diff options
author | Peter Xu <peterx@redhat.com> | 2018-05-02 18:47:20 +0800 |
---|---|---|
committer | Juan Quintela <quintela@redhat.com> | 2018-05-15 20:24:27 +0200 |
commit | b411b844fb2e038c6ba92fd50fed3213a27c6445 (patch) | |
tree | 62a1cf5d1b36d66bdc16d97a93d50315e295077f /migration | |
parent | b23c2ade250718fe77b51e116f95f3c34c8a4c24 (diff) | |
download | qemu-b411b844fb2e038c6ba92fd50fed3213a27c6445.zip qemu-b411b844fb2e038c6ba92fd50fed3213a27c6445.tar.gz qemu-b411b844fb2e038c6ba92fd50fed3213a27c6445.tar.bz2 |
migration: allow dst vm pause on postcopy
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.
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20180502104740.12123-5-peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Diffstat (limited to 'migration')
-rw-r--r-- | migration/migration.c | 1 | ||||
-rw-r--r-- | migration/migration.h | 3 | ||||
-rw-r--r-- | migration/savevm.c | 63 | ||||
-rw-r--r-- | migration/trace-events | 2 |
4 files changed, 67 insertions, 2 deletions
diff --git a/migration/migration.c b/migration/migration.c index 8392cf4..4a7c02f 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -159,6 +159,7 @@ MigrationIncomingState *migration_incoming_get_current(void) sizeof(struct PostCopyFD)); 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); init_dirty_bitmap_incoming_migration(); diff --git a/migration/migration.h b/migration/migration.h index 60283c3..0ccdcb8 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -73,6 +73,9 @@ struct MigrationIncomingState { * live migration, to calculate vCPU block time * */ struct PostcopyBlocktimeContext *blocktime_ctx; + + /* 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 e2be02a..8ad99b1 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1564,8 +1564,8 @@ 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, @@ -1579,6 +1579,14 @@ 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); @@ -1668,7 +1676,7 @@ 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); @@ -2055,11 +2063,44 @@ 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); @@ -2104,6 +2145,24 @@ 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 409b4b8..e23ec01 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) "" |