From 35a6ed4f716c1027c04d12a3c499b2e9d6b62c24 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:42:52 +0800 Subject: migration: Introduce capability 'x-colo' to migration We add helper function colo_supported() to indicate whether colo is supported or not, with which we use to control whether or not showing 'x-colo' string to users, they can use qmp command 'query-migrate-capabilities' or hmp command 'info migrate_capabilities' to learn if colo is supported. The default value for COLO (COarse-Grain LOck Stepping) is disabled. Cc: Juan Quintela Cc: Amit Shah Cc: Eric Blake Cc: Markus Armbruster Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Gonglei Reviewed-by: Eric Blake Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/Makefile.objs | 1 + migration/colo.c | 19 +++++++++++++++++++ migration/migration.c | 18 ++++++++++++++++++ 3 files changed, 38 insertions(+) create mode 100644 migration/colo.c (limited to 'migration') diff --git a/migration/Makefile.objs b/migration/Makefile.objs index 30ad945918..cff96f0a06 100644 --- a/migration/Makefile.objs +++ b/migration/Makefile.objs @@ -1,5 +1,6 @@ common-obj-y += migration.o socket.o fd.o exec.o common-obj-y += tls.o +common-obj-$(CONFIG_COLO) += colo.o common-obj-y += vmstate.o common-obj-y += qemu-file.o common-obj-y += qemu-file-channel.o diff --git a/migration/colo.c b/migration/colo.c new file mode 100644 index 0000000000..d21505794e --- /dev/null +++ b/migration/colo.c @@ -0,0 +1,19 @@ +/* + * 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/colo.h" + +bool colo_supported(void) +{ + return false; +} diff --git a/migration/migration.c b/migration/migration.c index 156e70791a..c7869e5779 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -36,6 +36,7 @@ #include "exec/address-spaces.h" #include "io/channel-buffer.h" #include "io/channel-tls.h" +#include "migration/colo.h" #define MAX_THROTTLE (32 << 20) /* Migration transfer speed throttling */ @@ -531,6 +532,9 @@ MigrationCapabilityStatusList *qmp_query_migrate_capabilities(Error **errp) caps = NULL; /* silence compiler warning */ for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) { + if (i == MIGRATION_CAPABILITY_X_COLO && !colo_supported()) { + continue; + } if (head == NULL) { head = g_malloc0(sizeof(*caps)); caps = head; @@ -733,6 +737,14 @@ void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params, } for (cap = params; cap; cap = cap->next) { + if (cap->value->capability == MIGRATION_CAPABILITY_X_COLO) { + if (!colo_supported()) { + error_setg(errp, "COLO is not currently supported, please" + " configure with --enable-colo option in order to" + " support COLO feature"); + continue; + } + } s->enabled_capabilities[cap->value->capability] = cap->value->state; } @@ -1713,6 +1725,12 @@ fail: MIGRATION_STATUS_FAILED); } +bool migrate_colo_enabled(void) +{ + MigrationState *s = migrate_get_current(); + return s->enabled_capabilities[MIGRATION_CAPABILITY_X_COLO]; +} + /* * Master migration thread on the source VM. * It drives the migration and pumps the data down the outgoing channel. -- cgit v1.2.1 From 5821ebf93b1da9f74dc04c20e2923aadfaf803df Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:42:53 +0800 Subject: COLO: migrate COLO related info to secondary node We can determine whether or not VM in destination should go into COLO mode by referring to the info that was migrated. We skip this section if COLO is not enabled (i.e. migrate_set_capability colo off), so that, It doesn't break compatibility with migration no matter whether users configure the --enable-colo/disable-colo on the source/destination side or not; Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Gonglei Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/Makefile.objs | 1 + migration/colo-comm.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+) create mode 100644 migration/colo-comm.c (limited to 'migration') diff --git a/migration/Makefile.objs b/migration/Makefile.objs index cff96f0a06..4bbe9ab313 100644 --- a/migration/Makefile.objs +++ b/migration/Makefile.objs @@ -1,6 +1,7 @@ common-obj-y += migration.o socket.o fd.o exec.o common-obj-y += tls.o common-obj-$(CONFIG_COLO) += colo.o +common-obj-y += colo-comm.o common-obj-y += vmstate.o common-obj-y += qemu-file.o common-obj-y += qemu-file-channel.o diff --git a/migration/colo-comm.c b/migration/colo-comm.c new file mode 100644 index 0000000000..a2d5185a8a --- /dev/null +++ b/migration/colo-comm.c @@ -0,0 +1,51 @@ +/* + * 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 +#include "trace.h" + +typedef struct { + bool colo_requested; +} COLOInfo; + +static COLOInfo colo_info; + +static void colo_info_pre_save(void *opaque) +{ + COLOInfo *s = opaque; + + s->colo_requested = migrate_colo_enabled(); +} + +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); +} -- cgit v1.2.1 From 0b827d5e7291193887d22d058bc20c12b423047c Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:42:54 +0800 Subject: migration: Enter into COLO mode after migration if COLO is enabled Add a new migration state: MIGRATION_STATUS_COLO. Migration source side enters this state after the first live migration successfully finished if COLO is enabled by command 'migrate_set_capability x-colo on'. We reuse migration thread, so the process of checkpointing will be handled in migration thread. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Gonglei Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo.c | 29 +++++++++++++++++++++++++++++ migration/migration.c | 38 +++++++++++++++++++++++++++++++++----- migration/trace-events | 3 +++ 3 files changed, 65 insertions(+), 5 deletions(-) (limited to 'migration') diff --git a/migration/colo.c b/migration/colo.c index d21505794e..f480431972 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -11,9 +11,38 @@ */ #include "qemu/osdep.h" +#include "sysemu/sysemu.h" #include "migration/colo.h" +#include "trace.h" bool colo_supported(void) { return false; } + +bool migration_in_colo_state(void) +{ + MigrationState *s = migrate_get_current(); + + return (s->state == MIGRATION_STATUS_COLO); +} + +static void colo_process_checkpoint(MigrationState *s) +{ + qemu_mutex_lock_iothread(); + vm_start(); + qemu_mutex_unlock_iothread(); + trace_colo_vm_state_change("stop", "run"); + + /* TODO: COLO checkpoint savevm loop */ + +} + +void migrate_start_colo_process(MigrationState *s) +{ + qemu_mutex_unlock_iothread(); + migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE, + MIGRATION_STATUS_COLO); + colo_process_checkpoint(s); + qemu_mutex_lock_iothread(); +} diff --git a/migration/migration.c b/migration/migration.c index c7869e5779..aff3eb460d 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -695,6 +695,10 @@ MigrationInfo *qmp_query_migrate(Error **errp) get_xbzrle_cache_stats(info); break; + case MIGRATION_STATUS_COLO: + info->has_status = true; + /* TODO: display COLO specific information (checkpoint info etc.) */ + break; case MIGRATION_STATUS_COMPLETED: get_xbzrle_cache_stats(info); @@ -1113,7 +1117,8 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk, params.shared = has_inc && inc; if (migration_is_setup_or_active(s->state) || - s->state == MIGRATION_STATUS_CANCELLING) { + s->state == MIGRATION_STATUS_CANCELLING || + s->state == MIGRATION_STATUS_COLO) { error_setg(errp, QERR_MIGRATION_ACTIVE); return; } @@ -1661,7 +1666,11 @@ static void migration_completion(MigrationState *s, int current_active_state, if (!ret) { ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE); - if (ret >= 0) { + /* + * Don't mark the image with BDRV_O_INACTIVE flag if + * we will go into COLO stage later. + */ + if (ret >= 0 && !migrate_colo_enabled()) { ret = bdrv_inactivate_all(); } if (ret >= 0) { @@ -1703,8 +1712,11 @@ static void migration_completion(MigrationState *s, int current_active_state, goto fail_invalidate; } - migrate_set_state(&s->state, current_active_state, - MIGRATION_STATUS_COMPLETED); + if (!migrate_colo_enabled()) { + migrate_set_state(&s->state, current_active_state, + MIGRATION_STATUS_COMPLETED); + } + return; fail_invalidate: @@ -1749,6 +1761,7 @@ static void *migration_thread(void *opaque) bool entered_postcopy = false; /* The active state we expect to be in; ACTIVE or POSTCOPY_ACTIVE */ enum MigrationStatus current_active_state = MIGRATION_STATUS_ACTIVE; + bool enable_colo = migrate_colo_enabled(); rcu_register_thread(); @@ -1857,7 +1870,13 @@ static void *migration_thread(void *opaque) end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); qemu_mutex_lock_iothread(); - qemu_savevm_state_cleanup(); + /* + * The resource has been allocated by migration will be reused in COLO + * process, so don't release them. + */ + if (!enable_colo) { + qemu_savevm_state_cleanup(); + } if (s->state == MIGRATION_STATUS_COMPLETED) { uint64_t transferred_bytes = qemu_ftell(s->to_dst_file); s->total_time = end_time - s->total_time; @@ -1870,6 +1889,15 @@ static void *migration_thread(void *opaque) } runstate_set(RUN_STATE_POSTMIGRATE); } else { + if (s->state == MIGRATION_STATUS_ACTIVE && enable_colo) { + migrate_start_colo_process(s); + qemu_savevm_state_cleanup(); + /* + * Fixme: we will run VM in COLO no matter its old running state. + * After exited COLO, we will keep running. + */ + old_vm_running = true; + } if (old_vm_running && !entered_postcopy) { vm_start(); } else { diff --git a/migration/trace-events b/migration/trace-events index dfee75abf4..a29e5a09ea 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -207,3 +207,6 @@ migration_tls_outgoing_handshake_complete(void) "" migration_tls_incoming_handshake_start(void) "" migration_tls_incoming_handshake_error(const char *err) "err=%s" migration_tls_incoming_handshake_complete(void) "" + +# migration/colo.c +colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'" -- cgit v1.2.1 From 25d0c16f625feb3b6b9bf8079388cdd314e63916 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:42:55 +0800 Subject: migration: Switch to COLO process after finishing loadvm Switch from normal migration loadvm process into COLO checkpoint process if COLO mode is enabled. We add three new members to struct MigrationIncomingState, 'have_colo_incoming_thread' and 'colo_incoming_thread' record the COLO related thread for secondary VM, 'migration_incoming_co' records the original migration incoming coroutine. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo-comm.c | 10 ++++++++++ migration/colo.c | 21 +++++++++++++++++++++ migration/migration.c | 12 ++++++++++++ 3 files changed, 43 insertions(+) (limited to 'migration') diff --git a/migration/colo-comm.c b/migration/colo-comm.c index a2d5185a8a..bf44f76440 100644 --- a/migration/colo-comm.c +++ b/migration/colo-comm.c @@ -49,3 +49,13 @@ 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 f480431972..550cc5f122 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -27,6 +27,13 @@ bool migration_in_colo_state(void) return (s->state == MIGRATION_STATUS_COLO); } +bool migration_incoming_in_colo_state(void) +{ + MigrationIncomingState *mis = migration_incoming_get_current(); + + return mis && (mis->state == MIGRATION_STATUS_COLO); +} + static void colo_process_checkpoint(MigrationState *s) { qemu_mutex_lock_iothread(); @@ -46,3 +53,17 @@ void migrate_start_colo_process(MigrationState *s) colo_process_checkpoint(s); qemu_mutex_lock_iothread(); } + +void *colo_process_incoming_thread(void *opaque) +{ + MigrationIncomingState *mis = opaque; + + migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, + MIGRATION_STATUS_COLO); + + /* TODO: COLO checkpoint restore loop */ + + migration_incoming_exit_colo(); + + return NULL; +} diff --git a/migration/migration.c b/migration/migration.c index aff3eb460d..d8421b5085 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -407,6 +407,18 @@ static void process_incoming_migration_co(void *opaque) /* Else if something went wrong then just fall out of the normal exit */ } + /* we get COLO info, and know if we are in COLO mode */ + if (!ret && migration_incoming_enable_colo()) { + mis->migration_incoming_co = qemu_coroutine_self(); + qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming", + colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE); + mis->have_colo_incoming_thread = true; + qemu_coroutine_yield(); + + /* Wait checkpoint incoming thread exit before free resource */ + qemu_thread_join(&mis->colo_incoming_thread); + } + qemu_fclose(f); free_xbzrle_decoded_buf(); -- cgit v1.2.1 From 56ba83d2a871a28ec18b8bb0fcec74ed02bbe06c Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:42:56 +0800 Subject: COLO: Establish a new communicating path for COLO This new communication path will be used for returning messages from Secondary side to Primary side. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'migration') diff --git a/migration/colo.c b/migration/colo.c index 550cc5f122..3a0d8043e6 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -14,6 +14,7 @@ #include "sysemu/sysemu.h" #include "migration/colo.h" #include "trace.h" +#include "qemu/error-report.h" bool colo_supported(void) { @@ -36,6 +37,12 @@ bool migration_incoming_in_colo_state(void) static void colo_process_checkpoint(MigrationState *s) { + s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file); + if (!s->rp_state.from_dst_file) { + error_report("Open QEMUFile from_dst_file failed"); + goto out; + } + qemu_mutex_lock_iothread(); vm_start(); qemu_mutex_unlock_iothread(); @@ -43,6 +50,10 @@ static void colo_process_checkpoint(MigrationState *s) /* TODO: COLO checkpoint savevm loop */ +out: + if (s->rp_state.from_dst_file) { + qemu_fclose(s->rp_state.from_dst_file); + } } void migrate_start_colo_process(MigrationState *s) @@ -61,8 +72,25 @@ void *colo_process_incoming_thread(void *opaque) migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, MIGRATION_STATUS_COLO); + mis->to_src_file = qemu_file_get_return_path(mis->from_src_file); + if (!mis->to_src_file) { + error_report("COLO incoming thread: Open QEMUFile to_src_file failed"); + goto out; + } + /* + * Note: the communication between Primary side and Secondary side + * should be sequential, we set the fd to unblocked in migration incoming + * coroutine, and here we are in the COLO incoming thread, so it is ok to + * set the fd back to blocked. + */ + qemu_file_set_blocking(mis->from_src_file, true); + /* TODO: COLO checkpoint restore loop */ +out: + if (mis->to_src_file) { + qemu_fclose(mis->to_src_file); + } migration_incoming_exit_colo(); return NULL; -- cgit v1.2.1 From 4f97558e100f66f953ba7576b0ced146e6846997 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:42:57 +0800 Subject: COLO: Introduce checkpointing protocol We need communications protocol of user-defined to control the checkpointing process. The new checkpointing request is started by Primary VM, and the interactive process like below: Checkpoint synchronizing points: Primary Secondary initial work 'checkpoint-ready' <-------------------- @ 'checkpoint-request' @ --------------------> Suspend (Only in hybrid mode) 'checkpoint-reply' <-------------------- @ Suspend&Save state 'vmstate-send' @ --------------------> Send state Receive state 'vmstate-received' <-------------------- @ Release packets Load state 'vmstate-load' <-------------------- @ Resume Resume (Only in hybrid mode) Start Comparing (Only in hybrid mode) NOTE: 1) '@' who sends the message 2) Every sync-point is synchronized by two sides with only one handshake(single direction) for low-latency. If more strict synchronization is required, a opposite direction sync-point should be added. 3) Since sync-points are single direction, the remote side may go forward a lot when this side just receives the sync-point. 4) For now, we only support 'periodic' checkpoint, for which the Secondary VM is not running, later we will support 'hybrid' mode. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Gonglei Cc: Eric Blake Cc: Markus Armbruster Cc: Dr. David Alan Gilbert Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo.c | 201 ++++++++++++++++++++++++++++++++++++++++++++++++- migration/trace-events | 2 + 2 files changed, 201 insertions(+), 2 deletions(-) (limited to 'migration') diff --git a/migration/colo.c b/migration/colo.c index 3a0d8043e6..fcc9047595 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -15,6 +15,7 @@ #include "migration/colo.h" #include "trace.h" #include "qemu/error-report.h" +#include "qapi/error.h" bool colo_supported(void) { @@ -35,22 +36,147 @@ bool migration_incoming_in_colo_state(void) return mis && (mis->state == MIGRATION_STATUS_COLO); } +static void colo_send_message(QEMUFile *f, COLOMessage msg, + Error **errp) +{ + int ret; + + if (msg >= COLO_MESSAGE__MAX) { + error_setg(errp, "%s: Invalid message", __func__); + return; + } + qemu_put_be32(f, msg); + qemu_fflush(f); + + ret = qemu_file_get_error(f); + if (ret < 0) { + error_setg_errno(errp, -ret, "Can't send COLO message"); + } + trace_colo_send_message(COLOMessage_lookup[msg]); +} + +static COLOMessage colo_receive_message(QEMUFile *f, Error **errp) +{ + COLOMessage msg; + int ret; + + msg = qemu_get_be32(f); + ret = qemu_file_get_error(f); + if (ret < 0) { + error_setg_errno(errp, -ret, "Can't receive COLO message"); + return msg; + } + if (msg >= COLO_MESSAGE__MAX) { + error_setg(errp, "%s: Invalid message", __func__); + return msg; + } + trace_colo_receive_message(COLOMessage_lookup[msg]); + return msg; +} + +static void colo_receive_check_message(QEMUFile *f, COLOMessage expect_msg, + Error **errp) +{ + COLOMessage msg; + Error *local_err = NULL; + + msg = colo_receive_message(f, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + if (msg != expect_msg) { + error_setg(errp, "Unexpected COLO message %d, expected %d", + msg, expect_msg); + } +} + +static int colo_do_checkpoint_transaction(MigrationState *s) +{ + Error *local_err = NULL; + + colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST, + &local_err); + if (local_err) { + goto out; + } + + colo_receive_check_message(s->rp_state.from_dst_file, + COLO_MESSAGE_CHECKPOINT_REPLY, &local_err); + if (local_err) { + goto out; + } + + /* TODO: suspend and save vm state to colo buffer */ + + colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err); + if (local_err) { + goto out; + } + + /* TODO: send vmstate to Secondary */ + + colo_receive_check_message(s->rp_state.from_dst_file, + COLO_MESSAGE_VMSTATE_RECEIVED, &local_err); + if (local_err) { + goto out; + } + + colo_receive_check_message(s->rp_state.from_dst_file, + COLO_MESSAGE_VMSTATE_LOADED, &local_err); + if (local_err) { + goto out; + } + + /* TODO: resume Primary */ + + return 0; +out: + if (local_err) { + error_report_err(local_err); + } + return -EINVAL; +} + static void colo_process_checkpoint(MigrationState *s) { + Error *local_err = NULL; + int ret; + s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file); if (!s->rp_state.from_dst_file) { error_report("Open QEMUFile from_dst_file failed"); goto out; } + /* + * Wait for Secondary finish loading VM states and enter COLO + * restore. + */ + colo_receive_check_message(s->rp_state.from_dst_file, + COLO_MESSAGE_CHECKPOINT_READY, &local_err); + if (local_err) { + goto out; + } + qemu_mutex_lock_iothread(); vm_start(); qemu_mutex_unlock_iothread(); trace_colo_vm_state_change("stop", "run"); - /* TODO: COLO checkpoint savevm loop */ + while (s->state == MIGRATION_STATUS_COLO) { + ret = colo_do_checkpoint_transaction(s); + if (ret < 0) { + goto out; + } + } out: + /* Throw the unreported error message after exited from loop */ + if (local_err) { + error_report_err(local_err); + } + if (s->rp_state.from_dst_file) { qemu_fclose(s->rp_state.from_dst_file); } @@ -65,9 +191,33 @@ void migrate_start_colo_process(MigrationState *s) qemu_mutex_lock_iothread(); } +static void colo_wait_handle_message(QEMUFile *f, int *checkpoint_request, + Error **errp) +{ + COLOMessage msg; + Error *local_err = NULL; + + msg = colo_receive_message(f, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + switch (msg) { + case COLO_MESSAGE_CHECKPOINT_REQUEST: + *checkpoint_request = 1; + break; + default: + *checkpoint_request = 0; + error_setg(errp, "Got unknown COLO message: %d", msg); + break; + } +} + void *colo_process_incoming_thread(void *opaque) { MigrationIncomingState *mis = opaque; + Error *local_err = NULL; migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, MIGRATION_STATUS_COLO); @@ -85,9 +235,56 @@ void *colo_process_incoming_thread(void *opaque) */ qemu_file_set_blocking(mis->from_src_file, true); - /* TODO: COLO checkpoint restore loop */ + colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, + &local_err); + if (local_err) { + goto out; + } + + while (mis->state == MIGRATION_STATUS_COLO) { + int request; + + colo_wait_handle_message(mis->from_src_file, &request, &local_err); + if (local_err) { + goto out; + } + assert(request); + /* FIXME: This is unnecessary for periodic checkpoint mode */ + colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY, + &local_err); + if (local_err) { + goto out; + } + + colo_receive_check_message(mis->from_src_file, + COLO_MESSAGE_VMSTATE_SEND, &local_err); + if (local_err) { + goto out; + } + + /* TODO: read migration data into colo buffer */ + + colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED, + &local_err); + if (local_err) { + goto out; + } + + /* TODO: load vm state */ + + colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED, + &local_err); + if (local_err) { + goto out; + } + } out: + /* Throw the unreported error message after exited from loop */ + if (local_err) { + error_report_err(local_err); + } + if (mis->to_src_file) { qemu_fclose(mis->to_src_file); } diff --git a/migration/trace-events b/migration/trace-events index a29e5a09ea..f374c8cf27 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -210,3 +210,5 @@ migration_tls_incoming_handshake_complete(void) "" # migration/colo.c colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'" +colo_send_message(const char *msg) "Send '%s' message" +colo_receive_message(const char *msg) "Receive '%s' message" -- cgit v1.2.1 From a91246c95f913dc6fd391eee32f6c9796de70183 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:42:59 +0800 Subject: COLO: Send PVM state to secondary side when do checkpoint VM checkpointing is to synchronize the state of PVM to SVM, just like migration does, we re-use save helpers to achieve migrating PVM's state to Secondary side. COLO need to cache the data of VM's state in the secondary side before synchronize it to SVM. COLO need the size of the data to determine how much data should be read in the secondary side. So here, we can get the size of the data by saving it into I/O channel before send it to the secondary side. Signed-off-by: zhanghailiang Signed-off-by: Gonglei Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert Cc: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++++----- migration/ram.c | 37 +++++++++++++++++------- 2 files changed, 105 insertions(+), 17 deletions(-) (limited to 'migration') diff --git a/migration/colo.c b/migration/colo.c index fcc9047595..9dc54fc7e9 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -13,10 +13,13 @@ #include "qemu/osdep.h" #include "sysemu/sysemu.h" #include "migration/colo.h" +#include "io/channel-buffer.h" #include "trace.h" #include "qemu/error-report.h" #include "qapi/error.h" +#define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024) + bool colo_supported(void) { return false; @@ -55,6 +58,27 @@ static void colo_send_message(QEMUFile *f, COLOMessage msg, trace_colo_send_message(COLOMessage_lookup[msg]); } +static void colo_send_message_value(QEMUFile *f, COLOMessage msg, + uint64_t value, Error **errp) +{ + Error *local_err = NULL; + int ret; + + colo_send_message(f, msg, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + qemu_put_be64(f, value); + qemu_fflush(f); + + ret = qemu_file_get_error(f); + if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to send value for message:%s", + COLOMessage_lookup[msg]); + } +} + static COLOMessage colo_receive_message(QEMUFile *f, Error **errp) { COLOMessage msg; @@ -91,9 +115,12 @@ static void colo_receive_check_message(QEMUFile *f, COLOMessage expect_msg, } } -static int colo_do_checkpoint_transaction(MigrationState *s) +static int colo_do_checkpoint_transaction(MigrationState *s, + QIOChannelBuffer *bioc, + QEMUFile *fb) { Error *local_err = NULL; + int ret = -1; colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST, &local_err); @@ -106,15 +133,46 @@ static int colo_do_checkpoint_transaction(MigrationState *s) if (local_err) { goto out; } + /* Reset channel-buffer directly */ + qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL); + bioc->usage = 0; - /* TODO: suspend and save vm state to colo buffer */ + qemu_mutex_lock_iothread(); + vm_stop_force_state(RUN_STATE_COLO); + qemu_mutex_unlock_iothread(); + trace_colo_vm_state_change("run", "stop"); + + /* Disable block migration */ + s->params.blk = 0; + s->params.shared = 0; + qemu_savevm_state_header(fb); + qemu_savevm_state_begin(fb, &s->params); + qemu_mutex_lock_iothread(); + qemu_savevm_state_complete_precopy(fb, false); + qemu_mutex_unlock_iothread(); + + qemu_fflush(fb); colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err); if (local_err) { goto out; } + /* + * We need the size of the VMstate data in Secondary side, + * With which we can decide how much data should be read. + */ + colo_send_message_value(s->to_dst_file, COLO_MESSAGE_VMSTATE_SIZE, + bioc->usage, &local_err); + if (local_err) { + goto out; + } - /* TODO: send vmstate to Secondary */ + qemu_put_buffer(s->to_dst_file, bioc->data, bioc->usage); + qemu_fflush(s->to_dst_file); + ret = qemu_file_get_error(s->to_dst_file); + if (ret < 0) { + goto out; + } colo_receive_check_message(s->rp_state.from_dst_file, COLO_MESSAGE_VMSTATE_RECEIVED, &local_err); @@ -128,18 +186,24 @@ static int colo_do_checkpoint_transaction(MigrationState *s) goto out; } - /* TODO: resume Primary */ + ret = 0; + + qemu_mutex_lock_iothread(); + vm_start(); + qemu_mutex_unlock_iothread(); + trace_colo_vm_state_change("stop", "run"); - return 0; out: if (local_err) { error_report_err(local_err); } - return -EINVAL; + return ret; } static void colo_process_checkpoint(MigrationState *s) { + QIOChannelBuffer *bioc; + QEMUFile *fb = NULL; Error *local_err = NULL; int ret; @@ -158,6 +222,9 @@ static void colo_process_checkpoint(MigrationState *s) if (local_err) { goto out; } + bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE); + fb = qemu_fopen_channel_output(QIO_CHANNEL(bioc)); + object_unref(OBJECT(bioc)); qemu_mutex_lock_iothread(); vm_start(); @@ -165,7 +232,7 @@ static void colo_process_checkpoint(MigrationState *s) trace_colo_vm_state_change("stop", "run"); while (s->state == MIGRATION_STATUS_COLO) { - ret = colo_do_checkpoint_transaction(s); + ret = colo_do_checkpoint_transaction(s, bioc, fb); if (ret < 0) { goto out; } @@ -177,6 +244,10 @@ out: error_report_err(local_err); } + if (fb) { + qemu_fclose(fb); + } + if (s->rp_state.from_dst_file) { qemu_fclose(s->rp_state.from_dst_file); } diff --git a/migration/ram.c b/migration/ram.c index d032d389c4..fb9252d722 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -43,6 +43,7 @@ #include "trace.h" #include "exec/ram_addr.h" #include "qemu/rcu_queue.h" +#include "migration/colo.h" #ifdef DEBUG_MIGRATION_RAM #define DPRINTF(fmt, ...) \ @@ -1871,16 +1872,8 @@ err: return ret; } - -/* Each of ram_save_setup, ram_save_iterate and ram_save_complete has - * long-running RCU critical section. When rcu-reclaims in the code - * start to become numerous it will be necessary to reduce the - * granularity of these critical sections. - */ - -static int ram_save_setup(QEMUFile *f, void *opaque) +static int ram_save_init_globals(void) { - RAMBlock *block; int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */ dirty_rate_high_cnt = 0; @@ -1947,6 +1940,29 @@ static int ram_save_setup(QEMUFile *f, void *opaque) migration_bitmap_sync(); qemu_mutex_unlock_ramlist(); qemu_mutex_unlock_iothread(); + rcu_read_unlock(); + + return 0; +} + +/* Each of ram_save_setup, ram_save_iterate and ram_save_complete has + * long-running RCU critical section. When rcu-reclaims in the code + * start to become numerous it will be necessary to reduce the + * granularity of these critical sections. + */ + +static int ram_save_setup(QEMUFile *f, void *opaque) +{ + RAMBlock *block; + + /* migration has already setup the bitmap, reuse it. */ + if (!migration_in_colo_state()) { + if (ram_save_init_globals() < 0) { + return -1; + } + } + + rcu_read_lock(); qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE); @@ -2048,7 +2064,8 @@ static int ram_save_complete(QEMUFile *f, void *opaque) while (true) { int pages; - pages = ram_find_and_save_block(f, true, &bytes_transferred); + pages = ram_find_and_save_block(f, !migration_in_colo_state(), + &bytes_transferred); /* no more blocks to sent */ if (pages == 0) { break; -- cgit v1.2.1 From 4291d372e22425e6e8b45466b46a051c82ac4ce1 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:43:00 +0800 Subject: COLO: Load VMState into QIOChannelBuffer before restore it We should not destroy the state of SVM (Secondary VM) until we receive the complete data of PVM's state, in case the primary fails in the process of sending the state, so we cache the VM's state in secondary side before load it into SVM. Besides, we should call qemu_system_reset() before load VM state, which can ensure the data is intact. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Gonglei Reviewed-by: Dr. David Alan Gilbert Cc: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 65 insertions(+), 2 deletions(-) (limited to 'migration') diff --git a/migration/colo.c b/migration/colo.c index 9dc54fc7e9..bb9b8703f1 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -115,6 +115,28 @@ static void colo_receive_check_message(QEMUFile *f, COLOMessage expect_msg, } } +static uint64_t colo_receive_message_value(QEMUFile *f, uint32_t expect_msg, + Error **errp) +{ + Error *local_err = NULL; + uint64_t value; + int ret; + + colo_receive_check_message(f, expect_msg, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return 0; + } + + value = qemu_get_be64(f); + ret = qemu_file_get_error(f); + if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to get value for COLO message: %s", + COLOMessage_lookup[expect_msg]); + } + return value; +} + static int colo_do_checkpoint_transaction(MigrationState *s, QIOChannelBuffer *bioc, QEMUFile *fb) @@ -288,6 +310,10 @@ static void colo_wait_handle_message(QEMUFile *f, int *checkpoint_request, void *colo_process_incoming_thread(void *opaque) { MigrationIncomingState *mis = opaque; + QEMUFile *fb = NULL; + QIOChannelBuffer *bioc = NULL; /* Cache incoming device state */ + uint64_t total_size; + uint64_t value; Error *local_err = NULL; migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, @@ -306,6 +332,10 @@ void *colo_process_incoming_thread(void *opaque) */ qemu_file_set_blocking(mis->from_src_file, true); + bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE); + fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc)); + object_unref(OBJECT(bioc)); + colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, &local_err); if (local_err) { @@ -333,7 +363,29 @@ void *colo_process_incoming_thread(void *opaque) goto out; } - /* TODO: read migration data into colo buffer */ + value = colo_receive_message_value(mis->from_src_file, + COLO_MESSAGE_VMSTATE_SIZE, &local_err); + if (local_err) { + goto out; + } + + /* + * Read VM device state data into channel buffer, + * It's better to re-use the memory allocated. + * Here we need to handle the channel buffer directly. + */ + if (value > bioc->capacity) { + bioc->capacity = value; + bioc->data = g_realloc(bioc->data, bioc->capacity); + } + total_size = qemu_get_buffer(mis->from_src_file, bioc->data, value); + if (total_size != value) { + error_report("Got %" PRIu64 " VMState data, less than expected" + " %" PRIu64, total_size, value); + goto out; + } + bioc->usage = total_size; + qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL); colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED, &local_err); @@ -341,7 +393,14 @@ void *colo_process_incoming_thread(void *opaque) goto out; } - /* TODO: load vm state */ + qemu_mutex_lock_iothread(); + qemu_system_reset(VMRESET_SILENT); + if (qemu_loadvm_state(fb) < 0) { + error_report("COLO: loadvm failed"); + qemu_mutex_unlock_iothread(); + goto out; + } + qemu_mutex_unlock_iothread(); colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED, &local_err); @@ -356,6 +415,10 @@ out: error_report_err(local_err); } + if (fb) { + qemu_fclose(fb); + } + if (mis->to_src_file) { qemu_fclose(mis->to_src_file); } -- cgit v1.2.1 From 68b5359187c3d4164cc546dcdd5ba3e37f0ffb55 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:43:01 +0800 Subject: COLO: Add checkpoint-delay parameter for migrate-set-parameters Add checkpoint-delay parameter for migrate-set-parameters, so that we can control the checkpoint frequency when COLO is in periodic mode. Cc: Luiz Capitulino Cc: Eric Blake Cc: Markus Armbruster Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Eric Blake Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/migration.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'migration') diff --git a/migration/migration.c b/migration/migration.c index d8421b5085..d87065a270 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -63,6 +63,11 @@ /* Migration XBZRLE default cache size */ #define DEFAULT_MIGRATE_CACHE_SIZE (64 * 1024 * 1024) +/* The delay time (in ms) between two COLO checkpoints + * Note: Please change this default value to 10000 when we support hybrid mode. + */ +#define DEFAULT_MIGRATE_X_CHECKPOINT_DELAY 200 + static NotifierList migration_state_notifiers = NOTIFIER_LIST_INITIALIZER(migration_state_notifiers); @@ -95,6 +100,7 @@ MigrationState *migrate_get_current(void) .cpu_throttle_increment = DEFAULT_MIGRATE_CPU_THROTTLE_INCREMENT, .max_bandwidth = MAX_THROTTLE, .downtime_limit = DEFAULT_MIGRATE_SET_DOWNTIME, + .x_checkpoint_delay = DEFAULT_MIGRATE_X_CHECKPOINT_DELAY, }, }; @@ -587,6 +593,7 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp) params->max_bandwidth = s->parameters.max_bandwidth; params->has_downtime_limit = true; params->downtime_limit = s->parameters.downtime_limit; + params->x_checkpoint_delay = s->parameters.x_checkpoint_delay; return params; } @@ -845,6 +852,11 @@ void qmp_migrate_set_parameters(MigrationParameters *params, Error **errp) "an integer in the range of 0 to 2000000 milliseconds"); return; } + if (params->has_x_checkpoint_delay && (params->x_checkpoint_delay < 0)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "x_checkpoint_delay", + "is invalid, it should be positive"); + } if (params->has_compress_level) { s->parameters.compress_level = params->compress_level; @@ -879,6 +891,10 @@ void qmp_migrate_set_parameters(MigrationParameters *params, Error **errp) if (params->has_downtime_limit) { s->parameters.downtime_limit = params->downtime_limit; } + + if (params->has_x_checkpoint_delay) { + s->parameters.x_checkpoint_delay = params->x_checkpoint_delay; + } } -- cgit v1.2.1 From 18cc23d72cabf708d5a7e6b5948ec0420a1a2ebd Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:43:02 +0800 Subject: COLO: Synchronize PVM's state to SVM periodically Do checkpoint periodically, the default interval is 200ms. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'migration') diff --git a/migration/colo.c b/migration/colo.c index bb9b8703f1..a35cc59731 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -11,6 +11,7 @@ */ #include "qemu/osdep.h" +#include "qemu/timer.h" #include "sysemu/sysemu.h" #include "migration/colo.h" #include "io/channel-buffer.h" @@ -226,6 +227,7 @@ static void colo_process_checkpoint(MigrationState *s) { QIOChannelBuffer *bioc; QEMUFile *fb = NULL; + int64_t current_time, checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST); Error *local_err = NULL; int ret; @@ -254,10 +256,20 @@ static void colo_process_checkpoint(MigrationState *s) trace_colo_vm_state_change("stop", "run"); while (s->state == MIGRATION_STATUS_COLO) { + current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST); + if (current_time - checkpoint_time < + s->parameters.x_checkpoint_delay) { + int64_t delay_ms; + + delay_ms = s->parameters.x_checkpoint_delay - + (current_time - checkpoint_time); + g_usleep(delay_ms * 1000); + } ret = colo_do_checkpoint_transaction(s, bioc, fb); if (ret < 0) { goto out; } + checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST); } out: -- cgit v1.2.1 From d89e666e0666a0023e4aa6b6b4c4d25d049c5215 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:43:03 +0800 Subject: COLO: Add 'x-colo-lost-heartbeat' command to trigger failover We leave users to choose whatever heartbeat solution they want, if the heartbeat is lost, or other errors they detect, they can use experimental command 'x_colo_lost_heartbeat' to tell COLO to do failover, COLO will do operations accordingly. For example, if the command is sent to the Primary side, the Primary side will exit COLO mode, does cleanup work, and then, PVM will take over the service work. If sent to the Secondary side, the Secondary side will run failover work, then takes over PVM's service work. Cc: Luiz Capitulino Cc: Eric Blake Cc: Markus Armbruster Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/Makefile.objs | 2 +- migration/colo-comm.c | 11 +++++++++++ migration/colo-failover.c | 42 ++++++++++++++++++++++++++++++++++++++++++ migration/colo.c | 1 + 4 files changed, 55 insertions(+), 1 deletion(-) create mode 100644 migration/colo-failover.c (limited to 'migration') diff --git a/migration/Makefile.objs b/migration/Makefile.objs index 4bbe9ab313..3f3e237142 100644 --- a/migration/Makefile.objs +++ b/migration/Makefile.objs @@ -1,7 +1,7 @@ common-obj-y += migration.o socket.o fd.o exec.o common-obj-y += tls.o -common-obj-$(CONFIG_COLO) += colo.o common-obj-y += colo-comm.o +common-obj-$(CONFIG_COLO) += colo.o colo-failover.o common-obj-y += vmstate.o common-obj-y += qemu-file.o common-obj-y += qemu-file-channel.o diff --git a/migration/colo-comm.c b/migration/colo-comm.c index bf44f76440..20b60ec384 100644 --- a/migration/colo-comm.c +++ b/migration/colo-comm.c @@ -21,6 +21,17 @@ typedef struct { 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 void colo_info_pre_save(void *opaque) { COLOInfo *s = opaque; diff --git a/migration/colo-failover.c b/migration/colo-failover.c new file mode 100644 index 0000000000..e31fc10c82 --- /dev/null +++ b/migration/colo-failover.c @@ -0,0 +1,42 @@ +/* + * 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/colo.h" +#include "migration/failover.h" +#include "qmp-commands.h" +#include "qapi/qmp/qerror.h" + +static QEMUBH *failover_bh; + +static void colo_failover_bh(void *opaque) +{ + qemu_bh_delete(failover_bh); + failover_bh = NULL; + /* TODO: Do failover work */ +} + +void failover_request_active(Error **errp) +{ + failover_bh = qemu_bh_new(colo_failover_bh, NULL); + qemu_bh_schedule(failover_bh); +} + +void qmp_x_colo_lost_heartbeat(Error **errp) +{ + if (get_colo_mode() == COLO_MODE_UNKNOWN) { + error_setg(errp, QERR_FEATURE_DISABLED, "colo"); + return; + } + + failover_request_active(errp); +} diff --git a/migration/colo.c b/migration/colo.c index a35cc59731..12fa0b4111 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -18,6 +18,7 @@ #include "trace.h" #include "qemu/error-report.h" #include "qapi/error.h" +#include "migration/failover.h" #define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024) -- cgit v1.2.1 From aef060850bd0e35aa7128e0ae3cef9d62c328314 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:43:04 +0800 Subject: COLO: Introduce state to record failover process When handling failover, COLO processes differently according to the different stage of failover process, here we introduce a global atomic variable to record the status of failover. We add four failover status to indicate the different stage of failover process. You should use the helpers to get and set the value. Signed-off-by: zhanghailiang Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo-failover.c | 41 +++++++++++++++++++++++++++++++++++++++++ migration/colo.c | 4 ++++ migration/trace-events | 1 + 3 files changed, 46 insertions(+) (limited to 'migration') diff --git a/migration/colo-failover.c b/migration/colo-failover.c index e31fc10c82..6cca039eb9 100644 --- a/migration/colo-failover.c +++ b/migration/colo-failover.c @@ -15,22 +15,63 @@ #include "migration/failover.h" #include "qmp-commands.h" #include "qapi/qmp/qerror.h" +#include "qemu/error-report.h" +#include "trace.h" static QEMUBH *failover_bh; +static FailoverStatus failover_state; static void colo_failover_bh(void *opaque) { + int old_state; + qemu_bh_delete(failover_bh); failover_bh = NULL; + + old_state = failover_set_state(FAILOVER_STATUS_REQUIRE, + FAILOVER_STATUS_ACTIVE); + if (old_state != FAILOVER_STATUS_REQUIRE) { + error_report("Unknown error for failover, old_state = %s", + FailoverStatus_lookup[old_state]); + return; + } + /* TODO: Do failover work */ } void failover_request_active(Error **errp) { + if (failover_set_state(FAILOVER_STATUS_NONE, + FAILOVER_STATUS_REQUIRE) != FAILOVER_STATUS_NONE) { + error_setg(errp, "COLO failover is already actived"); + return; + } failover_bh = qemu_bh_new(colo_failover_bh, NULL); qemu_bh_schedule(failover_bh); } +void failover_init_state(void) +{ + failover_state = FAILOVER_STATUS_NONE; +} + +FailoverStatus failover_set_state(FailoverStatus old_state, + FailoverStatus new_state) +{ + FailoverStatus old; + + old = atomic_cmpxchg(&failover_state, old_state, new_state); + if (old == old_state) { + trace_colo_failover_set_state(FailoverStatus_lookup[new_state]); + } + return old; +} + +FailoverStatus failover_get_state(void) +{ + return atomic_read(&failover_state); +} + void qmp_x_colo_lost_heartbeat(Error **errp) { if (get_colo_mode() == COLO_MODE_UNKNOWN) { diff --git a/migration/colo.c b/migration/colo.c index 12fa0b4111..6b32c9183c 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -232,6 +232,8 @@ static void colo_process_checkpoint(MigrationState *s) Error *local_err = NULL; int ret; + failover_init_state(); + s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file); if (!s->rp_state.from_dst_file) { error_report("Open QEMUFile from_dst_file failed"); @@ -332,6 +334,8 @@ void *colo_process_incoming_thread(void *opaque) migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, MIGRATION_STATUS_COLO); + failover_init_state(); + mis->to_src_file = qemu_file_get_return_path(mis->from_src_file); if (!mis->to_src_file) { error_report("COLO incoming thread: Open QEMUFile to_src_file failed"); diff --git a/migration/trace-events b/migration/trace-events index f374c8cf27..94134f700b 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -212,3 +212,4 @@ migration_tls_incoming_handshake_complete(void) "" colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'" colo_send_message(const char *msg) "Send '%s' message" colo_receive_message(const char *msg) "Receive '%s' message" +colo_failover_set_state(const char *new_state) "new state %s" -- cgit v1.2.1 From b3f7f0c5e6449be7275f1762bccbfa2177395a3b Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:43:05 +0800 Subject: COLO: Implement the process of failover for primary VM For primary side, if COLO gets failover request from users. To be exact, gets 'x_colo_lost_heartbeat' command. COLO thread will exit the loop while the failover BH does the cleanup work and resumes VM. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo-failover.c | 2 +- migration/colo.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+), 1 deletion(-) (limited to 'migration') diff --git a/migration/colo-failover.c b/migration/colo-failover.c index 6cca039eb9..cc229f5ab1 100644 --- a/migration/colo-failover.c +++ b/migration/colo-failover.c @@ -36,7 +36,7 @@ static void colo_failover_bh(void *opaque) return; } - /* TODO: Do failover work */ + colo_do_failover(NULL); } void failover_request_active(Error **errp) diff --git a/migration/colo.c b/migration/colo.c index 6b32c9183c..04f7c55a84 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -41,6 +41,40 @@ bool migration_incoming_in_colo_state(void) return mis && (mis->state == MIGRATION_STATUS_COLO); } +static bool colo_runstate_is_stopped(void) +{ + return runstate_check(RUN_STATE_COLO) || !runstate_is_running(); +} + +static void primary_vm_do_failover(void) +{ + MigrationState *s = migrate_get_current(); + int old_state; + + migrate_set_state(&s->state, MIGRATION_STATUS_COLO, + MIGRATION_STATUS_COMPLETED); + + old_state = failover_set_state(FAILOVER_STATUS_ACTIVE, + FAILOVER_STATUS_COMPLETED); + if (old_state != FAILOVER_STATUS_ACTIVE) { + error_report("Incorrect state (%s) while doing failover for Primary VM", + FailoverStatus_lookup[old_state]); + return; + } +} + +void colo_do_failover(MigrationState *s) +{ + /* Make sure VM stopped while failover happened. */ + if (!colo_runstate_is_stopped()) { + vm_stop_force_state(RUN_STATE_COLO); + } + + if (get_colo_mode() == COLO_MODE_PRIMARY) { + primary_vm_do_failover(); + } +} + static void colo_send_message(QEMUFile *f, COLOMessage msg, Error **errp) { @@ -162,9 +196,20 @@ static int colo_do_checkpoint_transaction(MigrationState *s, bioc->usage = 0; qemu_mutex_lock_iothread(); + if (failover_get_state() != FAILOVER_STATUS_NONE) { + qemu_mutex_unlock_iothread(); + goto out; + } vm_stop_force_state(RUN_STATE_COLO); qemu_mutex_unlock_iothread(); trace_colo_vm_state_change("run", "stop"); + /* + * Failover request bh could be called after vm_stop_force_state(), + * So we need check failover_request_is_active() again. + */ + if (failover_get_state() != FAILOVER_STATUS_NONE) { + goto out; + } /* Disable block migration */ s->params.blk = 0; @@ -259,6 +304,11 @@ static void colo_process_checkpoint(MigrationState *s) trace_colo_vm_state_change("stop", "run"); while (s->state == MIGRATION_STATUS_COLO) { + if (failover_get_state() != FAILOVER_STATUS_NONE) { + error_report("failover request"); + goto out; + } + current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST); if (current_time - checkpoint_time < s->parameters.x_checkpoint_delay) { -- cgit v1.2.1 From 9d2db3760be9e32414e22889e3e2bffdf4898f32 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:43:06 +0800 Subject: COLO: Implement failover work for secondary VM If users require SVM to takeover work, COLO incoming thread should exit from loop while failover BH helps backing to migration incoming coroutine. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'migration') diff --git a/migration/colo.c b/migration/colo.c index 04f7c55a84..1f9c699d32 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -46,6 +46,33 @@ static bool colo_runstate_is_stopped(void) return runstate_check(RUN_STATE_COLO) || !runstate_is_running(); } +static void secondary_vm_do_failover(void) +{ + int old_state; + MigrationIncomingState *mis = migration_incoming_get_current(); + + migrate_set_state(&mis->state, MIGRATION_STATUS_COLO, + MIGRATION_STATUS_COMPLETED); + + if (!autostart) { + error_report("\"-S\" qemu option will be ignored in secondary side"); + /* recover runstate to normal migration finish state */ + autostart = true; + } + + old_state = failover_set_state(FAILOVER_STATUS_ACTIVE, + FAILOVER_STATUS_COMPLETED); + if (old_state != FAILOVER_STATUS_ACTIVE) { + error_report("Incorrect state (%s) while doing failover for " + "secondary VM", FailoverStatus_lookup[old_state]); + return; + } + /* For Secondary VM, jump to incoming co */ + if (mis->migration_incoming_co) { + qemu_coroutine_enter(mis->migration_incoming_co); + } +} + static void primary_vm_do_failover(void) { MigrationState *s = migrate_get_current(); @@ -72,6 +99,8 @@ void colo_do_failover(MigrationState *s) if (get_colo_mode() == COLO_MODE_PRIMARY) { primary_vm_do_failover(); + } else { + secondary_vm_do_failover(); } } @@ -417,6 +446,11 @@ void *colo_process_incoming_thread(void *opaque) goto out; } assert(request); + if (failover_get_state() != FAILOVER_STATUS_NONE) { + error_report("failover request"); + goto out; + } + /* FIXME: This is unnecessary for periodic checkpoint mode */ colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY, &local_err); -- cgit v1.2.1 From 180fb750004ffd99e20300d9d2eaa4e5f5adae72 Mon Sep 17 00:00:00 2001 From: zhanghailiang Date: Thu, 27 Oct 2016 14:43:08 +0800 Subject: configure: Support enable/disable COLO feature configure --enable-colo/--disable-colo to switch COLO support on/off. COLO feature doesn't depend on any other external libraries, So here it is reasonable to enable COLO by default, to avoid re-compile QEMU if users want to use this capability. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Gonglei Reviewed-by: Dr. David Alan Gilbert Reviewed-by: Amit Shah Signed-off-by: Amit Shah --- migration/colo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'migration') diff --git a/migration/colo.c b/migration/colo.c index 1f9c699d32..e7224b8a0a 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -24,7 +24,7 @@ bool colo_supported(void) { - return false; + return true; } bool migration_in_colo_state(void) -- cgit v1.2.1