[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH COLO-Frame v6 31/31] COLO: Add block replication int
From: |
zhanghailiang |
Subject: |
[Qemu-devel] [PATCH COLO-Frame v6 31/31] COLO: Add block replication into colo process |
Date: |
Thu, 18 Jun 2015 16:58:55 +0800 |
Make sure master start block replication after slave's block replication
started.
Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Wen Congyang <address@hidden>
Signed-off-by: Yang Hongyang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
---
migration/colo.c | 139 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
trace-events | 2 +
2 files changed, 139 insertions(+), 2 deletions(-)
diff --git a/migration/colo.c b/migration/colo.c
index 499a042..8c7e674 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -20,6 +20,8 @@
#include "qapi-event.h"
#include "net/colo-nic.h"
#include "qmp-commands.h"
+#include "block/block.h"
+#include "sysemu/block-backend.h"
/*
* We should not do checkpoint one after another without any time interval,
@@ -108,6 +110,76 @@ static bool colo_runstate_is_stopped(void)
return runstate_check(RUN_STATE_COLO) || !runstate_is_running();
}
+static void blk_start_replication(bool primary, Error **errp)
+{
+ ReplicationMode mode = primary ? REPLICATION_MODE_PRIMARY :
+ REPLICATION_MODE_SECONDARY;
+ BlockBackend *blk, *temp;
+ Error *local_err = NULL;
+
+ for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
+ if (blk_is_read_only(blk) || !blk_is_inserted(blk)) {
+ continue;
+ }
+
+ bdrv_start_replication(blk_bs(blk), mode, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ goto fail;
+ }
+ }
+
+ return;
+
+fail:
+ for (temp = blk_next(NULL); temp != blk; temp = blk_next(temp)) {
+ bdrv_stop_replication(blk_bs(temp), false, NULL);
+ }
+}
+
+static void blk_do_checkpoint(Error **errp)
+{
+ BlockBackend *blk;
+ Error *local_err = NULL;
+
+ for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
+ if (blk_is_read_only(blk) || !blk_is_inserted(blk)) {
+ continue;
+ }
+
+ bdrv_do_checkpoint(blk_bs(blk), &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return;
+ }
+ }
+}
+
+static void blk_stop_replication(bool failover, Error **errp)
+{
+ BlockBackend *blk;
+ Error *local_err = NULL;
+
+ for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
+ if (blk_is_read_only(blk) || !blk_is_inserted(blk)) {
+ continue;
+ }
+
+ bdrv_stop_replication(blk_bs(blk), failover, &local_err);
+ if (!errp) {
+ /*
+ * The caller doesn't care the result, they just
+ * want to stop all block's replication.
+ */
+ continue;
+ }
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return;
+ }
+ }
+}
+
/*
* there are two way to entry this function
* 1. From colo checkpoint incoming thread, in this case
@@ -118,6 +190,8 @@ static bool colo_runstate_is_stopped(void)
*/
static void secondary_vm_do_failover(void)
{
+ Error *local_err = NULL;
+
/* Wait for incoming thread loading vmstate */
while (vmstate_loading) {
;
@@ -128,6 +202,12 @@ static void secondary_vm_do_failover(void)
}
colo_proxy_destroy(COLO_MODE_SECONDARY);
+ blk_stop_replication(true, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ trace_colo_stop_block_replication("failover");
+
colo = NULL;
if (!autostart) {
@@ -145,6 +225,7 @@ static void secondary_vm_do_failover(void)
static void primary_vm_do_failover(void)
{
MigrationState *s = migrate_get_current();
+ Error *local_err = NULL;
if (!colo_runstate_is_stopped()) {
vm_stop_force_state(RUN_STATE_COLO);
@@ -156,6 +237,12 @@ static void primary_vm_do_failover(void)
migrate_set_state(s, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
}
+ blk_stop_replication(true, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ trace_colo_stop_block_replication("failover");
+
vm_start();
}
@@ -229,6 +316,7 @@ static int colo_do_checkpoint_transaction(MigrationState
*s, QEMUFile *control)
int colo_shutdown, ret;
size_t size;
QEMUFile *trans = NULL;
+ Error *local_err = NULL;
ret = colo_ctl_put(s->file, COLO_CHECKPOINT_NEW);
if (ret < 0) {
@@ -282,6 +370,16 @@ static int colo_do_checkpoint_transaction(MigrationState
*s, QEMUFile *control)
goto out;
}
+ /* we call this api although this may do nothing on primary side */
+ qemu_mutex_lock_iothread();
+ blk_do_checkpoint(&local_err);
+ qemu_mutex_unlock_iothread();
+ if (local_err) {
+ error_report_err(local_err);
+ ret = -1;
+ goto out;
+ }
+
ret = colo_ctl_put(s->file, COLO_CHECKPOINT_SEND);
if (ret < 0) {
goto out;
@@ -313,6 +411,10 @@ static int colo_do_checkpoint_transaction(MigrationState
*s, QEMUFile *control)
trace_colo_receive_message("COLO_CHECKPOINT_LOADED");
if (colo_shutdown) {
+ qemu_mutex_lock_iothread();
+ blk_stop_replication(false, NULL);
+ trace_colo_stop_block_replication("shutdown");
+ qemu_mutex_unlock_iothread();
colo_ctl_put(s->file, COLO_GUEST_SHUTDOWN);
qemu_fflush(s->file);
colo_shutdown_requested = 0;
@@ -344,6 +446,7 @@ static void *colo_thread(void *opaque)
QEMUFile *colo_control = NULL;
int64_t current_time, checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
int i, ret;
+ Error *local_err = NULL;
if (colo_proxy_init(COLO_MODE_PRIMARY) != 0) {
error_report("Init colo proxy error");
@@ -375,6 +478,12 @@ static void *colo_thread(void *opaque)
}
qemu_mutex_lock_iothread();
+ /* start block replication */
+ blk_start_replication(true, &local_err);
+ if (local_err) {
+ goto out;
+ }
+ trace_colo_start_block_replication();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
@@ -425,7 +534,11 @@ do_checkpoint:
}
out:
- error_report("colo: some error happens in colo_thread");
+ if (local_err) {
+ error_report_err(local_err);
+ } else {
+ error_report("colo: some error happens in colo_thread");
+ }
qapi_event_send_colo_exit("primary", true, "unknown", NULL);;
/* Give users time (2s) to get involved in this verdict */
for (i = 0; i < 10; i++) {
@@ -510,6 +623,8 @@ static int colo_wait_handle_cmd(QEMUFile *f, int
*checkpoint_request)
case COLO_GUEST_SHUTDOWN:
qemu_mutex_lock_iothread();
vm_stop_force_state(RUN_STATE_COLO);
+ blk_stop_replication(false, NULL);
+ trace_colo_stop_block_replication("shutdown");
qemu_system_shutdown_request_core();
qemu_mutex_unlock_iothread();
trace_colo_receive_message("COLO_GUEST_SHUTDOWN");
@@ -533,6 +648,7 @@ void *colo_process_incoming_checkpoints(void *opaque)
QEMUFile *ctl = NULL, *fb = NULL;
int i, ret;
uint64_t total_size;
+ Error *local_err = NULL;
qdev_hotplug = 0;
@@ -562,6 +678,15 @@ void *colo_process_incoming_checkpoints(void *opaque)
goto out;
}
+ qemu_mutex_lock_iothread();
+ /* start block replication */
+ blk_start_replication(false, &local_err);
+ if (local_err) {
+ goto out;
+ }
+ qemu_mutex_unlock_iothread();
+ trace_colo_start_block_replication();
+
ret = colo_ctl_put(ctl, COLO_CHECPOINT_READY);
if (ret < 0) {
goto out;
@@ -648,7 +773,13 @@ void *colo_process_incoming_checkpoints(void *opaque)
}
vmstate_loading = false;
+
+ /* discard colo disk buffer */
+ blk_do_checkpoint(&local_err);
qemu_mutex_unlock_iothread();
+ if (local_err) {
+ goto out;
+ }
ret = colo_ctl_put(ctl, COLO_CHECKPOINT_LOADED);
if (ret < 0) {
@@ -666,7 +797,11 @@ void *colo_process_incoming_checkpoints(void *opaque)
}
out:
- error_report("Detect some error or get a failover request");
+ if (local_err) {
+ error_report_err(local_err);
+ } else {
+ error_report("Detect some error or get a failover request");
+ }
/*
* Here, we raise a qmp event to the user,
* It can help user to know what happens, and help deciding whether to
diff --git a/trace-events b/trace-events
index a84a04b..98d503f 100644
--- a/trace-events
+++ b/trace-events
@@ -1474,6 +1474,8 @@ colo_vm_state_change(const char *old, const char *new)
"Change '%s' => '%s'"
colo_receive_message(const char *msg) "Receive '%s'"
colo_do_failover(void) ""
colo_rcv_pkt(int result) "Result of net packets comparing is different: %d"
+colo_start_block_replication(void) "Block replication is started"
+colo_stop_block_replication(const char *reason) "Block replication is
stopped(reason: '%s')"
# kvm-all.c
kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
--
1.7.12.4
- [Qemu-devel] [PATCH COLO-Frame v6 17/31] COLO failover: Don't do failover during loading VM's state, (continued)
- [Qemu-devel] [PATCH COLO-Frame v6 17/31] COLO failover: Don't do failover during loading VM's state, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 21/31] COLO NIC: Implement colo nic device interface configure(), zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 24/31] COLO: Handle nfnetlink message from proxy module, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 19/31] COLO NIC: Init/remove colo nic devices when add/cleanup tap devices, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 26/31] COLO: Improve checkpoint efficiency by do additional periodic checkpoint, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 25/31] COLO: Do checkpoint according to the result of packets comparation, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 20/31] tap: Make launch_script() public, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 16/31] qmp event: Add event notification for COLO error, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 22/31] COLO NIC : Implement colo nic init/destroy function, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 29/31] COLO: Disable qdev hotplug when VM is in COLO mode, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 31/31] COLO: Add block replication into colo process,
zhanghailiang <=
- [Qemu-devel] [PATCH COLO-Frame v6 28/31] COLO NIC: Implement NIC checkpoint and failover, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 18/31] COLO: Add new command parameter 'colo_nicname' 'colo_script' for net, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 30/31] COLO: Implement shutdown checkpoint, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 27/31] COLO: Add colo-set-checkpoint-period command, zhanghailiang, 2015/06/18
- [Qemu-devel] [PATCH COLO-Frame v6 23/31] COLO NIC: Some init work related with proxy module, zhanghailiang, 2015/06/18
- Re: [Qemu-devel] [PATCH COLO-Frame v6 00/31] COarse-grain LOck-stepping(COLO) Virtual Machines for Non-stop Service, Dr. David Alan Gilbert, 2015/06/30