From 3d661c8ab18ad2013992c622ab307422ace891a2 Mon Sep 17 00:00:00 2001 From: Yury Kotov Date: Mon, 22 Apr 2019 13:34:20 +0300 Subject: migration: Add error_desc for file channel errors Currently, there is no information about error if outgoing migration was failed because of file channel errors. Example (QMP session): -> { "execute": "migrate", "arguments": { "uri": "exec:head -c 1" }} <- { "return": {} } ... -> { "execute": "query-migrate" } <- { "return": { "status": "failed" }} // There is not error's description And even in the QEMU's output there is nothing. This patch 1) Adds errp for the most of QEMUFileOps 2) Adds qemu_file_get_error_obj/qemu_file_set_error_obj 3) And finally using of qemu_file_get_error_obj in migration.c And now, the status for the mentioned fail will be: -> { "execute": "query-migrate" } <- { "return": { "status": "failed", "error-desc": "Unable to write to command: Broken pipe" }} Signed-off-by: Yury Kotov Message-Id: <20190422103420.15686-1-yury-kotov@yandex-team.ru> Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Dr. David Alan Gilbert --- migration/migration.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'migration/migration.c') diff --git a/migration/migration.c b/migration/migration.c index 8a607fe1e2..28342969ea 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -2963,6 +2963,7 @@ static MigThrError migration_detect_error(MigrationState *s) { int ret; int state = s->state; + Error *local_error = NULL; if (state == MIGRATION_STATUS_CANCELLING || state == MIGRATION_STATUS_CANCELLED) { @@ -2971,13 +2972,18 @@ static MigThrError migration_detect_error(MigrationState *s) } /* Try to detect any file errors */ - ret = qemu_file_get_error(s->to_dst_file); - + ret = qemu_file_get_error_obj(s->to_dst_file, &local_error); if (!ret) { /* Everything is fine */ + assert(!local_error); return MIG_THR_ERR_NONE; } + if (local_error) { + migrate_set_error(s, local_error); + error_free(local_error); + } + if (state == MIGRATION_STATUS_POSTCOPY_ACTIVE && ret == -EIO) { /* * For postcopy, we allow the network to be down for a -- cgit 1.4.1 From 640dfb14db919462dedc1b4fa0feaaf99a0bff42 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 16 Jul 2019 08:54:11 +0800 Subject: migration: consolidate time info into populate_time_info Consolidate time information fill up into its function for better readability. Signed-off-by: Wei Yang Message-Id: <20190716005411.4156-1-richardw.yang@linux.intel.com> Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Dr. David Alan Gilbert --- migration/migration.c | 40 ++++++++++++++++++++++------------------ 1 file changed, 22 insertions(+), 18 deletions(-) (limited to 'migration/migration.c') diff --git a/migration/migration.c b/migration/migration.c index 28342969ea..7c66da3a83 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -823,6 +823,25 @@ bool migration_is_setup_or_active(int state) } } +static void populate_time_info(MigrationInfo *info, MigrationState *s) +{ + info->has_status = true; + info->has_setup_time = true; + info->setup_time = s->setup_time; + if (s->state == MIGRATION_STATUS_COMPLETED) { + info->has_total_time = true; + info->total_time = s->total_time; + info->has_downtime = true; + info->downtime = s->downtime; + } else { + info->has_total_time = true; + info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) - + s->start_time; + info->has_expected_downtime = true; + info->expected_downtime = s->expected_downtime; + } +} + static void populate_ram_info(MigrationInfo *info, MigrationState *s) { info->has_ram = true; @@ -908,16 +927,8 @@ static void fill_source_migration_info(MigrationInfo *info) case MIGRATION_STATUS_DEVICE: case MIGRATION_STATUS_POSTCOPY_PAUSED: case MIGRATION_STATUS_POSTCOPY_RECOVER: - /* TODO add some postcopy stats */ - info->has_status = true; - info->has_total_time = true; - info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) - - s->start_time; - info->has_expected_downtime = true; - info->expected_downtime = s->expected_downtime; - info->has_setup_time = true; - info->setup_time = s->setup_time; - + /* TODO add some postcopy stats */ + populate_time_info(info, s); populate_ram_info(info, s); populate_disk_info(info); break; @@ -926,14 +937,7 @@ static void fill_source_migration_info(MigrationInfo *info) /* TODO: display COLO specific information (checkpoint info etc.) */ break; case MIGRATION_STATUS_COMPLETED: - info->has_status = true; - info->has_total_time = true; - info->total_time = s->total_time; - info->has_downtime = true; - info->downtime = s->downtime; - info->has_setup_time = true; - info->setup_time = s->setup_time; - + populate_time_info(info, s); populate_ram_info(info, s); break; case MIGRATION_STATUS_FAILED: -- cgit 1.4.1 From 52aec70923a19e73f7ecf5da484a9fd1b07634f5 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 18 Jul 2019 16:37:47 +0800 Subject: migration/postcopy: start_postcopy could be true only when migrate_postcopy() return true There is only one place to set start_postcopy to true, qmp_migrate_start_postcopy(), which make sure start_postcopy could be set to true when migrate_postcopy() return true. So start_postcopy is true implies the other one. Signed-off-by: Wei Yang Message-Id: <20190718083747.5859-1-richardw.yang@linux.intel.com> Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Dr. David Alan Gilbert --- migration/migration.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'migration/migration.c') diff --git a/migration/migration.c b/migration/migration.c index 7c66da3a83..8331e62831 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -3103,8 +3103,7 @@ static MigIterateState migration_iteration_run(MigrationState *s) if (pending_size && pending_size >= s->threshold_size) { /* Still a significant amount to transfer */ - if (migrate_postcopy() && !in_postcopy && - pend_pre <= s->threshold_size && + if (!in_postcopy && pend_pre <= s->threshold_size && atomic_read(&s->start_postcopy)) { if (postcopy_start(s)) { error_report("%s: postcopy failed to start", __func__); -- cgit 1.4.1 From 14adf288d3a1617bf9ccf2da346b2b002a07d8f2 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 2 Apr 2019 08:31:06 +0800 Subject: migration: remove unused field bytes_xfer MigrationState->bytes_xfer is only set to 0 in migrate_init(). Remove this unnecessary field. Signed-off-by: Wei Yang Message-Id: <20190402003106.17614-1-richardw.yang@linux.intel.com> Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Dr. David Alan Gilbert --- migration/migration.c | 1 - migration/migration.h | 1 - 2 files changed, 2 deletions(-) (limited to 'migration/migration.c') diff --git a/migration/migration.c b/migration/migration.c index 8331e62831..12b8e5dbe5 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -1699,7 +1699,6 @@ void migrate_init(MigrationState *s) * parameters/capabilities that the user set, and * locks. */ - s->bytes_xfer = 0; s->cleanup_bh = 0; s->to_dst_file = NULL; s->state = MIGRATION_STATUS_NONE; diff --git a/migration/migration.h b/migration/migration.h index 1fdd7b21fd..5bc60709db 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -132,7 +132,6 @@ struct MigrationState DeviceState parent_obj; /*< public >*/ - size_t bytes_xfer; QemuThread thread; QEMUBH *cleanup_bh; QEMUFile *to_dst_file; -- cgit 1.4.1 From 87f3bd8717cd88932de302e215f1da51bfb8051a Mon Sep 17 00:00:00 2001 From: Ivan Ren Date: Fri, 2 Aug 2019 18:18:41 +0800 Subject: migration: always initialise ram_counters for a new migration This patch fix a multifd migration bug in migration speed calculation, this problem can be reproduced as follows: 1. start a vm and give a heavy memory write stress to prevent the vm be successfully migrated to destination 2. begin a migration with multifd 3. migrate for a long time [actually, this can be measured by transferred bytes] 4. migrate cancel 5. begin a new migration with multifd, the migration will directly run into migration_completion phase Reason as follows: Migration update bandwidth and s->threshold_size in function migration_update_counters after BUFFER_DELAY time: current_bytes = migration_total_bytes(s); transferred = current_bytes - s->iteration_initial_bytes; time_spent = current_time - s->iteration_start_time; bandwidth = (double)transferred / time_spent; s->threshold_size = bandwidth * s->parameters.downtime_limit; In multifd migration, migration_total_bytes function return qemu_ftell(s->to_dst_file) + ram_counters.multifd_bytes. s->iteration_initial_bytes will be initialized to 0 at every new migration, but ram_counters is a global variable, and history migration data will be accumulated. So if the ram_counters.multifd_bytes is big enough, it may lead pending_size >= s->threshold_size become false in migration_iteration_run after the first migration_update_counters. Signed-off-by: Ivan Ren Reviewed-by: Juan Quintela Reviewed-by: Wei Yang Suggested-by: Wei Yang Message-Id: <1564741121-1840-1-git-send-email-ivanren@tencent.com> Signed-off-by: Dr. David Alan Gilbert --- migration/migration.c | 25 +++++++++++++++++++------ migration/savevm.c | 1 + 2 files changed, 20 insertions(+), 6 deletions(-) (limited to 'migration/migration.c') diff --git a/migration/migration.c b/migration/migration.c index 12b8e5dbe5..c49e9dc035 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -1911,6 +1911,11 @@ static bool migrate_prepare(MigrationState *s, bool blk, bool blk_inc, } migrate_init(s); + /* + * set ram_counters memory to zero for a + * new migration + */ + memset(&ram_counters, 0, sizeof(ram_counters)); return true; } @@ -3034,6 +3039,17 @@ static void migration_calculate_complete(MigrationState *s) } } +static void update_iteration_initial_status(MigrationState *s) +{ + /* + * Update these three fields at the same time to avoid mismatch info lead + * wrong speed calculation. + */ + s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + s->iteration_initial_bytes = migration_total_bytes(s); + s->iteration_initial_pages = ram_get_total_transferred_pages(); +} + static void migration_update_counters(MigrationState *s, int64_t current_time) { @@ -3069,9 +3085,7 @@ static void migration_update_counters(MigrationState *s, qemu_file_reset_rate_limit(s->to_dst_file); - s->iteration_start_time = current_time; - s->iteration_initial_bytes = current_bytes; - s->iteration_initial_pages = ram_get_total_transferred_pages(); + update_iteration_initial_status(s); trace_migrate_transferred(transferred, time_spent, bandwidth, s->threshold_size); @@ -3194,7 +3208,7 @@ static void *migration_thread(void *opaque) rcu_register_thread(); object_ref(OBJECT(s)); - s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + update_iteration_initial_status(s); qemu_savevm_state_header(s->to_dst_file); @@ -3259,8 +3273,7 @@ static void *migration_thread(void *opaque) * the local variables. This is important to avoid * breaking transferred_bytes and bandwidth calculation */ - s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); - s->iteration_initial_bytes = 0; + update_iteration_initial_status(s); } current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); diff --git a/migration/savevm.c b/migration/savevm.c index 412768216c..1ac15301ad 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1456,6 +1456,7 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp) } migrate_init(ms); + memset(&ram_counters, 0, sizeof(ram_counters)); ms->to_dst_file = f; qemu_mutex_unlock_iothread(); -- cgit 1.4.1