[KVM-AUTOTEST] stress_boot - Boot VMs until one of them becomes unresponsive - Version2

Commit Message

Yolkfull Chow June 12, 2009, 1:27 p.m. UTC

Following are the differences between version 1:

1) use framework to destroy VMs except the main_vm
2) use snapshot to boot other VMs except the first one


Regards,
Yolkfull

Comments

Lucas Meneghel Rodrigues June 18, 2009, 8:17 a.m. UTC | #1

On Fri, 2009-06-12 at 21:27 +0800, Yolkfull Chow wrote:
> Following are the differences between version 1:
> 
> 1) use framework to destroy VMs except the main_vm
> 2) use snapshot to boot other VMs except the first one
> 
> 
> Regards,
> Yolkfull

Hi Yolkfull, Michael and Uri already made a thorough first comment about
your test, and I have a minor thing to note (and I admit I'm being picky
here):

+            # check whether all previous ssh sessions are responsive
+            for i, vm_session in enumerate(sessions):
+                if vm_session.get_command_status(params.get("alive_test_cmd")):
+                    raise error.TestFail("Session #%d is not responsive" % i)
+            num += 1
+
+        except (error.TestFail, OSError):
+            for se in sessions:
+                se.close()
+            logging.info("Total number booted: %d" % num)
+            raise
+    else:
+        for se in sessions:
+            se.close()
+        logging.info("Total number booted: %d" % num)

When the test finishes successfuly, the counter num will be incremented
by one, will break the while condition and later will be used to print
the number of vms successfuly booted. In the end the total number of vms
booted that the test will report is the actual number of vms booted plus
1. To fix this we can either:

 * Just subtract 1 from num at the last info logging call;
 * Remove num initialization and replace the while loop by a

for num in range(1, int(params.get("max_vms")):

this way we don't even need to increment num manually.

It's up to you which one you're going to implement. I have tested your
code and it works fine (aside from the minor cosmetic issue). Once you
send me an updated version, I am going to apply it. 

Thanks for your work!

Patch

diff --git a/client/tests/kvm/kvm.py b/client/tests/kvm/kvm.py
index 9428162..1f553b4 100644
--- a/client/tests/kvm/kvm.py
+++ b/client/tests/kvm/kvm.py
@@ -53,6 +53,7 @@  class kvm(test.test):
                 "autotest":     test_routine("kvm_tests", "run_autotest"),
                 "kvm_install":  test_routine("kvm_install", "run_kvm_install"),
                 "linux_s3":     test_routine("kvm_tests", "run_linux_s3"),
+		"stress_boot":	test_routine("kvm_tests", "run_stress_boot"),
                 }
 
         # Make it possible to import modules from the test's bindir
diff --git a/client/tests/kvm/kvm_tests.cfg.sample b/client/tests/kvm/kvm_tests.cfg.sample
index c73da7c..ff7abea 100644
--- a/client/tests/kvm/kvm_tests.cfg.sample
+++ b/client/tests/kvm/kvm_tests.cfg.sample
@@ -81,6 +81,10 @@  variants:
     - linux_s3:      install setup
         type = linux_s3
 
+    - stress_boot:
+	type = stress_boot
+	max_vms = 5
+
 # NICs
 variants:
     - @rtl8139:
@@ -101,6 +105,8 @@  variants:
         ssh_status_test_command = echo $?
         username = root
         password = 123456
+	stress_boot:
+	    alive_test_cmd = ps aux
 
         variants:
             - Fedora:
@@ -291,6 +297,8 @@  variants:
         password = 123456
         migrate:
             migration_test_command = ver && vol
+	stress_boot:
+	    alive_test_cmd = systeminfo
 
         variants:
             - Win2000:
diff --git a/client/tests/kvm/kvm_tests.py b/client/tests/kvm/kvm_tests.py
index 54d2a7a..fde33bb 100644
--- a/client/tests/kvm/kvm_tests.py
+++ b/client/tests/kvm/kvm_tests.py
@@ -466,3 +466,77 @@  def run_linux_s3(test, params, env):
     logging.info("VM resumed after S3")
 
     session.close()
+
+
+def run_stress_boot(tests, params, env):
+    """
+    Boots VMs until one of them becomes unresponsive, and records the maximum
+    number of VMs successfully started:
+    1) boot the first vm
+    2) boot the second vm cloned from the first vm, check whether it boots up
+       and all booted vms can ssh-login
+    3) go on until cannot create VM anymore or cannot allocate memory for VM
+
+    @param test:   kvm test object
+    @param params: Dictionary with the test parameters
+    @param env:    Dictionary with test environment.
+    """
+    # boot the first vm
+    vm = kvm_utils.env_get_vm(env, params.get("main_vm"))
+
+    if not vm:
+        raise error.TestError("VM object not found in environment")
+    if not vm.is_alive():
+        raise error.TestError("VM seems to be dead; Test requires a living VM")
+
+    logging.info("Waiting for first guest to be up...")
+
+    session = kvm_utils.wait_for(vm.ssh_login, 240, 0, 2)
+    if not session:
+        raise error.TestFail("Could not log into first guest")
+
+    num = 1
+    vms = []
+    sessions = [session]
+
+    # boot the VMs
+    while num <= int(params.get("max_vms")):
+        try:
+            vm_name = "vm" + str(num)
+
+            # clone vm according to the first one
+            vm_params = params.copy()
+            vm_params['image_snapshot'] = "yes"
+            vm_params['kill_vm'] = "yes"
+            vm_params['kill_vm_gracefully'] = "no"
+            curr_vm = vm.clone(vm_name, vm_params)
+            kvm_utils.env_register_vm(env, vm_name, curr_vm)
+            params['vms'] += " " + vm_name
+
+            #vms.append(curr_vm)
+            logging.info("Booting guest #%d" % num)
+            if not curr_vm.create():
+                raise error.TestFail("Cannot create VM #%d" % num)
+
+            curr_vm_session = kvm_utils.wait_for(curr_vm.ssh_login, 240, 0, 2)
+            if not curr_vm_session:
+                raise error.TestFail("Could not log into guest #%d" % num)
+
+            logging.info("Guest #%d boots up successfully" % num)
+            sessions.append(curr_vm_session)
+
+            # check whether all previous ssh sessions are responsive
+            for i, vm_session in enumerate(sessions):
+                if vm_session.get_command_status(params.get("alive_test_cmd")):
+                    raise error.TestFail("Session #%d is not responsive" % i)
+            num += 1
+
+        except (error.TestFail, OSError):
+            for se in sessions:
+                se.close()
+            logging.info("Total number booted: %d" % num)
+            raise
+    else:
+        for se in sessions:
+            se.close()
+        logging.info("Total number booted: %d" % num)