* Wei Wang (wei.w.w...@intel.com) wrote:
> Start the free page optimization when the bulk stage starts. In case the
> guest is slow in reporting, actively stops it when the bulk stage ends.
> The optimization avoids sending guest free pages during the bulk stage.
> Currently, the optimization is added to precopy only.
>
> Signed-off-by: Wei Wang <wei.w.w...@intel.com>
> CC: Dr. David Alan Gilbert <dgilb...@redhat.com>
> CC: Juan Quintela <quint...@redhat.com>
> CC: Michael S. Tsirkin <m...@redhat.com>
I think this is OK, but with the only problem being that postcopy will
break; we need to disable the mechanism if postcopy is enabled.
Dave
> ---
> migration/ram.c | 19 ++++++++++++++++++-
> 1 file changed, 18 insertions(+), 1 deletion(-)
>
> diff --git a/migration/ram.c b/migration/ram.c
> index 769a0f6..f6af7e6 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -51,6 +51,7 @@
> #include "qemu/rcu_queue.h"
> #include "migration/colo.h"
> #include "migration/block.h"
> +#include "sysemu/balloon.h"
>
> /***********************************************************/
> /* ram save/restore */
> @@ -208,6 +209,8 @@ struct RAMState {
> uint32_t last_version;
> /* We are in the first round */
> bool ram_bulk_stage;
> + /* The free pages optimization feature is supported */
> + bool free_page_support;
> /* How many times we have dirty too many pages */
> int dirty_rate_high_cnt;
> /* these variables are used for bitmap sync */
> @@ -775,7 +778,7 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs,
> RAMBlock *rb,
> unsigned long *bitmap = rb->bmap;
> unsigned long next;
>
> - if (rs->ram_bulk_stage && start > 0) {
> + if (rs->ram_bulk_stage && start > 0 && !rs->free_page_support) {
> next = start + 1;
> } else {
> next = find_next_bit(bitmap, size, start);
> @@ -1225,6 +1228,10 @@ static bool find_dirty_block(RAMState *rs,
> PageSearchStatus *pss, bool *again)
> /* Flag that we've looped */
> pss->complete_round = true;
> rs->ram_bulk_stage = false;
> + if (rs->free_page_support) {
> + balloon_free_page_stop();
> + rs->free_page_support = false;
> + }
> if (migrate_use_xbzrle()) {
> /* If xbzrle is on, stop using the data compression at this
> * point. In theory, xbzrle can do better than compression.
> @@ -1656,6 +1663,8 @@ static void ram_state_reset(RAMState *rs)
> rs->last_page = 0;
> rs->last_version = ram_list.version;
> rs->ram_bulk_stage = true;
> + rs->free_page_support = balloon_free_page_support() &
> + !migration_in_postcopy();
> }
>
> #define MAX_WAIT 50 /* ms, half buffered_file limit */
> @@ -2235,6 +2244,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
> return -1;
> }
> }
> +
> + if ((*rsp)->free_page_support) {
> + balloon_free_page_start();
> + }
> +
> (*rsp)->f = f;
>
> rcu_read_lock();
> @@ -2329,6 +2343,9 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
>
> ret = qemu_file_get_error(f);
> if (ret < 0) {
> + if (rs->ram_bulk_stage && rs->free_page_support) {
> + balloon_free_page_stop();
> + }
> return ret;
> }
>
> --
> 1.8.3.1
>
--
Dr. David Alan Gilbert / dgilb...@redhat.com / Manchester, UK
