Cgroups api refactor (#6)

* Initial changes for log collector cgroups v2 support

* Fix pylint issues

* Fix pylint issues

* Fix pylint issues

* Check that both controllers are mounted in the chosen cgroups version for log collector

* Fix regex

* Update test_agent unit tests

* Fix unit tests

* Update format strings

* Fix broken cgroupconfigurator unit tests

* pyling

* Fix cgroups api unit tests

* Ignore unused args

* Ignore unused args

* Add cgroup configurator tests

* v2 required check in parent cgroup

* unit tests is_controller_enabled

* Fix test failure and pylint:

* pylint

* Update agent checks

* Fix controller enable logic and unit tests

* Remove changes to collect logs

* Fix pylint

* Add e2e test for v2

azurelinuxagent/agent.py

@@ -30,7 +30,8 @@
 import threading
 from azurelinuxagent.ga import logcollector, cgroupconfigurator
 from azurelinuxagent.ga.cgroup import AGENT_LOG_COLLECTOR, CpuCgroup, MemoryCgroup
-from azurelinuxagent.ga.cgroupapi import SystemdCgroupsApi
+from azurelinuxagent.ga.cgroupapi import get_cgroup_api
+from azurelinuxagent.ga.cgroupstelemetry import log_cgroup_warning
 
 import azurelinuxagent.common.conf as conf
 import azurelinuxagent.common.event as event
@@ -206,18 +207,29 @@ def collect_logs(self, is_full_mode):
 
         # Check the cgroups unit
         log_collector_monitor = None
-        cgroups_api = SystemdCgroupsApi()
-        cpu_cgroup_path, memory_cgroup_path = cgroups_api.get_process_cgroup_paths("self")
+        cgroups_api = get_cgroup_api()
+        cpu_cgroup_path = None
+        memory_cgroup_path = None
         if CollectLogsHandler.is_enabled_monitor_cgroups_check():
-            cpu_slice_matches = (cgroupconfigurator.LOGCOLLECTOR_SLICE in cpu_cgroup_path)
-            memory_slice_matches = (cgroupconfigurator.LOGCOLLECTOR_SLICE in memory_cgroup_path)
+            if cgroups_api is None:
+                log_cgroup_warning("Unable to determine what version of cgroups to use for log collector resource "
+                                   "monitoring and enforcement.")
+                sys.exit(logcollector.INVALID_CGROUPS_ERRCODE)
+
+            cpu_cgroup_path, memory_cgroup_path = cgroups_api.get_process_cgroup_paths("self")
+            cpu_slice_matches = False
+            memory_slice_matches = False
+            if cpu_cgroup_path is not None:
+                cpu_slice_matches = (cgroupconfigurator.LOGCOLLECTOR_SLICE in cpu_cgroup_path)
+            if memory_cgroup_path is not None:
+                memory_slice_matches = (cgroupconfigurator.LOGCOLLECTOR_SLICE in memory_cgroup_path)
 
             if not cpu_slice_matches or not memory_slice_matches:
-                logger.info("The Log Collector process is not in the proper cgroups:")
+                log_cgroup_warning("The Log Collector process is not in the proper cgroups:", send_event=False)
                 if not cpu_slice_matches:
-                    logger.info("\tunexpected cpu slice")
+                    log_cgroup_warning("\tunexpected cpu slice", send_event=False)
                 if not memory_slice_matches:
-                    logger.info("\tunexpected memory slice")
+                    log_cgroup_warning("\tunexpected memory slice", send_event=False)
 
                 sys.exit(logcollector.INVALID_CGROUPS_ERRCODE)
 

azurelinuxagent/ga/cgroupstelemetry.py

@@ -17,10 +17,23 @@
 import threading
 
 from azurelinuxagent.common import logger
+from azurelinuxagent.common.event import WALAEventOperation, add_event
 from azurelinuxagent.ga.cgroup import CpuCgroup
 from azurelinuxagent.common.future import ustr
 
 
+def log_cgroup_info(formatted_string, op=WALAEventOperation.CGroupsInfo, send_event=True):
+    logger.info("[CGI] " + formatted_string)
+    if send_event:
+        add_event(op=op, message=formatted_string)
+
+
+def log_cgroup_warning(formatted_string, op=WALAEventOperation.CGroupsInfo, send_event=True):
+    logger.info("[CGW] " + formatted_string)  # log as INFO for now, in the future it should be logged as WARNING
+    if send_event:
+        add_event(op=op, message=formatted_string, is_success=False, log_event=False)
+
+
 class CGroupsTelemetry(object):
     """
     """

tests/data/cgroups/v1_and_v2/proc_pid_cgroup

@@ -0,0 +1,12 @@
+12:devices:/system.slice/Microsoft.A.Sample.Extension_1.0.1_aeac05dc-8c24-4542-95f2-a0d6be1c5ba7.scope
+11:perf_event:/
+10:rdma:/
+9:blkio:/system.slice/Microsoft.A.Sample.Extension_1.0.1_aeac05dc-8c24-4542-95f2-a0d6be1c5ba7.scope
+8:net_cls,net_prio:/
+7:freezer:/
+6:hugetlb:/
+4:cpuset:/
+3:cpu,cpuacct:/system.slice/Microsoft.A.Sample.Extension_1.0.1_aeac05dc-8c24-4542-95f2-a0d6be1c5ba7.scope
+2:pids:/system.slice/Microsoft.A.Sample.Extension_1.0.1_aeac05dc-8c24-4542-95f2-a0d6be1c5ba7.scope
+1:name=systemd:/system.slice/Microsoft.A.Sample.Extension_1.0.1_aeac05dc-8c24-4542-95f2-a0d6be1c5ba7.scope
+0::/system.slice/Microsoft.A.Sample.Extension_1.0.1_aeac05dc-8c24-4542-95f2-a0d6be1c5ba7.scope

tests/data/cgroups/v1_and_v2/proc_self_cgroup

@@ -0,0 +1,12 @@
+12:blkio:/system.slice/walinuxagent.service
+11:cpu,cpuacct:/system.slice/walinuxagent.service
+10:devices:/system.slice/walinuxagent.service
+9:pids:/system.slice/walinuxagent.service
+7:freezer:/
+6:hugetlb:/
+5:perf_event:/
+4:net_cls,net_prio:/
+3:cpuset:/
+2:rdma:/
+1:name=systemd:/system.slice/walinuxagent.service
+0::/system.slice/walinuxagent.service

tests/data/cgroups/v1_and_v2/sys_fs_cgroup_cgroup.subtree_control

@@ -0,0 +1 @@
+memory

tests/data/cgroups/v2/proc_pid_cgroup

@@ -0,0 +1 @@
+0::/system.slice/Microsoft.A.Sample.Extension_1.0.1_aeac05dc-8c24-4542-95f2-a0d6be1c5ba7.scope

tests/data/cgroups/v2/proc_self_cgroup

@@ -0,0 +1 @@
+0::/system.slice/walinuxagent.service

tests/data/cgroups/v2/sys_fs_cgroup_cgroup.subtree_control

@@ -0,0 +1 @@
+cpuset cpu io memory pids