def local_main():
current_dir = os.path.dirname(os.path.realpath(__file__))
data_path = os.path.join(current_dir, "data")
for pid in {"1", "2"}:
# define name for the workflow
workflow_name = "aspirin-local-test-" + pid
# configure conclave
conclave_config = CodeGenConfig(workflow_name, int(pid))
conclave_config.all_pids = [int(pid)]
sharemind_conf = SharemindCodeGenConfig("/mnt/shared", use_docker=False, use_hdfs=False)
conclave_config.with_sharemind_config(sharemind_conf)
# point conclave to the directory where the generated code should be stored/ read from
conclave_config.code_path = os.path.join("/mnt/shared", workflow_name)
# point conclave to directory where data is to be read from...
conclave_config.input_path = data_path
# and written to
conclave_config.output_path = data_path
suffix = "left" if pid == "1" else "right"
# define this party's unique ID (in this demo there is only one party)
job_queue = generate_code(lambda: protocol_local(suffix, int(pid)), conclave_config, ["sharemind"], ["python"],
apply_optimizations=False)
dispatch_jobs(job_queue, conclave_config)
res_mpc = read_rel(data_path + "/" + "actual_mpc_open.csv")
res_left = read_rel(data_path + "/" + "actual_left.csv")
res_right = read_rel(data_path + "/" + "actual_right.csv")
assert len(res_mpc) == 1
assert len(res_left) == 1
assert len(res_right) == 1
res = [[res_mpc[0][0] + res_left[0][0] + res_right[0][0]]]
write_rel(data_path, "actual_open.csv", res, "1")
def run_mpc(pid: str, data_root: str, mpc_backend: str):
workflow_name = "aspirin-mpc-join-" + pid + "-" + data_root
conclave_config = CodeGenConfig(workflow_name, int(pid))
conclave_config.use_leaky_ops = False
conclave_config.code_path = os.path.join("/mnt/shared", workflow_name)
conclave_config.input_path = os.path.join("/mnt/shared", data_root)
conclave_config.output_path = os.path.join("/mnt/shared", data_root)
job_queue = generate_code(lambda: protocol_mpc(conclave_config.all_pids),
conclave_config, [mpc_backend], ["python"],
apply_optimizations=True)
dispatch_jobs(job_queue, conclave_config)
def main_mpc(pid: str, mpc_backend: str):
# define name for the workflow
workflow_name = "real-aspirin-partitioned-" + pid
# configure conclave
mpc_backend = sys.argv[2]
conclave_config = CodeGenConfig(workflow_name, int(pid)) \
.with_default_mpc_config(mpc_backend)
current_dir = os.path.dirname(os.path.realpath(__file__))
# point conclave to the directory where the generated code should be stored/ read from
conclave_config.code_path = os.path.join("/mnt/shared", workflow_name)
# point conclave to directory where data is to be read from...
conclave_config.input_path = os.path.join(current_dir, "data")
# and written to
conclave_config.output_path = os.path.join(current_dir, "data")
job_queue = generate_code(lambda: protocol_mpc(conclave_config.all_pids), conclave_config, [mpc_backend],
["python"], apply_optimizations=True)
dispatch_jobs(job_queue, conclave_config)
def run_local(pid: str, data_root: str):
workflow_name = "aspirin-local-join-" + pid + "-" + data_root
conclave_config = CodeGenConfig(workflow_name, int(pid))
conclave_config.all_pids = [int(pid)]
sharemind_conf = SharemindCodeGenConfig("/mnt/shared",
use_docker=False,
use_hdfs=False)
conclave_config.with_sharemind_config(sharemind_conf)
conclave_config.code_path = os.path.join("/mnt/shared", workflow_name)
conclave_config.input_path = os.path.join("/mnt/shared", data_root)
conclave_config.output_path = os.path.join("/mnt/shared", data_root)
suffix = "left" if pid == "1" else "right"
job_queue = generate_code(lambda: protocol_local(suffix, int(pid)),
conclave_config, ["sharemind"], ["python"],
apply_optimizations=False)
dispatch_jobs(job_queue, conclave_config)
def main():
pid = sys.argv[1]
data_root = sys.argv[2]
mpc_backend = sys.argv[3]
# define name for the workflow
workflow_name = "aspirin-large-join-" + pid + "-" + data_root
# configure conclave
conclave_config = CodeGenConfig(workflow_name, int(pid))
if mpc_backend == "sharemind":
sharemind_conf = SharemindCodeGenConfig("/mnt/shared",
use_docker=True,
use_hdfs=False)
conclave_config.with_sharemind_config(sharemind_conf)
elif mpc_backend == "obliv-c":
conclave_config.all_pids = [1, 2]
net_conf = [{
"host": "ca-spark-node-0",
"port": 8001
}, {
"host": "cb-spark-node-0",
"port": 8002
}]
net = NetworkConfig(net_conf, int(pid))
conclave_config.with_network_config(net)
oc_conf = OblivcConfig("/obliv-c/bin/oblivcc", "ca-spark-node-0:9000")
conclave_config.with_oc_config(oc_conf)
else:
raise Exception("Unknown MPC backend {}".format(mpc_backend))
conclave_config.code_path = os.path.join("/mnt/shared", workflow_name)
conclave_config.input_path = os.path.join("/mnt/shared", data_root)
conclave_config.output_path = os.path.join("/mnt/shared", data_root)
job_queue = generate_code(protocol,
conclave_config, [mpc_backend], ["python"],
apply_optimizations=True)
dispatch_jobs(job_queue, conclave_config)
joined = cc.join(left, right, "joined", ["a"], ["c"])
cc.aggregate(joined, "expected", ["b"], "d", "sum", "total")
return {left, right}
if __name__ == "__main__":
pid = sys.argv[1]
# define name for the workflow
workflow_name = "simple-oblivious-test-" + pid
# configure conclave
conclave_config = CodeGenConfig(workflow_name, int(pid))
conclave_config.all_pids = [1]
sharemind_conf = SharemindCodeGenConfig("/mnt/shared",
use_docker=False,
use_hdfs=False)
conclave_config.with_sharemind_config(sharemind_conf)
current_dir = os.path.dirname(os.path.realpath(__file__))
# point conclave to the directory where the generated code should be stored/ read from
conclave_config.code_path = os.path.join("/mnt/shared", workflow_name)
# point conclave to directory where data is to be read from...
conclave_config.input_path = os.path.join(current_dir, "data")
# and written to
conclave_config.output_path = os.path.join(current_dir, "data")
# define this party's unique ID (in this demo there is only one party)
job_queue = generate_code(protocol,
conclave_config, ["sharemind"], ["python"],
apply_optimizations=False)
dispatch_jobs(job_queue, conclave_config)
squared = lang.multiply(input_relation, "squared", "column_b",
["column_b", "column_b"])
# sum group by column_a on column_b and rename group-over column to summed
lang.aggregate(squared, "aggregated", ["column_a"], "column_b", "+",
"summed")
# leaf nodes are automatically written to file so aggregated will be written to ./data/aggregated.csv
# return all input relations
return {input_relation}
if __name__ == "__main__":
# define name for the workflow
workflow_name = "python-demo"
# configure conclave
conclave_config = CodeGenConfig(workflow_name)
# need the absolute path to current directory
current_dir = os.path.dirname(os.path.realpath(__file__))
# point conclave to the directory where the generated code should be stored/ read from
conclave_config.code_path = os.path.join(current_dir, workflow_name)
# point conclave to directory where data is to be read from...
conclave_config.input_path = os.path.join(current_dir, "data")
# and written to
conclave_config.output_path = os.path.join(current_dir, "data")
# define this party's unique ID (in this demo there is only one party)
conclave_config.pid = 1
# define all parties involved in this workflow
conclave_config.all_pids = [1]
# compile and execute protocol, specifying available mpc and local processing backends
generate_and_dispatch(protocol, conclave_config, ["sharemind"], ["python"])
