From: Hyman Huang(黄勇) <yong.hu...@smartx.com> Implement dirty-limit convergence algo for live migration, which is kind of like auto-converge algo but using dirty-limit instead of cpu throttle to make migration convergent.
Enable dirty page limit if dirty_rate_high_cnt greater than 2 when dirty-limit capability enabled, Disable dirty-limit if migration be cancled. Note that "set_vcpu_dirty_limit", "cancel_vcpu_dirty_limit" commands are not allowed during dirty-limit live migration. Signed-off-by: Hyman Huang(黄勇) <yong.hu...@smartx.com> Signed-off-by: Markus Armbruster <arm...@redhat.com> --- migration/migration.c | 3 ++ migration/ram.c | 63 ++++++++++++++++++++++++++++++++---------- migration/trace-events | 1 + softmmu/dirtylimit.c | 22 +++++++++++++++ 4 files changed, 74 insertions(+), 15 deletions(-) diff --git a/migration/migration.c b/migration/migration.c index dc05c6f6ea..4278b48af0 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -165,6 +165,9 @@ void migration_cancel(const Error *error) if (error) { migrate_set_error(current_migration, error); } + if (migrate_dirty_limit()) { + qmp_cancel_vcpu_dirty_limit(false, -1, NULL); + } migrate_fd_cancel(current_migration); } diff --git a/migration/ram.c b/migration/ram.c index 132f1a81d9..d26c7a8193 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -46,6 +46,7 @@ #include "qapi/error.h" #include "qapi/qapi-types-migration.h" #include "qapi/qapi-events-migration.h" +#include "qapi/qapi-commands-migration.h" #include "qapi/qmp/qerror.h" #include "trace.h" #include "exec/ram_addr.h" @@ -59,6 +60,8 @@ #include "multifd.h" #include "sysemu/runstate.h" #include "options.h" +#include "sysemu/dirtylimit.h" +#include "sysemu/kvm.h" #include "hw/boards.h" /* for machine_dump_guest_core() */ @@ -983,6 +986,30 @@ static void migration_update_rates(RAMState *rs, int64_t end_time) } } +/* + * Enable dirty-limit to throttle down the guest + */ +static void migration_dirty_limit_guest(void) +{ + static int64_t quota_dirtyrate; + MigrationState *s = migrate_get_current(); + + /* + * If dirty limit already enabled and migration parameter + * vcpu-dirty-limit untouched. + */ + if (dirtylimit_in_service() && + quota_dirtyrate == s->parameters.vcpu_dirty_limit) { + return; + } + + quota_dirtyrate = s->parameters.vcpu_dirty_limit; + + /* Set or update quota dirty limit */ + qmp_set_vcpu_dirty_limit(false, -1, quota_dirtyrate, NULL); + trace_migration_dirty_limit_guest(quota_dirtyrate); +} + static void migration_trigger_throttle(RAMState *rs) { uint64_t threshold = migrate_throttle_trigger_threshold(); @@ -991,26 +1018,32 @@ static void migration_trigger_throttle(RAMState *rs) uint64_t bytes_dirty_period = rs->num_dirty_pages_period * TARGET_PAGE_SIZE; uint64_t bytes_dirty_threshold = bytes_xfer_period * threshold / 100; - /* During block migration the auto-converge logic incorrectly detects - * that ram migration makes no progress. Avoid this by disabling the - * throttling logic during the bulk phase of block migration. */ - if (blk_mig_bulk_active()) { - return; - } + /* + * The following detection logic can be refined later. For now: + * Check to see if the ratio between dirtied bytes and the approx. + * amount of bytes that just got transferred since the last time + * we were in this routine reaches the threshold. If that happens + * twice, start or increase throttling. + */ - if (migrate_auto_converge()) { - /* The following detection logic can be refined later. For now: - Check to see if the ratio between dirtied bytes and the approx. - amount of bytes that just got transferred since the last time - we were in this routine reaches the threshold. If that happens - twice, start or increase throttling. */ + if ((bytes_dirty_period > bytes_dirty_threshold) && + (++rs->dirty_rate_high_cnt >= 2)) { + rs->dirty_rate_high_cnt = 0; + /* + * During block migration the auto-converge logic incorrectly detects + * that ram migration makes no progress. Avoid this by disabling the + * throttling logic during the bulk phase of block migration + */ + if (blk_mig_bulk_active()) { + return; + } - if ((bytes_dirty_period > bytes_dirty_threshold) && - (++rs->dirty_rate_high_cnt >= 2)) { + if (migrate_auto_converge()) { trace_migration_throttle(); - rs->dirty_rate_high_cnt = 0; mig_throttle_guest_down(bytes_dirty_period, bytes_dirty_threshold); + } else if (migrate_dirty_limit()) { + migration_dirty_limit_guest(); } } } diff --git a/migration/trace-events b/migration/trace-events index cdaef7a1ea..c5cb280d95 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -91,6 +91,7 @@ migration_bitmap_sync_start(void) "" migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64 migration_bitmap_clear_dirty(char *str, uint64_t start, uint64_t size, unsigned long page) "rb %s start 0x%"PRIx64" size 0x%"PRIx64" page 0x%lx" migration_throttle(void) "" +migration_dirty_limit_guest(int64_t dirtyrate) "guest dirty page rate limit %" PRIi64 " MB/s" ram_discard_range(const char *rbname, uint64_t start, size_t len) "%s: start: %" PRIx64 " %zx" ram_load_loop(const char *rbname, uint64_t addr, int flags, void *host) "%s: addr: 0x%" PRIx64 " flags: 0x%x host: %p" ram_load_postcopy_loop(int channel, uint64_t addr, int flags) "chan=%d addr=0x%" PRIx64 " flags=0x%x" diff --git a/softmmu/dirtylimit.c b/softmmu/dirtylimit.c index 3f1103b04b..ee47158986 100644 --- a/softmmu/dirtylimit.c +++ b/softmmu/dirtylimit.c @@ -440,6 +440,8 @@ void qmp_cancel_vcpu_dirty_limit(bool has_cpu_index, int64_t cpu_index, Error **errp) { + MigrationState *ms = migrate_get_current(); + if (!kvm_enabled() || !kvm_dirty_ring_enabled()) { return; } @@ -453,6 +455,15 @@ void qmp_cancel_vcpu_dirty_limit(bool has_cpu_index, return; } + if (migration_is_running(ms->state) && + (!qemu_thread_is_self(&ms->thread)) && + migrate_dirty_limit() && + dirtylimit_in_service()) { + error_setg(errp, "can't cancel dirty page limit while" + " migration is running"); + return; + } + dirtylimit_state_lock(); if (has_cpu_index) { @@ -488,6 +499,8 @@ void qmp_set_vcpu_dirty_limit(bool has_cpu_index, uint64_t dirty_rate, Error **errp) { + MigrationState *ms = migrate_get_current(); + if (!kvm_enabled() || !kvm_dirty_ring_enabled()) { error_setg(errp, "dirty page limit feature requires KVM with" " accelerator property 'dirty-ring-size' set'"); @@ -504,6 +517,15 @@ void qmp_set_vcpu_dirty_limit(bool has_cpu_index, return; } + if (migration_is_running(ms->state) && + (!qemu_thread_is_self(&ms->thread)) && + migrate_dirty_limit() && + dirtylimit_in_service()) { + error_setg(errp, "can't cancel dirty page limit while" + " migration is running"); + return; + } + dirtylimit_state_lock(); if (!dirtylimit_in_service()) { -- 2.38.5