__init__.py 文件源码

def split(args):
    chunk_mem_gb = cr_utils.get_mem_gb_request_from_barcode_whitelist(args.barcode_whitelist)
    whitelist_mem_gb = cr_utils.get_mem_gb_request_from_barcode_whitelist(args.barcode_whitelist, args.gem_groups, use_min=False)

    # Estimate the total number of rows in the final molecule info. Worst case.
    total_reads = cr_utils.get_metric_from_json(args.extract_reads_summary, 'total_reads')
    mol_info_rows = total_reads

    # Memory for sorting in MoleculeCounter.concatenate_sort:
    # N = total number of rows
    # 8*N bytes to store the sort indices
    # (8+8+8)*N bytes to load, concatenate, and index into a 64-bit data column
    mol_info_mem_gb = int(math.ceil((32 * mol_info_rows)/1e9))
    join_mem_gb = min(MAX_MEM_GB, max(cr_constants.MIN_MEM_GB, whitelist_mem_gb + mol_info_mem_gb))

    chunks = []
    for chunk_input in args.inputs:
        chunks.append({
            'chunk_input': chunk_input,
            '__mem_gb': chunk_mem_gb,
        })
    join = {
        '__mem_gb': join_mem_gb,
    }
    return {'chunks': chunks, 'join': join}