Files
rocm-systems/tests/hsa-memory-allocation/validate.py
T
itrowbri 3bd7773cf7 Memory Allocation Tracking (#1142)
* Initial commit: Need to implement wrapper function to collect data and test that wrapper function is correctly replacing core HSA functions

* Attempted to implement wrapper implementation for hsa memory allocation functions. Need to modify generate record files and test if implementation is working as expected

* Debugging and implementing generateCSV function

* Memory allocation size and starting address outputted to csv and json file formats

* Formatting

* Initial setup for OTF2 and Perfetto generation

* Collecting agent id for memory_allocation and formatting

* Modified memory_allocation.cpp to set up code for AMD_EXT commands

* Support for memory_pool_allocate added

* Removed accidently added file

* Made flag optional and added more OTF2 and Perfetto code. Needs testing to ensure perfetto and OTF2 works

* Formatting

* Fixed perfetto and otf2 output

* Fixed flag issue due to incorrect buffer use

* Updated documentation

* Small cleaning and comments

* Added test for HSA memory allocation tracing

* Fixed summary test validation errors due to allocation tracing. Added type to location_base to create unique event ids for allocation due to OTF2 trace error

* Decreased lower limit of hip calls for test

* Modified summary tests to vary number of allocate requests

* Minor fixes to address comments. Still need to address OTF2 comments

* Fix docs and changed OTF2 to use enum for type specified in location_base construction

* Fixed schema error

* Added vmem command tracking. Need to add test

* Updated test to work with vmem command and updated generateCSV to output int instead of hex string.

* OTF2 enum update and mispelling fix

* CI does not support Virtual Memory API. Removed vmem test. Will add back if CI is modifed to suport vmem API

* Update CMakeLists.txt for memory allocation test

* Updated summary test

* Minor fixes to address comments

* Moved domain_type.hpp enum to before LAST

* Fixed compile errors and formatting

* Fixed stats summary domain name error

* Added rocprofv3 test

* Page migration test fix

* Undo page migration test changes. Failures do not appear to have to do with memory allocation
2024-11-18 20:22:14 -06:00

290 lines
11 KiB
Python

#!/usr/bin/env python3
import sys
import pytest
# helper function
def node_exists(name, data, min_len=1):
assert name in data
assert data[name] is not None
if isinstance(data[name], (list, tuple, dict, set)):
assert len(data[name]) >= min_len, f"{name}:\n{data}"
def test_data_structure(input_data):
"""verify minimum amount of expected data is present"""
data = input_data
node_exists("rocprofiler-sdk-json-tool", data)
sdk_data = data["rocprofiler-sdk-json-tool"]
node_exists("metadata", sdk_data)
node_exists("pid", sdk_data["metadata"])
node_exists("main_tid", sdk_data["metadata"])
node_exists("init_time", sdk_data["metadata"])
node_exists("fini_time", sdk_data["metadata"])
node_exists("agents", sdk_data)
node_exists("call_stack", sdk_data)
node_exists("callback_records", sdk_data)
node_exists("buffer_records", sdk_data)
node_exists("names", sdk_data["callback_records"])
node_exists("hsa_api_traces", sdk_data["callback_records"])
node_exists("memory_allocations", sdk_data["callback_records"])
node_exists("names", sdk_data["buffer_records"])
node_exists("hsa_api_traces", sdk_data["callback_records"])
node_exists("memory_allocations", sdk_data["buffer_records"])
def test_size_entries(input_data):
# check that size fields are > 0 but account for function arguments
# which are named "size"
def check_size(data, bt):
if "size" in data.keys():
if isinstance(data["size"], str) and bt.endswith('["args"]'):
pass
else:
assert data["size"] > 0, f"origin: {bt}"
# recursively check the entire data structure
def iterate_data(data, bt):
if isinstance(data, (list, tuple)):
for i, itr in enumerate(data):
if isinstance(itr, dict):
check_size(itr, f"{bt}[{i}]")
iterate_data(itr, f"{bt}[{i}]")
elif isinstance(data, dict):
check_size(data, f"{bt}")
for key, itr in data.items():
iterate_data(itr, f'{bt}["{key}"]')
# start recursive check over entire JSON dict
iterate_data(input_data, "input_data")
def test_timestamps(input_data):
"""Verify starting timestamps are less than ending timestamps"""
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
cb_start = {}
cb_end = {}
for titr in ["hsa_api_traces"]:
for itr in sdk_data["callback_records"][titr]:
cid = itr["correlation_id"]["internal"]
phase = itr["phase"]
if phase == 1:
cb_start[cid] = itr["timestamp"]
elif phase == 2:
cb_end[cid] = itr["timestamp"]
assert cb_start[cid] <= itr["timestamp"]
else:
assert phase == 1 or phase == 2
for itr in sdk_data["buffer_records"][titr]:
assert itr["start_timestamp"] <= itr["end_timestamp"]
for titr in ["memory_allocations"]:
for itr in sdk_data["buffer_records"][titr]:
assert itr["start_timestamp"] < itr["end_timestamp"], f"[{titr}] {itr}"
assert itr["correlation_id"]["internal"] > 0, f"[{titr}] {itr}"
assert itr["correlation_id"]["external"] > 0, f"[{titr}] {itr}"
assert (
sdk_data["metadata"]["init_time"] < itr["start_timestamp"]
), f"[{titr}] {itr}"
assert (
sdk_data["metadata"]["init_time"] < itr["end_timestamp"]
), f"[{titr}] {itr}"
assert (
sdk_data["metadata"]["fini_time"] > itr["start_timestamp"]
), f"[{titr}] {itr}"
assert (
sdk_data["metadata"]["fini_time"] > itr["end_timestamp"]
), f"[{titr}] {itr}"
api_start = cb_start[itr["correlation_id"]["internal"]]
# api_end = cb_end[itr["correlation_id"]["internal"]]
assert api_start < itr["start_timestamp"], f"[{titr}] {itr}"
# assert api_end <= itr["end_timestamp"], f"[{titr}] {itr}"
def test_internal_correlation_ids(input_data):
"""Assure correlation ids are unique"""
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
api_corr_ids = []
for titr in ["hsa_api_traces"]:
for itr in sdk_data["callback_records"][titr]:
api_corr_ids.append(itr["correlation_id"]["internal"])
for itr in sdk_data["buffer_records"][titr]:
api_corr_ids.append(itr["correlation_id"]["internal"])
api_corr_ids_sorted = sorted(api_corr_ids)
api_corr_ids_unique = list(set(api_corr_ids))
for itr in sdk_data["buffer_records"]["memory_allocations"]:
assert itr["correlation_id"]["internal"] in api_corr_ids_unique
len_corr_id_unq = len(api_corr_ids_unique)
assert len(api_corr_ids) != len_corr_id_unq
assert max(api_corr_ids_sorted) == len_corr_id_unq
def test_external_correlation_ids(input_data):
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
extern_corr_ids = []
for titr in ["hsa_api_traces"]:
for itr in sdk_data["callback_records"][titr]:
assert itr["correlation_id"]["external"] > 0
assert itr["thread_id"] == itr["correlation_id"]["external"]
extern_corr_ids.append(itr["correlation_id"]["external"])
extern_corr_ids = list(set(sorted(extern_corr_ids)))
for titr in ["hsa_api_traces"]:
for itr in sdk_data["buffer_records"][titr]:
assert itr["correlation_id"]["external"] > 0, f"[{titr}] {itr}"
assert (
itr["thread_id"] == itr["correlation_id"]["external"]
), f"[{titr}] {itr}"
assert itr["thread_id"] in extern_corr_ids, f"[{titr}] {itr}"
assert itr["correlation_id"]["external"] in extern_corr_ids, f"[{titr}] {itr}"
for titr in ["memory_allocations"]:
for itr in sdk_data["buffer_records"][titr]:
assert itr["correlation_id"]["external"] > 0, f"[{titr}] {itr}"
assert itr["correlation_id"]["external"] in extern_corr_ids, f"[{titr}] {itr}"
for itr in sdk_data["callback_records"][titr]:
assert itr["correlation_id"]["external"] > 0, f"[{titr}] {itr}"
assert itr["correlation_id"]["external"] in extern_corr_ids, f"[{titr}] {itr}"
def test_memory_alloc_sizes(input_data):
"""Ensure trace file memory allocation operations match up with the memory allocation operations performed in hsa-memory-allocation"""
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
# Op values:
# 0 == ??? (unknown)
# 1 == hsa_memory_allocate
# 2 == hsa_amd_ext_memory_allocate
# 3 == hsa_amd_vmem_handle_create
memory_alloc_cnt = dict(
[
(idx, {"agent": set(), "starting_addr": set(), "size": set(), "count": 0})
for idx in range(1, 4)
]
)
for itr in sdk_data["buffer_records"]["memory_allocations"]:
op_id = itr["operation"]
assert op_id > 0 and op_id <= 3, f"{itr}"
memory_alloc_cnt[op_id]["count"] += 1
memory_alloc_cnt[op_id]["starting_addr"].add(itr.starting_address)
memory_alloc_cnt[op_id]["size"].add(itr.allocation_size)
memory_alloc_cnt[op_id]["agent"].add(itr.agent_id.handle)
for itr in sdk_data["callback_records"]["memory_copies"]:
op_id = itr.operation
assert op_id > 0 and op_id <= 3, f"{itr}"
memory_alloc_cnt[op_id]["count"] += 1
phase = itr.phase
pitr = itr.payload
assert phase is not None, f"{itr}"
assert pitr is not None, f"{itr}"
if phase == 1:
assert pitr.start_timestamp == 0, f"{itr}"
assert pitr.end_timestamp == 0, f"{itr}"
elif phase == 2:
assert pitr.start_timestamp > 0, f"{itr}"
assert pitr.end_timestamp > 0, f"{itr}"
assert pitr.end_timestamp >= pitr.start_timestamp, f"{itr}"
memory_alloc_cnt[op_id]["starting_addr"].add(pitr.starting_address)
memory_alloc_cnt[op_id]["size"].add(pitr.allocation_size)
memory_alloc_cnt[op_id]["agent"].add(pitr.agent_id.handle)
else:
assert phase == 1 or phase == 2, f"{itr}"
# In the memory allocation test which generates this file
# 6 hsa_memory_allocation calls with 1024 bytes were called
# and 9 hsa_amd_memory_pool_allocations with 512 bytes
# were called
assert memory_alloc_cnt[1]["count"] == 6
assert memory_alloc_cnt[2]["count"] == 9
# assert memory_alloc_cnt[3]["count"] == 3
assert len(memory_alloc_cnt[1]["starting_addr"]) == 6
assert len(memory_alloc_cnt[2]["starting_addr"]) == 9
# assert len(memory_alloc_cnt[3]["starting_addr"]) == 3
assert len(memory_alloc_cnt[1]["size"]) == 1
assert len(memory_alloc_cnt[2]["size"]) == 1
# assert len(memory_alloc_cnt[3]["size"]) == 1
assert 1024 in memory_alloc_cnt[1]["size"]
assert 512 in memory_alloc_cnt[2]["size"]
assert len(memory_alloc_cnt[1]["agent"]) == 1
assert len(memory_alloc_cnt[2]["agent"]) == 1
# assert len(memory_alloc_cnt[3]["agent"]) == 1
assert memory_alloc_cnt[1]["agent"] != memory_alloc_cnt[2]["agent"]
# assert memory_alloc_cnt[2]["agent"] == memory_alloc_cnt[3]["agent"]
def test_retired_correlation_ids(input_data):
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
def _sort_dict(inp):
return dict(sorted(inp.items()))
api_corr_ids = {}
for titr in ["hsa_api_traces"]:
for itr in sdk_data["buffer_records"][titr]:
corr_id = itr["correlation_id"]["internal"]
assert corr_id not in api_corr_ids.keys()
api_corr_ids[corr_id] = itr
alloc_corr_ids = {}
for titr in ["memory_allocations"]:
for itr in sdk_data["buffer_records"][titr]:
corr_id = itr["correlation_id"]["internal"]
assert corr_id not in alloc_corr_ids.keys()
alloc_corr_ids[corr_id] = itr
retired_corr_ids = {}
for itr in sdk_data["buffer_records"]["retired_correlation_ids"]:
corr_id = itr["internal_correlation_id"]
assert corr_id not in retired_corr_ids.keys()
retired_corr_ids[corr_id] = itr
api_corr_ids = _sort_dict(api_corr_ids)
alloc_corr_ids = _sort_dict(alloc_corr_ids)
retired_corr_ids = _sort_dict(retired_corr_ids)
for cid, itr in alloc_corr_ids.items():
assert cid in retired_corr_ids.keys()
retired_ts = retired_corr_ids[cid]["timestamp"]
end_ts = itr["end_timestamp"]
assert (retired_ts - end_ts) > 0, f"correlation-id: {cid}, data: {itr}"
for cid, itr in api_corr_ids.items():
assert cid in retired_corr_ids.keys()
retired_ts = retired_corr_ids[cid]["timestamp"]
end_ts = itr["end_timestamp"]
assert (retired_ts - end_ts) > 0, f"correlation-id: {cid}, data: {itr}"
assert len(api_corr_ids.keys()) == (len(retired_corr_ids.keys()))
if __name__ == "__main__":
exit_code = pytest.main(["-x", __file__] + sys.argv[1:])
sys.exit(exit_code)