| Message ID | 1446551816-15768-15-git-send-email-zhang.zhanghailiang@huawei.com |
|---|---|
| State | New |
| Headers | show |
* zhanghailiang (zhang.zhanghailiang@huawei.com) wrote: > We should not destroy the state of SVM (Secondary VM) until we receive the whole > state from the PVM (Primary VM), in case the primary fails in the middle of sending > the state, so, here we cache the device state in Secondary before restore it. > > Besides, we should call qemu_system_reset() before load VM state, > which can ensure the data is intact. > > Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com> > Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> > Signed-off-by: Gonglei <arei.gonglei@huawei.com> > Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> > --- > migration/colo.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++- > 1 file changed, 46 insertions(+), 1 deletion(-) > > diff --git a/migration/colo.c b/migration/colo.c > index 25f85b2..1339774 100644 > --- a/migration/colo.c > +++ b/migration/colo.c > @@ -287,6 +287,9 @@ static int colo_wait_handle_cmd(QEMUFile *f, int *checkpoint_request) > void *colo_process_incoming_thread(void *opaque) > { > MigrationIncomingState *mis = opaque; > + QEMUFile *fb = NULL; > + QEMUSizedBuffer *buffer = NULL; /* Cache incoming device state */ > + int total_size; > int fd, ret = 0; > > migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, > @@ -310,6 +313,12 @@ void *colo_process_incoming_thread(void *opaque) > goto out; > } > > + buffer = qsb_create(NULL, COLO_BUFFER_BASE_SIZE); > + if (buffer == NULL) { > + error_report("Failed to allocate colo buffer!"); > + goto out; > + } > + > ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY, 0); > if (ret < 0) { > goto out; > @@ -337,19 +346,50 @@ void *colo_process_incoming_thread(void *opaque) > goto out; > } > > - /* TODO Load VM state */ > + /* read the VM state total size first */ > + total_size = colo_ctl_get(mis->from_src_file, > + COLO_COMMAND_VMSTATE_SIZE); > + if (total_size <= 0) { Error message? > + goto out; > + } OK, and when you fix up the colo_ctl_get in the previous patch to take a separate pointer for value, you can make total_size a size_t. Other than those, it looks good. Dave > + /* read vm device state into colo buffer */ > + ret = qsb_fill_buffer(buffer, mis->from_src_file, total_size); > + if (ret != total_size) { > + error_report("can't get all migration data"); > + goto out; > + } > > ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_VMSTATE_RECEIVED, 0); > if (ret < 0) { > goto out; > } > > + /* open colo buffer for read */ > + fb = qemu_bufopen("r", buffer); > + if (!fb) { > + error_report("can't open colo buffer for read"); > + goto out; > + } > + > + qemu_mutex_lock_iothread(); > + qemu_system_reset(VMRESET_SILENT); > + if (qemu_loadvm_state(fb) < 0) { > + error_report("COLO: loadvm failed"); > + qemu_mutex_unlock_iothread(); > + goto out; > + } > + qemu_mutex_unlock_iothread(); > + > /* TODO: flush vm state */ > > ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_VMSTATE_LOADED, 0); > if (ret < 0) { > goto out; > } > + > + qemu_fclose(fb); > + fb = NULL; > } > > out: > @@ -358,6 +398,11 @@ out: > strerror(-ret)); > } > > + if (fb) { > + qemu_fclose(fb); > + } > + qsb_free(buffer); > + > qemu_mutex_lock_iothread(); > colo_release_ram_cache(); > qemu_mutex_unlock_iothread(); > -- > 1.8.3.1 > > -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
On 2015/11/14 0:02, Dr. David Alan Gilbert wrote: > * zhanghailiang (zhang.zhanghailiang@huawei.com) wrote: >> We should not destroy the state of SVM (Secondary VM) until we receive the whole >> state from the PVM (Primary VM), in case the primary fails in the middle of sending >> the state, so, here we cache the device state in Secondary before restore it. >> >> Besides, we should call qemu_system_reset() before load VM state, >> which can ensure the data is intact. >> >> Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com> >> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> >> Signed-off-by: Gonglei <arei.gonglei@huawei.com> >> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> >> --- >> migration/colo.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++- >> 1 file changed, 46 insertions(+), 1 deletion(-) >> >> diff --git a/migration/colo.c b/migration/colo.c >> index 25f85b2..1339774 100644 >> --- a/migration/colo.c >> +++ b/migration/colo.c >> @@ -287,6 +287,9 @@ static int colo_wait_handle_cmd(QEMUFile *f, int *checkpoint_request) >> void *colo_process_incoming_thread(void *opaque) >> { >> MigrationIncomingState *mis = opaque; >> + QEMUFile *fb = NULL; >> + QEMUSizedBuffer *buffer = NULL; /* Cache incoming device state */ >> + int total_size; >> int fd, ret = 0; >> >> migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, >> @@ -310,6 +313,12 @@ void *colo_process_incoming_thread(void *opaque) >> goto out; >> } >> >> + buffer = qsb_create(NULL, COLO_BUFFER_BASE_SIZE); >> + if (buffer == NULL) { >> + error_report("Failed to allocate colo buffer!"); >> + goto out; >> + } >> + >> ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY, 0); >> if (ret < 0) { >> goto out; >> @@ -337,19 +346,50 @@ void *colo_process_incoming_thread(void *opaque) >> goto out; >> } >> >> - /* TODO Load VM state */ >> + /* read the VM state total size first */ >> + total_size = colo_ctl_get(mis->from_src_file, >> + COLO_COMMAND_VMSTATE_SIZE); >> + if (total_size <= 0) { > > Error message? > OK, we need one. >> + goto out; >> + } > > OK, and when you fix up the colo_ctl_get in the previous patch to > take a separate pointer for value, you can make total_size a size_t. > Yes, i have updated it after addressing your review comment on patch 11. > > Other than those, it looks good. > Thanks. > Dave > >> + /* read vm device state into colo buffer */ >> + ret = qsb_fill_buffer(buffer, mis->from_src_file, total_size); >> + if (ret != total_size) { >> + error_report("can't get all migration data"); >> + goto out; >> + } >> >> ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_VMSTATE_RECEIVED, 0); >> if (ret < 0) { >> goto out; >> } >> >> + /* open colo buffer for read */ >> + fb = qemu_bufopen("r", buffer); >> + if (!fb) { >> + error_report("can't open colo buffer for read"); >> + goto out; >> + } >> + >> + qemu_mutex_lock_iothread(); >> + qemu_system_reset(VMRESET_SILENT); >> + if (qemu_loadvm_state(fb) < 0) { >> + error_report("COLO: loadvm failed"); >> + qemu_mutex_unlock_iothread(); >> + goto out; >> + } >> + qemu_mutex_unlock_iothread(); >> + >> /* TODO: flush vm state */ >> >> ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_VMSTATE_LOADED, 0); >> if (ret < 0) { >> goto out; >> } >> + >> + qemu_fclose(fb); >> + fb = NULL; >> } >> >> out: >> @@ -358,6 +398,11 @@ out: >> strerror(-ret)); >> } >> >> + if (fb) { >> + qemu_fclose(fb); >> + } >> + qsb_free(buffer); >> + >> qemu_mutex_lock_iothread(); >> colo_release_ram_cache(); >> qemu_mutex_unlock_iothread(); >> -- >> 1.8.3.1 >> >> > -- > Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK > > . >
diff --git a/migration/colo.c b/migration/colo.c index 25f85b2..1339774 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -287,6 +287,9 @@ static int colo_wait_handle_cmd(QEMUFile *f, int *checkpoint_request) void *colo_process_incoming_thread(void *opaque) { MigrationIncomingState *mis = opaque; + QEMUFile *fb = NULL; + QEMUSizedBuffer *buffer = NULL; /* Cache incoming device state */ + int total_size; int fd, ret = 0; migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, @@ -310,6 +313,12 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + buffer = qsb_create(NULL, COLO_BUFFER_BASE_SIZE); + if (buffer == NULL) { + error_report("Failed to allocate colo buffer!"); + goto out; + } + ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY, 0); if (ret < 0) { goto out; @@ -337,19 +346,50 @@ void *colo_process_incoming_thread(void *opaque) goto out; } - /* TODO Load VM state */ + /* read the VM state total size first */ + total_size = colo_ctl_get(mis->from_src_file, + COLO_COMMAND_VMSTATE_SIZE); + if (total_size <= 0) { + goto out; + } + + /* read vm device state into colo buffer */ + ret = qsb_fill_buffer(buffer, mis->from_src_file, total_size); + if (ret != total_size) { + error_report("can't get all migration data"); + goto out; + } ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_VMSTATE_RECEIVED, 0); if (ret < 0) { goto out; } + /* open colo buffer for read */ + fb = qemu_bufopen("r", buffer); + if (!fb) { + error_report("can't open colo buffer for read"); + goto out; + } + + qemu_mutex_lock_iothread(); + qemu_system_reset(VMRESET_SILENT); + if (qemu_loadvm_state(fb) < 0) { + error_report("COLO: loadvm failed"); + qemu_mutex_unlock_iothread(); + goto out; + } + qemu_mutex_unlock_iothread(); + /* TODO: flush vm state */ ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_VMSTATE_LOADED, 0); if (ret < 0) { goto out; } + + qemu_fclose(fb); + fb = NULL; } out: @@ -358,6 +398,11 @@ out: strerror(-ret)); } + if (fb) { + qemu_fclose(fb); + } + qsb_free(buffer); + qemu_mutex_lock_iothread(); colo_release_ram_cache(); qemu_mutex_unlock_iothread();