From: zhanghailiang <zhang.zhanghailiang@huawei.com>
To: qemu-devel@nongnu.org
Cc: lizhijian@cn.fujitsu.com, quintela@redhat.com,
yunhong.jiang@intel.com, eddie.dong@intel.com,
peter.huangpeng@huawei.com, dgilbert@redhat.com,
arei.gonglei@huawei.com, amit.shah@redhat.com,
Lai Jiangshan <laijs@cn.fujitsu.com>,
Yang Hongyang <yanghy@cn.fujitsu.com>,
zhanghailiang <zhang.zhanghailiang@huawei.com>
Subject: [Qemu-devel] [PATCH COLO-Frame v7 07/34] COLO: Implement colo checkpoint protocol
Date: Thu, 9 Jul 2015 11:16:15 +0800 [thread overview]
Message-ID: <1436411802-181876-8-git-send-email-zhang.zhanghailiang@huawei.com> (raw)
In-Reply-To: <1436411802-181876-1-git-send-email-zhang.zhanghailiang@huawei.com>
We need communications protocol of user-defined to control the checkpoint
process.
The new checkpoint request is started by Primary VM, and the interactive process
like below:
Checkpoint synchronizing points,
Primary Secondary
NEW @
Suspend
SUSPENDED @
Suspend&Save state
SEND @
Send state Receive state
RECEIVED @
Flush network Load state
LOADED @
Resume Resume
Start Comparing
NOTE:
1) '@' who sends the message
2) Every sync-point is synchronized by two sides with only
one handshake(single direction) for low-latency.
If more strict synchronization is required, a opposite direction
sync-point should be added.
3) Since sync-points are single direction, the remote side may
go forward a lot when this side just receives the sync-point.
Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
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>
---
migration/colo.c | 237 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 235 insertions(+), 2 deletions(-)
diff --git a/migration/colo.c b/migration/colo.c
index e1ffd1f..f4a0b4e 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -15,6 +15,41 @@
#include "trace.h"
#include "qemu/error-report.h"
+enum {
+ COLO_CHECPOINT_READY = 0x46,
+
+ /*
+ * Checkpoint synchronizing points.
+ *
+ * Primary Secondary
+ * NEW @
+ * Suspend
+ * SUSPENDED @
+ * Suspend&Save state
+ * SEND @
+ * Send state Receive state
+ * RECEIVED @
+ * Flush network Load state
+ * LOADED @
+ * Resume Resume
+ *
+ * Start Comparing
+ * NOTE:
+ * 1) '@' who sends the message
+ * 2) Every sync-point is synchronized by two sides with only
+ * one handshake(single direction) for low-latency.
+ * If more strict synchronization is required, a opposite direction
+ * sync-point should be added.
+ * 3) Since sync-points are single direction, the remote side may
+ * go forward a lot when this side just receives the sync-point.
+ */
+ COLO_CHECKPOINT_NEW,
+ COLO_CHECKPOINT_SUSPENDED,
+ COLO_CHECKPOINT_SEND,
+ COLO_CHECKPOINT_RECEIVED,
+ COLO_CHECKPOINT_LOADED,
+};
+
static QEMUBH *colo_bh;
static Coroutine *colo;
@@ -34,19 +69,136 @@ bool loadvm_in_colo_state(void)
return colo != NULL;
}
+/* colo checkpoint control helper */
+static int colo_ctl_put(QEMUFile *f, uint64_t request)
+{
+ int ret = 0;
+
+ qemu_put_be64(f, request);
+ qemu_fflush(f);
+
+ ret = qemu_file_get_error(f);
+
+ return ret;
+}
+
+static int colo_ctl_get_value(QEMUFile *f, uint64_t *value)
+{
+ int ret = 0;
+ uint64_t temp;
+
+ temp = qemu_get_be64(f);
+
+ ret = qemu_file_get_error(f);
+ if (ret < 0) {
+ return -1;
+ }
+
+ *value = temp;
+ return 0;
+}
+
+static int colo_ctl_get(QEMUFile *f, uint64_t require)
+{
+ int ret;
+ uint64_t value;
+
+ ret = colo_ctl_get_value(f, &value);
+ if (ret < 0) {
+ return ret;
+ }
+
+ if (value != require) {
+ error_report("unexpected state! expected: %"PRIu64
+ ", received: %"PRIu64, require, value);
+ exit(1);
+ }
+
+ return ret;
+}
+
+static int colo_do_checkpoint_transaction(MigrationState *s, QEMUFile *control)
+{
+ int ret;
+
+ ret = colo_ctl_put(s->file, COLO_CHECKPOINT_NEW);
+ if (ret < 0) {
+ goto out;
+ }
+
+ ret = colo_ctl_get(control, COLO_CHECKPOINT_SUSPENDED);
+ if (ret < 0) {
+ goto out;
+ }
+
+ /* TODO: suspend and save vm state to colo buffer */
+
+ ret = colo_ctl_put(s->file, COLO_CHECKPOINT_SEND);
+ if (ret < 0) {
+ goto out;
+ }
+
+ /* TODO: send vmstate to Secondary */
+
+ ret = colo_ctl_get(control, COLO_CHECKPOINT_RECEIVED);
+ if (ret < 0) {
+ goto out;
+ }
+ trace_colo_receive_message("COLO_CHECKPOINT_RECEIVED");
+
+ ret = colo_ctl_get(control, COLO_CHECKPOINT_LOADED);
+ if (ret < 0) {
+ goto out;
+ }
+ trace_colo_receive_message("COLO_CHECKPOINT_LOADED");
+
+ /* TODO: resume Primary */
+
+out:
+ return ret;
+}
+
static void *colo_thread(void *opaque)
{
MigrationState *s = opaque;
+ QEMUFile *colo_control = NULL;
+ int ret;
+
+ colo_control = qemu_fopen_socket(qemu_get_fd(s->file), "rb");
+ if (!colo_control) {
+ error_report("Open colo_control failed!");
+ goto out;
+ }
+
+ /*
+ * Wait for Secondary finish loading vm states and enter COLO
+ * restore.
+ */
+ ret = colo_ctl_get(colo_control, COLO_CHECPOINT_READY);
+ if (ret < 0) {
+ goto out;
+ }
+ trace_colo_receive_message("COLO_CHECPOINT_READY");
qemu_mutex_lock_iothread();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
- /*TODO: COLO checkpoint savevm loop*/
+ while (s->state == MIGRATION_STATUS_COLO) {
+ /* start a colo checkpoint */
+ if (colo_do_checkpoint_transaction(s, colo_control)) {
+ goto out;
+ }
+ }
+out:
migrate_set_state(s, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED);
+ if (colo_control) {
+ qemu_fclose(colo_control);
+ }
+
qemu_mutex_lock_iothread();
qemu_bh_schedule(s->cleanup_bh);
qemu_mutex_unlock_iothread();
@@ -79,14 +231,95 @@ void colo_init_checkpointer(MigrationState *s)
qemu_bh_schedule(colo_bh);
}
+/*
+ * return:
+ * 0: start a checkpoint
+ * -1: some error happened, exit colo restore
+ */
+static int colo_wait_handle_cmd(QEMUFile *f, int *checkpoint_request)
+{
+ int ret;
+ uint64_t cmd;
+
+ ret = colo_ctl_get_value(f, &cmd);
+ if (ret < 0) {
+ return -1;
+ }
+
+ switch (cmd) {
+ case COLO_CHECKPOINT_NEW:
+ *checkpoint_request = 1;
+ return 0;
+ default:
+ return -1;
+ }
+}
+
void *colo_process_incoming_checkpoints(void *opaque)
{
+ struct colo_incoming *colo_in = opaque;
+ QEMUFile *f = colo_in->file;
+ int fd = qemu_get_fd(f);
+ QEMUFile *ctl = NULL;
+ int ret;
colo = qemu_coroutine_self();
assert(colo != NULL);
- /* TODO: COLO checkpoint restore loop */
+ ctl = qemu_fopen_socket(fd, "wb");
+ if (!ctl) {
+ error_report("Can't open incoming channel!");
+ goto out;
+ }
+ ret = colo_ctl_put(ctl, COLO_CHECPOINT_READY);
+ if (ret < 0) {
+ goto out;
+ }
+ /* TODO: in COLO mode, Secondary is runing, so start the vm */
+ while (true) {
+ int request = 0;
+ int ret = colo_wait_handle_cmd(f, &request);
+
+ if (ret < 0) {
+ break;
+ } else {
+ if (!request) {
+ continue;
+ }
+ }
+ /* TODO: suspend guest */
+ ret = colo_ctl_put(ctl, COLO_CHECKPOINT_SUSPENDED);
+ if (ret < 0) {
+ goto out;
+ }
+
+ ret = colo_ctl_get(f, COLO_CHECKPOINT_SEND);
+ if (ret < 0) {
+ goto out;
+ }
+ trace_colo_receive_message("COLO_CHECKPOINT_SEND");
+
+ /* TODO: read migration data into colo buffer */
+
+ ret = colo_ctl_put(ctl, COLO_CHECKPOINT_RECEIVED);
+ if (ret < 0) {
+ goto out;
+ }
+ trace_colo_receive_message("COLO_CHECKPOINT_RECEIVED");
+
+ /* TODO: load vm state */
+
+ ret = colo_ctl_put(ctl, COLO_CHECKPOINT_LOADED);
+ if (ret < 0) {
+ goto out;
+ }
+}
+
+out:
colo = NULL;
+ if (ctl) {
+ qemu_fclose(ctl);
+ }
loadvm_exit_colo();
return NULL;
--
1.7.12.4
next prev parent reply other threads:[~2015-07-09 3:18 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-09 3:16 [Qemu-devel] [PATCH COLO-Frame v7 00/34] COarse-grain LOck-stepping(COLO) Virtual Machines for Non-stop Service (FT) zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 01/34] configure: Add parameter for configure to enable/disable COLO support zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 02/34] migration: Introduce capability 'colo' to migration zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 03/34] COLO: migrate colo related info to slave zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 04/34] colo-comm/migration: skip colo info section for special cases zhanghailiang
2015-07-17 17:07 ` Dr. David Alan Gilbert
2015-07-20 8:42 ` zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 05/34] migration: Integrate COLO checkpoint process into migration zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 06/34] migration: Integrate COLO checkpoint process into loadvm zhanghailiang
2015-07-09 3:16 ` zhanghailiang [this message]
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 08/34] COLO: Add a new RunState RUN_STATE_COLO zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 09/34] QEMUSizedBuffer: Introduce two help functions for qsb zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 10/34] COLO: Save VM state to slave when do checkpoint zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 11/34] COLO RAM: Load PVM's dirty page into SVM's RAM cache temporarily zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 12/34] COLO VMstate: Load VM state into qsb before restore it zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 13/34] arch_init: Start to trace dirty pages of SVM zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 14/34] COLO RAM: Flush cached RAM into SVM's memory zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 15/34] COLO failover: Introduce a new command to trigger a failover zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 16/34] COLO failover: Introduce state to record failover process zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 17/34] COLO failover: Implement COLO primary/secondary vm failover work zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 18/34] qmp event: Add event notification for COLO error zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 19/34] COLO failover: Don't do failover during loading VM's state zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 20/34] COLO: Add new command parameter 'forward_nic' 'colo_script' for net zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 21/34] COLO NIC: Init/remove colo nic devices when add/cleanup tap devices zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 22/34] tap: Make launch_script() public zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 23/34] COLO NIC: Implement colo nic device interface configure() zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 24/34] colo-nic: Handle secondary VM's original net device configure zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 25/34] COLO NIC: Implement colo nic init/destroy function zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 26/34] COLO NIC: Some init work related with proxy module zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 27/34] COLO: Handle nfnetlink message from " zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 28/34] COLO: Do checkpoint according to the result of packets comparation zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 29/34] COLO: Improve checkpoint efficiency by do additional periodic checkpoint zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 30/34] COLO: Add colo-set-checkpoint-period command zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 31/34] COLO NIC: Implement NIC checkpoint and failover zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 32/34] COLO: Disable qdev hotplug when VM is in COLO mode zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 33/34] COLO: Implement shutdown checkpoint zhanghailiang
2015-07-09 3:16 ` [Qemu-devel] [PATCH COLO-Frame v7 34/34] COLO: Add block replication into colo process zhanghailiang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1436411802-181876-8-git-send-email-zhang.zhanghailiang@huawei.com \
--to=zhang.zhanghailiang@huawei.com \
--cc=amit.shah@redhat.com \
--cc=arei.gonglei@huawei.com \
--cc=dgilbert@redhat.com \
--cc=eddie.dong@intel.com \
--cc=laijs@cn.fujitsu.com \
--cc=lizhijian@cn.fujitsu.com \
--cc=peter.huangpeng@huawei.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
--cc=yanghy@cn.fujitsu.com \
--cc=yunhong.jiang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).