[PATCH] KVM test: Add a subtest kdump

[Lucas Meneghel Rodrigues <lmr@redhat.com>]

From: Jason Wang <jasowang@redhat.com>

Add a new subtest to check whether kdump work correctly in guest. This test just
try to trigger crash on each vcpu and then verify it by checking the vmcore.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 client/tests/kvm/tests/kdump.py              |   80 ++++++++++++++++++++++++++
 client/tests/kvm/tests_base.cfg.sample       |   11 ++++
 client/tests/kvm/unattended/RHEL-5-series.ks |    1 +
 3 files changed, 92 insertions(+), 0 deletions(-)
 create mode 100644 client/tests/kvm/tests/kdump.py

diff --git a/client/tests/kvm/tests/kdump.py b/client/tests/kvm/tests/kdump.py
new file mode 100644
index 0000000..a5843c7
--- /dev/null
+++ b/client/tests/kvm/tests/kdump.py
@@ -0,0 +1,80 @@
+import logging, time
+from autotest_lib.client.common_lib import error
+import kvm_subprocess, kvm_test_utils, kvm_utils
+
+
+def run_kdump(test, params, env):
+    """
+    KVM reboot test:
+    1) Log into a guest
+    2) Check and enable the kdump
+    3) For each vcpu, trigger a crash and check the vmcore
+
+    @param test: kvm test object
+    @param params: Dictionary with the test parameters
+    @param env: Dictionary with test environment.
+    """
+    vm = kvm_test_utils.get_living_vm(env, params.get("main_vm"))
+    timeout = float(params.get("login_timeout", 240))
+    crash_timeout = float(params.get("crash_timeout", 360))
+    session = kvm_test_utils.wait_for_login(vm, 0, timeout, 0, 2)
+    def_kernel_param_cmd = ("grubby --update-kernel=`grubby --default-kernel`"
+                            " --args=crashkernel=128M@64M")
+    kernel_param_cmd = params.get("kernel_param_cmd", def_kernel_param_cmd)
+    def_kdump_enable_cmd = "chkconfig kdump on && service kdump start"
+    kdump_enable_cmd = params.get("kdump_enable_cmd", def_kdump_enable_cmd)
+
+    def crash_test(vcpu):
+        """
+        Trigger a crash dump through sysrq-trigger
+
+        @param vcpu: vcpu which is used to trigger a crash
+        """
+        session = kvm_test_utils.wait_for_login(vm, 0, timeout, 0, 2)
+        session.get_command_status("rm -rf /var/crash/*")
+
+        logging.info("Triggering crash on vcpu %d ...", vcpu)
+        crash_cmd = "taskset -c %d echo c > /proc/sysrq-trigger" % vcpu
+        session.sendline(crash_cmd)
+
+        if not kvm_utils.wait_for(lambda: not session.is_responsive(), 240, 0,
+                                  1):
+            raise error.TestFail("Could not trigger crash on vcpu %d" % vcpu)
+
+        logging.info("Waiting for kernel crash dump to complete")
+        session = kvm_test_utils.wait_for_login(vm, 0, crash_timeout, 0, 2)
+
+        logging.info("Probing vmcore file...")
+        s = session.get_command_status("ls -R /var/crash | grep vmcore")
+        if s != 0:
+            raise error.TestFail("Could not find the generated vmcore file")
+        else:
+            logging.info("Found vmcore.")
+
+        session.get_command_status("rm -rf /var/crash/*")
+
+    try:
+        logging.info("Checking the existence of crash kernel...")
+        prob_cmd = "grep -q 1 /sys/kernel/kexec_crash_loaded"
+        s = session.get_command_status(prob_cmd)
+        if s != 0:
+            logging.info("Crash kernel is not loaded. Trying to load it")
+            # We need to setup the kernel params
+            s, o = session.get_command_status_output(kernel_param_cmd)
+            if s != 0:
+                raise error.TestFail("Could not add crashkernel params to"
+                                     "kernel")
+            session = kvm_test_utils.reboot(vm, session, timeout=timeout);
+
+        logging.info("Enabling kdump service...")
+        # the initrd may be rebuilt here so we need to wait a little more
+        s, o = session.get_command_status_output(kdump_enable_cmd, timeout=120)
+        if s != 0:
+            raise error.TestFail("Could not enable kdump service: %s" % o)
+
+        nvcpu = int(params.get("smp", 1))
+        for i in range (nvcpu):
+            crash_test(i)
+
+    finally:
+        session.close()
diff --git a/client/tests/kvm/tests_base.cfg.sample b/client/tests/kvm/tests_base.cfg.sample
index 8fab6e2..00bd3bc 100644
--- a/client/tests/kvm/tests_base.cfg.sample
+++ b/client/tests/kvm/tests_base.cfg.sample
@@ -664,6 +664,15 @@ variants:
                 image_name_snapshot1 = sn1
                 image_name_snapshot2 = sn2
 
+    - kdump:
+        type = kdump
+        # time waited for the completion of crash dump
+        # crash_timeout = 360
+        # command to add the crashkernel=X@Y to kernel cmd line
+        # kernel_param_cmd = "grubby --update-kernel=`grubby --default-kernel` --args=crashkernel=128M@64M"
+        # command to enable kdump service
+        # kdump_enable_cmd = chkconfig kdump on && service kdump start
+
     # system_powerdown, system_reset and shutdown *must* be the last ones
     # defined (in this order), since the effect of such tests can leave
     # the VM on a bad state.
@@ -1924,6 +1933,8 @@ virtio_net|virtio_blk|e1000|balloon_check:
     only Fedora.11 Fedora.12 Fedora.13 RHEL.5 OpenSUSE.11 SLES.11 Ubuntu-8.10-server
     # only WinXP Win2003 Win2008 WinVista Win7 Fedora.11 Fedora.12 Fedora.13 RHEL.5 OpenSUSE.11 SLES.11 Ubuntu-8.10-server
 
+kdump:
+    only RHEL.5 RHEL.6
 
 variants:
     - @qcow2:
diff --git a/client/tests/kvm/unattended/RHEL-5-series.ks b/client/tests/kvm/unattended/RHEL-5-series.ks
index 92ff727..3ee84f1 100644
--- a/client/tests/kvm/unattended/RHEL-5-series.ks
+++ b/client/tests/kvm/unattended/RHEL-5-series.ks
@@ -21,6 +21,7 @@ reboot
 @base
 @development-libs
 @development-tools
+kexec-tools
 
 %post --interpreter /usr/bin/python
 import socket, os
-- 
1.7.2.3