From: Peter Xu <peterx@redhat.com>
To: qemu-devel@nongnu.org
Cc: Alexey Perevalov <a.perevalov@samsung.com>,
"Daniel P . Berrange" <berrange@redhat.com>,
Juan Quintela <quintela@redhat.com>,
Andrea Arcangeli <aarcange@redhat.com>,
"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
peterx@redhat.com
Subject: [Qemu-devel] [PATCH v8 03/24] migration: implement "postcopy-pause" src logic
Date: Wed, 2 May 2018 18:47:19 +0800 [thread overview]
Message-ID: <20180502104740.12123-4-peterx@redhat.com> (raw)
In-Reply-To: <20180502104740.12123-1-peterx@redhat.com>
Now when network down for postcopy, the source side will not fail the
migration. Instead we convert the status into this new paused state, and
we will try to wait for a rescue in the future.
If a recovery is detected, migration_thread() will reset its local
variables to prepare for that.
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
migration/migration.h | 3 ++
migration/migration.c | 99 +++++++++++++++++++++++++++++++++++++++++++++++---
migration/trace-events | 1 +
3 files changed, 97 insertions(+), 6 deletions(-)
diff --git a/migration/migration.h b/migration/migration.h
index 7c69598c54..9bf3418973 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -194,6 +194,9 @@ struct MigrationState
bool send_configuration;
/* Whether we send section footer during migration */
bool send_section_footer;
+
+ /* Needed by postcopy-pause state */
+ QemuSemaphore postcopy_pause_sem;
};
void migrate_set_state(int *state, int old_state, int new_state);
diff --git a/migration/migration.c b/migration/migration.c
index 57ff1010e5..b9dac8c3b9 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -2240,6 +2240,80 @@ bool migrate_colo_enabled(void)
return s->enabled_capabilities[MIGRATION_CAPABILITY_X_COLO];
}
+typedef enum MigThrError {
+ /* No error detected */
+ MIG_THR_ERR_NONE = 0,
+ /* Detected error, but resumed successfully */
+ MIG_THR_ERR_RECOVERED = 1,
+ /* Detected fatal error, need to exit */
+ MIG_THR_ERR_FATAL = 2,
+} MigThrError;
+
+/*
+ * We don't return until we are in a safe state to continue current
+ * postcopy migration. Returns MIG_THR_ERR_RECOVERED if recovered, or
+ * MIG_THR_ERR_FATAL if unrecovery failure happened.
+ */
+static MigThrError postcopy_pause(MigrationState *s)
+{
+ assert(s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE);
+ migrate_set_state(&s->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
+ MIGRATION_STATUS_POSTCOPY_PAUSED);
+
+ /* Current channel is possibly broken. Release it. */
+ assert(s->to_dst_file);
+ qemu_file_shutdown(s->to_dst_file);
+ qemu_fclose(s->to_dst_file);
+ s->to_dst_file = NULL;
+
+ error_report("Detected IO failure for postcopy. "
+ "Migration paused.");
+
+ /*
+ * We wait until things fixed up. Then someone will setup the
+ * status back for us.
+ */
+ while (s->state == MIGRATION_STATUS_POSTCOPY_PAUSED) {
+ qemu_sem_wait(&s->postcopy_pause_sem);
+ }
+
+ trace_postcopy_pause_continued();
+
+ return MIG_THR_ERR_RECOVERED;
+}
+
+static MigThrError migration_detect_error(MigrationState *s)
+{
+ int ret;
+
+ /* Try to detect any file errors */
+ ret = qemu_file_get_error(s->to_dst_file);
+
+ if (!ret) {
+ /* Everything is fine */
+ return MIG_THR_ERR_NONE;
+ }
+
+ if (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE && ret == -EIO) {
+ /*
+ * For postcopy, we allow the network to be down for a
+ * while. After that, it can be continued by a
+ * recovery phase.
+ */
+ return postcopy_pause(s);
+ } else {
+ /*
+ * For precopy (or postcopy with error outside IO), we fail
+ * with no time.
+ */
+ migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
+ trace_migration_thread_file_err();
+
+ /* Time to stop the migration, now. */
+ return MIG_THR_ERR_FATAL;
+ }
+}
+
static void migration_calculate_complete(MigrationState *s)
{
uint64_t bytes = qemu_ftell(s->to_dst_file);
@@ -2396,6 +2470,7 @@ static void *migration_thread(void *opaque)
{
MigrationState *s = opaque;
int64_t setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+ MigThrError thr_error;
rcu_register_thread();
@@ -2445,13 +2520,22 @@ static void *migration_thread(void *opaque)
}
}
- if (qemu_file_get_error(s->to_dst_file)) {
- if (migration_is_setup_or_active(s->state)) {
- migrate_set_state(&s->state, s->state,
- MIGRATION_STATUS_FAILED);
- }
- trace_migration_thread_file_err();
+ /*
+ * Try to detect any kind of failures, and see whether we
+ * should stop the migration now.
+ */
+ thr_error = migration_detect_error(s);
+ if (thr_error == MIG_THR_ERR_FATAL) {
+ /* Stop migration */
break;
+ } else if (thr_error == MIG_THR_ERR_RECOVERED) {
+ /*
+ * Just recovered from a e.g. network failure, reset all
+ * the local variables. This is important to avoid
+ * breaking transferred_bytes and bandwidth calculation
+ */
+ s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+ s->iteration_initial_bytes = 0;
}
current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
@@ -2609,6 +2693,7 @@ static void migration_instance_finalize(Object *obj)
g_free(params->tls_hostname);
g_free(params->tls_creds);
qemu_sem_destroy(&ms->pause_sem);
+ qemu_sem_destroy(&ms->postcopy_pause_sem);
error_free(ms->error);
}
@@ -2638,6 +2723,8 @@ static void migration_instance_init(Object *obj)
params->has_x_multifd_channels = true;
params->has_x_multifd_page_count = true;
params->has_xbzrle_cache_size = true;
+
+ qemu_sem_init(&ms->postcopy_pause_sem, 0);
}
/*
diff --git a/migration/trace-events b/migration/trace-events
index d6be74b7a7..409b4b8be3 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -99,6 +99,7 @@ migration_thread_setup_complete(void) ""
open_return_path_on_source(void) ""
open_return_path_on_source_continue(void) ""
postcopy_start(void) ""
+postcopy_pause_continued(void) ""
postcopy_start_set_run(void) ""
source_return_path_thread_bad_end(void) ""
source_return_path_thread_end(void) ""
--
2.14.3
next prev parent reply other threads:[~2018-05-02 10:48 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-02 10:47 [Qemu-devel] [PATCH v8 00/24] Migration: postcopy failure recovery Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 01/24] migration: let incoming side use thread context Peter Xu
2018-05-08 14:36 ` Juan Quintela
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 02/24] migration: new postcopy-pause state Peter Xu
2018-05-08 15:16 ` Juan Quintela
2018-05-09 4:05 ` Peter Xu
2018-05-09 6:59 ` Juan Quintela
2018-05-02 10:47 ` Peter Xu [this message]
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 04/24] migration: allow dst vm pause on postcopy Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 05/24] migration: allow src return path to pause Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 06/24] migration: allow fault thread " Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 07/24] qmp: hmp: add migrate "resume" option Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 08/24] migration: rebuild channel on source Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 09/24] migration: new state "postcopy-recover" Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 10/24] migration: wakeup dst ram-load-thread for recover Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 11/24] migration: new cmd MIG_CMD_RECV_BITMAP Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 12/24] migration: new message MIG_RP_MSG_RECV_BITMAP Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 13/24] migration: new cmd MIG_CMD_POSTCOPY_RESUME Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 14/24] migration: new message MIG_RP_MSG_RESUME_ACK Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 15/24] migration: introduce SaveVMHandlers.resume_prepare Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 16/24] migration: synchronize dirty bitmap for resume Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 17/24] migration: setup ramstate " Peter Xu
2018-05-08 10:54 ` Dr. David Alan Gilbert
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 18/24] migration: final handshake for the resume Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 19/24] migration: init dst in migration_object_init too Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 20/24] qmp/migration: new command migrate-recover Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 21/24] hmp/migration: add migrate_recover command Peter Xu
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 22/24] migration: introduce lock for to_dst_file Peter Xu
2018-05-08 11:31 ` Dr. David Alan Gilbert
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 23/24] migration/qmp: add command migrate-pause Peter Xu
2018-05-08 13:20 ` Dr. David Alan Gilbert
2018-05-02 10:47 ` [Qemu-devel] [PATCH v8 24/24] migration/hmp: add migrate_pause command Peter Xu
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=20180502104740.12123-4-peterx@redhat.com \
--to=peterx@redhat.com \
--cc=a.perevalov@samsung.com \
--cc=aarcange@redhat.com \
--cc=berrange@redhat.com \
--cc=dgilbert@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.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).