Message ID | 20171205065307.21853-7-peterx@redhat.com |
---|---|
State | New |
Headers | show |
Series | [v5,01/28] migration: better error handling with QEMUFile | expand |
* Peter Xu (peterx@redhat.com) wrote: > When there is IO error on the incoming channel (e.g., network down), > instead of bailing out immediately, we allow the dst vm to switch to the > new POSTCOPY_PAUSE state. Currently it is still simple - it waits the > new semaphore, until someone poke it for another attempt. > > One note is that here on ram loading thread we cannot detect the > POSTCOPY_ACTIVE state, but we need to detect the more specific > POSTCOPY_INCOMING_RUNNING state, to make sure we have already loaded all > the device states. > > Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> > --- > migration/migration.c | 1 + > migration/migration.h | 3 +++ > migration/savevm.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++-- > migration/trace-events | 2 ++ > 4 files changed, 67 insertions(+), 2 deletions(-) > > diff --git a/migration/migration.c b/migration/migration.c > index f69a48ac63..6f0d48bbed 100644 > --- a/migration/migration.c > +++ b/migration/migration.c > @@ -150,6 +150,7 @@ MigrationIncomingState *migration_incoming_get_current(void) > memset(&mis_current, 0, sizeof(MigrationIncomingState)); > qemu_mutex_init(&mis_current.rp_mutex); > qemu_event_init(&mis_current.main_thread_load_event, false); > + qemu_sem_init(&mis_current.postcopy_pause_sem_dst, 0); > once = true; > } > return &mis_current; > diff --git a/migration/migration.h b/migration/migration.h > index 36aaa13f50..55894ecb79 100644 > --- a/migration/migration.h > +++ b/migration/migration.h > @@ -61,6 +61,9 @@ struct MigrationIncomingState { > /* The coroutine we should enter (back) after failover */ > Coroutine *migration_incoming_co; > QemuSemaphore colo_incoming_sem; > + > + /* notify PAUSED postcopy incoming migrations to try to continue */ > + QemuSemaphore postcopy_pause_sem_dst; > }; > > MigrationIncomingState *migration_incoming_get_current(void); > diff --git a/migration/savevm.c b/migration/savevm.c > index 8814793255..1e5fc4f332 100644 > --- a/migration/savevm.c > +++ b/migration/savevm.c > @@ -1529,8 +1529,8 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, > */ > static void *postcopy_ram_listen_thread(void *opaque) > { > - QEMUFile *f = opaque; > MigrationIncomingState *mis = migration_incoming_get_current(); > + QEMUFile *f = mis->from_src_file; > int load_res; > > migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, > @@ -1544,6 +1544,14 @@ static void *postcopy_ram_listen_thread(void *opaque) > */ > qemu_file_set_blocking(f, true); > load_res = qemu_loadvm_state_main(f, mis); > + > + /* > + * This is tricky, but, mis->from_src_file can change after it > + * returns, when postcopy recovery happened. In the future, we may > + * want a wrapper for the QEMUFile handle. > + */ > + f = mis->from_src_file; > + > /* And non-blocking again so we don't block in any cleanup */ > qemu_file_set_blocking(f, false); > > @@ -1626,7 +1634,7 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) > /* Start up the listening thread and wait for it to signal ready */ > qemu_sem_init(&mis->listen_thread_sem, 0); > qemu_thread_create(&mis->listen_thread, "postcopy/listen", > - postcopy_ram_listen_thread, mis->from_src_file, > + postcopy_ram_listen_thread, NULL, > QEMU_THREAD_DETACHED); > qemu_sem_wait(&mis->listen_thread_sem); > qemu_sem_destroy(&mis->listen_thread_sem); > @@ -2011,11 +2019,44 @@ void qemu_loadvm_state_cleanup(void) > } > } > > +/* Return true if we should continue the migration, or false. */ > +static bool postcopy_pause_incoming(MigrationIncomingState *mis) > +{ > + trace_postcopy_pause_incoming(); > + > + migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE, > + MIGRATION_STATUS_POSTCOPY_PAUSED); > + > + assert(mis->from_src_file); > + qemu_file_shutdown(mis->from_src_file); > + qemu_fclose(mis->from_src_file); > + mis->from_src_file = NULL; > + > + assert(mis->to_src_file); > + qemu_file_shutdown(mis->to_src_file); > + qemu_mutex_lock(&mis->rp_mutex); > + qemu_fclose(mis->to_src_file); > + mis->to_src_file = NULL; > + qemu_mutex_unlock(&mis->rp_mutex); > + > + error_report("Detected IO failure for postcopy. " > + "Migration paused."); > + > + while (mis->state == MIGRATION_STATUS_POSTCOPY_PAUSED) { > + qemu_sem_wait(&mis->postcopy_pause_sem_dst); > + } > + > + trace_postcopy_pause_incoming_continued(); > + > + return true; > +} > + > static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) > { > uint8_t section_type; > int ret = 0; > > +retry: > while (true) { > section_type = qemu_get_byte(f); > > @@ -2060,6 +2101,24 @@ static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) > out: > if (ret < 0) { > qemu_file_set_error(f, ret); > + > + /* > + * Detect whether it is: > + * > + * 1. postcopy running (after receiving all device data, which > + * must be in POSTCOPY_INCOMING_RUNNING state. Note that > + * POSTCOPY_INCOMING_LISTENING is still not enough, it's > + * still receiving device states). > + * 2. network failure (-EIO) > + * > + * If so, we try to wait for a recovery. > + */ > + if (postcopy_state_get() == POSTCOPY_INCOMING_RUNNING && > + ret == -EIO && postcopy_pause_incoming(mis)) { > + /* Reset f to point to the newly created channel */ > + f = mis->from_src_file; > + goto retry; > + } > } > return ret; > } > diff --git a/migration/trace-events b/migration/trace-events > index da1c63a933..bed1646cd6 100644 > --- a/migration/trace-events > +++ b/migration/trace-events > @@ -100,6 +100,8 @@ open_return_path_on_source(void) "" > open_return_path_on_source_continue(void) "" > postcopy_start(void) "" > postcopy_pause_continued(void) "" > +postcopy_pause_incoming(void) "" > +postcopy_pause_incoming_continued(void) "" > postcopy_start_set_run(void) "" > source_return_path_thread_bad_end(void) "" > source_return_path_thread_end(void) "" > -- > 2.14.3 > -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
diff --git a/migration/migration.c b/migration/migration.c index f69a48ac63..6f0d48bbed 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -150,6 +150,7 @@ MigrationIncomingState *migration_incoming_get_current(void) memset(&mis_current, 0, sizeof(MigrationIncomingState)); qemu_mutex_init(&mis_current.rp_mutex); qemu_event_init(&mis_current.main_thread_load_event, false); + qemu_sem_init(&mis_current.postcopy_pause_sem_dst, 0); once = true; } return &mis_current; diff --git a/migration/migration.h b/migration/migration.h index 36aaa13f50..55894ecb79 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -61,6 +61,9 @@ struct MigrationIncomingState { /* The coroutine we should enter (back) after failover */ Coroutine *migration_incoming_co; QemuSemaphore colo_incoming_sem; + + /* notify PAUSED postcopy incoming migrations to try to continue */ + QemuSemaphore postcopy_pause_sem_dst; }; MigrationIncomingState *migration_incoming_get_current(void); diff --git a/migration/savevm.c b/migration/savevm.c index 8814793255..1e5fc4f332 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1529,8 +1529,8 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, */ static void *postcopy_ram_listen_thread(void *opaque) { - QEMUFile *f = opaque; MigrationIncomingState *mis = migration_incoming_get_current(); + QEMUFile *f = mis->from_src_file; int load_res; migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, @@ -1544,6 +1544,14 @@ static void *postcopy_ram_listen_thread(void *opaque) */ qemu_file_set_blocking(f, true); load_res = qemu_loadvm_state_main(f, mis); + + /* + * This is tricky, but, mis->from_src_file can change after it + * returns, when postcopy recovery happened. In the future, we may + * want a wrapper for the QEMUFile handle. + */ + f = mis->from_src_file; + /* And non-blocking again so we don't block in any cleanup */ qemu_file_set_blocking(f, false); @@ -1626,7 +1634,7 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) /* Start up the listening thread and wait for it to signal ready */ qemu_sem_init(&mis->listen_thread_sem, 0); qemu_thread_create(&mis->listen_thread, "postcopy/listen", - postcopy_ram_listen_thread, mis->from_src_file, + postcopy_ram_listen_thread, NULL, QEMU_THREAD_DETACHED); qemu_sem_wait(&mis->listen_thread_sem); qemu_sem_destroy(&mis->listen_thread_sem); @@ -2011,11 +2019,44 @@ void qemu_loadvm_state_cleanup(void) } } +/* Return true if we should continue the migration, or false. */ +static bool postcopy_pause_incoming(MigrationIncomingState *mis) +{ + trace_postcopy_pause_incoming(); + + migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE, + MIGRATION_STATUS_POSTCOPY_PAUSED); + + assert(mis->from_src_file); + qemu_file_shutdown(mis->from_src_file); + qemu_fclose(mis->from_src_file); + mis->from_src_file = NULL; + + assert(mis->to_src_file); + qemu_file_shutdown(mis->to_src_file); + qemu_mutex_lock(&mis->rp_mutex); + qemu_fclose(mis->to_src_file); + mis->to_src_file = NULL; + qemu_mutex_unlock(&mis->rp_mutex); + + error_report("Detected IO failure for postcopy. " + "Migration paused."); + + while (mis->state == MIGRATION_STATUS_POSTCOPY_PAUSED) { + qemu_sem_wait(&mis->postcopy_pause_sem_dst); + } + + trace_postcopy_pause_incoming_continued(); + + return true; +} + static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) { uint8_t section_type; int ret = 0; +retry: while (true) { section_type = qemu_get_byte(f); @@ -2060,6 +2101,24 @@ static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) out: if (ret < 0) { qemu_file_set_error(f, ret); + + /* + * Detect whether it is: + * + * 1. postcopy running (after receiving all device data, which + * must be in POSTCOPY_INCOMING_RUNNING state. Note that + * POSTCOPY_INCOMING_LISTENING is still not enough, it's + * still receiving device states). + * 2. network failure (-EIO) + * + * If so, we try to wait for a recovery. + */ + if (postcopy_state_get() == POSTCOPY_INCOMING_RUNNING && + ret == -EIO && postcopy_pause_incoming(mis)) { + /* Reset f to point to the newly created channel */ + f = mis->from_src_file; + goto retry; + } } return ret; } diff --git a/migration/trace-events b/migration/trace-events index da1c63a933..bed1646cd6 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -100,6 +100,8 @@ open_return_path_on_source(void) "" open_return_path_on_source_continue(void) "" postcopy_start(void) "" postcopy_pause_continued(void) "" +postcopy_pause_incoming(void) "" +postcopy_pause_incoming_continued(void) "" postcopy_start_set_run(void) "" source_return_path_thread_bad_end(void) "" source_return_path_thread_end(void) ""
When there is IO error on the incoming channel (e.g., network down), instead of bailing out immediately, we allow the dst vm to switch to the new POSTCOPY_PAUSE state. Currently it is still simple - it waits the new semaphore, until someone poke it for another attempt. One note is that here on ram loading thread we cannot detect the POSTCOPY_ACTIVE state, but we need to detect the more specific POSTCOPY_INCOMING_RUNNING state, to make sure we have already loaded all the device states. Signed-off-by: Peter Xu <peterx@redhat.com> --- migration/migration.c | 1 + migration/migration.h | 3 +++ migration/savevm.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++-- migration/trace-events | 2 ++ 4 files changed, 67 insertions(+), 2 deletions(-)