qemu-e2k/migration/trace-events

361 lines
22 KiB
Plaintext
Raw Normal View History

# See docs/devel/tracing.rst for syntax documentation.
# savevm.c
qemu_loadvm_state_section(unsigned int section_type) "%d"
qemu_loadvm_state_section_command(int ret) "%d"
qemu_loadvm_state_section_partend(uint32_t section_id) "%u"
qemu_loadvm_state_post_main(int ret) "%d"
qemu_loadvm_state_section_startfull(uint32_t section_id, const char *idstr, uint32_t instance_id, uint32_t version_id) "%u(%s) %u %u"
qemu_savevm_send_packaged(void) ""
loadvm_state_setup(void) ""
loadvm_state_cleanup(void) ""
loadvm_handle_cmd_packaged(unsigned int length) "%u"
loadvm_handle_cmd_packaged_main(int ret) "%d"
loadvm_handle_cmd_packaged_received(int ret) "%d"
loadvm_handle_recv_bitmap(char *s) "%s"
loadvm_postcopy_handle_advise(void) ""
loadvm_postcopy_handle_listen(const char *str) "%s"
loadvm_postcopy_handle_run(void) ""
loadvm_postcopy_handle_run_bh(const char *str) "%s"
loadvm_postcopy_handle_resume(void) ""
loadvm_postcopy_ram_handle_discard(void) ""
loadvm_postcopy_ram_handle_discard_end(void) ""
loadvm_postcopy_ram_handle_discard_header(const char *ramid, uint16_t len) "%s: %ud"
loadvm_process_command(const char *s, uint16_t len) "com=%s len=%d"
loadvm_process_command_ping(uint32_t val) "0x%x"
postcopy_ram_listen_thread_exit(void) ""
postcopy_ram_listen_thread_start(void) ""
qemu_savevm_send_postcopy_advise(void) ""
qemu_savevm_send_postcopy_ram_discard(const char *id, uint16_t len) "%s: %ud"
savevm_command_send(uint16_t command, uint16_t len) "com=0x%x len=%d"
savevm_section_start(const char *id, unsigned int section_id) "%s, section_id %u"
savevm_section_end(const char *id, unsigned int section_id, int ret) "%s, section_id %u -> %d"
savevm_section_skip(const char *id, unsigned int section_id) "%s, section_id %u"
savevm_send_open_return_path(void) ""
savevm_send_ping(uint32_t val) "0x%x"
savevm_send_postcopy_listen(void) ""
savevm_send_postcopy_run(void) ""
savevm_send_postcopy_resume(void) ""
savevm_send_colo_enable(void) ""
savevm_send_recv_bitmap(char *name) "%s"
savevm_state_setup(void) ""
savevm_state_resume_prepare(void) ""
savevm_state_header(void) ""
savevm_state_iterate(void) ""
savevm_state_cleanup(void) ""
savevm_state_complete_precopy(void) ""
vmstate_save(const char *idstr, const char *vmsd_name) "%s, %s"
vmstate_load(const char *idstr, const char *vmsd_name) "%s, %s"
postcopy_pause_incoming(void) ""
postcopy_pause_incoming_continued(void) ""
postcopy_page_req_sync(void *host_addr) "sync page req %p"
# vmstate.c
vmstate_load_field_error(const char *field, int ret) "field \"%s\" load failed, ret = %d"
vmstate_load_state(const char *name, int version_id) "%s v%d"
vmstate_load_state_end(const char *name, const char *reason, int val) "%s %s/%d"
vmstate_load_state_field(const char *name, const char *field) "%s:%s"
vmstate_n_elems(const char *name, int n_elems) "%s: %d"
vmstate_subsection_load(const char *parent) "%s"
vmstate_subsection_load_bad(const char *parent, const char *sub, const char *sub2) "%s: %s/%s"
vmstate_subsection_load_good(const char *parent) "%s"
vmstate_save_state_pre_save_res(const char *name, int res) "%s/%d"
vmstate_save_state_loop(const char *name, const char *field, int n_elems) "%s/%s[%d]"
vmstate_save_state_top(const char *idstr) "%s"
vmstate_subsection_save_loop(const char *name, const char *sub) "%s/%s"
vmstate_subsection_save_top(const char *idstr) "%s"
# vmstate-types.c
get_qtailq(const char *name, int version_id) "%s v%d"
get_qtailq_end(const char *name, const char *reason, int val) "%s %s/%d"
put_qtailq(const char *name, int version_id) "%s v%d"
put_qtailq_end(const char *name, const char *reason) "%s %s"
get_gtree(const char *field_name, const char *key_vmsd_name, const char *val_vmsd_name, uint32_t nnodes) "%s(%s/%s) nnodes=%d"
get_gtree_end(const char *field_name, const char *key_vmsd_name, const char *val_vmsd_name, int ret) "%s(%s/%s) %d"
put_gtree(const char *field_name, const char *key_vmsd_name, const char *val_vmsd_name, uint32_t nnodes) "%s(%s/%s) nnodes=%d"
put_gtree_end(const char *field_name, const char *key_vmsd_name, const char *val_vmsd_name, int ret) "%s(%s/%s) %d"
get_qlist(const char *field_name, const char *vmsd_name, int version_id) "%s(%s v%d)"
get_qlist_end(const char *field_name, const char *vmsd_name) "%s(%s)"
put_qlist(const char *field_name, const char *vmsd_name, int version_id) "%s(%s v%d)"
put_qlist_end(const char *field_name, const char *vmsd_name) "%s(%s)"
# qemu-file.c
qemu_file_fclose(void) ""
# ram.c
migration_bitmap_sync_start(void) ""
migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64
migration: Split log_clear() into smaller chunks Currently we are doing log_clear() right after log_sync() which mostly keeps the old behavior when log_clear() was still part of log_sync(). This patch tries to further optimize the migration log_clear() code path to split huge log_clear()s into smaller chunks. We do this by spliting the whole guest memory region into memory chunks, whose size is decided by MigrationState.clear_bitmap_shift (an example will be given below). With that, we don't do the dirty bitmap clear operation on the remote node (e.g., KVM) when we fetch the dirty bitmap, instead we explicitly clear the dirty bitmap for the memory chunk for each of the first time we send a page in that chunk. Here comes an example. Assuming the guest has 64G memory, then before this patch the KVM ioctl KVM_CLEAR_DIRTY_LOG will be a single one covering 64G memory. If after the patch, let's assume when the clear bitmap shift is 18, then the memory chunk size on x86_64 will be 1UL<<18 * 4K = 1GB. Then instead of sending a big 64G ioctl, we'll send 64 small ioctls, each of the ioctl will cover 1G of the guest memory. For each of the 64 small ioctls, we'll only send if any of the page in that small chunk was going to be sent right away. Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Message-Id: <20190603065056.25211-12-peterx@redhat.com> Signed-off-by: Juan Quintela <quintela@redhat.com>
2019-06-03 08:50:56 +02:00
migration_bitmap_clear_dirty(char *str, uint64_t start, uint64_t size, unsigned long page) "rb %s start 0x%"PRIx64" size 0x%"PRIx64" page 0x%lx"
migration_throttle(void) ""
ram_discard_range(const char *rbname, uint64_t start, size_t len) "%s: start: %" PRIx64 " %zx"
ram_load_loop(const char *rbname, uint64_t addr, int flags, void *host) "%s: addr: 0x%" PRIx64 " flags: 0x%x host: %p"
ram_load_postcopy_loop(int channel, uint64_t addr, int flags) "chan=%d addr=0x%" PRIx64 " flags=0x%x"
ram_postcopy_send_discard_bitmap(void) ""
ram_save_page(const char *rbname, uint64_t offset, void *host) "%s: offset: 0x%" PRIx64 " host: %p"
ram_save_queue_pages(const char *rbname, size_t start, size_t len) "%s: start: 0x%zx len: 0x%zx"
ram_dirty_bitmap_request(char *str) "%s"
ram_dirty_bitmap_reload_begin(char *str) "%s"
ram_dirty_bitmap_reload_complete(char *str) "%s"
ram_dirty_bitmap_sync_start(void) ""
ram_dirty_bitmap_sync_wait(void) ""
ram_dirty_bitmap_sync_complete(void) ""
ram_state_resume_prepare(uint64_t v) "%" PRId64
colo_flush_ram_cache_begin(uint64_t dirty_pages) "dirty_pages %" PRIu64
colo_flush_ram_cache_end(void) ""
save_xbzrle_page_skipping(void) ""
save_xbzrle_page_overflow(void) ""
ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRIu64 " milliseconds, %d iterations"
ram_load_complete(int ret, uint64_t seq_iter) "exit_code %d seq iteration %" PRIu64
ram_write_tracking_ramblock_start(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu"
ram_write_tracking_ramblock_stop(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu"
unqueue_page(char *block, uint64_t offset, bool dirty) "ramblock '%s' offset 0x%"PRIx64" dirty %d"
migration: Postcopy preemption enablement This patch enables postcopy-preempt feature. It contains two major changes to the migration logic: (1) Postcopy requests are now sent via a different socket from precopy background migration stream, so as to be isolated from very high page request delays. (2) For huge page enabled hosts: when there's postcopy requests, they can now intercept a partial sending of huge host pages on src QEMU. After this patch, we'll live migrate a VM with two channels for postcopy: (1) PRECOPY channel, which is the default channel that transfers background pages; and (2) POSTCOPY channel, which only transfers requested pages. There's no strict rule of which channel to use, e.g., if a requested page is already being transferred on precopy channel, then we will keep using the same precopy channel to transfer the page even if it's explicitly requested. In 99% of the cases we'll prioritize the channels so we send requested page via the postcopy channel as long as possible. On the source QEMU, when we found a postcopy request, we'll interrupt the PRECOPY channel sending process and quickly switch to the POSTCOPY channel. After we serviced all the high priority postcopy pages, we'll switch back to PRECOPY channel so that we'll continue to send the interrupted huge page again. There's no new thread introduced on src QEMU. On the destination QEMU, one new thread is introduced to receive page data from the postcopy specific socket (done in the preparation patch). This patch has a side effect: after sending postcopy pages, previously we'll assume the guest will access follow up pages so we'll keep sending from there. Now it's changed. Instead of going on with a postcopy requested page, we'll go back and continue sending the precopy huge page (which can be intercepted by a postcopy request so the huge page can be sent partially before). Whether that's a problem is debatable, because "assuming the guest will continue to access the next page" may not really suite when huge pages are used, especially if the huge page is large (e.g. 1GB pages). So that locality hint is much meaningless if huge pages are used. Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Message-Id: <20220707185504.27203-1-peterx@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2022-07-07 20:55:04 +02:00
postcopy_preempt_triggered(char *str, unsigned long page) "during sending ramblock %s offset 0x%lx"
postcopy_preempt_restored(char *str, unsigned long page) "ramblock %s offset 0x%lx"
postcopy_preempt_hit(char *str, uint64_t offset) "ramblock %s offset 0x%"PRIx64
postcopy_preempt_send_host_page(char *str, uint64_t offset) "ramblock %s offset 0x%"PRIx64
postcopy_preempt_switch_channel(int channel) "%d"
postcopy_preempt_reset_channel(void) ""
# multifd.c
multifd_new_send_channel_async(uint8_t id) "channel %u"
multifd_recv(uint8_t id, uint64_t packet_num, uint32_t used, uint32_t flags, uint32_t next_packet_size) "channel %u packet_num %" PRIu64 " pages %u flags 0x%x next packet size %u"
multifd_recv_new_channel(uint8_t id) "channel %u"
multifd_recv_sync_main(long packet_num) "packet num %ld"
multifd_recv_sync_main_signal(uint8_t id) "channel %u"
multifd_recv_sync_main_wait(uint8_t id) "channel %u"
multifd_recv_terminate_threads(bool error) "error %d"
multifd_recv_thread_end(uint8_t id, uint64_t packets, uint64_t pages) "channel %u packets %" PRIu64 " pages %" PRIu64
multifd_recv_thread_start(uint8_t id) "%u"
multifd_send(uint8_t id, uint64_t packet_num, uint32_t normal, uint32_t flags, uint32_t next_packet_size) "channel %u packet_num %" PRIu64 " normal pages %u flags 0x%x next packet size %u"
multifd_send_error(uint8_t id) "channel %u"
multifd_send_sync_main(long packet_num) "packet num %ld"
multifd_send_sync_main_signal(uint8_t id) "channel %u"
multifd_send_sync_main_wait(uint8_t id) "channel %u"
multifd_send_terminate_threads(bool error) "error %d"
multifd_send_thread_end(uint8_t id, uint64_t packets, uint64_t normal_pages) "channel %u packets %" PRIu64 " normal pages %" PRIu64
multifd_send_thread_start(uint8_t id) "%u"
multifd_tls_outgoing_handshake_start(void *ioc, void *tioc, const char *hostname) "ioc=%p tioc=%p hostname=%s"
multifd_tls_outgoing_handshake_error(void *ioc, const char *err) "ioc=%p err=%s"
multifd_tls_outgoing_handshake_complete(void *ioc) "ioc=%p"
multifd_set_outgoing_channel(void *ioc, const char *ioctype, const char *hostname, void *err) "ioc=%p ioctype=%s hostname=%s err=%p"
# migration.c
await_return_path_close_on_source_close(void) ""
await_return_path_close_on_source_joining(void) ""
migrate_set_state(const char *new_state) "new state %s"
migrate_fd_cleanup(void) ""
migrate_fd_error(const char *error_desc) "error=%s"
migrate_fd_cancel(void) ""
migrate_handle_rp_req_pages(const char *rbname, size_t start, size_t len) "in %s at 0x%zx len 0x%zx"
migrate_pending(uint64_t size, uint64_t max, uint64_t pre, uint64_t compat, uint64_t post) "pending size %" PRIu64 " max %" PRIu64 " (pre = %" PRIu64 " compat=%" PRIu64 " post=%" PRIu64 ")"
migrate_send_rp_message(int msg_type, uint16_t len) "%d: len %d"
migrate_send_rp_recv_bitmap(char *name, int64_t size) "block '%s' size 0x%"PRIi64
migration_completion_file_err(void) ""
migration_completion_vm_stop(int ret) "ret %d"
migration_completion_postcopy_end(void) ""
migration_completion_postcopy_end_after_complete(void) ""
migration_rate_limit_pre(int ms) "%d ms"
migration_rate_limit_post(int urgent) "urgent: %d"
migration_return_path_end_before(void) ""
migration_return_path_end_after(int rp_error) "%d"
migration_thread_after_loop(void) ""
migration_thread_file_err(void) ""
migration_thread_setup_complete(void) ""
open_return_path_on_source(void) ""
open_return_path_on_source_continue(void) ""
postcopy_start(void) ""
postcopy_pause_return_path(void) ""
postcopy_pause_return_path_continued(void) ""
postcopy_pause_continued(void) ""
postcopy_start_set_run(void) ""
migration: Maintain postcopy faulted addresses 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>
2020-10-21 23:27:18 +02:00
postcopy_page_req_add(void *addr, int count) "new page req %p total %d"
source_return_path_thread_bad_end(void) ""
source_return_path_thread_end(void) ""
source_return_path_thread_entry(void) ""
source_return_path_thread_loop_top(void) ""
source_return_path_thread_pong(uint32_t val) "0x%x"
source_return_path_thread_shut(uint32_t val) "0x%x"
source_return_path_thread_resume_ack(uint32_t v) "%"PRIu32
migration_thread_low_pending(uint64_t pending) "%" PRIu64
migrate_transferred(uint64_t tranferred, uint64_t time_spent, uint64_t bandwidth, uint64_t size) "transferred %" PRIu64 " time_spent %" PRIu64 " bandwidth %" PRIu64 " max_size %" PRId64
process_incoming_migration_co_end(int ret, int ps) "ret=%d postcopy-state=%d"
process_incoming_migration_co_postcopy_end_main(void) ""
migration: Postcopy preemption enablement This patch enables postcopy-preempt feature. It contains two major changes to the migration logic: (1) Postcopy requests are now sent via a different socket from precopy background migration stream, so as to be isolated from very high page request delays. (2) For huge page enabled hosts: when there's postcopy requests, they can now intercept a partial sending of huge host pages on src QEMU. After this patch, we'll live migrate a VM with two channels for postcopy: (1) PRECOPY channel, which is the default channel that transfers background pages; and (2) POSTCOPY channel, which only transfers requested pages. There's no strict rule of which channel to use, e.g., if a requested page is already being transferred on precopy channel, then we will keep using the same precopy channel to transfer the page even if it's explicitly requested. In 99% of the cases we'll prioritize the channels so we send requested page via the postcopy channel as long as possible. On the source QEMU, when we found a postcopy request, we'll interrupt the PRECOPY channel sending process and quickly switch to the POSTCOPY channel. After we serviced all the high priority postcopy pages, we'll switch back to PRECOPY channel so that we'll continue to send the interrupted huge page again. There's no new thread introduced on src QEMU. On the destination QEMU, one new thread is introduced to receive page data from the postcopy specific socket (done in the preparation patch). This patch has a side effect: after sending postcopy pages, previously we'll assume the guest will access follow up pages so we'll keep sending from there. Now it's changed. Instead of going on with a postcopy requested page, we'll go back and continue sending the precopy huge page (which can be intercepted by a postcopy request so the huge page can be sent partially before). Whether that's a problem is debatable, because "assuming the guest will continue to access the next page" may not really suite when huge pages are used, especially if the huge page is large (e.g. 1GB pages). So that locality hint is much meaningless if huge pages are used. Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Message-Id: <20220707185504.27203-1-peterx@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2022-07-07 20:55:04 +02:00
postcopy_preempt_enabled(bool value) "%d"
# channel.c
migration_set_incoming_channel(void *ioc, const char *ioctype) "ioc=%p ioctype=%s"
migration_set_outgoing_channel(void *ioc, const char *ioctype, const char *hostname, void *err) "ioc=%p ioctype=%s hostname=%s err=%p"
# global_state.c
migrate_state_too_big(void) ""
migrate_global_state_post_load(const char *state) "loaded state: %s"
migrate_global_state_pre_save(const char *state) "saved state: %s"
# rdma.c
qemu_rdma_accept_incoming_migration(void) ""
qemu_rdma_accept_incoming_migration_accepted(void) ""
qemu_rdma_accept_pin_state(bool pin) "%d"
qemu_rdma_accept_pin_verbsc(void *verbs) "Verbs context after listen: %p"
qemu_rdma_block_for_wrid_miss(const char *wcompstr, int wcomp, const char *gcompstr, uint64_t req) "A Wanted wrid %s (%d) but got %s (%" PRIu64 ")"
qemu_rdma_cleanup_disconnect(void) ""
qemu_rdma_close(void) ""
qemu_rdma_connect_pin_all_requested(void) ""
qemu_rdma_connect_pin_all_outcome(bool pin) "%d"
qemu_rdma_dest_init_trying(const char *host, const char *ip) "%s => %s"
qemu_rdma_dump_gid(const char *who, const char *src, const char *dst) "%s Source GID: %s, Dest GID: %s"
qemu_rdma_exchange_get_response_start(const char *desc) "CONTROL: %s receiving..."
qemu_rdma_exchange_get_response_none(const char *desc, int type) "Surprise: got %s (%d)"
qemu_rdma_exchange_send_issue_callback(void) ""
qemu_rdma_exchange_send_waiting(const char *desc) "Waiting for response %s"
qemu_rdma_exchange_send_received(const char *desc) "Response %s received."
qemu_rdma_fill(size_t control_len, size_t size) "RDMA %zd of %zd bytes already in buffer"
qemu_rdma_init_ram_blocks(int blocks) "Allocated %d local ram block structures"
qemu_rdma_poll_recv(const char *compstr, int64_t comp, int64_t id, int sent) "completion %s #%" PRId64 " received (%" PRId64 ") left %d"
qemu_rdma_poll_write(const char *compstr, int64_t comp, int left, uint64_t block, uint64_t chunk, void *local, void *remote) "completions %s (%" PRId64 ") left %d, block %" PRIu64 ", chunk: %" PRIu64 " %p %p"
qemu_rdma_poll_other(const char *compstr, int64_t comp, int left) "other completion %s (%" PRId64 ") received left %d"
qemu_rdma_post_send_control(const char *desc) "CONTROL: sending %s.."
qemu_rdma_register_and_get_keys(uint64_t len, void *start) "Registering %" PRIu64 " bytes @ %p"
qemu_rdma_register_odp_mr(const char *name) "Try to register On-Demand Paging memory region: %s"
qemu_rdma_advise_mr(const char *name, uint32_t len, uint64_t addr, const char *res) "Try to advise block %s prefetch at %" PRIu32 "@0x%" PRIx64 ": %s"
qemu_rdma_registration_handle_compress(int64_t length, int index, int64_t offset) "Zapping zero chunk: %" PRId64 " bytes, index %d, offset %" PRId64
qemu_rdma_registration_handle_finished(void) ""
qemu_rdma_registration_handle_ram_blocks(void) ""
qemu_rdma_registration_handle_ram_blocks_loop(const char *name, uint64_t offset, uint64_t length, void *local_host_addr, unsigned int src_index) "%s: @0x%" PRIx64 "/%" PRIu64 " host:@%p src_index: %u"
qemu_rdma_registration_handle_register(int requests) "%d requests"
qemu_rdma_registration_handle_register_loop(int req, int index, uint64_t addr, uint64_t chunks) "Registration request (%d): index %d, current_addr %" PRIu64 " chunks: %" PRIu64
qemu_rdma_registration_handle_register_rkey(int rkey) "0x%x"
qemu_rdma_registration_handle_unregister(int requests) "%d requests"
qemu_rdma_registration_handle_unregister_loop(int count, int index, uint64_t chunk) "Unregistration request (%d): index %d, chunk %" PRIu64
qemu_rdma_registration_handle_unregister_success(uint64_t chunk) "%" PRIu64
qemu_rdma_registration_handle_wait(void) ""
qemu_rdma_registration_start(uint64_t flags) "%" PRIu64
qemu_rdma_registration_stop(uint64_t flags) "%" PRIu64
qemu_rdma_registration_stop_ram(void) ""
qemu_rdma_resolve_host_trying(const char *host, const char *ip) "Trying %s => %s"
qemu_rdma_signal_unregister_append(uint64_t chunk, int pos) "Appending unregister chunk %" PRIu64 " at position %d"
qemu_rdma_signal_unregister_already(uint64_t chunk) "Unregister chunk %" PRIu64 " already in queue"
qemu_rdma_unregister_waiting_inflight(uint64_t chunk) "Cannot unregister inflight chunk: %" PRIu64
qemu_rdma_unregister_waiting_proc(uint64_t chunk, int pos) "Processing unregister for chunk: %" PRIu64 " at position %d"
qemu_rdma_unregister_waiting_send(uint64_t chunk) "Sending unregister for chunk: %" PRIu64
qemu_rdma_unregister_waiting_complete(uint64_t chunk) "Unregister for chunk: %" PRIu64 " complete."
qemu_rdma_write_flush(int sent) "sent total: %d"
qemu_rdma_write_one_block(int count, int block, uint64_t chunk, uint64_t current, uint64_t len, int nb_sent, int nb_chunks) "(%d) Not clobbering: block: %d chunk %" PRIu64 " current %" PRIu64 " len %" PRIu64 " %d %d"
qemu_rdma_write_one_post(uint64_t chunk, long addr, long remote, uint32_t len) "Posting chunk: %" PRIu64 ", addr: 0x%lx remote: 0x%lx, bytes %" PRIu32
qemu_rdma_write_one_queue_full(void) ""
qemu_rdma_write_one_recvregres(int mykey, int theirkey, uint64_t chunk) "Received registration result: my key: 0x%x their key 0x%x, chunk %" PRIu64
qemu_rdma_write_one_sendreg(uint64_t chunk, int len, int index, int64_t offset) "Sending registration request chunk %" PRIu64 " for %d bytes, index: %d, offset: %" PRId64
qemu_rdma_write_one_top(uint64_t chunks, uint64_t size) "Writing %" PRIu64 " chunks, (%" PRIu64 " MB)"
qemu_rdma_write_one_zero(uint64_t chunk, int len, int index, int64_t offset) "Entire chunk is zero, sending compress: %" PRIu64 " for %d bytes, index: %d, offset: %" PRId64
rdma_add_block(const char *block_name, int block, uint64_t addr, uint64_t offset, uint64_t len, uint64_t end, uint64_t bits, int chunks) "Added Block: '%s':%d, addr: %" PRIu64 ", offset: %" PRIu64 " length: %" PRIu64 " end: %" PRIu64 " bits %" PRIu64 " chunks %d"
rdma_block_notification_handle(const char *name, int index) "%s at %d"
rdma_delete_block(void *block, uint64_t addr, uint64_t offset, uint64_t len, uint64_t end, uint64_t bits, int chunks) "Deleted Block: %p, addr: %" PRIu64 ", offset: %" PRIu64 " length: %" PRIu64 " end: %" PRIu64 " bits %" PRIu64 " chunks %d"
rdma_start_incoming_migration(void) ""
rdma_start_incoming_migration_after_dest_init(void) ""
rdma_start_incoming_migration_after_rdma_listen(void) ""
rdma_start_outgoing_migration_after_rdma_connect(void) ""
rdma_start_outgoing_migration_after_rdma_source_init(void) ""
# postcopy-ram.c
postcopy_discard_send_finish(const char *ramblock, int nwords, int ncmds) "%s mask words sent=%d in %d commands"
postcopy_discard_send_range(const char *ramblock, unsigned long start, unsigned long length) "%s:%lx/%lx"
postcopy_cleanup_range(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=0x%zx length=0x%zx"
postcopy_init_range(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=0x%zx length=0x%zx"
postcopy_nhp_range(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=0x%zx length=0x%zx"
postcopy_place_page(void *host_addr) "host=%p"
postcopy_place_page_zero(void *host_addr) "host=%p"
postcopy_ram_enable_notify(void) ""
mark_postcopy_blocktime_begin(uint64_t addr, void *dd, uint32_t time, int cpu, int received) "addr: 0x%" PRIx64 ", dd: %p, time: %u, cpu: %d, already_received: %d"
mark_postcopy_blocktime_end(uint64_t addr, void *dd, uint32_t time, int affected_cpu) "addr: 0x%" PRIx64 ", dd: %p, time: %u, affected_cpu: %d"
postcopy_pause_fault_thread(void) ""
postcopy_pause_fault_thread_continued(void) ""
postcopy_pause_fast_load(void) ""
postcopy_pause_fast_load_continued(void) ""
postcopy_ram_fault_thread_entry(void) ""
postcopy_ram_fault_thread_exit(void) ""
postcopy_ram_fault_thread_fds_core(int baseufd, int quitfd) "ufd: %d quitfd: %d"
postcopy_ram_fault_thread_fds_extra(size_t index, const char *name, int fd) "%zd/%s: %d"
postcopy_ram_fault_thread_quit(void) ""
postcopy_ram_fault_thread_request(uint64_t hostaddr, const char *ramblock, size_t offset, uint32_t pid) "Request for HVA=0x%" PRIx64 " rb=%s offset=0x%zx pid=%u"
postcopy_ram_incoming_cleanup_closeuf(void) ""
postcopy_ram_incoming_cleanup_entry(void) ""
postcopy_ram_incoming_cleanup_exit(void) ""
postcopy_ram_incoming_cleanup_join(void) ""
postcopy_ram_incoming_cleanup_blocktime(uint64_t total) "total blocktime %" PRIu64
postcopy_request_shared_page(const char *sharer, const char *rb, uint64_t rb_offset) "for %s in %s offset 0x%"PRIx64
postcopy_request_shared_page_present(const char *sharer, const char *rb, uint64_t rb_offset) "%s already %s offset 0x%"PRIx64
postcopy_wake_shared(uint64_t client_addr, const char *rb) "at 0x%"PRIx64" in %s"
migration: Maintain postcopy faulted addresses 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>
2020-10-21 23:27:18 +02:00
postcopy_page_req_del(void *addr, int count) "resolved page req %p total %d"
postcopy_preempt_new_channel(void) ""
postcopy_preempt_thread_entry(void) ""
postcopy_preempt_thread_exit(void) ""
get_mem_fault_cpu_index(int cpu, uint32_t pid) "cpu: %d, pid: %u"
# exec.c
migration_exec_outgoing(const char *cmd) "cmd=%s"
migration_exec_incoming(const char *cmd) "cmd=%s"
# fd.c
migration_fd_outgoing(int fd) "fd=%d"
migration_fd_incoming(int fd) "fd=%d"
# socket.c
migration_socket_incoming_accepted(void) ""
migration_socket_outgoing_connected(const char *hostname) "hostname=%s"
migration_socket_outgoing_error(const char *err) "error=%s"
# tls.c
migration_tls_outgoing_handshake_start(const char *hostname) "hostname=%s"
migration_tls_outgoing_handshake_error(const char *err) "err=%s"
migration_tls_outgoing_handshake_complete(void) ""
migration_tls_incoming_handshake_start(void) ""
migration_tls_incoming_handshake_error(const char *err) "err=%s"
migration_tls_incoming_handshake_complete(void) ""
# colo.c
colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
COLO: Introduce checkpointing protocol We need communications protocol of user-defined to control the checkpointing process. The new checkpointing request is started by Primary VM, and the interactive process like below: Checkpoint synchronizing points: Primary Secondary initial work 'checkpoint-ready' <-------------------- @ 'checkpoint-request' @ --------------------> Suspend (Only in hybrid mode) 'checkpoint-reply' <-------------------- @ Suspend&Save state 'vmstate-send' @ --------------------> Send state Receive state 'vmstate-received' <-------------------- @ Release packets Load state 'vmstate-load' <-------------------- @ Resume Resume (Only in hybrid mode) Start Comparing (Only in hybrid mode) 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. 4) For now, we only support 'periodic' checkpoint, for which the Secondary VM is not running, later we will support 'hybrid' mode. 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> Cc: Eric Blake <eblake@redhat.com> Cc: Markus Armbruster <armbru@redhat.com> Cc: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Amit Shah <amit.shah@redhat.com> Signed-off-by: Amit Shah <amit@amitshah.net>
2016-10-27 08:42:57 +02:00
colo_send_message(const char *msg) "Send '%s' message"
colo_receive_message(const char *msg) "Receive '%s' message"
# colo-failover.c
colo_failover_set_state(const char *new_state) "new state %s"
# block-dirty-bitmap.c
send_bitmap_header_enter(void) ""
send_bitmap_bits(uint32_t flags, uint64_t start_sector, uint32_t nr_sectors, uint64_t data_size) "flags: 0x%x, start_sector: %" PRIu64 ", nr_sectors: %" PRIu32 ", data_size: %" PRIu64
dirty_bitmap_save_iterate(int in_postcopy) "in postcopy: %d"
dirty_bitmap_save_complete_enter(void) ""
dirty_bitmap_save_complete_finish(void) ""
dirty_bitmap_save_pending(uint64_t pending, uint64_t max_size) "pending %" PRIu64 " max: %" PRIu64
dirty_bitmap_load_complete(void) ""
dirty_bitmap_load_bits_enter(uint64_t first_sector, uint32_t nr_sectors) "chunk: %" PRIu64 " %" PRIu32
dirty_bitmap_load_bits_zeroes(void) ""
dirty_bitmap_load_header(uint32_t flags) "flags 0x%x"
dirty_bitmap_load_enter(void) ""
dirty_bitmap_load_success(void) ""
# dirtyrate.c
dirtyrate_set_state(const char *new_state) "new state %s"
query_dirty_rate_info(const char *new_state) "current state %s"
get_ramblock_vfn_hash(const char *idstr, uint64_t vfn, uint32_t crc) "ramblock name: %s, vfn: %"PRIu64 ", crc: %" PRIu32
calc_page_dirty_rate(const char *idstr, uint32_t new_crc, uint32_t old_crc) "ramblock name: %s, new crc: %" PRIu32 ", old crc: %" PRIu32
skip_sample_ramblock(const char *idstr, uint64_t ramblock_size) "ramblock name: %s, ramblock size: %" PRIu64
find_page_matched(const char *idstr) "ramblock %s addr or size changed"
dirtyrate_calculate(int64_t dirtyrate) "dirty rate: %" PRIi64 " MB/s"
dirtyrate_do_calculate_vcpu(int idx, uint64_t rate) "vcpu[%d]: %"PRIu64 " MB/s"
# block.c
migration_block_init_shared(const char *blk_device_name) "Start migration for %s with shared base image"
migration_block_init_full(const char *blk_device_name) "Start full migration for %s"
migration_block_save_device_dirty(int64_t sector) "Error reading sector %" PRId64
migration_block_flush_blks(const char *action, int submitted, int read_done, int transferred) "%s submitted %d read_done %d transferred %d"
migration_block_save(const char *mig_stage, int submitted, int transferred) "Enter save live %s submitted %d transferred %d"
migration_block_save_complete(void) "Block migration completed"
migration_block_save_pending(uint64_t pending) "Enter save live pending %" PRIu64
# page_cache.c
migration_pagecache_init(int64_t max_num_items) "Setting cache buckets to %" PRId64
migration_pagecache_insert(void) "Error allocating page"