From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:60712) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bUvGI-0000e4-AX for qemu-devel@nongnu.org; Wed, 03 Aug 2016 08:27:05 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bUvGG-0006Zb-VC for qemu-devel@nongnu.org; Wed, 03 Aug 2016 08:27:02 -0400 Received: from szxga01-in.huawei.com ([58.251.152.64]:30619) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bUvGG-0006YN-5s for qemu-devel@nongnu.org; Wed, 03 Aug 2016 08:27:00 -0400 From: zhanghailiang Date: Wed, 3 Aug 2016 20:25:56 +0800 Message-ID: <1470227172-13704-19-git-send-email-zhang.zhanghailiang@huawei.com> In-Reply-To: <1470227172-13704-1-git-send-email-zhang.zhanghailiang@huawei.com> References: <1470227172-13704-1-git-send-email-zhang.zhanghailiang@huawei.com> MIME-Version: 1.0 Content-Type: text/plain Subject: [Qemu-devel] [PATCH COLO-Frame v18 18/34] COLO: Implement failover work for Primary VM List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: amit.shah@redhat.com, quintela@redhat.com, dgilbert@redhat.com, peter.huangpeng@huawei.com, eddie.dong@intel.com, wency@cn.fujitsu.com, lizhijian@cn.fujitsu.com, zhangchen.fnst@cn.fujitsu.com, xiecl.fnst@cn.fujitsu.com, zhanghailiang For PVM, if there is failover request from users. The 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 --- v13: - Add Reviewed-by tag v12: - Fix error report and remove unnecessary check in primary_vm_do_failover() (Dave's suggestion) v11: - Don't call migration_end() in primary_vm_do_failover(), The cleanup work will be done in migration_thread(). - Remove vm_start() in primary_vm_do_failover() which also been done in migraiton_thread() v10: - Call migration_end() in primary_vm_do_failover() --- include/migration/colo.h | 3 +++ include/migration/failover.h | 1 + migration/colo-failover.c | 7 +++++- migration/colo.c | 54 ++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 62 insertions(+), 3 deletions(-) diff --git a/include/migration/colo.h b/include/migration/colo.h index e9ac2c3..e32eef4 100644 --- a/include/migration/colo.h +++ b/include/migration/colo.h @@ -32,4 +32,7 @@ void *colo_process_incoming_thread(void *opaque); bool migration_incoming_in_colo_state(void); COLOMode get_colo_mode(void); + +/* failover */ +void colo_do_failover(MigrationState *s); #endif diff --git a/include/migration/failover.h b/include/migration/failover.h index fe71bb4..c4bd81e 100644 --- a/include/migration/failover.h +++ b/include/migration/failover.h @@ -26,5 +26,6 @@ void failover_init_state(void); int failover_set_state(int old_state, int new_state); int failover_get_state(void); void failover_request_active(Error **errp); +bool failover_request_is_active(void); #endif diff --git a/migration/colo-failover.c b/migration/colo-failover.c index 69aac55..fa84172 100644 --- a/migration/colo-failover.c +++ b/migration/colo-failover.c @@ -33,7 +33,7 @@ static void colo_failover_bh(void *opaque) error_report("Unkown error for failover, old_state=%d", old_state); return; } - /*TODO: Do failover work */ + colo_do_failover(NULL); } void failover_request_active(Error **errp) @@ -68,6 +68,11 @@ int failover_get_state(void) return atomic_read(&failover_state); } +bool failover_request_is_active(void) +{ + return failover_get_state() != FAILOVER_STATUS_NONE; +} + 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 9afc527..a4fe334 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_HANDLING, + FAILOVER_STATUS_COMPLETED); + if (old_state != FAILOVER_STATUS_HANDLING) { + error_report("Incorrect state (%d) while doing failover for Primary VM", + 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_request_is_active()) { + 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_request_is_active()) { + 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_request_is_active()) { + 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) { @@ -280,9 +330,9 @@ out: if (local_err) { error_report_err(local_err); } - migrate_set_state(&s->state, MIGRATION_STATUS_COLO, - MIGRATION_STATUS_COMPLETED); + qemu_fclose(fb); + if (s->rp_state.from_dst_file) { qemu_fclose(s->rp_state.from_dst_file); } -- 1.8.3.1