thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 08:40:50 +00:00
Code Issues Packages Projects Releases Wiki Activity
6b2b3c1eb3
ClickHouse/tests/integration/test_catboost_evaluate/test.py
Robert Schulze 6b2b3c1eb3
feat: implement catboost in library-bridge 
This commit moves the catboost model evaluation out of the server
process into the library-bridge binary. This serves two goals: On the
one hand, crashes / memory corruptions of the catboost library no longer
affect the server. On the other hand, we can forbid loading dynamic
libraries in the server (catboost was the last consumer of this
functionality), thus improving security.

SQL syntax:

  SELECT
    catboostEvaluate('/path/to/model.bin', FEAT_1, ..., FEAT_N) > 0 AS prediction,
    ACTION AS target
  FROM amazon_train
  LIMIT 10

Required configuration:

  <catboost_lib_path>/path/to/libcatboostmodel.so</catboost_lib_path>

*** Implementation Details ***

The internal protocol between the server and the library-bridge is
simple:

- HTTP GET on path "/extdict_ping":
  A ping, used during the handshake to check if the library-bridge runs.

- HTTP POST on path "extdict_request"
  (1) Send a "catboost_GetTreeCount" request from the server to the
      bridge, containing a library path (e.g /home/user/libcatboost.so) and
      a model path (e.g. /home/user/model.bin). Rirst, this unloads the
      catboost library handler associated to the model path (if it was
      loaded), then loads the catboost library handler associated to the
      model path, then executes GetTreeCount() on the library handler and
      finally sends the result back to the server. Step (1) is called once
      by the server from FunctionCatBoostEvaluate::getReturnTypeImpl(). The
      library path handler is unloaded in the beginning because it contains
      state which may no longer be valid if the user runs
      catboost("/path/to/model.bin", ...) more than once and if "model.bin"
      was updated in between.
  (2) Send "catboost_Evaluate" from the server to the bridge, containing
      the model path and the features to run the interference on. Step (2)
      is called multiple times (once per chunk) by the server from function
      FunctionCatBoostEvaluate::executeImpl(). The library handler for the
      given model path is expected to be already loaded by Step (1).

Fixes #27870
2022-08-29 20:26:45 +00:00

203 lines
9.7 KiB
Python
Raw Blame History

import os
import sys
import time
import pytest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
from helpers.cluster import ClickHouseCluster
cluster = ClickHouseCluster(__file__)
instance = cluster.add_instance(
"instance", stay_alive=True, main_configs=["config/models_config.xml"]
)
@pytest.fixture(scope="module")
def ch_cluster():
try:
cluster.start()
os.system(
"docker cp {local} {cont_id}:{dist}".format(
local=os.path.join(SCRIPT_DIR, "model/."), cont_id=instance.docker_id, dist="/etc/clickhouse-server/model"
)
)
instance.restart_clickhouse()
yield cluster
finally:
cluster.shutdown()
# ---------------------------------------------------------------------------
# simple_model.bin has 2 float features and 9 categorical features
def testConstantFeatures(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
result = instance.query("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', 1.0, 2.0, 3, 4, 5, 6, 7, 8, 9, 10, 11);")
expected = "-1.930268705869267\n"
assert result == expected
def testNonConstantFeatures(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
instance.query("DROP TABLE IF EXISTS T;")
instance.query("CREATE TABLE T(ID UInt32, F1 Float32, F2 Float32, F3 UInt32, F4 UInt32, F5 UInt32, F6 UInt32, F7 UInt32, F8 UInt32, F9 Float32, F10 Float32, F11 Float32) ENGINE MergeTree ORDER BY ID;")
instance.query("INSERT INTO T VALUES(0, 1.0, 2.0, 3, 4, 5, 6, 7, 8, 9, 10, 11);")
result = instance.query("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', F1, F2, F3, F4, F5, F6, F7, F8, F9, F10, F11) from T;")
expected = "-1.930268705869267\n"
assert result == expected
instance.query("DROP TABLE IF EXISTS T;")
def testModelPathIsNotAConstString(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
err = instance.query_and_get_error("select catboostEvaluate(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11);")
assert "Illegal type UInt8 of first argument of function catboostEvaluate, expected a string" in err
instance.query("DROP TABLE IF EXISTS T;")
instance.query("CREATE TABLE T(ID UInt32, A String) ENGINE MergeTree ORDER BY ID")
instance.query("INSERT INTO T VALUES(0, 'test');")
err = instance.query_and_get_error("select catboostEvaluate(A, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11) FROM T;")
assert "First argument of function catboostEvaluate must be a constant string" in err
instance.query("DROP TABLE IF EXISTS T;")
def testWrongNumberOfFeatureArguments(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
err = instance.query_and_get_error("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin');")
assert "Function catboostEvaluate expects at least 2 arguments" in err
err = instance.query_and_get_error("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', 1, 2);")
assert "Number of columns is different with number of features: columns size 2 float features size 2 + cat features size 9" in err
def testFloatFeatureMustBeNumeric(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
err = instance.query_and_get_error("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', 1.0, 'a', 3, 4, 5, 6, 7, 8, 9, 10, 11);")
assert "Column 1 should be numeric to make float feature" in err
def testCategoricalFeatureMustBeNumericOrString(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
err = instance.query_and_get_error("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', 1.0, 2.0, 3, 4, 5, 6, 7, tuple(8), 9, 10, 11);")
assert "Column 7 should be numeric or string" in err
def testOnLowCardinalityFeatures(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
# same but on domain-compressed data
result = instance.query("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', toLowCardinality(1.0), toLowCardinality(2.0), toLowCardinality(3), toLowCardinality(4), toLowCardinality(5), toLowCardinality(6), toLowCardinality(7), toLowCardinality(8), toLowCardinality(9), toLowCardinality(10), toLowCardinality(11));")
expected = "-1.930268705869267\n"
assert result == expected
def testOnNullableFeatures(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
result = instance.query("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', toNullable(1.0), toNullable(2.0), toNullable(3), toNullable(4), toNullable(5), toNullable(6), toNullable(7), toNullable(8), toNullable(9), toNullable(10), toNullable(11));")
expected = "-1.930268705869267\n"
assert result == expected
# Actual NULLs are disallowed
err = instance.query_and_get_error("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', toNullable(NULL), toNullable(NULL), toNullable(NULL), toNullable(NULL), toNullable(NULL), toNullable(NULL), toNullable(NULL), toNullable(NULL), toNullable(NULL), toNullable(NULL), toNullable(NULL));")
assert "Column 0 should be numeric to make float feature" in err
def testInvalidLibraryPath(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
# temporarily move library elsewhere
instance.exec_in_container(["bash", "-c", "mv /etc/clickhouse-server/model/libcatboostmodel.so /etc/clickhouse-server/model/nonexistant.so"])
err = instance.query_and_get_error("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11);")
assert "Can't load library /etc/clickhouse-server/model/libcatboostmodel.so: file doesn't exist" in err
# restore
instance.exec_in_container(["bash", "-c", "mv /etc/clickhouse-server/model/nonexistant.so /etc/clickhouse-server/model/libcatboostmodel.so"])
def testInvalidModelPath(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
err = instance.query_and_get_error("select catboostEvaluate('', 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11);")
assert "Can't load model : file doesn't exist" in err
err = instance.query_and_get_error("select catboostEvaluate('model_non_existant.bin', 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11);")
assert "Can't load model model_non_existant.bin: file doesn't exist" in err
def testRecoveryAfterCrash(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
result = instance.query("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', 1.0, 2.0, 3, 4, 5, 6, 7, 8, 9, 10, 11);")
expected = "-1.930268705869267\n"
assert result == expected
instance.exec_in_container(
["bash", "-c", "kill -9 `pidof clickhouse-library-bridge`"], user="root"
)
result = instance.query("select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', 1.0, 2.0, 3, 4, 5, 6, 7, 8, 9, 10, 11);")
assert result == expected
# ---------------------------------------------------------------------------
# amazon_model.bin has 0 float features and 9 categorical features
def testAmazonModel(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
result = instance.query("select catboostEvaluate('/etc/clickhouse-server/model/amazon_model.bin', 1, 2, 3, 4, 5, 6, 7, 8, 9);")
expected = "0.7774665009089274\n"
assert result == expected
def testModelUpdate(ch_cluster):
if instance.is_built_with_memory_sanitizer():
pytest.skip("Memory Sanitizer cannot work with third-party shared libraries")
query = "select catboostEvaluate('/etc/clickhouse-server/model/simple_model.bin', 1.0, 2.0, 3, 4, 5, 6, 7, 8, 9, 10, 11);"
result = instance.query(query)
expected = "-1.930268705869267\n"
assert result == expected
# simulate an update of the model: temporarily move the amazon model in place of the simple model
instance.exec_in_container(["bash", "-c", "mv /etc/clickhouse-server/model/simple_model.bin /etc/clickhouse-server/model/simple_model.bin.bak"])
instance.exec_in_container(["bash", "-c", "mv /etc/clickhouse-server/model/amazon_model.bin /etc/clickhouse-server/model/simple_model.bin"])
# since the amazon model has a different number of features than the simple model, we should get an error
err = instance.query_and_get_error(query)
assert "Number of columns is different with number of features: columns size 11 float features size 0 + cat features size 9" in err
# restore
instance.exec_in_container(["bash", "-c", "mv /etc/clickhouse-server/model/simple_model.bin /etc/clickhouse-server/model/amazon_model.bin"])
instance.exec_in_container(["bash", "-c", "mv /etc/clickhouse-server/model/simple_model.bin.bak /etc/clickhouse-server/model/simple_model.bin"])
Reference in New Issue View Git Blame Copy Permalink