import os
import pickle

import torch
import torch.distributed as dist

# import torch.distributed.elastic.multiprocessing.api


def setup_for_distributed(is_master):
    """
    This function disables printing when not in master process
    """
    import builtins as __builtin__
    builtin_print = __builtin__.print

    def new_print(*args, **kwargs):
        force = kwargs.pop('force', False)
        if is_master or force:
            builtin_print(*args, **kwargs)

    __builtin__.print = new_print


def is_dist_avail_and_initialized():
    return dist.is_available() and dist.is_initialized()


def get_world_size():
    if not is_dist_avail_and_initialized():
        return 1
    return dist.get_world_size()


def get_rank():
    if not is_dist_avail_and_initialized():
        return 0
    return dist.get_rank()


def get_local_size():
    if not is_dist_avail_and_initialized():
        return 1
    return int(os.environ['LOCAL_SIZE'])


def get_local_rank():
    if not is_dist_avail_and_initialized():
        return 0
    return int(os.environ['LOCAL_RANK'])


def is_main_process():
    return get_rank() == 0


def save_on_master(*args, **kwargs):
    if is_main_process():
        torch.save(*args, **kwargs)


def init_distributed_mode(args):
    if 'RANK' in os.environ and 'WORLD_SIZE' in os.environ:
        args.rank = int(os.environ["RANK"])
        args.world_size = int(os.environ['WORLD_SIZE'])
        args.gpu = int(os.environ['LOCAL_RANK'])
        args.dist_url = 'env://'
        os.environ['LOCAL_SIZE'] = str(torch.cuda.device_count())
    else:
        print('Not using distributed mode')
        args.world_size = 1
        args.distributed = False
        return
    args.distributed = True
    torch.cuda.set_device(args.gpu)
    args.dist_backend = 'nccl'
    print('| distributed init (rank {}): {}'.format(
        args.rank, args.dist_url), flush=True)
    torch.distributed.init_process_group(backend=args.dist_backend, init_method=args.dist_url,
                                         world_size=args.world_size, rank=args.rank)
    torch.distributed.barrier()
    setup_for_distributed(args.rank == 0)

    if args.batch_size % args.world_size != 0:
        raise Exception("Batch size should be divisible by world size.")
    args.batch_size //= args.world_size
    args.eval_batch_size //= args.world_size


def all_gather(data):
    """
    Run all_gather on arbitrary picklable data (not necessarily tensors)
    Args:
        data: any picklable object
    Returns:
        list[data]: list of data gathered from each rank
    """
    world_size = get_world_size()
    if world_size == 1:
        return [data]

    # serialized to a Tensor
    buffer = pickle.dumps(data)
    storage = torch.ByteStorage.from_buffer(buffer)
    tensor = torch.ByteTensor(storage).to("cuda")

    # obtain Tensor size of each rank
    local_size = torch.tensor([tensor.numel()], device="cuda")
    size_list = [torch.tensor([0], device="cuda") for _ in range(world_size)]
    dist.all_gather(size_list, local_size)
    size_list = [int(size.item()) for size in size_list]
    max_size = max(size_list)

    # receiving Tensor from all ranks
    # we pad the tensor because torch all_gather does not support
    # gathering tensors of different shapes
    tensor_list = []
    for _ in size_list:
        tensor_list.append(torch.empty((max_size,), dtype=torch.uint8, device="cuda"))
    if local_size != max_size:
        padding = torch.empty(size=(max_size - local_size,), dtype=torch.uint8, device="cuda")
        tensor = torch.cat((tensor, padding), dim=0)
    dist.all_gather(tensor_list, tensor)

    data_list = []
    for size, tensor in zip(size_list, tensor_list):
        buffer = tensor.cpu().numpy().tobytes()[:size]
        data_list.append(pickle.loads(buffer))

    return data_list