From: Fabiano Rosas <farosas(a)suse.de&gt; This doubly linked list is common for all the multifd and migration threads so we need to avoid concurrent access. Add a mutex to protect the data from concurrent access. This fixes a crash when removing two MigrationThread objects from the list at the same time during cleanup of multifd threads. Fixes: 671326201d ("migration: Introduce interface query-migrationthreads") Signed-off-by: Fabiano Rosas <farosas(a)suse.de&gt; Reviewed-by: Peter Xu <peterx(a)redhat.com&gt; Reviewed-by: Juan Quintela <quintela(a)redhat.com&gt; Message-Id: <20230607161306.31425-3-farosas(a)suse.de&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- migration/threadinfo.h | 2 -- migration/threadinfo.c | 15 ++++++++++++++- 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/migration/threadinfo.h b/migration/threadinfo.h index 8aa6999d58..2f356ff312 100644 --- a/migration/threadinfo.h +++ b/migration/threadinfo.h @@ -10,8 +10,6 @@ * See the COPYING file in the top-level directory. */ -#include "qemu/queue.h" -#include "qemu/osdep.h" #include "qapi/error.h" #include "qapi/qapi-commands-migration.h" diff --git a/migration/threadinfo.c b/migration/threadinfo.c index 3dd9b14ae6..262990dd75 100644 --- a/migration/threadinfo.c +++ b/migration/threadinfo.c @@ -10,23 +10,35 @@ * See the COPYING file in the top-level directory. */ +#include "qemu/osdep.h" +#include "qemu/queue.h" +#include "qemu/lockable.h" #include "threadinfo.h" +QemuMutex migration_threads_lock; static QLIST_HEAD(, MigrationThread) migration_threads; +static void __attribute__((constructor)) migration_threads_init(void) +{ + qemu_mutex_init(&migration_threads_lock); +} + MigrationThread *migration_threads_add(const char *name, int thread_id) { MigrationThread *thread = g_new0(MigrationThread, 1); thread->name = name; thread->thread_id = thread_id; - QLIST_INSERT_HEAD(&migration_threads, thread, node); + WITH_QEMU_LOCK_GUARD(&migration_threads_lock) { + QLIST_INSERT_HEAD(&migration_threads, thread, node); + } return thread; } void migration_threads_remove(MigrationThread *thread) { + QEMU_LOCK_GUARD(&migration_threads_lock); if (thread) { QLIST_REMOVE(thread, node); g_free(thread); @@ -39,6 +51,7 @@ MigrationThreadInfoList *qmp_query_migrationthreads(Error **errp) MigrationThreadInfoList **tail = &head; MigrationThread *thread = NULL; + QEMU_LOCK_GUARD(&migration_threads_lock); QLIST_FOREACH(thread, &migration_threads, node) { MigrationThreadInfo *info = g_new0(MigrationThreadInfo, 1); info->name = g_strdup(thread->name); -- 2.40.1

From: Hyman Huang(黄勇) <yong.huang(a)smartx.com&gt; Introduce "x-vcpu-dirty-limit-period" migration experimental parameter, which is in the range of 1 to 1000ms and used to make dirtyrate calculation period configurable. Currently with the "x-vcpu-dirty-limit-period" varies, the total time of live migration changes, test results show the optimal value of "x-vcpu-dirty-limit-period" ranges from 500ms to 1000 ms. "x-vcpu-dirty-limit-period" should be made stable once it proves best value can not be determined with developer's experiments. Signed-off-by: Hyman Huang(黄勇) <yong.huang(a)smartx.com&gt; Reviewed-by: Markus Armbruster <armbru(a)redhat.com&gt; Reviewed-by: Juan Quintela <quintela(a)redhat.com&gt; Message-Id: <168618975839.6361.17407633874747688653-2(a)git.sr.ht&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- qapi/migration.json | 34 +++++++++++++++++++++++++++------- migration/migration-hmp-cmds.c | 8 ++++++++ migration/options.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+), 7 deletions(-) diff --git a/qapi/migration.json b/qapi/migration.json index 2a6565a0f8..d83b694fef 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -789,9 +789,14 @@ # Nodes are mapped to their block device name if there is one, and # to their node name otherwise. (Since 5.2) # +# @x-vcpu-dirty-limit-period: Periodic time (in milliseconds) of dirty limit during +# live migration. Should be in the range 1 to 1000ms, +# defaults to 1000ms. (Since 8.1) +# # Features: # -# @unstable: Member @x-checkpoint-delay is experimental. +# @unstable: Members @x-checkpoint-delay and @x-vcpu-dirty-limit-period +# are experimental. # # Since: 2.4 ## @@ -809,8 +814,9 @@ 'multifd-channels', 'xbzrle-cache-size', 'max-postcopy-bandwidth', 'max-cpu-throttle', 'multifd-compression', - 'multifd-zlib-level' ,'multifd-zstd-level', - 'block-bitmap-mapping' ] } + 'multifd-zlib-level', 'multifd-zstd-level', + 'block-bitmap-mapping', + { 'name': 'x-vcpu-dirty-limit-period', 'features': ['unstable'] } ] } ## # @MigrateSetParameters: @@ -945,9 +951,14 @@ # Nodes are mapped to their block device name if there is one, and # to their node name otherwise. (Since 5.2) # +# @x-vcpu-dirty-limit-period: Periodic time (in milliseconds) of dirty limit during +# live migration. Should be in the range 1 to 1000ms, +# defaults to 1000ms. (Since 8.1) +# # Features: # -# @unstable: Member @x-checkpoint-delay is experimental. +# @unstable: Members @x-checkpoint-delay and @x-vcpu-dirty-limit-period +# are experimental. # # TODO: either fuse back into MigrationParameters, or make # MigrationParameters members mandatory @@ -982,7 +993,9 @@ '*multifd-compression': 'MultiFDCompression', '*multifd-zlib-level': 'uint8', '*multifd-zstd-level': 'uint8', - '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } } + '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ], + '*x-vcpu-dirty-limit-period': { 'type': 'uint64', + 'features': [ 'unstable' ] } } } ## # @migrate-set-parameters: @@ -1137,9 +1150,14 @@ # Nodes are mapped to their block device name if there is one, and # to their node name otherwise. (Since 5.2) # +# @x-vcpu-dirty-limit-period: Periodic time (in milliseconds) of dirty limit during +# live migration. Should be in the range 1 to 1000ms, +# defaults to 1000ms. (Since 8.1) +# # Features: # -# @unstable: Member @x-checkpoint-delay is experimental. +# @unstable: Members @x-checkpoint-delay and @x-vcpu-dirty-limit-period +# are experimental. # # Since: 2.4 ## @@ -1171,7 +1189,9 @@ '*multifd-compression': 'MultiFDCompression', '*multifd-zlib-level': 'uint8', '*multifd-zstd-level': 'uint8', - '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } } + '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ], + '*x-vcpu-dirty-limit-period': { 'type': 'uint64', + 'features': [ 'unstable' ] } } } ## # @query-migrate-parameters: diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c index 9885d7c9f7..352e9ec716 100644 --- a/migration/migration-hmp-cmds.c +++ b/migration/migration-hmp-cmds.c @@ -364,6 +364,10 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) } } } + + monitor_printf(mon, "%s: %" PRIu64 " ms\n", + MigrationParameter_str(MIGRATION_PARAMETER_X_VCPU_DIRTY_LIMIT_PERIOD), + params->x_vcpu_dirty_limit_period); } qapi_free_MigrationParameters(params); @@ -620,6 +624,10 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict) error_setg(&err, "The block-bitmap-mapping parameter can only be set " "through QMP"); break; + case MIGRATION_PARAMETER_X_VCPU_DIRTY_LIMIT_PERIOD: + p->has_x_vcpu_dirty_limit_period = true; + visit_type_size(v, param, &p->x_vcpu_dirty_limit_period, &err); + break; default: assert(0); } diff --git a/migration/options.c b/migration/options.c index 5a9505adf7..1de63ba775 100644 --- a/migration/options.c +++ b/migration/options.c @@ -80,6 +80,8 @@ #define DEFINE_PROP_MIG_CAP(name, x) \ DEFINE_PROP_BOOL(name, MigrationState, capabilities[x], false) +#define DEFAULT_MIGRATE_VCPU_DIRTY_LIMIT_PERIOD 1000 /* milliseconds */ + Property migration_properties[] = { DEFINE_PROP_BOOL("store-global-state", MigrationState, store_global_state, true), @@ -163,6 +165,9 @@ Property migration_properties[] = { DEFINE_PROP_STRING("tls-creds", MigrationState, parameters.tls_creds), DEFINE_PROP_STRING("tls-hostname", MigrationState, parameters.tls_hostname), DEFINE_PROP_STRING("tls-authz", MigrationState, parameters.tls_authz), + DEFINE_PROP_UINT64("x-vcpu-dirty-limit-period", MigrationState, + parameters.x_vcpu_dirty_limit_period, + DEFAULT_MIGRATE_VCPU_DIRTY_LIMIT_PERIOD), /* Migration capabilities */ DEFINE_PROP_MIG_CAP("x-xbzrle", MIGRATION_CAPABILITY_XBZRLE), @@ -908,6 +913,9 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp) s->parameters.block_bitmap_mapping); } + params->has_x_vcpu_dirty_limit_period = true; + params->x_vcpu_dirty_limit_period = s->parameters.x_vcpu_dirty_limit_period; + return params; } @@ -940,6 +948,7 @@ void migrate_params_init(MigrationParameters *params) params->has_announce_max = true; params->has_announce_rounds = true; params->has_announce_step = true; + params->has_x_vcpu_dirty_limit_period = true; } /* @@ -1100,6 +1109,15 @@ bool migrate_params_check(MigrationParameters *params, Error **errp) } #endif + if (params->has_x_vcpu_dirty_limit_period && + (params->x_vcpu_dirty_limit_period < 1 || + params->x_vcpu_dirty_limit_period > 1000)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "x-vcpu-dirty-limit-period", + "a value between 1 and 1000"); + return false; + } + return true; } @@ -1199,6 +1217,11 @@ static void migrate_params_test_apply(MigrateSetParameters *params, dest->has_block_bitmap_mapping = true; dest->block_bitmap_mapping = params->block_bitmap_mapping; } + + if (params->has_x_vcpu_dirty_limit_period) { + dest->x_vcpu_dirty_limit_period = + params->x_vcpu_dirty_limit_period; + } } static void migrate_params_apply(MigrateSetParameters *params, Error **errp) @@ -1317,6 +1340,11 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp) QAPI_CLONE(BitmapMigrationNodeAliasList, params->block_bitmap_mapping); } + + if (params->has_x_vcpu_dirty_limit_period) { + s->parameters.x_vcpu_dirty_limit_period = + params->x_vcpu_dirty_limit_period; + } } void qmp_migrate_set_parameters(MigrateSetParameters *params, Error **errp) -- 2.40.1

From: Hyman Huang(黄勇) <yong.huang(a)smartx.com&gt; Introduce migration dirty-limit capability, which can be turned on before live migration and limit dirty page rate durty live migration. Introduce migrate_dirty_limit function to help check if dirty-limit capability enabled during live migration. Meanwhile, refactor vcpu_dirty_rate_stat_collect so that period can be configured instead of hardcoded. dirty-limit capability is kind of like auto-converge but using dirty limit instead of traditional cpu-throttle to throttle guest down. To enable this feature, turn on the dirty-limit capability before live migration using migrate-set-capabilities, and set the parameters "x-vcpu-dirty-limit-period", "vcpu-dirty-limit" suitably to speed up convergence. Signed-off-by: Hyman Huang(黄勇) <yong.huang(a)smartx.com&gt; Acked-by: Peter Xu <peterx(a)redhat.com&gt; Reviewed-by: Juan Quintela <quintela(a)redhat.com&gt; Message-Id: <168618975839.6361.17407633874747688653-4(a)git.sr.ht&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- qapi/migration.json | 13 ++++++++++++- migration/options.h | 1 + migration/options.c | 23 ++++++++++++++++++++++- softmmu/dirtylimit.c | 18 ++++++++++++++---- 4 files changed, 49 insertions(+), 6 deletions(-) diff --git a/qapi/migration.json b/qapi/migration.json index 22104cef08..e094438d74 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -497,6 +497,16 @@ # are present. 'return-path' capability must be enabled to use # it. (since 8.1) # +# @dirty-limit: If enabled, migration will use the dirty-limit algo to +# throttle down guest instead of auto-converge algo. +# Throttle algo only works when vCPU's dirtyrate greater +# than 'vcpu-dirty-limit', read processes in guest os +# aren't penalized any more, so this algo can improve +# performance of vCPU during live migration. This is an +# optional performance feature and should not affect the +# correctness of the existing auto-converge algo. +# (since 8.1) +# # Features: # # @unstable: Members @x-colo and @x-ignore-shared are experimental. @@ -512,7 +522,8 @@ 'dirty-bitmaps', 'postcopy-blocktime', 'late-block-activate', { 'name': 'x-ignore-shared', 'features': [ 'unstable' ] }, 'validate-uuid', 'background-snapshot', - 'zero-copy-send', 'postcopy-preempt', 'switchover-ack'] } + 'zero-copy-send', 'postcopy-preempt', 'switchover-ack', + 'dirty-limit'] } ## # @MigrationCapabilityStatus: diff --git a/migration/options.h b/migration/options.h index 9aaf363322..045e2a41a2 100644 --- a/migration/options.h +++ b/migration/options.h @@ -29,6 +29,7 @@ bool migrate_block(void); bool migrate_colo(void); bool migrate_compress(void); bool migrate_dirty_bitmaps(void); +bool migrate_dirty_limit(void); bool migrate_events(void); bool migrate_ignore_shared(void); bool migrate_late_block_activate(void); diff --git a/migration/options.c b/migration/options.c index 7d2d98830e..7d83f190d6 100644 --- a/migration/options.c +++ b/migration/options.c @@ -27,6 +27,7 @@ #include "qemu-file.h" #include "ram.h" #include "options.h" +#include "sysemu/kvm.h" /* Maximum migrate downtime set to 2000 seconds */ #define MAX_MIGRATE_DOWNTIME_SECONDS 2000 @@ -196,7 +197,7 @@ Property migration_properties[] = { #endif DEFINE_PROP_MIG_CAP("x-switchover-ack", MIGRATION_CAPABILITY_SWITCHOVER_ACK), - + DEFINE_PROP_MIG_CAP("x-dirty-limit", MIGRATION_CAPABILITY_DIRTY_LIMIT), DEFINE_PROP_END_OF_LIST(), }; @@ -242,6 +243,13 @@ bool migrate_dirty_bitmaps(void) return s->capabilities[MIGRATION_CAPABILITY_DIRTY_BITMAPS]; } +bool migrate_dirty_limit(void) +{ + MigrationState *s = migrate_get_current(); + + return s->capabilities[MIGRATION_CAPABILITY_DIRTY_LIMIT]; +} + bool migrate_events(void) { MigrationState *s = migrate_get_current(); @@ -572,6 +580,19 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp) return false; } } + if (new_caps[MIGRATION_CAPABILITY_DIRTY_LIMIT]) { + if (new_caps[MIGRATION_CAPABILITY_AUTO_CONVERGE]) { + error_setg(errp, "dirty-limit conflicts with auto-converge" + " either of then available currently"); + return false; + } + + if (!kvm_enabled() || !kvm_dirty_ring_enabled()) { + error_setg(errp, "dirty-limit requires KVM with accelerator" + " property 'dirty-ring-size' set"); + return false; + } + } return true; } diff --git a/softmmu/dirtylimit.c b/softmmu/dirtylimit.c index e80201097a..942d876523 100644 --- a/softmmu/dirtylimit.c +++ b/softmmu/dirtylimit.c @@ -24,6 +24,9 @@ #include "hw/boards.h" #include "sysemu/kvm.h" #include "trace.h" +#include "migration/misc.h" +#include "migration/migration.h" +#include "migration/options.h" /* * Dirtylimit stop working if dirty page rate error @@ -75,14 +78,21 @@ static bool dirtylimit_quit; static void vcpu_dirty_rate_stat_collect(void) { + MigrationState *s = migrate_get_current(); VcpuStat stat; int i = 0; + int64_t period = DIRTYLIMIT_CALC_TIME_MS; + + if (migrate_dirty_limit() && + migration_is_active(s)) { + period = s->parameters.x_vcpu_dirty_limit_period; + } /* calculate vcpu dirtyrate */ - vcpu_calculate_dirtyrate(DIRTYLIMIT_CALC_TIME_MS, - &stat, - GLOBAL_DIRTY_LIMIT, - false); + vcpu_calculate_dirtyrate(period, + &stat, + GLOBAL_DIRTY_LIMIT, + false); for (i = 0; i < stat.nvcpu; i++) { vcpu_dirty_rate_stat->stat.rates[i].id = i; -- 2.40.1

From: Hyman Huang(黄勇) <yong.huang(a)smartx.com&gt; This commit is prepared for the implementation of dirty-limit convergence algo. The detection logic of throttling condition can apply to both auto-converge and dirty-limit algo, putting it's position before the checking logic for auto-converge feature. Signed-off-by: Hyman Huang(黄勇) <yong.huang(a)smartx.com&gt; Reviewed-by: Juan Quintela <quintela(a)redhat.com&gt; Message-ID: <168733225273.5845.15871826788879741674-6(a)git.sr.ht&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- migration/ram.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/migration/ram.c b/migration/ram.c index f31de47a47..1d9300f4c5 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -999,17 +999,18 @@ static void migration_trigger_throttle(RAMState *rs) return; } - 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)) { + /* + * 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; + if (migrate_auto_converge()) { trace_migration_throttle(); - rs->dirty_rate_high_cnt = 0; mig_throttle_guest_down(bytes_dirty_period, bytes_dirty_threshold); } -- 2.40.1

From: Hyman Huang(黄勇) <yong.huang(a)smartx.com&gt; Extend query-migrate to provide throttle time and estimated ring full time with dirty-limit capability enabled, through which we can observe if dirty limit take effect during live migration. Signed-off-by: Hyman Huang(黄勇) <yong.huang(a)smartx.com&gt; Reviewed-by: Markus Armbruster <armbru(a)redhat.com&gt; Reviewed-by: Juan Quintela <quintela(a)redhat.com&gt; Message-ID: <168733225273.5845.15871826788879741674-8(a)git.sr.ht&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- qapi/migration.json | 16 +++++++++++++- include/sysemu/dirtylimit.h | 2 ++ migration/migration-hmp-cmds.c | 10 +++++++++ migration/migration.c | 10 +++++++++ softmmu/dirtylimit.c | 39 ++++++++++++++++++++++++++++++++++ 5 files changed, 76 insertions(+), 1 deletion(-) diff --git a/qapi/migration.json b/qapi/migration.json index e094438d74..440660bced 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -250,6 +250,18 @@ # blocked. Present and non-empty when migration is blocked. # (since 6.0) # +# @dirty-limit-throttle-time-per-round: Maximum throttle time (in microseconds) of virtual +# CPUs each dirty ring full round, which shows how +# MigrationCapability dirty-limit affects the guest +# during live migration. (since 8.1) +# +# @dirty-limit-ring-full-time: Estimated average dirty ring full time (in microseconds) +# each dirty ring full round, note that the value equals +# dirty ring memory size divided by average dirty page rate +# of virtual CPU, which can be used to observe the average +# memory load of virtual CPU indirectly. Note that zero +# means guest doesn't dirty memory (since 8.1) +# # Since: 0.14 ## { 'struct': 'MigrationInfo', @@ -267,7 +279,9 @@ '*postcopy-blocktime': 'uint32', '*postcopy-vcpu-blocktime': ['uint32'], '*compression': 'CompressionStats', - '*socket-address': ['SocketAddress'] } } + '*socket-address': ['SocketAddress'], + '*dirty-limit-throttle-time-per-round': 'uint64', + '*dirty-limit-ring-full-time': 'uint64'} } ## # @query-migrate: diff --git a/include/sysemu/dirtylimit.h b/include/sysemu/dirtylimit.h index 8d2c1f3a6b..d11ebbbbdb 100644 --- a/include/sysemu/dirtylimit.h +++ b/include/sysemu/dirtylimit.h @@ -34,4 +34,6 @@ void dirtylimit_set_vcpu(int cpu_index, void dirtylimit_set_all(uint64_t quota, bool enable); void dirtylimit_vcpu_execute(CPUState *cpu); +uint64_t dirtylimit_throttle_time_per_round(void); +uint64_t dirtylimit_ring_full_time(void); #endif diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c index 35e8020bbf..c115ef2d23 100644 --- a/migration/migration-hmp-cmds.c +++ b/migration/migration-hmp-cmds.c @@ -190,6 +190,16 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict) info->cpu_throttle_percentage); } + if (info->has_dirty_limit_throttle_time_per_round) { + monitor_printf(mon, "dirty-limit throttle time: %" PRIu64 " us\n", + info->dirty_limit_throttle_time_per_round); + } + + if (info->has_dirty_limit_ring_full_time) { + monitor_printf(mon, "dirty-limit ring full time: %" PRIu64 " us\n", + info->dirty_limit_ring_full_time); + } + if (info->has_postcopy_blocktime) { monitor_printf(mon, "postcopy blocktime: %u\n", info->postcopy_blocktime); diff --git a/migration/migration.c b/migration/migration.c index 49332251e8..1ea7512291 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -64,6 +64,7 @@ #include "yank_functions.h" #include "sysemu/qtest.h" #include "options.h" +#include "sysemu/dirtylimit.h" static NotifierList migration_state_notifiers = NOTIFIER_LIST_INITIALIZER(migration_state_notifiers); @@ -974,6 +975,15 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s) info->ram->dirty_pages_rate = stat64_get(&mig_stats.dirty_pages_rate); } + + if (migrate_dirty_limit() && dirtylimit_in_service()) { + info->has_dirty_limit_throttle_time_per_round = true; + info->dirty_limit_throttle_time_per_round = + dirtylimit_throttle_time_per_round(); + + info->has_dirty_limit_ring_full_time = true; + info->dirty_limit_ring_full_time = dirtylimit_ring_full_time(); + } } static void populate_disk_info(MigrationInfo *info) diff --git a/softmmu/dirtylimit.c b/softmmu/dirtylimit.c index a6d854d161..3c275ee55b 100644 --- a/softmmu/dirtylimit.c +++ b/softmmu/dirtylimit.c @@ -565,6 +565,45 @@ out: hmp_handle_error(mon, err); } +/* Return the max throttle time of each virtual CPU */ +uint64_t dirtylimit_throttle_time_per_round(void) +{ + CPUState *cpu; + int64_t max = 0; + + CPU_FOREACH(cpu) { + if (cpu->throttle_us_per_full > max) { + max = cpu->throttle_us_per_full; + } + } + + return max; +} + +/* + * Estimate average dirty ring full time of each virtaul CPU. + * Return 0 if guest doesn't dirty memory. + */ +uint64_t dirtylimit_ring_full_time(void) +{ + CPUState *cpu; + uint64_t curr_rate = 0; + int nvcpus = 0; + + CPU_FOREACH(cpu) { + if (cpu->running) { + nvcpus++; + curr_rate += vcpu_dirty_rate_get(cpu->cpu_index); + } + } + + if (!curr_rate || !nvcpus) { + return 0; + } + + return dirtylimit_dirty_ring_full_time(curr_rate / nvcpus); +} + static struct DirtyLimitInfo *dirtylimit_query_vcpu(int cpu_index) { DirtyLimitInfo *info = NULL; -- 2.40.1

Reviewed-by: Peter Xu <peterx(a)redhat.com&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; Message-ID: <20230608224943.3877-5-quintela(a)redhat.com&gt; --- tests/qtest/migration-test.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c index 2296ed4bf5..f51a25e299 100644 --- a/tests/qtest/migration-test.c +++ b/tests/qtest/migration-test.c @@ -739,7 +739,7 @@ static int test_migrate_start(QTestState **from, QTestState **to, start_address = S390_TEST_MEM_START; end_address = S390_TEST_MEM_END; } else if (strcmp(arch, "ppc64") == 0) { - machine_opts = "vsmt=8"; + machine_opts = "-machine vsmt=8"; memory_size = "256M"; start_address = PPC_TEST_MEM_START; end_address = PPC_TEST_MEM_END; @@ -751,7 +751,7 @@ static int test_migrate_start(QTestState **from, QTestState **to, arch_target = g_strdup("-nodefaults"); } else if (strcmp(arch, "aarch64") == 0) { init_bootfile(bootpath, aarch64_kernel, sizeof(aarch64_kernel)); - machine_opts = "virt,gic-version=max"; + machine_opts = "-machine virt,gic-version=max"; memory_size = "150M"; arch_source = g_strdup_printf("-cpu max " "-kernel %s", @@ -791,14 +791,13 @@ static int test_migrate_start(QTestState **from, QTestState **to, shmem_opts = g_strdup(""); } - cmd_source = g_strdup_printf("-accel kvm%s -accel tcg%s%s " + cmd_source = g_strdup_printf("-accel kvm%s -accel tcg %s " "-name source,debug-threads=on " "-m %s " "-serial file:%s/src_serial " "%s %s %s %s", args->use_dirty_ring ? ",dirty-ring-size=4096" : "", - machine_opts ? " -machine " : "", machine_opts ? machine_opts : "", memory_size, tmpfs, arch_source, shmem_opts, @@ -811,7 +810,7 @@ static int test_migrate_start(QTestState **from, QTestState **to, &got_src_stop); } - cmd_target = g_strdup_printf("-accel kvm%s -accel tcg%s%s " + cmd_target = g_strdup_printf("-accel kvm%s -accel tcg %s " "-name target,debug-threads=on " "-m %s " "-serial file:%s/dest_serial " @@ -819,7 +818,6 @@ static int test_migrate_start(QTestState **from, QTestState **to, "%s %s %s %s", args->use_dirty_ring ? ",dirty-ring-size=4096" : "", - machine_opts ? " -machine " : "", machine_opts ? machine_opts : "", memory_size, tmpfs, uri, arch_target, shmem_opts, -- 2.40.1

And it needs to be in both source and target, so put it on arch_opts. Reviewed-by: Peter Xu <peterx(a)redhat.com&gt; Message-ID: <20230608224943.3877-7-quintela(a)redhat.com&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- tests/qtest/migration-test.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c index c723f083da..fd145e38d9 100644 --- a/tests/qtest/migration-test.c +++ b/tests/qtest/migration-test.c @@ -711,7 +711,6 @@ static int test_migrate_start(QTestState **from, QTestState **to, g_autofree char *shmem_opts = NULL; g_autofree char *shmem_path = NULL; const char *arch = qtest_get_arch(); - const char *machine_opts = NULL; const char *memory_size; if (args->use_shmem) { @@ -739,7 +738,6 @@ static int test_migrate_start(QTestState **from, QTestState **to, start_address = S390_TEST_MEM_START; end_address = S390_TEST_MEM_END; } else if (strcmp(arch, "ppc64") == 0) { - machine_opts = "-machine vsmt=8"; memory_size = "256M"; start_address = PPC_TEST_MEM_START; end_address = PPC_TEST_MEM_END; @@ -747,12 +745,12 @@ static int test_migrate_start(QTestState **from, QTestState **to, "'nvramrc=hex .\" _\" begin %x %x " "do i c@ 1 + i c! 1000 +loop .\" B\" 0 " "until'", end_address, start_address); - arch_opts = g_strdup("-nodefaults"); + arch_opts = g_strdup("-nodefaults -machine vsmt=8"); } else if (strcmp(arch, "aarch64") == 0) { init_bootfile(bootpath, aarch64_kernel, sizeof(aarch64_kernel)); - machine_opts = "-machine virt,gic-version=max"; memory_size = "150M"; - arch_opts = g_strdup_printf("-cpu max -kernel %s", bootpath); + arch_opts = g_strdup_printf("-machine virt,gic-version=max -cpu max " + "-kernel %s", bootpath); start_address = ARM_TEST_MEM_START; end_address = ARM_TEST_MEM_END; @@ -787,14 +785,13 @@ static int test_migrate_start(QTestState **from, QTestState **to, shmem_opts = g_strdup(""); } - cmd_source = g_strdup_printf("-accel kvm%s -accel tcg %s " + cmd_source = g_strdup_printf("-accel kvm%s -accel tcg " "-name source,debug-threads=on " "-m %s " "-serial file:%s/src_serial " "%s %s %s %s %s", args->use_dirty_ring ? ",dirty-ring-size=4096" : "", - machine_opts ? machine_opts : "", memory_size, tmpfs, arch_opts ? arch_opts : "", arch_source ? arch_source : "", @@ -808,7 +805,7 @@ static int test_migrate_start(QTestState **from, QTestState **to, &got_src_stop); } - cmd_target = g_strdup_printf("-accel kvm%s -accel tcg %s " + cmd_target = g_strdup_printf("-accel kvm%s -accel tcg " "-name target,debug-threads=on " "-m %s " "-serial file:%s/dest_serial " @@ -816,7 +813,6 @@ static int test_migrate_start(QTestState **from, QTestState **to, "%s %s %s %s %s", args->use_dirty_ring ? ",dirty-ring-size=4096" : "", - machine_opts ? machine_opts : "", memory_size, tmpfs, uri, arch_opts ? arch_opts : "", arch_target ? arch_target : "", -- 2.40.1

From: Peter Xu <peterx(a)redhat.com&gt; We have postcopy recovery but not reflected in the document, do an update for that. Add a very small section on postcopy preempt. Touch up the pagemap section, dropping the unsent map because it's already been dropped in the source code in commit 1e7cf8c323 ("migration/postcopy: unsentmap is not necessary for postcopy"). Touch up the postcopy section to remove "network connection" failures as downside, because now it's not fatal and can be recovered. Suggested by Laszlo. Acked-by: Laszlo Ersek <lersek(a)redhat.com&gt; Signed-off-by: Peter Xu <peterx(a)redhat.com&gt; Reviewed-by: Juan Quintela <quintela(a)redhat.com&gt; Message-ID: <20230706115611.371048-1-peterx(a)redhat.com&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- docs/devel/migration.rst | 94 ++++++++++++++++++++++++++++------------ 1 file changed, 67 insertions(+), 27 deletions(-) diff --git a/docs/devel/migration.rst b/docs/devel/migration.rst index 6f65c23b47..c3e1400c0c 100644 --- a/docs/devel/migration.rst +++ b/docs/devel/migration.rst @@ -594,8 +594,7 @@ Postcopy 'Postcopy' migration is a way to deal with migrations that refuse to converge (or take too long to converge) its plus side is that there is an upper bound on the amount of migration traffic and time it takes, the down side is that during -the postcopy phase, a failure of *either* side or the network connection causes -the guest to be lost. +the postcopy phase, a failure of *either* side causes the guest to be lost. In postcopy the destination CPUs are started before all the memory has been transferred, and accesses to pages that are yet to be transferred cause @@ -721,6 +720,42 @@ processing. is no longer used by migration, while the listen thread carries on servicing page data until the end of migration. +Postcopy Recovery +----------------- + +Comparing to precopy, postcopy is special on error handlings. When any +error happens (in this case, mostly network errors), QEMU cannot easily +fail a migration because VM data resides in both source and destination +QEMU instances. On the other hand, when issue happens QEMU on both sides +will go into a paused state. It'll need a recovery phase to continue a +paused postcopy migration. + +The recovery phase normally contains a few steps: + + - When network issue occurs, both QEMU will go into PAUSED state + + - When the network is recovered (or a new network is provided), the admin + can setup the new channel for migration using QMP command + 'migrate-recover' on destination node, preparing for a resume. + + - On source host, the admin can continue the interrupted postcopy + migration using QMP command 'migrate' with resume=true flag set. + + - After the connection is re-established, QEMU will continue the postcopy + migration on both sides. + +During a paused postcopy migration, the VM can logically still continue +running, and it will not be impacted from any page access to pages that +were already migrated to destination VM before the interruption happens. +However, if any of the missing pages got accessed on destination VM, the VM +thread will be halted waiting for the page to be migrated, it means it can +be halted until the recovery is complete. + +The impact of accessing missing pages can be relevant to different +configurations of the guest. For example, when with async page fault +enabled, logically the guest can proactively schedule out the threads +accessing missing pages. + Postcopy states --------------- @@ -765,36 +800,31 @@ ADVISE->DISCARD->LISTEN->RUNNING->END (although it can't do the cleanup it would do as it finishes a normal migration). + - Paused + + Postcopy can run into a paused state (normally on both sides when + happens), where all threads will be temporarily halted mostly due to + network errors. When reaching paused state, migration will make sure + the qemu binary on both sides maintain the data without corrupting + the VM. To continue the migration, the admin needs to fix the + migration channel using the QMP command 'migrate-recover' on the + destination node, then resume the migration using QMP command 'migrate' + again on source node, with resume=true flag set. + - End The listen thread can now quit, and perform the cleanup of migration state, the migration is now complete. -Source side page maps ---------------------- - -The source side keeps two bitmaps during postcopy; 'the migration bitmap' -and 'unsent map'. The 'migration bitmap' is basically the same as in -the precopy case, and holds a bit to indicate that page is 'dirty' - -i.e. needs sending. During the precopy phase this is updated as the CPU -dirties pages, however during postcopy the CPUs are stopped and nothing -should dirty anything any more. - -The 'unsent map' is used for the transition to postcopy. It is a bitmap that -has a bit cleared whenever a page is sent to the destination, however during -the transition to postcopy mode it is combined with the migration bitmap -to form a set of pages that: - - a) Have been sent but then redirtied (which must be discarded) - b) Have not yet been sent - which also must be discarded to cause any - transparent huge pages built during precopy to be broken. - -Note that the contents of the unsentmap are sacrificed during the calculation -of the discard set and thus aren't valid once in postcopy. The dirtymap -is still valid and is used to ensure that no page is sent more than once. Any -request for a page that has already been sent is ignored. Duplicate requests -such as this can happen as a page is sent at about the same time the -destination accesses it. +Source side page map +-------------------- + +The 'migration bitmap' in postcopy is basically the same as in the precopy, +where each of the bit to indicate that page is 'dirty' - i.e. needs +sending. During the precopy phase this is updated as the CPU dirties +pages, however during postcopy the CPUs are stopped and nothing should +dirty anything any more. Instead, dirty bits are cleared when the relevant +pages are sent during postcopy. Postcopy with hugepages ----------------------- @@ -853,6 +883,16 @@ Retro-fitting postcopy to existing clients is possible: guest memory access is made while holding a lock then all other threads waiting for that lock will also be blocked. +Postcopy Preemption Mode +------------------------ + +Postcopy preempt is a new capability introduced in 8.0 QEMU release, it +allows urgent pages (those got page fault requested from destination QEMU +explicitly) to be sent in a separate preempt channel, rather than queued in +the background migration channel. Anyone who cares about latencies of page +faults during a postcopy migration should enable this feature. By default, +it's not enabled. + Firmware ======== -- 2.40.1

From: Wei Wang <wei.w.wang(a)intel.com&gt; qemu_start_incoming_migration needs to check the number of multifd channels or postcopy ram channels to configure the backlog parameter (i.e. the maximum length to which the queue of pending connections for sockfd may grow) of listen(). So enforce the usage of postcopy-preempt and multifd as below: - need to use "-incoming defer" on the destination; and - set_capability and set_parameter need to be done before migrate_incoming Otherwise, disable the use of the features and report error messages to remind users to adjust the commands. Signed-off-by: Wei Wang <wei.w.wang(a)intel.com&gt; Reviewed-by: Peter Xu <peterx(a)redhat.com&gt; Reviewed-by: Juan Quintela <quintela(a)redhat.com&gt; Message-ID: <20230606101910.20456-2-wei.w.wang(a)intel.com&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; Acked-by: Juan Quintela <quintela(a)redhat.com&gt; --- migration/options.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/migration/options.c b/migration/options.c index 7d83f190d6..1d1e1321b0 100644 --- a/migration/options.c +++ b/migration/options.c @@ -441,6 +441,11 @@ INITIALIZE_MIGRATE_CAPS_SET(check_caps_background_snapshot, MIGRATION_CAPABILITY_VALIDATE_UUID, MIGRATION_CAPABILITY_ZERO_COPY_SEND); +static bool migrate_incoming_started(void) +{ + return !!migration_incoming_get_current()->transport_data; +} + /** * @migration_caps_check - check capability compatibility * @@ -564,6 +569,12 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp) error_setg(errp, "Postcopy preempt not compatible with compress"); return false; } + + if (migrate_incoming_started()) { + error_setg(errp, + "Postcopy preempt must be set before incoming starts"); + return false; + } } if (new_caps[MIGRATION_CAPABILITY_MULTIFD]) { @@ -571,6 +582,10 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp) error_setg(errp, "Multifd is not compatible with compress"); return false; } + if (migrate_incoming_started()) { + error_setg(errp, "Multifd must be set before incoming starts"); + return false; + } } if (new_caps[MIGRATION_CAPABILITY_SWITCHOVER_ACK]) { -- 2.40.1

Fast don't say much. Noflush indicates more clearly that it is like qemu_file_transferred but without the flush. Reviewed-by: Philippe Mathieu-Daudé <philmd(a)linaro.org&gt; Message-ID: <20230530183941.7223-2-quintela(a)redhat.com&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- migration/qemu-file.h | 11 +++++------ migration/qemu-file.c | 2 +- migration/savevm.c | 4 ++-- migration/vmstate.c | 4 ++-- 4 files changed, 10 insertions(+), 11 deletions(-) diff --git a/migration/qemu-file.h b/migration/qemu-file.h index e649718492..aa6eee66da 100644 --- a/migration/qemu-file.h +++ b/migration/qemu-file.h @@ -86,16 +86,15 @@ int qemu_fclose(QEMUFile *f); uint64_t qemu_file_transferred(QEMUFile *f); /* - * qemu_file_transferred_fast: + * qemu_file_transferred_noflush: * - * As qemu_file_transferred except for writable - * files, where no flush is performed and the reported - * amount will include the size of any queued buffers, - * on top of the amount actually transferred. + * As qemu_file_transferred except for writable files, where no flush + * is performed and the reported amount will include the size of any + * queued buffers, on top of the amount actually transferred. * * Returns: the total bytes transferred and queued */ -uint64_t qemu_file_transferred_fast(QEMUFile *f); +uint64_t qemu_file_transferred_noflush(QEMUFile *f); /* * put_buffer without copying the buffer. diff --git a/migration/qemu-file.c b/migration/qemu-file.c index acc282654a..fdf115b5da 100644 --- a/migration/qemu-file.c +++ b/migration/qemu-file.c @@ -694,7 +694,7 @@ int coroutine_mixed_fn qemu_get_byte(QEMUFile *f) return result; } -uint64_t qemu_file_transferred_fast(QEMUFile *f) +uint64_t qemu_file_transferred_noflush(QEMUFile *f) { uint64_t ret = f->total_transferred; int i; diff --git a/migration/savevm.c b/migration/savevm.c index 51e40e3a0b..0b2583a205 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -927,9 +927,9 @@ static int vmstate_load(QEMUFile *f, SaveStateEntry *se) static void vmstate_save_old_style(QEMUFile *f, SaveStateEntry *se, JSONWriter *vmdesc) { - uint64_t old_offset = qemu_file_transferred_fast(f); + uint64_t old_offset = qemu_file_transferred_noflush(f); se->ops->save_state(f, se->opaque); - uint64_t size = qemu_file_transferred_fast(f) - old_offset; + uint64_t size = qemu_file_transferred_noflush(f) - old_offset; if (vmdesc) { json_writer_int64(vmdesc, "size", size); diff --git a/migration/vmstate.c b/migration/vmstate.c index af01d54b6f..31842c3afb 100644 --- a/migration/vmstate.c +++ b/migration/vmstate.c @@ -361,7 +361,7 @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, void *curr_elem = first_elem + size * i; vmsd_desc_field_start(vmsd, vmdesc_loop, field, i, n_elems); - old_offset = qemu_file_transferred_fast(f); + old_offset = qemu_file_transferred_noflush(f); if (field->flags & VMS_ARRAY_OF_POINTER) { assert(curr_elem); curr_elem = *(void **)curr_elem; @@ -391,7 +391,7 @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, return ret; } - written_bytes = qemu_file_transferred_fast(f) - old_offset; + written_bytes = qemu_file_transferred_noflush(f) - old_offset; vmsd_desc_field_end(vmsd, vmdesc_loop, field, written_bytes, i); /* Compressed arrays only care about the first element */ -- 2.40.1

It is not used outside of qemu_file, and it shouldn't. Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; Message-ID: <20230530183941.7223-19-quintela(a)redhat.com&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- migration/qemu-file.h | 1 - migration/qemu-file.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/migration/qemu-file.h b/migration/qemu-file.h index aa6eee66da..a081ef6c3f 100644 --- a/migration/qemu-file.h +++ b/migration/qemu-file.h @@ -103,7 +103,6 @@ uint64_t qemu_file_transferred_noflush(QEMUFile *f); void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, size_t size, bool may_free); bool qemu_file_mode_is_not_valid(const char *mode); -bool qemu_file_is_writable(QEMUFile *f); #include "migration/qemu-file-types.h" diff --git a/migration/qemu-file.c b/migration/qemu-file.c index fdf115b5da..9a89e17924 100644 --- a/migration/qemu-file.c +++ b/migration/qemu-file.c @@ -228,7 +228,7 @@ void qemu_file_set_error(QEMUFile *f, int ret) qemu_file_set_error_obj(f, ret, NULL); } -bool qemu_file_is_writable(QEMUFile *f) +static bool qemu_file_is_writable(QEMUFile *f) { return f->is_writable; } -- 2.40.1

It was not used outside of qemu_file.c anyways. Reviewed-by: Peter Xu <peterx(a)redhat.com&gt; Message-ID: <20230530183941.7223-21-quintela(a)redhat.com&gt; Signed-off-by: Juan Quintela <quintela(a)redhat.com&gt; --- migration/qemu-file.h | 1 - migration/qemu-file.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/migration/qemu-file.h b/migration/qemu-file.h index a081ef6c3f..8b8b7d27fe 100644 --- a/migration/qemu-file.h +++ b/migration/qemu-file.h @@ -128,7 +128,6 @@ void qemu_file_skip(QEMUFile *f, int size); * accounting information tracks the total migration traffic. */ void qemu_file_credit_transfer(QEMUFile *f, size_t size); -int qemu_file_get_error_obj(QEMUFile *f, Error **errp); int qemu_file_get_error_obj_any(QEMUFile *f1, QEMUFile *f2, Error **errp); void qemu_file_set_error_obj(QEMUFile *f, int ret, Error *err); void qemu_file_set_error(QEMUFile *f, int ret); diff --git a/migration/qemu-file.c b/migration/qemu-file.c index 4c577bdff8..d30bf3c377 100644 --- a/migration/qemu-file.c +++ b/migration/qemu-file.c @@ -158,7 +158,7 @@ void qemu_file_set_hooks(QEMUFile *f, const QEMUFileHooks *hooks) * is not 0. * */ -int qemu_file_get_error_obj(QEMUFile *f, Error **errp) +static int qemu_file_get_error_obj(QEMUFile *f, Error **errp) { if (errp) { *errp = f->last_error_obj ? error_copy(f->last_error_obj) : NULL; -- 2.40.1