Merge branch 'main' into pvtime

Author: roypat

.buildkite/common.py

@@ -14,15 +14,21 @@
 import subprocess
 from pathlib import Path
 
+# fmt: off
 DEFAULT_INSTANCES = [
-    "c5n.metal",  # Intel Skylake
-    "m5n.metal",  # Intel Cascade Lake
-    "m6i.metal",  # Intel Icelake
-    "m6a.metal",  # AMD Milan
-    "m7a.metal-48xl",  # AMD Genoa
-    "m6g.metal",  # Graviton2
-    "m7g.metal",  # Graviton3
+    "c5n.metal",      # Intel Skylake
+    "m5n.metal",      # Intel Cascade Lake
+    "m6i.metal",      # Intel Icelake
+    "m7i.metal-24xl", # Intel Sapphire Rapids
+    "m7i.metal-48xl", # Intel Sapphire Rapids
+    "m6a.metal",      # AMD Milan
+    "m7a.metal-48xl", # AMD Genoa
+    "m6g.metal",      # Graviton2
+    "m7g.metal",      # Graviton3
+    "m8g.metal-24xl", # Graviton4 1 socket
+    "m8g.metal-48xl", # Graviton4 2 sockets
 ]
+# fmt: on
 
 DEFAULT_PLATFORMS = [
     ("al2", "linux_5.10"),

.buildkite/pipeline_cpu_template.py

@@ -30,6 +30,8 @@ class BkStep(str, Enum):
             "c5n.metal",
             "m5n.metal",
             "m6i.metal",
+            "m7i.metal-24xl",
+            "m7i.metal-48xl",
             "m6a.metal",
             "m7a.metal-48xl",
         ],
@@ -69,8 +71,9 @@ class BkStep(str, Enum):
             "c5n.metal",
             "m5n.metal",
             "m6i.metal",
+            "m7i.metal-24xl",
+            "m7i.metal-48xl",
             "m6a.metal",
-            "m7a.metal-48xl",
         ],
     },
 }

.buildkite/pipeline_cross.py

@@ -22,6 +22,8 @@
         "c5n.metal",
         "m5n.metal",
         "m6i.metal",
+        "m7i.metal-24xl",
+        "m7i.metal-48xl",
         "m6a.metal",
         "m7a.metal-48xl",
     ]

.buildkite/pipeline_perf.py

@@ -27,21 +27,22 @@
         "devtool_opts": "-c 1-10 -m 0",
         "ab_opts": "--noise-threshold 0.1",
     },
-    "network-latency": {
-        "label": "📠 Network Latency",
-        "test_path": "integration_tests/performance/test_network_ab.py::test_network_latency",
+    "network": {
+        "label": "📠 Network Latency and Throughput",
+        "test_path": "integration_tests/performance/test_network_ab.py",
         "devtool_opts": "-c 1-10 -m 0",
         # Triggers if delta is > 0.01ms (10µs) or default relative threshold (5%)
+        # only relevant for latency test, throughput test will always be magnitudes above this anyway
         "ab_opts": "--absolute-strength 0.010",
     },
-    "network-throughput": {
-        "label": "📠 Network TCP Throughput",
-        "test_path": "integration_tests/performance/test_network_ab.py::test_network_tcp_throughput",
-        "devtool_opts": "-c 1-10 -m 0",
-    },
     "snapshot-latency": {
         "label": "📸 Snapshot Latency",
-        "test_path": "integration_tests/performance/test_snapshot_ab.py",
+        "test_path": "integration_tests/performance/test_snapshot_ab.py::test_restore_latency integration_tests/performance/test_snapshot_ab.py::test_post_restore_latency",
+        "devtool_opts": "-c 1-12 -m 0",
+    },
+    "population-latency": {
+        "label": "📸 Memory Population Latency",
+        "test_path": "integration_tests/performance/test_snapshot_ab.py::test_population_latency",
         "devtool_opts": "-c 1-12 -m 0",
     },
     "vsock-throughput": {

CHANGELOG.md

@@ -16,12 +16,23 @@ and this project adheres to
   Linux kernels newer than 5.0 compiled with `CONFIG_PVH=y` set this ELF Note,
   as do FreeBSD kernels.
 - [#5065](https://github.com/firecracker-microvm/firecracker/pull/5065) Added
-  support for Intel AMX (Advanced Matrix Extensions).
+  support for Intel AMX (Advanced Matrix Extensions). To be able to take and
+  restore a snapshot of Intel AMX state, `Xsave` is used instead of `kvm_xsave`,
+  so users need to regenerate snapshots.
 - [#4731](https://github.com/firecracker-microvm/firecracker/pull/4731): Added
   support for modifying the host TAP device name during snapshot restore.
 
 ### Changed
 
+- [#5118](https://github.com/firecracker-microvm/firecracker/pull/5118): Cleared
+  WAITPKG CPUID bit in CPUID normalization. The feature enables a guest to put a
+  physical processor into an idle state, which is undesirable in a FaaS
+  environment since that is what the host wants to decide.
+- [#5142](https://github.com/firecracker-microvm/firecracker/pull/5142):
+  Clarified what CPU models are supported by each existing CPU template.
+  Firecracker exits with an error if a CPU template is used on an unsupported
+  CPU model.
+
 ### Deprecated
 
 - [#4948](https://github.com/firecracker-microvm/firecracker/pull/4948):
@@ -39,6 +50,15 @@ and this project adheres to
   the `SendCtrlAltDel` command not working for ACPI-enabled guest kernels, by
   dropping the i8042.nopnp argument from the default kernel command line
   Firecracker constructs.
+- [#5122](https://github.com/firecracker-microvm/firecracker/pull/5122): Keep
+  the UFFD Unix domain socket open to prevent the race condition between the
+  guest memory mappings message and the shutdown event that was sometimes
+  causing arrival of an empty message on the UFFD handler side.
+- [#5143](https://github.com/firecracker-microvm/firecracker/pull/5143): Fixed
+  to report `process_startup_time_us` and `process_startup_time_cpu_us` metrics
+  for `api_server` right after the API server starts, while previously reported
+  before applying seccomp filter and starting the API server. Users may observe
+  a bit longer startup time metrics.
 
 ## [1.11.0]
 

Cargo.lock

@@ -135,10 +135,14 @@ We test all combinations of:
 | c5n.metal      | al2 linux_5.10   | ubuntu 24.04 | linux_5.10   |
 | m5n.metal      | al2023 linux_6.1 |              | linux_6.1    |
 | m6i.metal      |                  |              |              |
+| m7i.metal-24xl |                  |              |              |
+| m7i.metal-48xl |                  |              |              |
 | m6a.metal      |                  |              |              |
 | m7a.metal-48xl |                  |              |              |
 | m6g.metal      |                  |              |              |
 | m7g.metal      |                  |              |              |
+| m8g.metal-24xl |                  |              |              |
+| m8g.metal-48xl |                  |              |              |
 
 ## Known issues and Limitations