-----BEGIN PGP SIGNATURE----- iQJGBAABCAAwFiEENUvIs9frKmtoZ05fOHC0AOuRhlMFAl1WleASHGFybWJydUBy ZWRoYXQuY29tAAoJEDhwtADrkYZTBBYQALQLzIYb2Zux95bAxoJdhqNuEOGLfxeu gx0i0roPe6SBleHozUK+gf7kVYyw7he58n2dZURGqrpqktgZOFcea2a6Dq1rnVw6 JMJ2Oy7V326bHwJT0Np9rW4n+FHsMQZoAUEHjl9EeGCZfO/zy2aSWPsD8mbcbm0g hUW5Jr4+cpm28BCL8I+2HhWFazB6G2IPAF9oEXmNsOM6J1Ho8WGrTAjASe0Il5Yi m2B4QWG+4uz77WYnkttnssm41K1S95HYyaKluIVyNwTnsPTN303V/sUj+wdRaooL k1O6WqaavGhal7QeRqy+vCpF8m6qLq7NaYCzSCOrrkkuC8TAnpVn7Xmi9qI+vb6O kGBpDWhq5wOnphsEhnFvhPZgD+WZo3mwTgW4h0d3UhB6orOTPTMvWKEwFJ1j/O6/ gntV61o542c9gpZjS133221HRmNjteHF/5/TFzmX/G50sgivJn+WOP87naM2aBAz 8MW5HatTox+qQqYD4VMUIVnVkguxHDVhFRBunYu0HvZZ1Rud+Lc6Xzi6H4jDlZ81 vtOmAlMU3dbp97gNvJrAVqV4JIL3puOWbu0MMaQWoG53Kcdfu46LIr57TTg3dw61 R9e7HSOQjYILChoodwELlyeAsVeZo3IzX9vPX8aw7MoHvneyTUNqtha/rHsLEwsb 97G19dydGEC6 =eSUz -----END PGP SIGNATURE----- Merge remote-tracking branch 'remotes/armbru/tags/pull-include-2019-08-13-v2' into staging Header cleanup patches for 2019-08-13 # gpg: Signature made Fri 16 Aug 2019 12:39:12 BST # gpg: using RSA key 354BC8B3D7EB2A6B68674E5F3870B400EB918653 # gpg: issuer "armbru@redhat.com" # gpg: Good signature from "Markus Armbruster <armbru@redhat.com>" [full] # gpg: aka "Markus Armbruster <armbru@pond.sub.org>" [full] # Primary key fingerprint: 354B C8B3 D7EB 2A6B 6867 4E5F 3870 B400 EB91 8653 * remotes/armbru/tags/pull-include-2019-08-13-v2: (29 commits) sysemu: Split sysemu/runstate.h off sysemu/sysemu.h sysemu: Move the VMChangeStateEntry typedef to qemu/typedefs.h Include sysemu/sysemu.h a lot less Clean up inclusion of sysemu/sysemu.h numa: Move remaining NUMA declarations from sysemu.h to numa.h Include sysemu/hostmem.h less numa: Don't include hw/boards.h into sysemu/numa.h Include hw/boards.h a bit less Include hw/qdev-properties.h less Include qemu/main-loop.h less Include qemu/queue.h slightly less Include hw/hw.h exactly where needed Include qom/object.h slightly less Include exec/memory.h slightly less Include migration/vmstate.h less migration: Move the VMStateDescription typedef to typedefs.h Clean up inclusion of exec/cpu-common.h Include hw/irq.h a lot less typedefs: Separate incomplete types and function types ide: Include hw/ide/internal a bit less outside hw/ide/ ... Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
342 lines
10 KiB
C
342 lines
10 KiB
C
/*
|
|
* 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 "exec/cpu-common.h"
|
|
#include "hw/qdev-core.h"
|
|
#include "qapi/qapi-types-migration.h"
|
|
#include "qemu/thread.h"
|
|
#include "qemu/coroutine_int.h"
|
|
#include "io/channel.h"
|
|
#include "net/announce.h"
|
|
|
|
struct PostcopyBlocktimeContext;
|
|
|
|
#define MIGRATION_RESUME_ACK_VALUE (1)
|
|
|
|
/*
|
|
* 1<<6=64 pages -> 256K chunk when page size is 4K. This gives us
|
|
* the benefit that all the chunks are 64 pages aligned then the
|
|
* bitmaps are always aligned to LONG.
|
|
*/
|
|
#define CLEAR_BITMAP_SHIFT_MIN 6
|
|
/*
|
|
* 1<<18=256K pages -> 1G chunk when page size is 4K. This is the
|
|
* default value to use if no one specified.
|
|
*/
|
|
#define CLEAR_BITMAP_SHIFT_DEFAULT 18
|
|
/*
|
|
* 1<<31=2G pages -> 8T chunk when page size is 4K. This should be
|
|
* big enough and make sure we won't overflow easily.
|
|
*/
|
|
#define CLEAR_BITMAP_SHIFT_MAX 31
|
|
|
|
/* 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;
|
|
|
|
/* For network announces */
|
|
AnnounceTimer announce_timer;
|
|
|
|
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 */
|
|
/* RAMBlock of last request sent to source */
|
|
RAMBlock *last_rb;
|
|
void *postcopy_tmp_page;
|
|
void *postcopy_tmp_zero_page;
|
|
/* PostCopyFD's for external userfaultfds & handlers of shared memory */
|
|
GArray *postcopy_remote_fds;
|
|
|
|
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;
|
|
|
|
/*
|
|
* PostcopyBlocktimeContext to keep information for postcopy
|
|
* live migration, to calculate vCPU block time
|
|
* */
|
|
struct PostcopyBlocktimeContext *blocktime_ctx;
|
|
|
|
/* notify PAUSED postcopy incoming migrations to try to continue */
|
|
bool postcopy_recover_triggered;
|
|
QemuSemaphore postcopy_pause_sem_dst;
|
|
QemuSemaphore postcopy_pause_sem_fault;
|
|
|
|
/* List of listening socket addresses */
|
|
SocketAddressList *socket_address_list;
|
|
};
|
|
|
|
MigrationIncomingState *migration_incoming_get_current(void);
|
|
void migration_incoming_state_destroy(void);
|
|
/*
|
|
* Functions to work with blocktime context
|
|
*/
|
|
void fill_destination_postcopy_migration_info(MigrationInfo *info);
|
|
|
|
#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 >*/
|
|
QemuThread thread;
|
|
QEMUBH *cleanup_bh;
|
|
QEMUFile *to_dst_file;
|
|
/*
|
|
* Protects to_dst_file pointer. We need to make sure we won't
|
|
* yield or hang during the critical section, since this lock will
|
|
* be used in OOB command handler.
|
|
*/
|
|
QemuMutex qemu_file_lock;
|
|
|
|
/*
|
|
* Used to allow urgent requests to override rate limiting.
|
|
*/
|
|
QemuSemaphore rate_limit_sem;
|
|
|
|
/* pages already send at the beginning of current iteration */
|
|
uint64_t iteration_initial_pages;
|
|
|
|
/* pages transferred per second */
|
|
double pages_per_second;
|
|
|
|
/* bytes already send at the beginning of current iteration */
|
|
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;
|
|
QemuSemaphore rp_sem;
|
|
} 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;
|
|
|
|
/* 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;
|
|
|
|
/* 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 */
|
|
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 we send QEMU_VM_CONFIGURATION during migration */
|
|
bool send_configuration;
|
|
/* Whether we send section footer during migration */
|
|
bool send_section_footer;
|
|
|
|
/* Needed by postcopy-pause state */
|
|
QemuSemaphore postcopy_pause_sem;
|
|
QemuSemaphore postcopy_pause_rp_sem;
|
|
/*
|
|
* Whether we abort the migration if decompression errors are
|
|
* detected at the destination. It is left at false for qemu
|
|
* older than 3.0, since only newer qemu sends streams that
|
|
* do not trigger spurious decompression errors.
|
|
*/
|
|
bool decompress_error_check;
|
|
|
|
/*
|
|
* This decides the size of guest memory chunk that will be used
|
|
* to track dirty bitmap clearing. The size of memory chunk will
|
|
* be GUEST_PAGE_SIZE << N. Say, N=0 means we will clear dirty
|
|
* bitmap for each page to send (1<<0=1); N=10 means we will clear
|
|
* dirty bitmap only once for 1<<10=1K continuous guest pages
|
|
* (which is in 4M chunk).
|
|
*/
|
|
uint8_t clear_bitmap_shift;
|
|
};
|
|
|
|
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, Error **errp);
|
|
void migration_incoming_process(void);
|
|
|
|
bool migration_has_all_channels(void);
|
|
|
|
uint64_t migrate_max_downtime(void);
|
|
|
|
void migrate_set_error(MigrationState *s, const Error *error);
|
|
void migrate_fd_error(MigrationState *s, const Error *error);
|
|
|
|
void migrate_fd_connect(MigrationState *s, Error *error_in);
|
|
|
|
bool migration_is_setup_or_active(int state);
|
|
|
|
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_dirty_bitmaps(void);
|
|
bool migrate_ignore_shared(void);
|
|
|
|
bool migrate_auto_converge(void);
|
|
bool migrate_use_multifd(void);
|
|
bool migrate_pause_before_switchover(void);
|
|
int migrate_multifd_channels(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);
|
|
int migrate_max_cpu_throttle(void);
|
|
bool migrate_use_return_path(void);
|
|
|
|
uint64_t ram_get_total_transferred_pages(void);
|
|
|
|
bool migrate_use_compression(void);
|
|
int migrate_compress_level(void);
|
|
int migrate_compress_threads(void);
|
|
int migrate_compress_wait_thread(void);
|
|
int migrate_decompress_threads(void);
|
|
bool migrate_use_events(void);
|
|
bool migrate_postcopy_blocktime(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);
|
|
void migrate_send_rp_recv_bitmap(MigrationIncomingState *mis,
|
|
char *block_name);
|
|
void migrate_send_rp_resume_ack(MigrationIncomingState *mis, uint32_t value);
|
|
|
|
void dirty_bitmap_mig_before_vm_start(void);
|
|
void init_dirty_bitmap_incoming_migration(void);
|
|
void migrate_add_address(SocketAddress *address);
|
|
|
|
int foreach_not_ignored_block(RAMBlockIterFunc func, void *opaque);
|
|
|
|
#define qemu_ram_foreach_block \
|
|
#warning "Use foreach_not_ignored_block in migration code"
|
|
|
|
void migration_make_urgent_request(void);
|
|
void migration_consume_urgent_request(void);
|
|
|
|
#endif
|