[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH V10 05/20] COLO: Add block replication into colo
From: |
Dr. David Alan Gilbert |
Subject: |
Re: [Qemu-devel] [PATCH V10 05/20] COLO: Add block replication into colo process |
Date: |
Fri, 17 Aug 2018 12:07:09 +0100 |
User-agent: |
Mutt/1.10.1 (2018-07-13) |
* Zhang Chen (address@hidden) wrote:
> On Tue, Aug 7, 2018 at 10:30 PM Dr. David Alan Gilbert <address@hidden>
> wrote:
>
> > * Zhang Chen (address@hidden) wrote:
> > > Make sure master start block replication after slave's block
> > > replication started.
> > >
> > > Besides, we need to activate VM's blocks before goes into
> > > COLO state.
> > >
> > > Signed-off-by: zhanghailiang <address@hidden>
> > > Signed-off-by: Li Zhijian <address@hidden>
> > > Signed-off-by: Zhang Chen <address@hidden>
> > > ---
> > > migration/colo.c | 43 +++++++++++++++++++++++++++++++++++++++++++
> > > migration/migration.c | 9 +++++++++
> > > 2 files changed, 52 insertions(+)
> > >
> > > diff --git a/migration/colo.c b/migration/colo.c
> > > index 081df1835f..e06640c3d6 100644
> > > --- a/migration/colo.c
> > > +++ b/migration/colo.c
> > > @@ -27,6 +27,7 @@
> > > #include "replication.h"
> > > #include "net/colo-compare.h"
> > > #include "net/colo.h"
> > > +#include "block/block.h"
> > >
> > > static bool vmstate_loading;
> > > static Notifier packets_compare_notifier;
> > > @@ -56,6 +57,7 @@ static void secondary_vm_do_failover(void)
> > > {
> > > int old_state;
> > > MigrationIncomingState *mis = migration_incoming_get_current();
> > > + Error *local_err = NULL;
> > >
> > > /* Can not do failover during the process of VM's loading VMstate,
> > Or
> > > * it will break the secondary VM.
> > > @@ -73,6 +75,11 @@ static void secondary_vm_do_failover(void)
> > > migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
> > > MIGRATION_STATUS_COMPLETED);
> > >
> > > + replication_stop_all(true, &local_err);
> > > + if (local_err) {
> > > + error_report_err(local_err);
> > > + }
> > > +
> > > if (!autostart) {
> > > error_report("\"-S\" qemu option will be ignored in secondary
> > side");
> > > /* recover runstate to normal migration finish state */
> > > @@ -110,6 +117,7 @@ static void primary_vm_do_failover(void)
> > > {
> > > MigrationState *s = migrate_get_current();
> > > int old_state;
> > > + Error *local_err = NULL;
> > >
> > > migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
> > > MIGRATION_STATUS_COMPLETED);
> > > @@ -133,6 +141,13 @@ static void primary_vm_do_failover(void)
> > > FailoverStatus_str(old_state));
> > > return;
> > > }
> > > +
> > > + replication_stop_all(true, &local_err);
> > > + if (local_err) {
> > > + error_report_err(local_err);
> > > + local_err = NULL;
> > > + }
> > > +
> > > /* Notify COLO thread that failover work is finished */
> > > qemu_sem_post(&s->colo_exit_sem);
> > > }
> > > @@ -356,6 +371,11 @@ static int
> > colo_do_checkpoint_transaction(MigrationState *s,
> > > qemu_savevm_state_header(fb);
> > > qemu_savevm_state_setup(fb);
> > > qemu_mutex_lock_iothread();
> > > + replication_do_checkpoint_all(&local_err);
> > > + if (local_err) {
> > > + qemu_mutex_unlock_iothread();
> > > + goto out;
> > > + }
> >
> > In docs/block-replication.txt it says:
> > b. replication_do_checkpoint_all()
> > This interface is called after all VM state is transferred to
> > Secondary QEMU. The Disk buffer will be dropped in this interface.
> > The caller must hold the I/O mutex lock if it is in migration/checkpoint
> > thread.
> >
> > but we're making this call before the call below that actually transfers
> > all the state. Which is right?
> >
>
> Hi Dave,
>
> The "docs/block-replication.txt" means we should call the
> replication_do_checkpoint_all() after VM state is transferred in secondary
> node,
> and in primary node this function no need to call before transfers all the
> state.
OK, it might be worth clarifying the docs.
Dave
> Thanks
> Zhang Chen
>
>
>
> >
> > Other than that I think it's OK.
> >
> > Dave
> >
> > > qemu_savevm_state_complete_precopy(fb, false, false);
> > > qemu_mutex_unlock_iothread();
> > >
> > > @@ -446,6 +466,12 @@ static void colo_process_checkpoint(MigrationState
> > *s)
> > > object_unref(OBJECT(bioc));
> > >
> > > qemu_mutex_lock_iothread();
> > > + replication_start_all(REPLICATION_MODE_PRIMARY, &local_err);
> > > + if (local_err) {
> > > + qemu_mutex_unlock_iothread();
> > > + goto out;
> > > + }
> > > +
> > > vm_start();
> > > qemu_mutex_unlock_iothread();
> > > trace_colo_vm_state_change("stop", "run");
> > > @@ -585,6 +611,11 @@ void *colo_process_incoming_thread(void *opaque)
> > > object_unref(OBJECT(bioc));
> > >
> > > qemu_mutex_lock_iothread();
> > > + replication_start_all(REPLICATION_MODE_SECONDARY, &local_err);
> > > + if (local_err) {
> > > + qemu_mutex_unlock_iothread();
> > > + goto out;
> > > + }
> > > vm_start();
> > > trace_colo_vm_state_change("stop", "run");
> > > qemu_mutex_unlock_iothread();
> > > @@ -665,6 +696,18 @@ void *colo_process_incoming_thread(void *opaque)
> > > goto out;
> > > }
> > >
> > > + replication_get_error_all(&local_err);
> > > + if (local_err) {
> > > + qemu_mutex_unlock_iothread();
> > > + goto out;
> > > + }
> > > + /* discard colo disk buffer */
> > > + replication_do_checkpoint_all(&local_err);
> > > + if (local_err) {
> > > + qemu_mutex_unlock_iothread();
> > > + goto out;
> > > + }
> > > +
> > > vmstate_loading = false;
> > > vm_start();
> > > trace_colo_vm_state_change("stop", "run");
> > > diff --git a/migration/migration.c b/migration/migration.c
> > > index ce06941706..c97b7660af 100644
> > > --- a/migration/migration.c
> > > +++ b/migration/migration.c
> > > @@ -385,6 +385,7 @@ static void process_incoming_migration_co(void
> > *opaque)
> > > MigrationIncomingState *mis = migration_incoming_get_current();
> > > PostcopyState ps;
> > > int ret;
> > > + Error *local_err = NULL;
> > >
> > > assert(mis->from_src_file);
> > > mis->largest_page_size = qemu_ram_pagesize_largest();
> > > @@ -416,6 +417,14 @@ static void process_incoming_migration_co(void
> > *opaque)
> > >
> > > /* we get COLO info, and know if we are in COLO mode */
> > > if (!ret && migration_incoming_enable_colo()) {
> > > + /* Make sure all file formats flush their mutable metadata */
> > > + bdrv_invalidate_cache_all(&local_err);
> > > + if (local_err) {
> > > + migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
> > > + MIGRATION_STATUS_FAILED);
> > > + error_report_err(local_err);
> > > + exit(EXIT_FAILURE);
> > > + }
> > > mis->migration_incoming_co = qemu_coroutine_self();
> > > qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming",
> > > colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE);
> > > --
> > > 2.17.1
> > >
> > --
> > Dr. David Alan Gilbert / address@hidden / Manchester, UK
> >
--
Dr. David Alan Gilbert / address@hidden / Manchester, UK