Rename regression to test

.dockerignore

@@ -1,6 +1,6 @@
 # Ignore binaries to avoid performance issues
 target/
-regression/build/
+test/build/
 
 # QEMU log file
 qemu.log

.github/workflows/benchmark_asterinas.yml

@@ -27,7 +27,7 @@ jobs:
     - uses: actions/checkout@v2
     - name: Set up the environment
       run: |
-        chmod +x regression/benchmark/bench_linux_and_aster.sh
+        chmod +x test/benchmark/bench_linux_and_aster.sh
         # Set up git due to the network issue on the self-hosted runner
         git config --global --add safe.directory /__w/asterinas/asterinas
         git config --global http.sslVerify false
@@ -40,13 +40,13 @@ jobs:
         max_attempts: 3
         command: |
           make install_osdk
-          bash regression/benchmark/bench_linux_and_aster.sh ${{ matrix.benchmark }}
+          bash test/benchmark/bench_linux_and_aster.sh ${{ matrix.benchmark }}
         on_retry_command: make clean
 
     - name: Prepare threshold values
       run: |
         echo "Configuring thresholds..."
-        ALERT_THRESHOLD=$(jq -r '.alert_threshold' regression/benchmark/${{ matrix.benchmark }}/config.json)
+        ALERT_THRESHOLD=$(jq -r '.alert_threshold' test/benchmark/${{ matrix.benchmark }}/config.json)
         echo "ALERT_THRESHOLD=$ALERT_THRESHOLD" >> $GITHUB_ENV
 
     - name: Store benchmark results

.github/workflows/test_asterinas.yml

@@ -83,6 +83,6 @@ jobs:
             SYSCALL_TEST_DIR=/exfat EXTRA_BLOCKLISTS_DIRS=blocklists.exfat \
             ENABLE_KVM=0 BOOT_PROTOCOL=linux-efi-handover64 RELEASE=1
         
-      - name: Regression Test (Linux EFI Handover Boot Protocol)
-        id: regression_test_linux
-        run: make run AUTO_TEST=regression ENABLE_KVM=0 BOOT_PROTOCOL=linux-efi-handover64 RELEASE=1
+      - name: General Test (Linux EFI Handover Boot Protocol)
+        id: test_linux
+        run: make run AUTO_TEST=test ENABLE_KVM=0 BOOT_PROTOCOL=linux-efi-handover64 RELEASE=1

Makefile

@@ -31,13 +31,13 @@ BUILD_SYSCALL_TEST := 1
 CARGO_OSDK_ARGS += --kcmd-args="SYSCALL_TEST_DIR=$(SYSCALL_TEST_DIR)"
 CARGO_OSDK_ARGS += --kcmd-args="EXTRA_BLOCKLISTS_DIRS=$(EXTRA_BLOCKLISTS_DIRS)"
 CARGO_OSDK_ARGS += --init-args="/opt/syscall_test/run_syscall_test.sh"
-else ifeq ($(AUTO_TEST), regression)
-CARGO_OSDK_ARGS += --init-args="/regression/run_regression_test.sh"
+else ifeq ($(AUTO_TEST), test)
+CARGO_OSDK_ARGS += --init-args="/test/run_general_test.sh"
 else ifeq ($(AUTO_TEST), boot)
-CARGO_OSDK_ARGS += --init-args="/regression/boot_hello.sh"
+CARGO_OSDK_ARGS += --init-args="/test/boot_hello.sh"
 else ifeq ($(AUTO_TEST), vsock)
 export VSOCK=1
-CARGO_OSDK_ARGS += --init-args="/regression/run_vsock_test.sh"
+CARGO_OSDK_ARGS += --init-args="/test/run_vsock_test.sh"
 endif
 
 # If the BENCHMARK is set, we will run the benchmark in the kernel mode.
@@ -132,7 +132,7 @@ $(CARGO_OSDK):
 
 .PHONY: initramfs
 initramfs:
-	@make --no-print-directory -C regression
+	@make --no-print-directory -C test
 
 .PHONY: build
 build: initramfs $(CARGO_OSDK)
@@ -149,9 +149,9 @@ run: build
 ifeq ($(AUTO_TEST), syscall)
 	@tail --lines 100 qemu.log | grep -q "^.* of .* test cases passed." \
 		|| (echo "Syscall test failed" && exit 1)
-else ifeq ($(AUTO_TEST), regression)
-	@tail --lines 100 qemu.log | grep -q "^All regression tests passed." \
-		|| (echo "Regression test failed" && exit 1)
+else ifeq ($(AUTO_TEST), test)
+	@tail --lines 100 qemu.log | grep -q "^All general tests passed." \
+		|| (echo "General test failed" && exit 1)
 else ifeq ($(AUTO_TEST), boot)
 	@tail --lines 100 qemu.log | grep -q "^Successfully booted." \
 		|| (echo "Boot test failed" && exit 1)
@@ -196,7 +196,7 @@ docs: $(CARGO_OSDK)
 .PHONY: format
 format:
 	@./tools/format_all.sh
-	@make --no-print-directory -C regression format
+	@make --no-print-directory -C test format
 
 .PHONY: check
 check: $(CARGO_OSDK)
@@ -218,7 +218,7 @@ check: $(CARGO_OSDK)
 		echo "Checking $$dir"; \
 		(cd $$dir && cargo osdk clippy -- -- -D warnings) || exit 1; \
 	done
-	@make --no-print-directory -C regression check
+	@make --no-print-directory -C test check
 
 .PHONY: check_osdk
 check_osdk:
@@ -228,5 +228,5 @@ check_osdk:
 clean:
 	@cargo clean
 	@cd docs && mdbook clean
-	@make --no-print-directory -C regression clean
+	@make --no-print-directory -C test clean
 	@rm -f $(CARGO_OSDK)

OSDK.toml

@@ -22,7 +22,7 @@ kcmd_args = [
     "init=/usr/bin/busybox",
 ]
 init_args = ["sh", "-l"]
-initramfs = "regression/build/initramfs.cpio.gz"
+initramfs = "test/build/initramfs.cpio.gz"
 
 # Special options for testing
 [test.boot]

docs/src/kernel/advanced-instructions.md

@@ -32,12 +32,12 @@ cargo osdk test
 
 ## Integration Test
 
-### Regression Test
+### General Test
 
-The following command builds and runs the test binaries in `regression/apps` directory on Asterinas.
+The following command builds and runs the test binaries in `test/apps` directory on Asterinas.
 
 ```bash
-make run AUTO_TEST=regression
+make run AUTO_TEST=test
 ```
 
 ### Syscall Test

kernel/aster-nix/src/fs/exfat/mod.rs

@@ -104,7 +104,7 @@ mod test {
         }
     }
     /// Exfat disk image
-    static EXFAT_IMAGE: &[u8] = include_bytes!("../../../../../regression/build/exfat.img");
+    static EXFAT_IMAGE: &[u8] = include_bytes!("../../../../../test/build/exfat.img");
 
     /// Read exfat disk image
     fn new_vm_segment_from_image() -> Segment {

kernel/libs/comp-sys/cargo-component/tests/regression.rs

@@ -8,7 +8,7 @@
 mod test_utils;
 
 #[test]
-fn regression() {
+fn test() {
     let stderr = run_cargo_component_cmd!();
     assert!(!stderr.contains("access controlled entry point is disallowed"));
 }

regression/benchmark/README.md

@@ -1,58 +0,0 @@
-# Introduction to benchmarks
-
-## Sysbench
-Sysbench is a scriptable benchmark tool that evaluates system performance. It includes five kinds of tests: CPU, memory, file I/O, mutex performance, and thread performance. Detailed usage and options can be found by using:
-```shell
-sysbench --help
-sysbench --test=<test_name> help
-``` 
-Here we list some general commands for evaluation:
-```shell
-# CPU test
-sysbench --test=cpu --cpu-max-prime=<N> --num-threads=<N> run
-
-# Thread test
-sysbench --test=threads --thread-yields=<N> --num-threads=<N> --max-time=<N> run
-
-# Mutex test
-sysbench --test=mutex --mutex-num=<N> --mutex-locks=<N> --num-threads=<N>
-
-# File test, the file-total-size and file-num of prepare and run must be consistent 
-sysbench --test=fileio --file-total-size=<N><K,M,G> --file-num=<N> prepare
-sysbench --test=fileio --file-total-size=<N><K,M,G> --file-num=<N> --file-test-mode=<Type> --file-block-size=<N><K,M,G> --max-time=<N> run
-
-# Memory test
-sysbench --test=memory --memory-block-size=<N><K,M,G> --memory-access-mode=<Type> --memory-oper=<Type> run
-```
-
-## Membench
-Membench is used to establish a baseline for memory bandwidth and latency. For specific usage and options, use:
-```shell
-membench --help
-``` 
-Here we list some general commands to use membench:
-```shell
-# Measure the latency of mmap
-membench -runtime=5 -dir=/dev/zero -size=<N><K,M,G> -engine=mmap_lat
-
-# Measure the latency of page fault handling. The size must be consistent with the file size.
-membench -runtime=5 -dir=path_to_a_file -size=<N><K,M,G> -copysize=<N><K,M,G> -mode=<Type> -engine=page_fault 
-
-# This is a easy way to generate a file with target size in Linux.
-# The following command can create a file named 512K.file with the size 512K.
-dd if=/dev/zero of=512K.file bs=1K count=512
-```
-
-## Iperf
-iPerf is a tool for actively measuring the maximum achievable bandwidth on IP networks. Usage and options are detailed in:
-```shell
-iperf3 -h
-``` 
-iperf can run in the following instructions:
-```shell
-export HOST_ADDR=127.0.0.1
-export HOST_PORT=8888
-iperf3 -s -B $HOST_ADDR -p $HOST_PORT -D # Start the server as a daemon
-iperf3 -c $HOST_ADDR -p $HOST_PORT # Start the client
-```
-Note that [a variant of iperf3](https://github.com/stefano-garzarella/iperf-vsock) can measure the performance of `vsock`. But the implemented `vsock` has not been verified to work well in it.

test/Makefile

@@ -26,7 +26,7 @@ INITRAMFS_ALL_DIRS := \
 	$(INITRAMFS)/lib64 \
 	$(INITRAMFS)/bin \
 	$(INITRAMFS)/usr/bin \
-	$(INITRAMFS)/regression \
+	$(INITRAMFS)/test \
 	$(INITRAMFS)/benchmark \
 	$(INITRAMFS_EMPTY_DIRS)
 SYSCALL_TEST_DIR := $(INITRAMFS)/opt/syscall_test
@@ -74,8 +74,8 @@ $(INITRAMFS)/usr/bin: | $(INITRAMFS)/bin
 	@mkdir -p $@
 	@cp /usr/bin/busybox $@
 
-.PHONY: $(INITRAMFS)/regression
-$(INITRAMFS)/regression:
+.PHONY: $(INITRAMFS)/test
+$(INITRAMFS)/test:
 	@make --no-print-directory -C apps
 
 $(INITRAMFS)/benchmark: | $(INITRAMFS)/benchmark/bin

test/apps/Makefile

@@ -6,7 +6,7 @@ MKFILE_PATH := $(abspath $(lastword $(MAKEFILE_LIST)))
 CUR_DIR := $(patsubst %/,%,$(dir $(MKFILE_PATH)))
 
 INITRAMFS ?= $(CUR_DIR)/../build/initramfs
-REGRESSION_BUILD_DIR ?= $(INITRAMFS)/regression
+TEST_BUILD_DIR ?= $(INITRAMFS)/test
 
 # These test apps are sorted by name
 TEST_APPS := \
@@ -48,17 +48,17 @@ $(TEST_APPS):
 
 .PHONY: format
 format:
-	@echo "Fixing code format for regression tests..."
+	@echo "Fixing code format for general tests..."
 	@clang-format -i $(C_SOURCES)
 
 .PHONY: check
 check:
-	@echo "Checking code format for regression tests..."
+	@echo "Checking code format for general tests..."
 	@clang-format --dry-run --Werror $(C_SOURCES)
 
-$(REGRESSION_BUILD_DIR):
+$(TEST_BUILD_DIR):
 	@mkdir -p $@
 
 .PHONY: scripts
-scripts: | $(REGRESSION_BUILD_DIR)
-	@make --no-print-directory BUILD_DIR=$(REGRESSION_BUILD_DIR) -C scripts
+scripts: | $(TEST_BUILD_DIR)
+	@make --no-print-directory BUILD_DIR=$(TEST_BUILD_DIR) -C scripts

test/apps/execve/execve.c

@@ -11,7 +11,7 @@ int main()
 	printf("Execve a new file /execve/hello:\n");
 	// flush the stdout content to ensure the content print to console
 	fflush(stdout);
-	execve("/regression/execve/hello", argv, envp);
+	execve("/test/execve/hello", argv, envp);
 	printf("Should not print\n");
 	fflush(stdout);
 	return 0;

test/apps/mongoose/Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: MPL-2.0
 
 CUR_DIR := $(shell dirname $(realpath $(firstword $(MAKEFILE_LIST))))
-BUILD_DIR := $(CUR_DIR)/../../build/initramfs/regression/network
+BUILD_DIR := $(CUR_DIR)/../../build/initramfs/test/network
 MONGOOSE_DIR := $(CUR_DIR)
 MONGOOSE_C := $(MONGOOSE_DIR)/mongoose.c
 MONGOOSE_H := $(MONGOOSE_DIR)/mongoose.h

test/apps/network/test.h

@@ -1,16 +1,16 @@
 /* SPDX-License-Identifier: MPL-2.0 */
 
 /*
- * A framework for writing regression tests.
+ * A framework for writing general tests.
  *
- * A regression test typically consists of two parts, the setup part and the
+ * A general test typically consists of two parts, the setup part and the
  * test part. The setup part contains setup functions that set up the context
  * for the subsequent tests to run. The setup functions cannot fail, and if they
  * do, execution is aborted because the subsequent tests will not work as
  * expected either. The test functions, on the other hand, can fail, and if they
  * do, they are reported as test failures.
  *
- * The framework provides basic utilities for writing regression tests:
+ * The framework provides basic utilities for writing general tests:
  *
  *  - To define a setup function or a test function, FN_SETUP() or FN_TEST() can
  * be used. These functions are automatically executed in the order of their

test/apps/scripts/network.sh

@@ -4,7 +4,7 @@
 
 set -e
 
-NETTEST_DIR=/regression/network
+NETTEST_DIR=/test/network
 cd ${NETTEST_DIR}
 
 echo "Start network test......"

test/apps/scripts/process.sh

@@ -4,7 +4,7 @@
 
 set -e
 
-SCRIPT_DIR=/regression
+SCRIPT_DIR=/test
 cd ${SCRIPT_DIR}/..
 
 echo "Start process test......"

test/apps/scripts/run_general_test.sh

@@ -4,7 +4,7 @@
 
 set -e
 
-SCRIPT_DIR=/regression
+SCRIPT_DIR=/test
 cd ${SCRIPT_DIR}
 
 ./shell_cmd.sh
@@ -13,4 +13,4 @@ cd ${SCRIPT_DIR}
 ./network.sh
 ./test_epoll_pwait.sh
 
-echo "All regression tests passed."
+echo "All general tests passed."

test/apps/scripts/run_vsock_test.sh

@@ -8,7 +8,7 @@
 
 set -e
 
-VSOCK_DIR=/regression/vsock
+VSOCK_DIR=/test/vsock
 cd ${VSOCK_DIR}
 
 echo "Start vsock test......"

test/apps/scripts/shell_cmd.sh

@@ -5,7 +5,7 @@
 set -e
 set -x
 
-SCRIPT_DIR=/regression
+SCRIPT_DIR=/test
 cd ${SCRIPT_DIR}
 
 touch hello.txt

test/apps/scripts/test_epoll_pwait.sh

@@ -4,7 +4,7 @@
 
 set -e
 
-EPOLLTEST_DIR=/regression/epoll
+EPOLLTEST_DIR=/test/epoll
 cd ${EPOLLTEST_DIR}
 
 echo "Start epoll_pwait test......"

test/apps/test_common.mk

@@ -5,7 +5,7 @@ INCLUDE_MAKEFILE := $(lastword $(MAKEFILE_LIST))
 CUR_DIR := $(shell dirname $(realpath $(MAIN_MAKEFILE)))
 CUR_DIR_NAME := $(shell basename $(realpath $(CUR_DIR)))
 BUILD_DIR := $(CUR_DIR)/../../build
-OBJ_OUTPUT_DIR := $(BUILD_DIR)/initramfs/regression/$(CUR_DIR_NAME)
+OBJ_OUTPUT_DIR := $(BUILD_DIR)/initramfs/test/$(CUR_DIR_NAME)
 DEP_OUTPUT_DIR := $(BUILD_DIR)/dep/$(CUR_DIR_NAME)
 C_SRCS := $(wildcard *.c)
 C_OBJS := $(addprefix $(OBJ_OUTPUT_DIR)/,$(C_SRCS:%.c=%))

test/benchmark/README.md

@@ -0,0 +1,146 @@
+# Introduction to benchmarks
+
+## Overview of supported benchmarks
+The benchmark suite contains several benchmarks that can be used to evaluate the performance of the Asterinas platform. The following benchmarks are supported:
+
+- [Sysbench](#Sysbench)
+- [Membench](#Membench)
+- [Iperf](#Iperf)
+
+### Sysbench
+Sysbench is a scriptable benchmark tool that evaluates system performance. It includes five kinds of tests: CPU, memory, file I/O, mutex performance, and thread performance. Detailed usage and options can be found by using:
+```shell
+sysbench --help
+sysbench --test=<test_name> help
+``` 
+Here we list some general commands for evaluation:
+```shell
+# CPU test
+sysbench --test=cpu --cpu-max-prime=<N> --num-threads=<N> run
+
+# Thread test
+sysbench --test=threads --thread-yields=<N> --num-threads=<N> --max-time=<N> run
+
+# Mutex test
+sysbench --test=mutex --mutex-num=<N> --mutex-locks=<N> --num-threads=<N>
+
+# File test, the file-total-size and file-num of prepare and run must be consistent 
+sysbench --test=fileio --file-total-size=<N><K,M,G> --file-num=<N> prepare
+sysbench --test=fileio --file-total-size=<N><K,M,G> --file-num=<N> --file-test-mode=<Type> --file-block-size=<N><K,M,G> --max-time=<N> run
+
+# Memory test
+sysbench --test=memory --memory-block-size=<N><K,M,G> --memory-access-mode=<Type> --memory-oper=<Type> run
+```
+
+### Membench
+Membench is used to establish a baseline for memory bandwidth and latency. For specific usage and options, use:
+```shell
+membench --help
+``` 
+Here we list some general commands to use membench:
+```shell
+# Measure the latency of mmap
+membench -runtime=5 -dir=/dev/zero -size=<N><K,M,G> -engine=mmap_lat
+
+# Measure the latency of page fault handling. The size must be consistent with the file size.
+membench -runtime=5 -dir=path_to_a_file -size=<N><K,M,G> -copysize=<N><K,M,G> -mode=<Type> -engine=page_fault 
+
+# This is a easy way to generate a file with target size in Linux.
+# The following command can create a file named 512K.file with the size 512K.
+dd if=/dev/zero of=512K.file bs=1K count=512
+```
+
+### Iperf
+iPerf is a tool for actively measuring the maximum achievable bandwidth on IP networks. Usage and options are detailed in:
+```shell
+iperf3 -h
+``` 
+iperf can run in the following instructions:
+```shell
+export HOST_ADDR=127.0.0.1
+export HOST_PORT=8888
+iperf3 -s -B $HOST_ADDR -p $HOST_PORT -D # Start the server as a daemon
+iperf3 -c $HOST_ADDR -p $HOST_PORT # Start the client
+```
+Note that [a variant of iperf3](https://github.com/stefano-garzarella/iperf-vsock) can measure the performance of `vsock`. But the implemented `vsock` has not been verified to work well in it.
+
+## Add benchmark to benchmark CI
+
+To add a new benchmark to the Asternias Continuous Integration (CI) system, follow these detailed steps:
+
+### Step 1: Add the Benchmark to the `asterinas/test/benchmarks` Directory
+
+1. **Create the Benchmark Directory:**
+   - Navigate to `asterinas/test/benchmarks`.
+   - Create a new directory named after your benchmark, e.g., `getpid`.
+
+2. **Create the Necessary Files:**
+   - **config.json:**
+     ```json
+     {
+         "alert_threshold": "125%",
+         "pattern": "Syscall average latency:",
+         "field": "4"
+     }
+     ```
+     - `alert_threshold`: Set the threshold for alerting. If the benchmark result exceeds this threshold, an alert will be triggered.
+     - `pattern`: Define the pattern to extract the benchmark result from the output.
+     - `field`: Specify the index of the result in the extracted output.
+    
+      For example, if the benchmark output is "Syscall average latency: 1000 ns", the `pattern` is "Syscall average latency:", and the `field` is "4". `jq` will extract "1000" as the benchmark result.
+
+   - **result_template.json:**
+     ```json
+     [
+         {
+             "name": "Average Syscall Latency on Linux",
+             "unit": "ns",
+             "value": 0,
+             "extra": "linux_avg"
+         },
+         {
+             "name": "Average Syscall Latency on Asterinas",
+             "unit": "ns",
+             "value": 0,
+             "extra": "aster_avg"
+         }
+     ]
+     ```
+     - Adjust `name` and `unit` according to your benchmark specifics.
+
+   - **run.sh:**
+     ```bash
+     #!/bin/bash
+
+     /benchmark/bin/getpid
+     ```
+     - This script runs the benchmark. Ensure the path to the benchmark binary is correct. `asterinas/test/Makefile` handles the benchmark binaries.
+
+### Step 2: Update the `asterinas/.github/benchmarks.yml` File
+
+1. **Edit the Benchmarks Configuration:**
+   - Open `asterinas/.github/benchmarks.yml`.
+   - Add your benchmark to the `strategy.matrix.benchmark` list:
+     ```yaml
+     strategy:
+       matrix:
+         benchmark: [getpid]
+       fail-fast: false
+     ```
+
+### Step 3: Test the Benchmark Locally
+
+1. **Run the Benchmark:**
+   - Execute the following command to test the benchmark locally:
+     ```bash
+     cd asterinas
+     bash test/benchmark/bench_linux_aster.sh getpid
+     ```
+   - Ensure the benchmark runs successfully and check the results in `asterinas/result_getpid.json`.
+
+### Additional Considerations
+
+- **Validation:** After adding and testing the benchmark, ensure that the CI pipeline correctly integrates the new benchmark by triggering a CI build.
+- **Documentation:** Update any relevant documentation to include the new benchmark, explaining its purpose and how to interpret its results.
+
+By following these steps, you will successfully integrate a new benchmark into the Asternias CI system, enhancing its capability to evaluate platform performance.