mirror of
https://gitlab.com/qemu-project/qemu
synced 2024-09-06 18:05:37 +00:00
![Peter Xu](/assets/img/avatar_default.png)
Maintain a list of faulted addresses on the destination host for which we're waiting on. This is implemented using a GTree rather than a real list to make sure even there're plenty of vCPUs/threads that are faulting, the lookup will still be fast with O(log(N)) (because we'll do that after placing each page). It should bring a slight overhead, but ideally that shouldn't be a big problem simply because in most cases the requested page list will be short. Actually we did similar things for postcopy blocktime measurements. This patch didn't use that simply because: (1) blocktime measurement is towards vcpu threads only, but here we need to record all faulted addresses, including main thread and external thread (like, DPDK via vhost-user). (2) blocktime measurement will require UFFD_FEATURE_THREAD_ID, but here we don't want to add that extra dependency on the kernel version since not necessary. E.g., we don't need to know which thread faulted on which page, we also don't care about multiple threads faulting on the same page. But we only care about what addresses are faulted so waiting for a page copying from src. (3) blocktime measurement is not enabled by default. However we need this by default especially for postcopy recover. Another thing to mention is that this patch introduced a new mutex to serialize the receivedmap and the page_requested tree, however that serialization does not cover other procedures like UFFDIO_COPY. Signed-off-by: Peter Xu <peterx@redhat.com> Message-Id: <20201021212721.440373-4-peterx@redhat.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
376 lines
12 KiB
C
376 lines
12 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"
|
|
#include "qom/object.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;
|
|
|
|
/* A tree of pages that we requested to the source VM */
|
|
GTree *page_requested;
|
|
/* For debugging purpose only, but would be nice to keep */
|
|
int page_requested_count;
|
|
/*
|
|
* The mutex helps to maintain the requested pages that we sent to the
|
|
* source, IOW, to guarantee coherent between the page_requests tree and
|
|
* the per-ramblock receivedmap. Note! This does not guarantee consistency
|
|
* of the real page copy procedures (using UFFDIO_[ZERO]COPY). E.g., even
|
|
* if one bit in receivedmap is cleared, UFFDIO_COPY could have happened
|
|
* for that page already. This is intended so that the mutex won't
|
|
* serialize and blocked by slow operations like UFFDIO_* ioctls. However
|
|
* this should be enough to make sure the page_requested tree always
|
|
* contains valid information.
|
|
*/
|
|
QemuMutex page_request_mutex;
|
|
};
|
|
|
|
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"
|
|
|
|
typedef struct MigrationClass MigrationClass;
|
|
DECLARE_OBJ_CHECKERS(MigrationState, MigrationClass,
|
|
MIGRATION_OBJ, TYPE_MIGRATION)
|
|
|
|
struct MigrationClass {
|
|
/*< private >*/
|
|
DeviceClass parent_class;
|
|
};
|
|
|
|
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 waiting for guest to unplug device */
|
|
QemuSemaphore wait_unplug_sem;
|
|
|
|
/* 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 event is used to notify COLO thread to do checkpoint */
|
|
QemuEvent colo_checkpoint_event;
|
|
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;
|
|
|
|
/*
|
|
* This save hostname when out-going migration starts
|
|
*/
|
|
char *hostname;
|
|
};
|
|
|
|
void migrate_set_state(int *state, int old_state, int new_state);
|
|
|
|
void migration_fd_process_incoming(QEMUFile *f, Error **errp);
|
|
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);
|
|
bool migration_is_running(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_validate_uuid(void);
|
|
|
|
bool migrate_auto_converge(void);
|
|
bool migrate_use_multifd(void);
|
|
bool migrate_pause_before_switchover(void);
|
|
int migrate_multifd_channels(void);
|
|
MultiFDCompression migrate_multifd_compression(void);
|
|
int migrate_multifd_zlib_level(void);
|
|
int migrate_multifd_zstd_level(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, RAMBlock *rb,
|
|
ram_addr_t start, uint64_t haddr);
|
|
int migrate_send_rp_message_req_pages(MigrationIncomingState *mis,
|
|
RAMBlock *rb, ram_addr_t start);
|
|
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 dirty_bitmap_mig_cancel_outgoing(void);
|
|
void dirty_bitmap_mig_cancel_incoming(void);
|
|
bool check_dirty_bitmap_mig_alias_map(const BitmapMigrationNodeAliasList *bbm,
|
|
Error **errp);
|
|
|
|
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);
|
|
bool migration_rate_limit(void);
|
|
|
|
#endif
|