16 PM, Chao Fan wrote:
> This RFC PATCH is my demo about the new feature, here is my POC mail:
> https://lists.gnu.org/archive/html/qemu-devel/2016-12/msg00646.html
> 
> When migration_bitmap_sync executed, get the time and read bitmap to
> calculate how many dirty pages born between two sync.
> Use inst_dirty_pages / (time_now - time_prev) / ram_size to get
> inst_dirty_pages_rate. Then map from the inst_dirty_pages_rate
> to cpu throttle value. I have no idea how to map it. So I just do
> that in a simple way. The mapping way is just a guess and should
> be improved.
> 
> This is just a demo. There are more methods.
> 1.In another file, calculate the inst_dirty_pages_rate every second
>   or two seconds or another fixed time. Then set the cpu throttle
>   value according to the inst_dirty_pages_rate
> 2.When inst_dirty_pages_rate gets a threshold, begin cpu throttle
>   and set the throttle value.
> 
> Any comments will be welcome.
> 
> Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com>
> ---
>  include/qemu/bitmap.h | 17 +++++++++++++++++
>  migration/ram.c       | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 66 insertions(+)
> 
> diff --git a/include/qemu/bitmap.h b/include/qemu/bitmap.h
> index 63ea2d0..dc99f9b 100644
> --- a/include/qemu/bitmap.h
> +++ b/include/qemu/bitmap.h
> @@ -235,4 +235,21 @@ static inline unsigned long *bitmap_zero_extend(unsigned long *old,
>      return new;
>  }
>  
> +static inline unsigned long bitmap_weight(const unsigned long *src, long nbits)
> +{
> +    unsigned long i, count = 0, nlong = nbits / BITS_PER_LONG;
> +
> +    if (small_nbits(nbits)) {
> +        return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
> +    }
> +    for (i = 0; i < nlong; i++) {
> +        count += hweight_long(src[i]);
> +    }
> +    if (nbits % BITS_PER_LONG) {
> +        count += hweight_long(src[i] & BITMAP_LAST_WORD_MASK(nbits));
> +    }
> +
> +    return count;
> +}
> +
>  #endif /* BITMAP_H */
> diff --git a/migration/ram.c b/migration/ram.c
> index a1c8089..f96e3e3 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -44,6 +44,7 @@
>  #include "exec/ram_addr.h"
>  #include "qemu/rcu_queue.h"
>  #include "migration/colo.h"
> +#include "hw/boards.h"
>  
>  #ifdef DEBUG_MIGRATION_RAM
>  #define DPRINTF(fmt, ...) \
> @@ -599,6 +600,9 @@ static int64_t num_dirty_pages_period;
>  static uint64_t xbzrle_cache_miss_prev;
>  static uint64_t iterations_prev;
>  
> +static int64_t dirty_pages_time_prev;
> +static int64_t dirty_pages_time_now;
> +
>  static void migration_bitmap_sync_init(void)
>  {
>      start_time = 0;
> @@ -606,6 +610,49 @@ static void migration_bitmap_sync_init(void)
>      num_dirty_pages_period = 0;
>      xbzrle_cache_miss_prev = 0;
>      iterations_prev = 0;
> +
> +    dirty_pages_time_prev = 0;
> +    dirty_pages_time_now = 0;
> +}
> +
> +static void migration_inst_rate(void)
> +{
> +    RAMBlock *block;
> +    MigrationState *s = migrate_get_current();
> +    int64_t inst_dirty_pages_rate, inst_dirty_pages = 0;
> +    int64_t i;
> +    unsigned long *num;
> +    unsigned long len = 0;
> +
> +    dirty_pages_time_now = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
> +    if (dirty_pages_time_prev != 0) {
> +        rcu_read_lock();
> +        DirtyMemoryBlocks *blocks = atomic_rcu_read(
> +                         &ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION]);
> +        QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
> +            if (len == 0) {
> +                len = block->offset;
> +            }
> +            len += block->used_length;
> +        }
> +        ram_addr_t idx = (len >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE;
> +        if (((len >> TARGET_PAGE_BITS) % DIRTY_MEMORY_BLOCK_SIZE) != 0) {
> +            idx++;
> +        }
> +        for (i = 0; i < idx; i++) {
> +            num = blocks->blocks[i];
> +            inst_dirty_pages += bitmap_weight(num, DIRTY_MEMORY_BLOCK_SIZE);
> +        }
> +        rcu_read_unlock();
> +
> +        inst_dirty_pages_rate = inst_dirty_pages * TARGET_PAGE_SIZE *
> +                            1024 * 1024 * 1000 /
> +                            (dirty_pages_time_now - dirty_pages_time_prev) /
> +                            current_machine->ram_size;
> +        s->parameters.cpu_throttle_initial = inst_dirty_pages_rate / 200;
> +        s->parameters.cpu_throttle_increment = inst_dirty_pages_rate / 200;
> +    }
> +    dirty_pages_time_prev = dirty_pages_time_now;
>  }
>  
>  static void migration_bitmap_sync(void)
> @@ -629,6 +676,8 @@ static void migration_bitmap_sync(void)
>      trace_migration_bitmap_sync_start();
>      memory_global_dirty_log_sync();
>  
> +    migration_inst_rate();
> +
>      qemu_mutex_lock(&migration_bitmap_mutex);
>      rcu_read_lock();
>      QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
>