| Message ID | 1460096797-14916-14-git-send-email-zhang.zhanghailiang@huawei.com (mailing list archive) |
|---|---|
| State | New, archived |
| 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. You'll need to figure out how to merge this with Dan Berrange's TLS series ( http://lists.gnu.org/archive/html/qemu-devel/2016-03/msg04591.html ); in particular note that he's killed off the QEMUSizedBuffer but now has a QIOChannelBuffer. I did review his full set last month, so I think it's ready to go. Dave > > 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> > Cc: Dr. David Alan Gilbert <dgilbert@redhat.com> > --- > v16: > - Rename colo_get_cmd_value() to colo_receive_mesage_value(); > v13: > - Fix the define of colo_get_cmd_value() to use 'Error **errp' instead of > return value. > v12: > - Use the new helper colo_get_cmd_value() instead of colo_ctl_get() > --- > migration/colo.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-- > 1 file changed, 72 insertions(+), 2 deletions(-) > > diff --git a/migration/colo.c b/migration/colo.c > index fb2b705..52a2c3e 100644 > --- a/migration/colo.c > +++ b/migration/colo.c > @@ -115,6 +115,28 @@ static void colo_receive_check_message(QEMUFile *f, COLOMessage expect_msg, > } > } > > +static uint64_t colo_receive_message_value(QEMUFile *f, uint32_t expect_msg, > + Error **errp) > +{ > + Error *local_err = NULL; > + uint64_t value; > + int ret; > + > + colo_receive_check_message(f, expect_msg, &local_err); > + if (local_err) { > + error_propagate(errp, local_err); > + return 0; > + } > + > + value = qemu_get_be64(f); > + ret = qemu_file_get_error(f); > + if (ret < 0) { > + error_setg_errno(errp, -ret, "Failed to get value for COLO message: %s", > + COLOMessage_lookup[expect_msg]); > + } > + return value; > +} > + > static int colo_do_checkpoint_transaction(MigrationState *s, > QEMUSizedBuffer *buffer) > { > @@ -298,6 +320,10 @@ static void colo_wait_handle_message(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 */ > + uint64_t total_size; > + uint64_t value; > Error *local_err = NULL; > int ret; > > @@ -321,6 +347,12 @@ 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; > + } > + > colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, > &local_err); > if (local_err) { > @@ -348,7 +380,21 @@ void *colo_process_incoming_thread(void *opaque) > goto out; > } > > - /* TODO: read migration data into colo buffer */ > + /* read the VM state total size first */ > + value = colo_receive_message_value(mis->from_src_file, > + COLO_MESSAGE_VMSTATE_SIZE, &local_err); > + if (local_err) { > + goto out; > + } > + > + /* read vm device state into colo buffer */ > + total_size = qsb_fill_buffer(buffer, mis->from_src_file, value); > + if (total_size != value) { > + error_report("Got %lu VMState data, less than expected %lu", > + total_size, value); > + ret = -EINVAL; > + goto out; > + } > > colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED, > &local_err); > @@ -356,13 +402,32 @@ void *colo_process_incoming_thread(void *opaque) > goto out; > } > > - /* TODO: load vm state */ > + /* 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 */ > > colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED, > &local_err); > if (local_err) { > goto out; > } > + > + qemu_fclose(fb); > + fb = NULL; > } > > out: > @@ -371,6 +436,11 @@ out: > error_report_err(local_err); > } > > + 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 2016/4/22 18:12, 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. > > You'll need to figure out how to merge this with Dan Berrange's TLS series > ( http://lists.gnu.org/archive/html/qemu-devel/2016-03/msg04591.html ); > in particular note that he's killed off the QEMUSizedBuffer but now has > a QIOChannelBuffer. > > I did review his full set last month, so I think it's ready to go. Yes, i already noticed it, if that series merged first, we need to do some other rebase works, i will look at it later. Thanks, Hailiang > Dave > >> >> 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> >> Cc: Dr. David Alan Gilbert <dgilbert@redhat.com> >> --- >> v16: >> - Rename colo_get_cmd_value() to colo_receive_mesage_value(); >> v13: >> - Fix the define of colo_get_cmd_value() to use 'Error **errp' instead of >> return value. >> v12: >> - Use the new helper colo_get_cmd_value() instead of colo_ctl_get() >> --- >> migration/colo.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-- >> 1 file changed, 72 insertions(+), 2 deletions(-) >> >> diff --git a/migration/colo.c b/migration/colo.c >> index fb2b705..52a2c3e 100644 >> --- a/migration/colo.c >> +++ b/migration/colo.c >> @@ -115,6 +115,28 @@ static void colo_receive_check_message(QEMUFile *f, COLOMessage expect_msg, >> } >> } >> >> +static uint64_t colo_receive_message_value(QEMUFile *f, uint32_t expect_msg, >> + Error **errp) >> +{ >> + Error *local_err = NULL; >> + uint64_t value; >> + int ret; >> + >> + colo_receive_check_message(f, expect_msg, &local_err); >> + if (local_err) { >> + error_propagate(errp, local_err); >> + return 0; >> + } >> + >> + value = qemu_get_be64(f); >> + ret = qemu_file_get_error(f); >> + if (ret < 0) { >> + error_setg_errno(errp, -ret, "Failed to get value for COLO message: %s", >> + COLOMessage_lookup[expect_msg]); >> + } >> + return value; >> +} >> + >> static int colo_do_checkpoint_transaction(MigrationState *s, >> QEMUSizedBuffer *buffer) >> { >> @@ -298,6 +320,10 @@ static void colo_wait_handle_message(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 */ >> + uint64_t total_size; >> + uint64_t value; >> Error *local_err = NULL; >> int ret; >> >> @@ -321,6 +347,12 @@ 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; >> + } >> + >> colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, >> &local_err); >> if (local_err) { >> @@ -348,7 +380,21 @@ void *colo_process_incoming_thread(void *opaque) >> goto out; >> } >> >> - /* TODO: read migration data into colo buffer */ >> + /* read the VM state total size first */ >> + value = colo_receive_message_value(mis->from_src_file, >> + COLO_MESSAGE_VMSTATE_SIZE, &local_err); >> + if (local_err) { >> + goto out; >> + } >> + >> + /* read vm device state into colo buffer */ >> + total_size = qsb_fill_buffer(buffer, mis->from_src_file, value); >> + if (total_size != value) { >> + error_report("Got %lu VMState data, less than expected %lu", >> + total_size, value); >> + ret = -EINVAL; >> + goto out; >> + } >> >> colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED, >> &local_err); >> @@ -356,13 +402,32 @@ void *colo_process_incoming_thread(void *opaque) >> goto out; >> } >> >> - /* TODO: load vm state */ >> + /* 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 */ >> >> colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED, >> &local_err); >> if (local_err) { >> goto out; >> } >> + >> + qemu_fclose(fb); >> + fb = NULL; >> } >> >> out: >> @@ -371,6 +436,11 @@ out: >> error_report_err(local_err); >> } >> >> + 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 fb2b705..52a2c3e 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -115,6 +115,28 @@ static void colo_receive_check_message(QEMUFile *f, COLOMessage expect_msg, } } +static uint64_t colo_receive_message_value(QEMUFile *f, uint32_t expect_msg, + Error **errp) +{ + Error *local_err = NULL; + uint64_t value; + int ret; + + colo_receive_check_message(f, expect_msg, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return 0; + } + + value = qemu_get_be64(f); + ret = qemu_file_get_error(f); + if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to get value for COLO message: %s", + COLOMessage_lookup[expect_msg]); + } + return value; +} + static int colo_do_checkpoint_transaction(MigrationState *s, QEMUSizedBuffer *buffer) { @@ -298,6 +320,10 @@ static void colo_wait_handle_message(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 */ + uint64_t total_size; + uint64_t value; Error *local_err = NULL; int ret; @@ -321,6 +347,12 @@ 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; + } + colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY, &local_err); if (local_err) { @@ -348,7 +380,21 @@ void *colo_process_incoming_thread(void *opaque) goto out; } - /* TODO: read migration data into colo buffer */ + /* read the VM state total size first */ + value = colo_receive_message_value(mis->from_src_file, + COLO_MESSAGE_VMSTATE_SIZE, &local_err); + if (local_err) { + goto out; + } + + /* read vm device state into colo buffer */ + total_size = qsb_fill_buffer(buffer, mis->from_src_file, value); + if (total_size != value) { + error_report("Got %lu VMState data, less than expected %lu", + total_size, value); + ret = -EINVAL; + goto out; + } colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED, &local_err); @@ -356,13 +402,32 @@ void *colo_process_incoming_thread(void *opaque) goto out; } - /* TODO: load vm state */ + /* 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 */ colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED, &local_err); if (local_err) { goto out; } + + qemu_fclose(fb); + fb = NULL; } out: @@ -371,6 +436,11 @@ out: error_report_err(local_err); } + if (fb) { + qemu_fclose(fb); + } + qsb_free(buffer); + qemu_mutex_lock_iothread(); colo_release_ram_cache(); qemu_mutex_unlock_iothread();