[PATCH v4] dts: Change hugepage runtime config to 2MB Exclusively

[Nicholas Pratte <npratte@iol.unh.edu>]

The previous implementation configures and allocates hugepage sizes
based on a system default. This can lead to two problems: overallocation of
hugepages (which may crash the remote host), and configuration of hugepage
sizes that are not recommended during runtime. This new implementation
allows only 2MB hugepage allocation during runtime; any other unique
hugepage size must be configured by the end-user for initializing DTS.

If the amount of 2MB hugepages requested exceeds the amount of 2MB
hugepages already configured on the system, then the system will remount
hugepages to cover the difference. If the amount of hugepages requested is
either less than or equal to the amount already configured on the system,
then nothing is done.

Bugzilla ID: 1370
Signed-off-by: Nicholas Pratte <npratte@iol.unh.edu>
Reviewed-by: Jeremy Spewock <jspewock@iol.unh.edu>
---

v4:
 * dts.rst punctuation/grammar corrections and 2mb exclusivity
   justifications included in documentation
---
 doc/guides/tools/dts.rst                     |  6 ++++-
 dts/conf.yaml                                |  4 ++--
 dts/framework/config/__init__.py             |  4 ++--
 dts/framework/config/conf_yaml_schema.json   |  6 ++---
 dts/framework/config/types.py                |  2 +-
 dts/framework/testbed_model/linux_session.py | 24 +++++++++++---------
 dts/framework/testbed_model/node.py          |  8 ++++++-
 dts/framework/testbed_model/os_session.py    |  5 +++-
 8 files changed, 37 insertions(+), 22 deletions(-)

diff --git a/doc/guides/tools/dts.rst b/doc/guides/tools/dts.rst
index 47b218b2c6..71473dbb3d 100644
--- a/doc/guides/tools/dts.rst
+++ b/doc/guides/tools/dts.rst
@@ -131,7 +131,11 @@ There are two areas that need to be set up on a System Under Test:
 
      You may specify the optional hugepage configuration in the DTS config file.
      If you do, DTS will take care of configuring hugepages,
-     overwriting your current SUT hugepage configuration.
+     overwriting your current SUT hugepage configuration. Configuration of hugepages via DTS
+     allows only for allocation of 2MB hugepages, as doing so prevents accidental/over
+     allocation of hugepages and hugepages sizes not recommended during runtime due to
+     contiguous memory space requirements. Thus, if you require hugepage
+     sizes not equal to 2MB, then this configuration must be done outside of the DTS framework.
 
    * System under test configuration
 
diff --git a/dts/conf.yaml b/dts/conf.yaml
index 8068345dd5..56c3ae6f4c 100644
--- a/dts/conf.yaml
+++ b/dts/conf.yaml
@@ -35,7 +35,7 @@ nodes:
     lcores: "" # use all the available logical cores
     use_first_core: false # tells DPDK to use any physical core
     memory_channels: 4 # tells DPDK to use 4 memory channels
-    hugepages:  # optional; if removed, will use system hugepage configuration
+    hugepages_2mb: # optional; if removed, will use system hugepage configuration
         amount: 256
         force_first_numa: false
     ports:
@@ -71,7 +71,7 @@ nodes:
         os_driver: rdma
         peer_node: "SUT 1"
         peer_pci: "0000:00:08.1"
-    hugepages:  # optional; if removed, will use system hugepage configuration
+    hugepages_2mb: # optional; if removed, will use system hugepage configuration
         amount: 256
         force_first_numa: false
     traffic_generator:
diff --git a/dts/framework/config/__init__.py b/dts/framework/config/__init__.py
index 4cb5c74059..b6f820e39e 100644
--- a/dts/framework/config/__init__.py
+++ b/dts/framework/config/__init__.py
@@ -255,8 +255,8 @@ def from_dict(
             Either an SUT or TG configuration instance.
         """
         hugepage_config = None
-        if "hugepages" in d:
-            hugepage_config_dict = d["hugepages"]
+        if "hugepages_2mb" in d:
+            hugepage_config_dict = d["hugepages_2mb"]
             if "force_first_numa" not in hugepage_config_dict:
                 hugepage_config_dict["force_first_numa"] = False
             hugepage_config = HugepageConfiguration(**hugepage_config_dict)
diff --git a/dts/framework/config/conf_yaml_schema.json b/dts/framework/config/conf_yaml_schema.json
index 4731f4511d..f4d7199523 100644
--- a/dts/framework/config/conf_yaml_schema.json
+++ b/dts/framework/config/conf_yaml_schema.json
@@ -146,7 +146,7 @@
         "compiler"
       ]
     },
-    "hugepages": {
+    "hugepages_2mb": {
       "type": "object",
       "description": "Optional hugepage configuration. If not specified, hugepages won't be configured and DTS will use system configuration.",
       "properties": {
@@ -253,8 +253,8 @@
             "type": "integer",
             "description": "How many memory channels to use. Optional, defaults to 1."
           },
-          "hugepages": {
-            "$ref": "#/definitions/hugepages"
+          "hugepages_2mb": {
+            "$ref": "#/definitions/hugepages_2mb"
           },
           "ports": {
             "type": "array",
diff --git a/dts/framework/config/types.py b/dts/framework/config/types.py
index 1927910d88..016e0c3dbd 100644
--- a/dts/framework/config/types.py
+++ b/dts/framework/config/types.py
@@ -46,7 +46,7 @@ class NodeConfigDict(TypedDict):
     """Allowed keys and values."""
 
     #:
-    hugepages: HugepageConfigurationDict
+    hugepages_2mb: HugepageConfigurationDict
     #:
     name: str
     #:
diff --git a/dts/framework/testbed_model/linux_session.py b/dts/framework/testbed_model/linux_session.py
index 5d24030c3d..d0f7cfa77c 100644
--- a/dts/framework/testbed_model/linux_session.py
+++ b/dts/framework/testbed_model/linux_session.py
@@ -15,7 +15,7 @@
 
 from typing_extensions import NotRequired
 
-from framework.exception import RemoteCommandExecutionError
+from framework.exception import ConfigurationError, RemoteCommandExecutionError
 from framework.utils import expand_range
 
 from .cpu import LogicalCore
@@ -84,14 +84,20 @@ def get_dpdk_file_prefix(self, dpdk_prefix: str) -> str:
         """Overrides :meth:`~.os_session.OSSession.get_dpdk_file_prefix`."""
         return dpdk_prefix
 
-    def setup_hugepages(self, hugepage_count: int, force_first_numa: bool) -> None:
+    def setup_hugepages(
+        self, hugepage_count: int, hugepage_size: int, force_first_numa: bool
+    ) -> None:
         """Overrides :meth:`~.os_session.OSSession.setup_hugepages`."""
         self._logger.info("Getting Hugepage information.")
-        hugepage_size = self._get_hugepage_size()
-        hugepages_total = self._get_hugepages_total()
+        hugepages_total = self._get_hugepages_total(hugepage_size)
+        if (
+            f"hugepages-{hugepage_size}kB"
+            not in self.send_command("ls /sys/kernel/mm/hugepages").stdout
+        ):
+            raise ConfigurationError("hugepage size not supported by operating system")
         self._numa_nodes = self._get_numa_nodes()
 
-        if force_first_numa or hugepages_total != hugepage_count:
+        if force_first_numa or hugepages_total < hugepage_count:
             # when forcing numa, we need to clear existing hugepages regardless
             # of size, so they can be moved to the first numa node
             self._configure_huge_pages(hugepage_count, hugepage_size, force_first_numa)
@@ -99,13 +105,9 @@ def setup_hugepages(self, hugepage_count: int, force_first_numa: bool) -> None:
             self._logger.info("Hugepages already configured.")
         self._mount_huge_pages()
 
-    def _get_hugepage_size(self) -> int:
-        hugepage_size = self.send_command("awk '/Hugepagesize/ {print $2}' /proc/meminfo").stdout
-        return int(hugepage_size)
-
-    def _get_hugepages_total(self) -> int:
+    def _get_hugepages_total(self, hugepage_size: int) -> int:
         hugepages_total = self.send_command(
-            "awk '/HugePages_Total/ { print $2 }' /proc/meminfo"
+            f"cat /sys/kernel/mm/hugepages/hugepages-{hugepage_size}kB/nr_hugepages"
         ).stdout
         return int(hugepages_total)
 
diff --git a/dts/framework/testbed_model/node.py b/dts/framework/testbed_model/node.py
index 74061f6262..056a031ca0 100644
--- a/dts/framework/testbed_model/node.py
+++ b/dts/framework/testbed_model/node.py
@@ -97,6 +97,10 @@ def __init__(self, node_config: NodeConfiguration):
         self.virtual_devices = []
         self._init_ports()
 
+    @property
+    def _hugepage_default_size(self) -> int:
+        return 2048
+
     def _init_ports(self) -> None:
         self.ports = [Port(self.name, port_config) for port_config in self.config.ports]
         self.main_session.update_ports(self.ports)
@@ -266,7 +270,9 @@ def _setup_hugepages(self) -> None:
         """
         if self.config.hugepages:
             self.main_session.setup_hugepages(
-                self.config.hugepages.amount, self.config.hugepages.force_first_numa
+                self.config.hugepages.amount,
+                self._hugepage_default_size,
+                self.config.hugepages.force_first_numa,
             )
 
     def configure_port_state(self, port: Port, enable: bool = True) -> None:
diff --git a/dts/framework/testbed_model/os_session.py b/dts/framework/testbed_model/os_session.py
index d5bf7e0401..5d58400cbe 100644
--- a/dts/framework/testbed_model/os_session.py
+++ b/dts/framework/testbed_model/os_session.py
@@ -345,7 +345,9 @@ def get_dpdk_file_prefix(self, dpdk_prefix: str) -> str:
         """
 
     @abstractmethod
-    def setup_hugepages(self, hugepage_count: int, force_first_numa: bool) -> None:
+    def setup_hugepages(
+        self, hugepage_count: int, hugepage_size: int, force_first_numa: bool
+    ) -> None:
         """Configure hugepages on the node.
 
         Get the node's Hugepage Size, configure the specified count of hugepages
@@ -353,6 +355,7 @@ def setup_hugepages(self, hugepage_count: int, force_first_numa: bool) -> None:
 
         Args:
             hugepage_count: Configure this many hugepages.
+            hugepage_size: Configure hugepages of this size (currently not used in the config)
             force_first_numa:  If :data:`True`, configure hugepages just on the first numa node.
         """
 
-- 
2.44.0