From 131b2153fc7970fab780dc875f59823e3b23612a Mon Sep 17 00:00:00 2001 From: Zhang Chen Date: Mon, 3 Sep 2018 12:38:45 +0800 Subject: COLO: integrate colo compare with colo frame For COLO FT, both the PVM and SVM run at the same time, only sync the state while it needs. So here, let SVM runs while not doing checkpoint, change DEFAULT_MIGRATE_X_CHECKPOINT_DELAY to 200*100. Besides, we forgot to release colo_checkpoint_semd and colo_delay_timer, fix them here. Signed-off-by: zhanghailiang Signed-off-by: Zhang Chen Signed-off-by: Zhang Chen Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Jason Wang --- migration/colo.c | 42 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) (limited to 'migration/colo.c') diff --git a/migration/colo.c b/migration/colo.c index 88936f5962..f4bdfde170 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -25,8 +25,11 @@ #include "qemu/error-report.h" #include "migration/failover.h" #include "replication.h" +#include "net/colo-compare.h" +#include "net/colo.h" static bool vmstate_loading; +static Notifier packets_compare_notifier; #define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024) @@ -343,6 +346,11 @@ static int colo_do_checkpoint_transaction(MigrationState *s, goto out; } + colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err); + if (local_err) { + goto out; + } + /* Disable block migration */ migrate_set_block_enabled(false, &local_err); qemu_savevm_state_header(fb); @@ -400,6 +408,11 @@ out: return ret; } +static void colo_compare_notify_checkpoint(Notifier *notifier, void *data) +{ + colo_checkpoint_notify(data); +} + static void colo_process_checkpoint(MigrationState *s) { QIOChannelBuffer *bioc; @@ -416,6 +429,9 @@ static void colo_process_checkpoint(MigrationState *s) goto out; } + packets_compare_notifier.notify = colo_compare_notify_checkpoint; + colo_compare_register_notifier(&packets_compare_notifier); + /* * Wait for Secondary finish loading VM states and enter COLO * restore. @@ -461,11 +477,21 @@ out: qemu_fclose(fb); } - timer_del(s->colo_delay_timer); - /* Hope this not to be too long to wait here */ qemu_sem_wait(&s->colo_exit_sem); qemu_sem_destroy(&s->colo_exit_sem); + + /* + * It is safe to unregister notifier after failover finished. + * Besides, colo_delay_timer and colo_checkpoint_sem can't be + * released befor unregister notifier, or there will be use-after-free + * error. + */ + colo_compare_unregister_notifier(&packets_compare_notifier); + timer_del(s->colo_delay_timer); + timer_free(s->colo_delay_timer); + qemu_sem_destroy(&s->colo_checkpoint_sem); + /* * Must be called after failover BH is completed, * Or the failover BH may shutdown the wrong fd that @@ -559,6 +585,11 @@ void *colo_process_incoming_thread(void *opaque) fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc)); object_unref(OBJECT(bioc)); + qemu_mutex_lock_iothread(); + vm_start(); + trace_colo_vm_state_change("stop", "run"); + qemu_mutex_unlock_iothread(); + colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, &local_err); if (local_err) { @@ -578,6 +609,11 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + qemu_mutex_lock_iothread(); + vm_stop_force_state(RUN_STATE_COLO); + trace_colo_vm_state_change("run", "stop"); + qemu_mutex_unlock_iothread(); + /* FIXME: This is unnecessary for periodic checkpoint mode */ colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY, &local_err); @@ -631,6 +667,8 @@ void *colo_process_incoming_thread(void *opaque) } vmstate_loading = false; + vm_start(); + trace_colo_vm_state_change("stop", "run"); qemu_mutex_unlock_iothread(); if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) { -- cgit 1.4.1 From 8e48ac95865ac97d10a81cb7a5bbae310878f519 Mon Sep 17 00:00:00 2001 From: Zhang Chen Date: Mon, 3 Sep 2018 12:38:46 +0800 Subject: COLO: Add block replication into colo process Make sure master start block replication after slave's block replication started. Besides, we need to activate VM's blocks before goes into COLO state. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Zhang Chen Signed-off-by: Zhang Chen Signed-off-by: Jason Wang --- migration/colo.c | 43 +++++++++++++++++++++++++++++++++++++++++++ migration/migration.c | 10 ++++++++++ 2 files changed, 53 insertions(+) (limited to 'migration/colo.c') diff --git a/migration/colo.c b/migration/colo.c index f4bdfde170..af04010061 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -27,6 +27,7 @@ #include "replication.h" #include "net/colo-compare.h" #include "net/colo.h" +#include "block/block.h" static bool vmstate_loading; static Notifier packets_compare_notifier; @@ -56,6 +57,7 @@ static void secondary_vm_do_failover(void) { int old_state; MigrationIncomingState *mis = migration_incoming_get_current(); + Error *local_err = NULL; /* Can not do failover during the process of VM's loading VMstate, Or * it will break the secondary VM. @@ -73,6 +75,11 @@ static void secondary_vm_do_failover(void) migrate_set_state(&mis->state, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED); + replication_stop_all(true, &local_err); + if (local_err) { + error_report_err(local_err); + } + if (!autostart) { error_report("\"-S\" qemu option will be ignored in secondary side"); /* recover runstate to normal migration finish state */ @@ -110,6 +117,7 @@ static void primary_vm_do_failover(void) { MigrationState *s = migrate_get_current(); int old_state; + Error *local_err = NULL; migrate_set_state(&s->state, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED); @@ -133,6 +141,13 @@ static void primary_vm_do_failover(void) FailoverStatus_str(old_state)); return; } + + replication_stop_all(true, &local_err); + if (local_err) { + error_report_err(local_err); + local_err = NULL; + } + /* Notify COLO thread that failover work is finished */ qemu_sem_post(&s->colo_exit_sem); } @@ -356,6 +371,11 @@ static int colo_do_checkpoint_transaction(MigrationState *s, qemu_savevm_state_header(fb); qemu_savevm_state_setup(fb); qemu_mutex_lock_iothread(); + replication_do_checkpoint_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } qemu_savevm_state_complete_precopy(fb, false, false); qemu_mutex_unlock_iothread(); @@ -446,6 +466,12 @@ static void colo_process_checkpoint(MigrationState *s) object_unref(OBJECT(bioc)); qemu_mutex_lock_iothread(); + replication_start_all(REPLICATION_MODE_PRIMARY, &local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vm_start(); qemu_mutex_unlock_iothread(); trace_colo_vm_state_change("stop", "run"); @@ -586,6 +612,11 @@ void *colo_process_incoming_thread(void *opaque) object_unref(OBJECT(bioc)); qemu_mutex_lock_iothread(); + replication_start_all(REPLICATION_MODE_SECONDARY, &local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } vm_start(); trace_colo_vm_state_change("stop", "run"); qemu_mutex_unlock_iothread(); @@ -666,6 +697,18 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + replication_get_error_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + /* discard colo disk buffer */ + replication_do_checkpoint_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vmstate_loading = false; vm_start(); trace_colo_vm_state_change("stop", "run"); diff --git a/migration/migration.c b/migration/migration.c index 32ce058b38..bf5fcd1009 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -386,6 +386,7 @@ static void process_incoming_migration_co(void *opaque) MigrationIncomingState *mis = migration_incoming_get_current(); PostcopyState ps; int ret; + Error *local_err = NULL; assert(mis->from_src_file); mis->migration_incoming_co = qemu_coroutine_self(); @@ -418,6 +419,15 @@ static void process_incoming_migration_co(void *opaque) /* we get COLO info, and know if we are in COLO mode */ if (!ret && migration_incoming_enable_colo()) { + /* Make sure all file formats flush their mutable metadata */ + bdrv_invalidate_cache_all(&local_err); + if (local_err) { + migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, + MIGRATION_STATUS_FAILED); + error_report_err(local_err); + exit(EXIT_FAILURE); + } + qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming", colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE); mis->have_colo_incoming_thread = true; -- cgit 1.4.1 From aad555c2294b5de22524b7dbacc728d51cc63bcc Mon Sep 17 00:00:00 2001 From: Zhang Chen Date: Mon, 3 Sep 2018 12:38:47 +0800 Subject: COLO: Remove colo_state migration struct We need to know if migration is going into COLO state for incoming side before start normal migration. Instead by using the VMStateDescription to send colo_state from source side to destination side, we use MIG_CMD_ENABLE_COLO to indicate whether COLO is enabled or not. Signed-off-by: zhanghailiang Signed-off-by: Zhang Chen Signed-off-by: Zhang Chen Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Jason Wang --- include/migration/colo.h | 5 ++-- migration/Makefile.objs | 2 +- migration/colo-comm.c | 76 ------------------------------------------------ migration/colo.c | 13 ++++++++- migration/migration.c | 23 ++++++++++++++- migration/savevm.c | 17 +++++++++++ migration/savevm.h | 1 + migration/trace-events | 1 + vl.c | 2 -- 9 files changed, 57 insertions(+), 83 deletions(-) delete mode 100644 migration/colo-comm.c (limited to 'migration/colo.c') diff --git a/include/migration/colo.h b/include/migration/colo.h index fefb2fcf4c..99ce17aca7 100644 --- a/include/migration/colo.h +++ b/include/migration/colo.h @@ -28,8 +28,9 @@ void migrate_start_colo_process(MigrationState *s); bool migration_in_colo_state(void); /* loadvm */ -bool migration_incoming_enable_colo(void); -void migration_incoming_exit_colo(void); +void migration_incoming_enable_colo(void); +void migration_incoming_disable_colo(void); +bool migration_incoming_colo_enabled(void); void *colo_process_incoming_thread(void *opaque); bool migration_incoming_in_colo_state(void); diff --git a/migration/Makefile.objs b/migration/Makefile.objs index c83ec47ba8..a4f3bafd86 100644 --- a/migration/Makefile.objs +++ b/migration/Makefile.objs @@ -1,6 +1,6 @@ common-obj-y += migration.o socket.o fd.o exec.o common-obj-y += tls.o channel.o savevm.o -common-obj-y += colo-comm.o colo.o colo-failover.o +common-obj-y += colo.o colo-failover.o common-obj-y += vmstate.o vmstate-types.o page_cache.o common-obj-y += qemu-file.o global_state.o common-obj-y += qemu-file-channel.o diff --git a/migration/colo-comm.c b/migration/colo-comm.c deleted file mode 100644 index df26e4dfe7..0000000000 --- a/migration/colo-comm.c +++ /dev/null @@ -1,76 +0,0 @@ -/* - * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO) - * (a.k.a. Fault Tolerance or Continuous Replication) - * - * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD. - * Copyright (c) 2016 FUJITSU LIMITED - * Copyright (c) 2016 Intel Corporation - * - * This work is licensed under the terms of the GNU GPL, version 2 or - * later. See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "migration.h" -#include "migration/colo.h" -#include "migration/vmstate.h" -#include "trace.h" - -typedef struct { - bool colo_requested; -} COLOInfo; - -static COLOInfo colo_info; - -COLOMode get_colo_mode(void) -{ - if (migration_in_colo_state()) { - return COLO_MODE_PRIMARY; - } else if (migration_incoming_in_colo_state()) { - return COLO_MODE_SECONDARY; - } else { - return COLO_MODE_UNKNOWN; - } -} - -static int colo_info_pre_save(void *opaque) -{ - COLOInfo *s = opaque; - - s->colo_requested = migrate_colo_enabled(); - - return 0; -} - -static bool colo_info_need(void *opaque) -{ - return migrate_colo_enabled(); -} - -static const VMStateDescription colo_state = { - .name = "COLOState", - .version_id = 1, - .minimum_version_id = 1, - .pre_save = colo_info_pre_save, - .needed = colo_info_need, - .fields = (VMStateField[]) { - VMSTATE_BOOL(colo_requested, COLOInfo), - VMSTATE_END_OF_LIST() - }, -}; - -void colo_info_init(void) -{ - vmstate_register(NULL, 0, &colo_state, &colo_info); -} - -bool migration_incoming_enable_colo(void) -{ - return colo_info.colo_requested; -} - -void migration_incoming_exit_colo(void) -{ - colo_info.colo_requested = false; -} diff --git a/migration/colo.c b/migration/colo.c index af04010061..d3163b51c8 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -152,6 +152,17 @@ static void primary_vm_do_failover(void) qemu_sem_post(&s->colo_exit_sem); } +COLOMode get_colo_mode(void) +{ + if (migration_in_colo_state()) { + return COLO_MODE_PRIMARY; + } else if (migration_incoming_in_colo_state()) { + return COLO_MODE_SECONDARY; + } else { + return COLO_MODE_UNKNOWN; + } +} + void colo_do_failover(MigrationState *s) { /* Make sure VM stopped while failover happened. */ @@ -746,7 +757,7 @@ out: if (mis->to_src_file) { qemu_fclose(mis->to_src_file); } - migration_incoming_exit_colo(); + migration_incoming_disable_colo(); rcu_unregister_thread(); return NULL; diff --git a/migration/migration.c b/migration/migration.c index bf5fcd1009..215e81a190 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -296,6 +296,22 @@ int migrate_send_rp_req_pages(MigrationIncomingState *mis, const char *rbname, return migrate_send_rp_message(mis, msg_type, msglen, bufc); } +static bool migration_colo_enabled; +bool migration_incoming_colo_enabled(void) +{ + return migration_colo_enabled; +} + +void migration_incoming_disable_colo(void) +{ + migration_colo_enabled = false; +} + +void migration_incoming_enable_colo(void) +{ + migration_colo_enabled = true; +} + void qemu_start_incoming_migration(const char *uri, Error **errp) { const char *p; @@ -418,7 +434,7 @@ static void process_incoming_migration_co(void *opaque) } /* we get COLO info, and know if we are in COLO mode */ - if (!ret && migration_incoming_enable_colo()) { + if (!ret && migration_incoming_colo_enabled()) { /* Make sure all file formats flush their mutable metadata */ bdrv_invalidate_cache_all(&local_err); if (local_err) { @@ -3025,6 +3041,11 @@ static void *migration_thread(void *opaque) qemu_savevm_send_postcopy_advise(s->to_dst_file); } + if (migrate_colo_enabled()) { + /* Notify migration destination that we enable COLO */ + qemu_savevm_send_colo_enable(s->to_dst_file); + } + qemu_savevm_state_setup(s->to_dst_file); s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start; diff --git a/migration/savevm.c b/migration/savevm.c index 2d10e45582..09ad962a8f 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -56,6 +56,7 @@ #include "io/channel-file.h" #include "sysemu/replay.h" #include "qjson.h" +#include "migration/colo.h" #ifndef ETH_P_RARP #define ETH_P_RARP 0x8035 @@ -82,6 +83,7 @@ enum qemu_vm_cmd { were previously sent during precopy but are dirty. */ MIG_CMD_PACKAGED, /* Send a wrapped stream within this stream */ + MIG_CMD_ENABLE_COLO, /* Enable COLO */ MIG_CMD_POSTCOPY_RESUME, /* resume postcopy on dest */ MIG_CMD_RECV_BITMAP, /* Request for recved bitmap on dst */ MIG_CMD_MAX @@ -841,6 +843,12 @@ static void qemu_savevm_command_send(QEMUFile *f, qemu_fflush(f); } +void qemu_savevm_send_colo_enable(QEMUFile *f) +{ + trace_savevm_send_colo_enable(); + qemu_savevm_command_send(f, MIG_CMD_ENABLE_COLO, 0, NULL); +} + void qemu_savevm_send_ping(QEMUFile *f, uint32_t value) { uint32_t buf; @@ -1922,6 +1930,12 @@ static int loadvm_handle_recv_bitmap(MigrationIncomingState *mis, return 0; } +static int loadvm_process_enable_colo(MigrationIncomingState *mis) +{ + migration_incoming_enable_colo(); + return 0; +} + /* * Process an incoming 'QEMU_VM_COMMAND' * 0 just a normal return @@ -2001,6 +2015,9 @@ static int loadvm_process_command(QEMUFile *f) case MIG_CMD_RECV_BITMAP: return loadvm_handle_recv_bitmap(mis, len); + + case MIG_CMD_ENABLE_COLO: + return loadvm_process_enable_colo(mis); } return 0; diff --git a/migration/savevm.h b/migration/savevm.h index a5e65b8ae3..8373c2f6bd 100644 --- a/migration/savevm.h +++ b/migration/savevm.h @@ -55,6 +55,7 @@ void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name, uint16_t len, uint64_t *start_list, uint64_t *length_list); +void qemu_savevm_send_colo_enable(QEMUFile *f); int qemu_loadvm_state(QEMUFile *f); void qemu_loadvm_state_cleanup(void); diff --git a/migration/trace-events b/migration/trace-events index 9430f3cbe0..fa0ff3f3bf 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -37,6 +37,7 @@ savevm_send_ping(uint32_t val) "0x%x" savevm_send_postcopy_listen(void) "" savevm_send_postcopy_run(void) "" savevm_send_postcopy_resume(void) "" +savevm_send_colo_enable(void) "" savevm_send_recv_bitmap(char *name) "%s" savevm_state_setup(void) "" savevm_state_resume_prepare(void) "" diff --git a/vl.c b/vl.c index 4e25c78bff..ac3ed17de4 100644 --- a/vl.c +++ b/vl.c @@ -4365,8 +4365,6 @@ int main(int argc, char **argv, char **envp) #endif } - colo_info_init(); - if (net_init_clients(&err) < 0) { error_report_err(err); exit(1); -- cgit 1.4.1 From 9ecff6d66e196701de92f596c250e34c1bd11432 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Mon, 3 Sep 2018 12:38:51 +0800 Subject: qmp event: Add COLO_EXIT event to notify users while exited COLO If some errors happen during VM's COLO FT stage, it's important to notify the users of this event. Together with 'x-colo-lost-heartbeat', Users can intervene in COLO's failover work immediately. If users don't want to get involved in COLO's failover verdict, it is still necessary to notify users that we exited COLO mode. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Zhang Chen Signed-off-by: Zhang Chen Signed-off-by: Jason Wang --- migration/colo.c | 31 +++++++++++++++++++++++++++++++ qapi/migration.json | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) (limited to 'migration/colo.c') diff --git a/migration/colo.c b/migration/colo.c index d3163b51c8..bd7390d6aa 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -28,6 +28,7 @@ #include "net/colo-compare.h" #include "net/colo.h" #include "block/block.h" +#include "qapi/qapi-events-migration.h" static bool vmstate_loading; static Notifier packets_compare_notifier; @@ -514,6 +515,23 @@ out: qemu_fclose(fb); } + /* + * There are only two reasons we can get here, some error happened + * or the user triggered failover. + */ + switch (failover_get_state()) { + case FAILOVER_STATUS_NONE: + qapi_event_send_colo_exit(COLO_MODE_PRIMARY, + COLO_EXIT_REASON_ERROR); + break; + case FAILOVER_STATUS_REQUIRE: + qapi_event_send_colo_exit(COLO_MODE_PRIMARY, + COLO_EXIT_REASON_REQUEST); + break; + default: + abort(); + } + /* Hope this not to be too long to wait here */ qemu_sem_wait(&s->colo_exit_sem); qemu_sem_destroy(&s->colo_exit_sem); @@ -746,6 +764,19 @@ out: error_report_err(local_err); } + switch (failover_get_state()) { + case FAILOVER_STATUS_NONE: + qapi_event_send_colo_exit(COLO_MODE_SECONDARY, + COLO_EXIT_REASON_ERROR); + break; + case FAILOVER_STATUS_REQUIRE: + qapi_event_send_colo_exit(COLO_MODE_SECONDARY, + COLO_EXIT_REASON_REQUEST); + break; + default: + abort(); + } + if (fb) { qemu_fclose(fb); } diff --git a/qapi/migration.json b/qapi/migration.json index 6e8c21258a..4a18209e03 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -956,6 +956,44 @@ { 'enum': 'FailoverStatus', 'data': [ 'none', 'require', 'active', 'completed', 'relaunch' ] } +## +# @COLO_EXIT: +# +# Emitted when VM finishes COLO mode due to some errors happening or +# at the request of users. +# +# @mode: report COLO mode when COLO exited. +# +# @reason: describes the reason for the COLO exit. +# +# Since: 3.1 +# +# Example: +# +# <- { "timestamp": {"seconds": 2032141960, "microseconds": 417172}, +# "event": "COLO_EXIT", "data": {"mode": "primary", "reason": "request" } } +# +## +{ 'event': 'COLO_EXIT', + 'data': {'mode': 'COLOMode', 'reason': 'COLOExitReason' } } + +## +# @COLOExitReason: +# +# The reason for a COLO exit +# +# @none: no failover has ever happened. This can't occur in the +# COLO_EXIT event, only in the result of query-colo-status. +# +# @request: COLO exit is due to an external request +# +# @error: COLO exit is due to an internal error +# +# Since: 3.1 +## +{ 'enum': 'COLOExitReason', + 'data': [ 'none', 'request', 'error' ] } + ## # @x-colo-lost-heartbeat: # -- cgit 1.4.1 From 41b6b7792179591553432b207e1b545fb8bd965b Mon Sep 17 00:00:00 2001 From: Zhang Chen Date: Mon, 3 Sep 2018 12:38:52 +0800 Subject: qapi/migration.json: Rename COLO unknown mode to none mode. Suggested by Markus Armbruster rename COLO unknown mode to none mode. Signed-off-by: Zhang Chen Signed-off-by: Zhang Chen Reviewed-by: Eric Blake Reviewed-by: Markus Armbruster Signed-off-by: Jason Wang --- migration/colo-failover.c | 2 +- migration/colo.c | 2 +- qapi/migration.json | 10 +++++----- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'migration/colo.c') diff --git a/migration/colo-failover.c b/migration/colo-failover.c index 0ae0c41221..4854a96c92 100644 --- a/migration/colo-failover.c +++ b/migration/colo-failover.c @@ -77,7 +77,7 @@ FailoverStatus failover_get_state(void) void qmp_x_colo_lost_heartbeat(Error **errp) { - if (get_colo_mode() == COLO_MODE_UNKNOWN) { + if (get_colo_mode() == COLO_MODE_NONE) { error_setg(errp, QERR_FEATURE_DISABLED, "colo"); return; } diff --git a/migration/colo.c b/migration/colo.c index bd7390d6aa..2cdd366276 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -160,7 +160,7 @@ COLOMode get_colo_mode(void) } else if (migration_incoming_in_colo_state()) { return COLO_MODE_SECONDARY; } else { - return COLO_MODE_UNKNOWN; + return COLO_MODE_NONE; } } diff --git a/qapi/migration.json b/qapi/migration.json index 4a18209e03..0776e0f1c0 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -923,18 +923,18 @@ ## # @COLOMode: # -# The colo mode +# The COLO current mode. # -# @unknown: unknown mode +# @none: COLO is disabled. # -# @primary: master side +# @primary: COLO node in primary side. # -# @secondary: slave side +# @secondary: COLO node in slave side. # # Since: 2.8 ## { 'enum': 'COLOMode', - 'data': [ 'unknown', 'primary', 'secondary'] } + 'data': [ 'none', 'primary', 'secondary'] } ## # @FailoverStatus: -- cgit 1.4.1 From f56c0065b8dd65489621bb7ca1a94d8004d68da1 Mon Sep 17 00:00:00 2001 From: Zhang Chen Date: Mon, 3 Sep 2018 12:38:53 +0800 Subject: qapi: Add new command to query colo status Libvirt or other high level software can use this command query colo status. You can test this command like that: {'execute':'query-colo-status'} Signed-off-by: Zhang Chen Signed-off-by: Zhang Chen Signed-off-by: Jason Wang --- migration/colo.c | 21 +++++++++++++++++++++ qapi/migration.json | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) (limited to 'migration/colo.c') diff --git a/migration/colo.c b/migration/colo.c index 2cdd366276..94c4e097da 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -29,6 +29,7 @@ #include "net/colo.h" #include "block/block.h" #include "qapi/qapi-events-migration.h" +#include "qapi/qmp/qerror.h" static bool vmstate_loading; static Notifier packets_compare_notifier; @@ -237,6 +238,26 @@ void qmp_xen_colo_do_checkpoint(Error **errp) #endif } +COLOStatus *qmp_query_colo_status(Error **errp) +{ + COLOStatus *s = g_new0(COLOStatus, 1); + + s->mode = get_colo_mode(); + + switch (failover_get_state()) { + case FAILOVER_STATUS_NONE: + s->reason = COLO_EXIT_REASON_NONE; + break; + case FAILOVER_STATUS_REQUIRE: + s->reason = COLO_EXIT_REASON_REQUEST; + break; + default: + s->reason = COLO_EXIT_REASON_ERROR; + } + + return s; +} + static void colo_send_message(QEMUFile *f, COLOMessage msg, Error **errp) { diff --git a/qapi/migration.json b/qapi/migration.json index 0776e0f1c0..0928f4b727 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -1307,6 +1307,38 @@ ## { 'command': 'xen-colo-do-checkpoint' } +## +# @COLOStatus: +# +# The result format for 'query-colo-status'. +# +# @mode: COLO running mode. If COLO is running, this field will return +# 'primary' or 'secondary'. +# +# @reason: describes the reason for the COLO exit. +# +# Since: 3.0 +## +{ 'struct': 'COLOStatus', + 'data': { 'mode': 'COLOMode', 'reason': 'COLOExitReason' } } + +## +# @query-colo-status: +# +# Query COLO status while the vm is running. +# +# Returns: A @COLOStatus object showing the status. +# +# Example: +# +# -> { "execute": "query-colo-status" } +# <- { "return": { "mode": "primary", "active": true, "reason": "request" } } +# +# Since: 3.0 +## +{ 'command': 'query-colo-status', + 'returns': 'COLOStatus' } + ## # @migrate-recover: # -- cgit 1.4.1 From 3f6df99d9dc8ce33deae1835e96e659063fa3037 Mon Sep 17 00:00:00 2001 From: Zhang Chen Date: Mon, 3 Sep 2018 12:38:54 +0800 Subject: savevm: split the process of different stages for loadvm/savevm There are several stages during loadvm/savevm process. In different stage, migration incoming processes different types of sections. We want to control these stages more accuracy, it will benefit COLO performance, we don't have to save type of QEMU_VM_SECTION_START sections everytime while do checkpoint, besides, we want to separate the process of saving/loading memory and devices state. So we add three new helper functions: qemu_load_device_state() and qemu_savevm_live_state() to achieve different process during migration. Besides, we make qemu_loadvm_state_main() and qemu_save_device_state() public, and simplify the codes of qemu_save_device_state() by calling the wrapper qemu_savevm_state_header(). Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Zhang Chen Signed-off-by: Zhang Chen Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Jason Wang --- migration/colo.c | 41 ++++++++++++++++++++++++++++++++--------- migration/savevm.c | 36 +++++++++++++++++++++++++++++------- migration/savevm.h | 4 ++++ 3 files changed, 65 insertions(+), 16 deletions(-) (limited to 'migration/colo.c') diff --git a/migration/colo.c b/migration/colo.c index 94c4e097da..59bb507189 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -30,6 +30,7 @@ #include "block/block.h" #include "qapi/qapi-events-migration.h" #include "qapi/qmp/qerror.h" +#include "sysemu/cpus.h" static bool vmstate_loading; static Notifier packets_compare_notifier; @@ -401,23 +402,34 @@ static int colo_do_checkpoint_transaction(MigrationState *s, /* Disable block migration */ migrate_set_block_enabled(false, &local_err); - qemu_savevm_state_header(fb); - qemu_savevm_state_setup(fb); qemu_mutex_lock_iothread(); replication_do_checkpoint_all(&local_err); if (local_err) { qemu_mutex_unlock_iothread(); goto out; } - qemu_savevm_state_complete_precopy(fb, false, false); - qemu_mutex_unlock_iothread(); - - qemu_fflush(fb); colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err); if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + /* Note: device state is saved into buffer */ + ret = qemu_save_device_state(fb); + + qemu_mutex_unlock_iothread(); + if (ret < 0) { goto out; } + /* + * Only save VM's live state, which not including device state. + * TODO: We may need a timeout mechanism to prevent COLO process + * to be blocked here. + */ + qemu_savevm_live_state(s->to_dst_file); + + qemu_fflush(fb); + /* * We need the size of the VMstate data in Secondary side, * With which we can decide how much data should be read. @@ -635,6 +647,7 @@ void *colo_process_incoming_thread(void *opaque) uint64_t total_size; uint64_t value; Error *local_err = NULL; + int ret; rcu_register_thread(); qemu_sem_init(&mis->colo_incoming_sem, 0); @@ -708,6 +721,16 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + qemu_mutex_lock_iothread(); + cpu_synchronize_all_pre_loadvm(); + ret = qemu_loadvm_state_main(mis->from_src_file, mis); + qemu_mutex_unlock_iothread(); + + if (ret < 0) { + error_report("Load VM's live state (ram) error"); + goto out; + } + value = colo_receive_message_value(mis->from_src_file, COLO_MESSAGE_VMSTATE_SIZE, &local_err); if (local_err) { @@ -739,10 +762,10 @@ void *colo_process_incoming_thread(void *opaque) } qemu_mutex_lock_iothread(); - qemu_system_reset(SHUTDOWN_CAUSE_NONE); vmstate_loading = true; - if (qemu_loadvm_state(fb) < 0) { - error_report("COLO: loadvm failed"); + ret = qemu_load_device_state(fb); + if (ret < 0) { + error_report("COLO: load device state failed"); qemu_mutex_unlock_iothread(); goto out; } diff --git a/migration/savevm.c b/migration/savevm.c index 288b8075be..e4caff9a6a 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1378,13 +1378,21 @@ done: return ret; } -static int qemu_save_device_state(QEMUFile *f) +void qemu_savevm_live_state(QEMUFile *f) { - SaveStateEntry *se; + /* save QEMU_VM_SECTION_END section */ + qemu_savevm_state_complete_precopy(f, true, false); + qemu_put_byte(f, QEMU_VM_EOF); +} - qemu_put_be32(f, QEMU_VM_FILE_MAGIC); - qemu_put_be32(f, QEMU_VM_FILE_VERSION); +int qemu_save_device_state(QEMUFile *f) +{ + SaveStateEntry *se; + if (!migration_in_colo_state()) { + qemu_put_be32(f, QEMU_VM_FILE_MAGIC); + qemu_put_be32(f, QEMU_VM_FILE_VERSION); + } cpu_synchronize_all_states(); QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { @@ -1440,8 +1448,6 @@ enum LoadVMExitCodes { LOADVM_QUIT = 1, }; -static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis); - /* ------ incoming postcopy messages ------ */ /* 'advise' arrives before any transfers just to tell us that a postcopy * *might* happen - it might be skipped if precopy transferred everything @@ -2247,7 +2253,7 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis) return true; } -static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) +int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) { uint8_t section_type; int ret = 0; @@ -2418,6 +2424,22 @@ int qemu_loadvm_state(QEMUFile *f) return ret; } +int qemu_load_device_state(QEMUFile *f) +{ + MigrationIncomingState *mis = migration_incoming_get_current(); + int ret; + + /* Load QEMU_VM_SECTION_FULL section */ + ret = qemu_loadvm_state_main(f, mis); + if (ret < 0) { + error_report("Failed to load device state: %d", ret); + return ret; + } + + cpu_synchronize_all_post_init(); + return 0; +} + int save_snapshot(const char *name, Error **errp) { BlockDriverState *bs, *bs1; diff --git a/migration/savevm.h b/migration/savevm.h index 8373c2f6bd..51a4b9caa8 100644 --- a/migration/savevm.h +++ b/migration/savevm.h @@ -56,8 +56,12 @@ void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name, uint64_t *start_list, uint64_t *length_list); void qemu_savevm_send_colo_enable(QEMUFile *f); +void qemu_savevm_live_state(QEMUFile *f); +int qemu_save_device_state(QEMUFile *f); int qemu_loadvm_state(QEMUFile *f); void qemu_loadvm_state_cleanup(void); +int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis); +int qemu_load_device_state(QEMUFile *f); #endif -- cgit 1.4.1 From 7b3435309d27910587c7e6e8ba07e4070fb37bbb Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Mon, 3 Sep 2018 12:38:58 +0800 Subject: COLO: notify net filters about checkpoint/failover event Notify all net filters about the checkpoint and failover event. Signed-off-by: zhanghailiang Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Jason Wang --- migration/colo.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'migration/colo.c') diff --git a/migration/colo.c b/migration/colo.c index 59bb507189..57a85424fc 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -31,6 +31,7 @@ #include "qapi/qapi-events-migration.h" #include "qapi/qmp/qerror.h" #include "sysemu/cpus.h" +#include "net/filter.h" static bool vmstate_loading; static Notifier packets_compare_notifier; @@ -83,6 +84,12 @@ static void secondary_vm_do_failover(void) error_report_err(local_err); } + /* Notify all filters of all NIC to do checkpoint */ + colo_notify_filters_event(COLO_EVENT_FAILOVER, &local_err); + if (local_err) { + error_report_err(local_err); + } + if (!autostart) { error_report("\"-S\" qemu option will be ignored in secondary side"); /* recover runstate to normal migration finish state */ @@ -782,6 +789,14 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + /* Notify all filters of all NIC to do checkpoint */ + colo_notify_filters_event(COLO_EVENT_CHECKPOINT, &local_err); + + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vmstate_loading = false; vm_start(); trace_colo_vm_state_change("stop", "run"); -- cgit 1.4.1 From 2518aec19250531c4e03208b273a6b44b1344c33 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Mon, 3 Sep 2018 12:38:59 +0800 Subject: COLO: quick failover process by kick COLO thread COLO thread may sleep at qemu_sem_wait(&s->colo_checkpoint_sem), while failover works begin, It's better to wakeup it to quick the process. Signed-off-by: zhanghailiang Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Jason Wang --- migration/colo.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'migration/colo.c') diff --git a/migration/colo.c b/migration/colo.c index 57a85424fc..956ac236b7 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -131,6 +131,11 @@ static void primary_vm_do_failover(void) migrate_set_state(&s->state, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED); + /* + * kick COLO thread which might wait at + * qemu_sem_wait(&s->colo_checkpoint_sem). + */ + colo_checkpoint_notify(migrate_get_current()); /* * Wake up COLO thread which may blocked in recv() or send(), @@ -539,6 +544,9 @@ static void colo_process_checkpoint(MigrationState *s) qemu_sem_wait(&s->colo_checkpoint_sem); + if (s->state != MIGRATION_STATUS_COLO) { + goto out; + } ret = colo_do_checkpoint_transaction(s, bioc, fb); if (ret < 0) { goto out; -- cgit 1.4.1