qemu/migration/migration.h

237 lines
6.8 KiB
C
Raw Normal View History

/*
* QEMU live migration
*
* Copyright IBM, Corp. 2008
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#ifndef QEMU_MIGRATION_H
#define QEMU_MIGRATION_H
#include "qemu-common.h"
#include "qemu/thread.h"
#include "exec/cpu-common.h"
#include "qemu/coroutine_int.h"
#include "hw/qdev.h"
#include "io/channel.h"
/* State for the incoming migration */
struct MigrationIncomingState {
QEMUFile *from_src_file;
/*
* Free at the start of the main state load, set as the main thread finishes
* loading state.
*/
QemuEvent main_thread_load_event;
size_t largest_page_size;
bool have_fault_thread;
QemuThread fault_thread;
QemuSemaphore fault_thread_sem;
/* Set this when we want the fault thread to quit */
bool fault_thread_quit;
bool have_listen_thread;
QemuThread listen_thread;
QemuSemaphore listen_thread_sem;
/* For the kernel to send us notifications */
int userfault_fd;
/* To notify the fault_thread to wake, e.g., when need to quit */
int userfault_event_fd;
QEMUFile *to_src_file;
QemuMutex rp_mutex; /* We send replies from multiple threads */
void *postcopy_tmp_page;
void *postcopy_tmp_zero_page;
QEMUBH *bh;
int state;
bool have_colo_incoming_thread;
QemuThread colo_incoming_thread;
/* The coroutine we should enter (back) after failover */
Coroutine *migration_incoming_co;
QemuSemaphore colo_incoming_sem;
};
MigrationIncomingState *migration_incoming_get_current(void);
void migration_incoming_state_destroy(void);
#define TYPE_MIGRATION "migration"
#define MIGRATION_CLASS(klass) \
OBJECT_CLASS_CHECK(MigrationClass, (klass), TYPE_MIGRATION)
#define MIGRATION_OBJ(obj) \
OBJECT_CHECK(MigrationState, (obj), TYPE_MIGRATION)
#define MIGRATION_GET_CLASS(obj) \
OBJECT_GET_CLASS(MigrationClass, (obj), TYPE_MIGRATION)
typedef struct MigrationClass {
/*< private >*/
DeviceClass parent_class;
} MigrationClass;
struct MigrationState
{
/*< private >*/
DeviceState parent_obj;
/*< public >*/
size_t bytes_xfer;
size_t xfer_limit;
QemuThread thread;
QEMUBH *cleanup_bh;
QEMUFile *to_dst_file;
/* bytes already send at the beggining of current interation */
uint64_t iteration_initial_bytes;
/* time at the start of current iteration */
int64_t iteration_start_time;
/*
* The final stage happens when the remaining data is smaller than
* this threshold; it's calculated from the requested downtime and
* measured bandwidth
*/
int64_t threshold_size;
/* params from 'migrate-set-parameters' */
MigrationParameters parameters;
int state;
/* State related to return path */
struct {
QEMUFile *from_dst_file;
QemuThread rp_thread;
bool error;
} rp_state;
double mbps;
/* Timestamp when recent migration starts (ms) */
int64_t start_time;
/* Total time used by latest migration (ms) */
int64_t total_time;
/* Timestamp when VM is down (ms) to migrate the last stuff */
int64_t downtime_start;
int64_t downtime;
int64_t expected_downtime;
bool enabled_capabilities[MIGRATION_CAPABILITY__MAX];
int64_t setup_time;
/*
* Whether guest was running when we enter the completion stage.
* If migration is interrupted by any reason, we need to continue
* running the guest on source.
*/
bool vm_was_running;
/* Flag set once the migration has been asked to enter postcopy */
bool start_postcopy;
/* Flag set after postcopy has sent the device state */
bool postcopy_after_devices;
/* Flag set once the migration thread is running (and needs joining) */
bool migration_thread_running;
migration: re-active images while migration been canceled after inactive them commit fe904ea8242cbae2d7e69c052c754b8f5f1ba1d6 fixed a case which migration aborted QEMU because it didn't regain the control of images while some errors happened. Actually, there are another two cases can trigger the same error reports: " bdrv_co_do_pwritev: Assertion `!(bs->open_flags & 0x0800)' failed", Case 1, codes path: migration_thread() migration_completion() bdrv_inactivate_all() ----------------> inactivate images qemu_savevm_state_complete_precopy() socket_writev_buffer() --------> error because destination fails qemu_fflush() ----------------> set error on migration stream -> qmp_migrate_cancel() ----------------> user cancelled migration concurrently -> migrate_set_state() ------------------> set migrate CANCELLIN migration_completion() -----------------> go on to fail_invalidate if (s->state == MIGRATION_STATUS_ACTIVE) -> Jump this branch Case 2, codes path: migration_thread() migration_completion() bdrv_inactivate_all() ----------------> inactivate images migreation_completion() finished -> qmp_migrate_cancel() ---------------> user cancelled migration concurrently qemu_mutex_lock_iothread(); qemu_bh_schedule (s->cleanup_bh); As we can see from above, qmp_migrate_cancel can slip in whenever migration_thread does not hold the global lock. If this happens after bdrv_inactive_all() been called, the above error reports will appear. To prevent this, we can call bdrv_invalidate_cache_all() in qmp_migrate_cancel() directly if we find images become inactive. Besides, bdrv_invalidate_cache_all() in migration_completion() doesn't have the protection of big lock, fix it by add the missing qemu_mutex_lock_iothread(); Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com> Message-Id: <1485244792-11248-1-git-send-email-zhang.zhanghailiang@huawei.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2017-01-24 10:59:52 +03:00
/* Flag set once the migration thread called bdrv_inactivate_all */
bool block_inactive;
/* Migration is paused due to pause-before-switchover */
QemuSemaphore pause_sem;
/* The semaphore is used to notify COLO thread that failover is finished */
QemuSemaphore colo_exit_sem;
migration: add reporting of errors for outgoing migration Currently if an application initiates an outgoing migration, it may or may not, get an error reported back on failure. If the error occurs synchronously to the 'migrate' command execution, the client app will see the error message. This is the case for DNS lookup failures. If the error occurs asynchronously to the monitor command though, the error will be thrown away and the client left guessing about what went wrong. This is the case for failure to connect to the TCP server (eg due to wrong port, or firewall rules, or other similar errors). In the future we'll be adding more scope for errors to happen asynchronously with the TLS protocol handshake. TLS errors are hard to diagnose even when they are well reported, so discarding errors entirely will make it impossible to debug TLS connection problems. Management apps which do migration are already using 'query-migrate' / 'info migrate' to check up on progress of background migration operations and to see their end status. This is a fine place to also include the error message when things go wrong. This patch thus adds an 'error-desc' field to the MigrationInfo struct, which will be populated when the 'status' is set to 'failed': (qemu) migrate -d tcp:localhost:9001 (qemu) info migrate capabilities: xbzrle: off rdma-pin-all: off auto-converge: off zero-blocks: off compress: off events: off x-postcopy-ram: off Migration status: failed (Error connecting to socket: Connection refused) total time: 0 milliseconds In the HMP, when doing non-detached migration, it is also possible to display this error message directly to the app. (qemu) migrate tcp:localhost:9001 Error connecting to socket: Connection refused Or with QMP { "execute": "query-migrate", "arguments": {} } { "return": { "status": "failed", "error-desc": "address resolution failed for myhost:9000: No address associated with hostname" } } Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Message-Id: <1461751518-12128-11-git-send-email-berrange@redhat.com> Signed-off-by: Amit Shah <amit.shah@redhat.com>
2016-04-27 13:05:00 +03:00
/* The semaphore is used to notify COLO thread to do checkpoint */
QemuSemaphore colo_checkpoint_sem;
int64_t colo_checkpoint_time;
QEMUTimer *colo_delay_timer;
/* The first error that has occurred.
We used the mutex to be able to return the 1st error message */
migration: add reporting of errors for outgoing migration Currently if an application initiates an outgoing migration, it may or may not, get an error reported back on failure. If the error occurs synchronously to the 'migrate' command execution, the client app will see the error message. This is the case for DNS lookup failures. If the error occurs asynchronously to the monitor command though, the error will be thrown away and the client left guessing about what went wrong. This is the case for failure to connect to the TCP server (eg due to wrong port, or firewall rules, or other similar errors). In the future we'll be adding more scope for errors to happen asynchronously with the TLS protocol handshake. TLS errors are hard to diagnose even when they are well reported, so discarding errors entirely will make it impossible to debug TLS connection problems. Management apps which do migration are already using 'query-migrate' / 'info migrate' to check up on progress of background migration operations and to see their end status. This is a fine place to also include the error message when things go wrong. This patch thus adds an 'error-desc' field to the MigrationInfo struct, which will be populated when the 'status' is set to 'failed': (qemu) migrate -d tcp:localhost:9001 (qemu) info migrate capabilities: xbzrle: off rdma-pin-all: off auto-converge: off zero-blocks: off compress: off events: off x-postcopy-ram: off Migration status: failed (Error connecting to socket: Connection refused) total time: 0 milliseconds In the HMP, when doing non-detached migration, it is also possible to display this error message directly to the app. (qemu) migrate tcp:localhost:9001 Error connecting to socket: Connection refused Or with QMP { "execute": "query-migrate", "arguments": {} } { "return": { "status": "failed", "error-desc": "address resolution failed for myhost:9000: No address associated with hostname" } } Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Message-Id: <1461751518-12128-11-git-send-email-berrange@redhat.com> Signed-off-by: Amit Shah <amit.shah@redhat.com>
2016-04-27 13:05:00 +03:00
Error *error;
/* mutex to protect errp */
QemuMutex error_mutex;
/* Do we have to clean up -b/-i from old migrate parameters */
/* This feature is deprecated and will be removed */
bool must_remove_block_options;
/*
* Global switch on whether we need to store the global state
* during migration.
*/
bool store_global_state;
/* Whether the VM is only allowing for migratable devices */
bool only_migratable;
/* Whether we send QEMU_VM_CONFIGURATION during migration */
bool send_configuration;
/* Whether we send section footer during migration */
bool send_section_footer;
};
void migrate_set_state(int *state, int old_state, int new_state);
void migration_fd_process_incoming(QEMUFile *f);
void migration_ioc_process_incoming(QIOChannel *ioc);
bool migration_has_all_channels(void);
uint64_t migrate_max_downtime(void);
void migrate_set_error(MigrationState *s, const Error *error);
migration: add reporting of errors for outgoing migration Currently if an application initiates an outgoing migration, it may or may not, get an error reported back on failure. If the error occurs synchronously to the 'migrate' command execution, the client app will see the error message. This is the case for DNS lookup failures. If the error occurs asynchronously to the monitor command though, the error will be thrown away and the client left guessing about what went wrong. This is the case for failure to connect to the TCP server (eg due to wrong port, or firewall rules, or other similar errors). In the future we'll be adding more scope for errors to happen asynchronously with the TLS protocol handshake. TLS errors are hard to diagnose even when they are well reported, so discarding errors entirely will make it impossible to debug TLS connection problems. Management apps which do migration are already using 'query-migrate' / 'info migrate' to check up on progress of background migration operations and to see their end status. This is a fine place to also include the error message when things go wrong. This patch thus adds an 'error-desc' field to the MigrationInfo struct, which will be populated when the 'status' is set to 'failed': (qemu) migrate -d tcp:localhost:9001 (qemu) info migrate capabilities: xbzrle: off rdma-pin-all: off auto-converge: off zero-blocks: off compress: off events: off x-postcopy-ram: off Migration status: failed (Error connecting to socket: Connection refused) total time: 0 milliseconds In the HMP, when doing non-detached migration, it is also possible to display this error message directly to the app. (qemu) migrate tcp:localhost:9001 Error connecting to socket: Connection refused Or with QMP { "execute": "query-migrate", "arguments": {} } { "return": { "status": "failed", "error-desc": "address resolution failed for myhost:9000: No address associated with hostname" } } Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Message-Id: <1461751518-12128-11-git-send-email-berrange@redhat.com> Signed-off-by: Amit Shah <amit.shah@redhat.com>
2016-04-27 13:05:00 +03:00
void migrate_fd_error(MigrationState *s, const Error *error);
void migrate_fd_connect(MigrationState *s, Error *error_in);
void migrate_init(MigrationState *s);
bool migration_is_blocked(Error **errp);
/* True if outgoing migration has entered postcopy phase */
bool migration_in_postcopy(void);
MigrationState *migrate_get_current(void);
bool migrate_postcopy(void);
bool migrate_release_ram(void);
bool migrate_postcopy_ram(void);
bool migrate_zero_blocks(void);
bool migrate_auto_converge(void);
bool migrate_use_multifd(void);
bool migrate_pause_before_switchover(void);
int migrate_multifd_channels(void);
int migrate_multifd_page_count(void);
int migrate_use_xbzrle(void);
int64_t migrate_xbzrle_cache_size(void);
bool migrate_colo_enabled(void);
bool migrate_use_block(void);
bool migrate_use_block_incremental(void);
bool migrate_use_return_path(void);
bool migrate_use_compression(void);
int migrate_compress_level(void);
int migrate_compress_threads(void);
int migrate_decompress_threads(void);
bool migrate_use_events(void);
/* Sending on the return path - generic and then for each message type */
void migrate_send_rp_shut(MigrationIncomingState *mis,
uint32_t value);
void migrate_send_rp_pong(MigrationIncomingState *mis,
uint32_t value);
int migrate_send_rp_req_pages(MigrationIncomingState *mis, const char* rbname,
ram_addr_t start, size_t len);
#endif