Nir Soffer has uploaded a new change for review.
Change subject: freeze: Freeze guest even when creating memory snapshot
......................................................................
freeze: Freeze guest even when creating memory snapshot
We used to skip freezing the guest if creating memory snapshot. This was
probably done because qemu is pausing the vm for creating memory
snapshot.
However, this is not consistent with snapshots of external disks such as
network disks, where we always freeze the vm before taking the snapshot.
Also, it is probably safer to freeze even when creating memory snapshot,
giving applications on the guest chance to pause in consistent state.
This patch removes the check for memory snapshot, and freeze the guest
unless it is already frozen.
Change-Id: I8aa7ac0dea8690ca33df8067f84734d788da8bf8
Signed-off-by: Nir Soffer <nsoffer(a)redhat.com>
---
M vdsm/virt/vm.py
1 file changed, 3 insertions(+), 6 deletions(-)
git pull ssh://gerrit.ovirt.org:29418/vdsm refs/changes/99/43299/1
diff --git a/vdsm/virt/vm.py b/vdsm/virt/vm.py
index 332281b..ecbbe1d 100644
--- a/vdsm/virt/vm.py
+++ b/vdsm/virt/vm.py
@@ -3093,9 +3093,6 @@
else:
snapFlags |= libvirt.VIR_DOMAIN_SNAPSHOT_CREATE_DISK_ONLY
- # When creating memory snapshot libvirt will pause the vm
- should_freeze = not (memoryParams or frozen)
-
snapxml = snap.toprettyxml()
# TODO: this is debug information. For 3.6.x we still need to
# see the XML even with 'info' as default level.
@@ -3109,7 +3106,7 @@
self.stopDisksStatsCollection()
try:
- if should_freeze:
+ if not frozen:
freezed = self.freeze()
try:
self._dom.snapshotCreateXML(snapxml, snapFlags)
@@ -3120,7 +3117,7 @@
# Must always thaw, even if freeze failed; in case the guest
# did freeze the filesystems, but failed to reply in time.
# Libvirt is using same logic (see src/qemu/qemu_driver.c).
- if should_freeze:
+ if not frozen:
self.thaw()
# We are padding the memory volume with block size of zeroes
@@ -3148,7 +3145,7 @@
# Returning quiesce to notify the manager whether the guest agent
# froze and flushed the filesystems or not.
return {'status': doneCode,
- 'quiesce': should_freeze and freezed["status"]["code"] == 0}
+ 'quiesce': not frozen and freezed["status"]["code"] == 0}
def diskReplicateStart(self, srcDisk, dstDisk):
try:
--
To view, visit https://gerrit.ovirt.org/43299
To unsubscribe, visit https://gerrit.ovirt.org/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I8aa7ac0dea8690ca33df8067f84734d788da8bf8
Gerrit-PatchSet: 1
Gerrit-Project: vdsm
Gerrit-Branch: master
Gerrit-Owner: Nir Soffer <nsoffer(a)redhat.com>
Nir Soffer has uploaded a new change for review.
Change subject: log: Use INFO log level as default
......................................................................
log: Use INFO log level as default
The current logs are much too verbose which cause trouble for users, and
make us look unprofessional. Mature project should not use debug log by
default.
To debug issues that are not clear enough using INFO logs, the relevant
logger level can be modified on a user machine as needed.
Change-Id: I767dcd9bad7b9fbeebb438e9ef13cb0ec3f042ee
Signed-off-by: Nir Soffer <nsoffer(a)redhat.com>
---
M vdsm/logger.conf.in
1 file changed, 4 insertions(+), 4 deletions(-)
git pull ssh://gerrit.ovirt.org:29418/vdsm refs/changes/04/32504/1
diff --git a/vdsm/logger.conf.in b/vdsm/logger.conf.in
index 64b154f..8e963dd 100644
--- a/vdsm/logger.conf.in
+++ b/vdsm/logger.conf.in
@@ -8,18 +8,18 @@
keys=long,simple,none,sysform
[logger_root]
-level=DEBUG
+level=INFO
handlers=syslog,logfile
propagate=0
[logger_vds]
-level=DEBUG
+level=INFO
handlers=syslog,logfile
qualname=vds
propagate=0
[logger_Storage]
-level=DEBUG
+level=INFO
handlers=logfile
qualname=Storage
propagate=0
@@ -31,7 +31,7 @@
propagate=1
[logger_connectivity]
-level=DEBUG
+level=INFO
handlers=connlogfile
qualname=connectivity
propagate=0
--
To view, visit http://gerrit.ovirt.org/32504
To unsubscribe, visit http://gerrit.ovirt.org/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I767dcd9bad7b9fbeebb438e9ef13cb0ec3f042ee
Gerrit-PatchSet: 1
Gerrit-Project: vdsm
Gerrit-Branch: master
Gerrit-Owner: Nir Soffer <nsoffer(a)redhat.com>
Nir Soffer has uploaded a new change for review.
Change subject: vm: Cleanup waiting for xml update
......................................................................
vm: Cleanup waiting for xml update
This patch cleans up a bit the code for waiting until libvirt xml is
updated after pivot was completed.
- Clarify confusing log message claiming that pivot failed after it
completed successfully
- Cleanup creation of volumes lists using generator expression
- More clear logic for checking current volumes list
- Replace detailed log message and unhelpful exception with detailed
exception
- Move comment out of the loop to make the loop more clear
- Remove unneeded keys() calls when looking up alias in chains
This code was added as temporary solution until libvirt is fixed, but I
think we would like keep a simplified version of it even after libvirt
is fixed, verifying that the operation was successful.
Change-Id: I9fec5416a62736bad461ddd0b54093d23960b7a6
Signed-off-by: Nir Soffer <nsoffer(a)redhat.com>
---
M vdsm/virt/vm.py
1 file changed, 27 insertions(+), 24 deletions(-)
git pull ssh://gerrit.ovirt.org:29418/vdsm refs/changes/38/39938/1
diff --git a/vdsm/virt/vm.py b/vdsm/virt/vm.py
index efadbdb..8ece47b 100644
--- a/vdsm/virt/vm.py
+++ b/vdsm/virt/vm.py
@@ -5100,40 +5100,43 @@
# synchronized and we may start the vm with a stale volume in the
# future. See https://bugzilla.redhat.com/show_bug.cgi?id=1202719 for
# more details.
- # TODO: Remove once we depend on a libvirt with this bug fixed.
# We expect libvirt to show that the original leaf has been removed
# from the active volume chain.
origVols = sorted([x['volumeID'] for x in self.drive.volumeChain])
- expectedVols = origVols[:]
- expectedVols.remove(self.drive.volumeID)
+ expectedVols = [v for v in origVols if v != self.driveVolumeID]
alias = self.drive['alias']
self.vm.log.info("Waiting for libvirt to update the XML after pivot "
"of drive %s completed", alias)
- while True:
- # This operation should complete in either one or two iterations of
- # this loop. Until libvirt updates the XML there is nothing to do
- # but wait. While we wait we continue to tell engine that the job
- # is ongoing. If we are still in this loop when the VM is powered
- # off, the merge will be resolved manually by engine using the
- # reconcileVolumeChain verb.
- chains = self.vm._driveGetActualVolumeChain([self.drive])
- if alias not in chains.keys():
- raise RuntimeError("Failed to retrieve volume chain for "
- "drive %s. Pivot failed.", alias)
- curVols = sorted([entry.uuid for entry in chains[alias]])
- if curVols == origVols:
- time.sleep(1)
- elif curVols == expectedVols:
+ # This operation should complete in either one or two iterations of
+ # this loop. Until libvirt updates the XML there is nothing to do
+ # but wait. While we wait we continue to tell engine that the job
+ # is ongoing. If we are still in this loop when the VM is powered
+ # off, the merge will be resolved manually by engine using the
+ # reconcileVolumeChain verb.
+ # TODO: Check once when we depend on a libvirt with this bug fixed.
+
+ while True:
+ chains = self.vm._driveGetActualVolumeChain([self.drive])
+ if alias not in chains:
+ raise RuntimeError("Failed to retrieve volume chain for "
+ "drive %s after pivot completed", alias)
+
+ curVols = sorted(entry.uuid for entry in chains[alias])
+
+ if curVols == expectedVols:
self.vm.log.info("The XML update has been completed")
- break
- else:
- self.log.error("Bad volume chain found for drive %s. Previous "
- "chain: %s, Expected chain: %s, Actual chain: "
- "%s", alias, origVols, expectedVols, curVols)
- raise RuntimeError("Bad volume chain found")
+ return
+
+ if curVols != origVols:
+ raise RuntimeError(
+ "Bad volume chain after pivot for drive %s. Previous "
+ "chain: %s, Expected chain: %s, Actual chain: %s" %
+ (alias, origVols, expectedVols, curVols))
+
+ time.sleep(1)
def _devicesWithAlias(domXML):
--
To view, visit https://gerrit.ovirt.org/39938
To unsubscribe, visit https://gerrit.ovirt.org/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I9fec5416a62736bad461ddd0b54093d23960b7a6
Gerrit-PatchSet: 1
Gerrit-Project: vdsm
Gerrit-Branch: master
Gerrit-Owner: Nir Soffer <nsoffer(a)redhat.com>
Nir Soffer has uploaded a new change for review.
Change subject: lib: Revert and refine error handling in tmap()
......................................................................
lib: Revert and refine error handling in tmap()
In commit 2b7155b696 (lib: Simplify and generalize concurrent.tmap()),
we simplified error handling by returning a named tuple with function
results. This turned out less useful then the original error handling.
This patch returns the previous error handling:
- Functions passed to tmap() should not raise - if they raise, this is
considered a bug in the function.
- The last error is raised by tmap() instead of returning the result.
This make it easier to fail loudly for unexpected errors.
- The original exception is re-raised now with the original traceback.
- Error handling is documented properly now
Previously you had to make sure function raises to signal failures:
def func():
try:
code that should not fail...
code that may fail...
code that should not fail...
except ExpectedError:
log.error(...)
raise
except Exception:
log.exception(...)
raise
results = concurrent.tmap(func, values)
if not all(r.succeeded for r in results):
...
Returning the result as is lets us have nicer code:
def func():
code that should not fail...
try:
code that may fail...
except ExpectedError:
log.error(...)
return False
code that should not fail...
return True
succeeded = concurrent.tmap(func, values)
if not all(succeeded):
...
We can ignore unexpected errors, since tmap() will log them and fail
loudly. We can also minimize try except block for expected errors.
Change-Id: I0154b28ff7822c63e77181bbbf444c712bd0c31e
Signed-off-by: Nir Soffer <nsoffer(a)redhat.com>
---
M lib/vdsm/concurrent.py
M tests/concurrentTests.py
2 files changed, 45 insertions(+), 19 deletions(-)
git pull ssh://gerrit.ovirt.org:29418/vdsm refs/changes/11/39211/1
diff --git a/lib/vdsm/concurrent.py b/lib/vdsm/concurrent.py
index 64e072d..5498052 100644
--- a/lib/vdsm/concurrent.py
+++ b/lib/vdsm/concurrent.py
@@ -18,22 +18,42 @@
# Refer to the README and COPYING files for full details of the license
#
+import logging
import threading
-from collections import namedtuple
-
-
-Result = namedtuple("Result", ["succeeded", "value"])
+import sys
def tmap(func, iterable):
+ """
+ Run func with arguments from iterable in multiple threads, a returning the
+ output in order of arguments.
+
+ func should not raise exceptions - we consider this a bug in func, and will
+ fail the call and re-raise the exception in the caller thread.
+
+ Expected exceptions should be handled in func. If the caller likes to
+ handle the error later, func should return it:
+
+ def func(value):
+ try:
+ return something(value)
+ except ExpectedError as e:
+ return e
+
+ Unexpected exceptions should not be handled, as they are logged in the
+ worker threads and re-raised in the caller thread. If multiple excpetions
+ raised, only the last one will be re-raised in the caller thread.
+ """
args = list(iterable)
results = [None] * len(args)
+ error = [None]
def worker(i, f, arg):
try:
- results[i] = Result(True, f(arg))
- except Exception as e:
- results[i] = Result(False, e)
+ results[i] = f(arg)
+ except Exception:
+ error[0] = sys.exc_info()
+ logging.exception("Unhandled exception in tmap worker thread")
threads = []
for i, arg in enumerate(args):
@@ -45,4 +65,8 @@
for t in threads:
t.join()
+ if error[0] is not None:
+ t, v, tb = error[0]
+ raise t, v, tb
+
return results
diff --git a/tests/concurrentTests.py b/tests/concurrentTests.py
index 307e397..5c0646b 100644
--- a/tests/concurrentTests.py
+++ b/tests/concurrentTests.py
@@ -26,13 +26,16 @@
from vdsm import concurrent
+class Error(Exception):
+ pass
+
+
class TMapTests(VdsmTestCase):
def test_results(self):
values = tuple(range(10))
results = concurrent.tmap(lambda x: x, values)
- expected = [concurrent.Result(True, x) for x in values]
- self.assertEqual(results, expected)
+ self.assertEqual(results, list(values))
def test_results_order(self):
def func(x):
@@ -40,8 +43,7 @@
return x
values = tuple(random.random() * 0.1 for x in range(10))
results = concurrent.tmap(func, values)
- expected = [concurrent.Result(True, x) for x in values]
- self.assertEqual(results, expected)
+ self.assertEqual(results, list(values))
def test_concurrency(self):
start = time.time()
@@ -49,12 +51,12 @@
elapsed = time.time() - start
self.assertTrue(0.1 < elapsed < 0.2)
- def test_error(self):
- error = RuntimeError("No result for you!")
-
+ def test_raise_last_error(self):
def func(x):
- raise error
-
- results = concurrent.tmap(func, range(10))
- expected = [concurrent.Result(False, error)] * 10
- self.assertEqual(results, expected)
+ raise Error(x)
+ try:
+ concurrent.tmap(func, (1, 2, 3))
+ except Error as e:
+ self.assertEqual(e.args, (3,))
+ else:
+ self.fail("Exception was not raised")
--
To view, visit https://gerrit.ovirt.org/39211
To unsubscribe, visit https://gerrit.ovirt.org/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I0154b28ff7822c63e77181bbbf444c712bd0c31e
Gerrit-PatchSet: 1
Gerrit-Project: vdsm
Gerrit-Branch: master
Gerrit-Owner: Nir Soffer <nsoffer(a)redhat.com>
Nir Soffer has uploaded a new change for review.
Change subject: misc: Safer and simpler itmap
......................................................................
misc: Safer and simpler itmap
The previous code had few issues:
- It used unlimited number of threads by default. This may lead to
creation of 100's of threads if you do not specify a value.
- It used non-daemon threads, which could lead to unwanted delay during
vdsm shutdown.
- It tried to yield results before all arguments were handled. This
could lead to unwanted delay in argument processing, if the caller
would block processing the results.
- It started one thread per value, even if maxthreads was smaller than
number of values.
- It was too complicated.
Changes:
- The caller must specify the maximum number of threads.
- Use daemon threads
- Queue all values before yielding results
- Start up to maxthreads worker threads, each processing multiple values
- Simplify the code
- Add test for error handling
Change-Id: Iba6116ac4003702c8e921cebaf494491a6f9afaf
Signed-off-by: Nir Soffer <nsoffer(a)redhat.com>
---
M tests/miscTests.py
M vdsm/storage/misc.py
2 files changed, 42 insertions(+), 42 deletions(-)
git pull ssh://gerrit.ovirt.org:29418/vdsm refs/changes/19/39119/1
diff --git a/tests/miscTests.py b/tests/miscTests.py
index 31f64fa..4b3e3c3 100644
--- a/tests/miscTests.py
+++ b/tests/miscTests.py
@@ -196,7 +196,7 @@
# outOfProcess operation + 1. it let us know that oop and itmap operate
# properly with their limitations
data = frozenset(range(oop.HELPERS_PER_DOMAIN + 1))
- ret = frozenset(misc.itmap(dummy, data, misc.UNLIMITED_THREADS))
+ ret = frozenset(misc.itmap(dummy, data, len(data)))
self.assertEquals(ret, data)
def testMoreThreadsThanArgs(self):
@@ -207,6 +207,13 @@
data = 1
self.assertRaises(ValueError, misc.itmap(int, data, 0).next)
+ def testErrors(self):
+ err = Exception()
+ def dummy(arg):
+ raise err
+ data = [1, 2, 3]
+ self.assertEqual(list(misc.itmap(dummy, data, 4)), [err] * len(data))
+
class RotateFiles(TestCaseBase):
diff --git a/vdsm/storage/misc.py b/vdsm/storage/misc.py
index eb484c7..463fd04 100644
--- a/vdsm/storage/misc.py
+++ b/vdsm/storage/misc.py
@@ -58,7 +58,6 @@
STR_UUID_SIZE = 36
UUID_HYPHENS = [8, 13, 18, 23]
MEGA = 1 << 20
-UNLIMITED_THREADS = -1
log = logging.getLogger('Storage.Misc')
@@ -882,53 +881,47 @@
raise exception
-def itmap(func, iterable, maxthreads=UNLIMITED_THREADS):
+def itmap(func, iterable, maxthreads):
"""
- Make an iterator that computes the function using
- arguments from the iterable. It works similar to tmap
- by running each operation in a different thread, this
- causes the results not to return in any particular
- order so it's good if you don't care about the order
- of the results.
- maxthreads stands for maximum threads that we can initiate simultaneosly.
- If we reached to max threads the function waits for thread to
- finish before initiate the next one.
+ Return an iterator calling func with arguments from iterable in multiple threads.
+
+ Unlike tmap, the results are not returned in the original order of the
+ arguments, and number of threads is limited to maxthreads.
"""
- if maxthreads < 1 and maxthreads != UNLIMITED_THREADS:
- raise ValueError("Wrong input to function itmap: %s", maxthreads)
+ if maxthreads < 1:
+ raise ValueError("Invalid maxthreads value: %s" % maxthreads)
- respQueue = Queue.Queue()
+ DONE = object()
+ values = Queue.Queue()
+ results = Queue.Queue()
- def wrapper(value):
- try:
- respQueue.put(func(value))
- except Exception as e:
- respQueue.put(e)
+ def worker():
+ while True:
+ value = values.get()
+ if value is DONE:
+ return
+ try:
+ results.put(func(value))
+ except Exception as e:
+ results.put(e)
- threadsCount = 0
- for arg in iterable:
- if maxthreads != UNLIMITED_THREADS:
- if maxthreads == 0:
- # This not supposed to happened. If it does, it's a bug.
- # maxthreads should get to 0 only after threadsCount is
- # greater than 1
- if threadsCount < 1:
- raise RuntimeError("No thread initiated")
- else:
- yield respQueue.get()
- # if yield returns one thread stopped, so we can run
- # another thread in queue
- maxthreads += 1
- threadsCount -= 1
+ count = 0
+ threads = 0
- t = threading.Thread(target=wrapper, args=(arg,))
- t.start()
- threadsCount += 1
- maxthreads -= 1
+ for value in iterable:
+ values.put(value)
+ count += 1
+ if threads < maxthreads:
+ t = threading.Thread(target=worker)
+ t.daemon = True
+ t.start()
+ threads += 1
- # waiting for rest threads to end
- for i in xrange(threadsCount):
- yield respQueue.get()
+ for _ in range(threads):
+ values.put(DONE)
+
+ for _ in xrange(count):
+ yield results.get()
def isAscii(s):
--
To view, visit https://gerrit.ovirt.org/39119
To unsubscribe, visit https://gerrit.ovirt.org/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: Iba6116ac4003702c8e921cebaf494491a6f9afaf
Gerrit-PatchSet: 1
Gerrit-Project: vdsm
Gerrit-Branch: master
Gerrit-Owner: Nir Soffer <nsoffer(a)redhat.com>
Nir Soffer has uploaded a new change for review.
Change subject: udevadm: More precise error handling
......................................................................
udevadm: More precise error handling
udevadm provides a --timeout option, but there is no robust way to
detect a timeout in EL6, EL7, and Fedora 20. In Fedora 21 and upstream,
udevadm ignores the timeout option. This patch improves error handling
by using our own timeout.
udevadm.settle() raises now udevadm.Failure or udevadm.Timeout, and the
caller is responsible to handle the error.
In both multipath.rescan() and IscsiConnection.connect(), we warn about
timeout but do not handle other errors, so real errors in udevadm will
fail loudly.
Change-Id: Ia0a7380b1b181ec93399ea741122cfa2e98086fb
Relates-To: https://bugzilla.redhat.com/1209474
Signed-off-by: Nir Soffer <nsoffer(a)redhat.com>
---
A tests/udevadmTests.py
M vdsm/storage/multipath.py
M vdsm/storage/storageServer.py
M vdsm/storage/udevadm.py
4 files changed, 106 insertions(+), 21 deletions(-)
git pull ssh://gerrit.ovirt.org:29418/vdsm refs/changes/40/39740/1
diff --git a/tests/udevadmTests.py b/tests/udevadmTests.py
new file mode 100644
index 0000000..90841b2
--- /dev/null
+++ b/tests/udevadmTests.py
@@ -0,0 +1,52 @@
+#
+# Copyright 2015 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+#
+# Refer to the README and COPYING files for full details of the license
+#
+
+
+from monkeypatch import MonkeyPatch
+from testlib import VdsmTestCase
+
+from vdsm import utils
+from storage import udevadm
+
+TRUE = utils.CommandPath("true", "/bin/true", "/usr/bin/true")
+FALSE = utils.CommandPath("false", "/bin/false", "/usr/bin/false")
+READ = utils.CommandPath("read", "/bin/read", "/usr/bin/read")
+
+
+class UdevadmSettleTests(VdsmTestCase):
+
+ @MonkeyPatch(udevadm, "_UDEVADM", TRUE)
+ def test_success(self):
+ udevadm.settle(5)
+
+ @MonkeyPatch(udevadm, "_UDEVADM", FALSE)
+ def test_error(self):
+ try:
+ udevadm.settle(5)
+ except udevadm.Failure as e:
+ self.assertEqual(e.rc, 1)
+ self.assertEqual(e.out, "")
+ self.assertEqual(e.err, "")
+ else:
+ self.fail("Failure not raised")
+
+ @MonkeyPatch(udevadm, "_UDEVADM", READ)
+ def test_timeout(self):
+ self.assertRaises(udevadm.Timeout, udevadm.settle, 1)
diff --git a/vdsm/storage/multipath.py b/vdsm/storage/multipath.py
index a1c42b3..925c411 100644
--- a/vdsm/storage/multipath.py
+++ b/vdsm/storage/multipath.py
@@ -73,7 +73,10 @@
# events are processed, ensuring detection of new devices and creation or
# update of multipath devices.
timeout = config.getint('irs', 'scsi_settle_timeout')
- udevadm.settle(timeout)
+ try:
+ udevadm.settle(timeout)
+ except udevadm.Timeout as e:
+ log.warning("Timeout waiting for udev events: %s", e)
def deduceType(a, b):
diff --git a/vdsm/storage/storageServer.py b/vdsm/storage/storageServer.py
index 22a90d1..c19fb8d 100644
--- a/vdsm/storage/storageServer.py
+++ b/vdsm/storage/storageServer.py
@@ -382,7 +382,10 @@
def connect(self):
iscsi.addIscsiNode(self._iface, self._target, self._cred)
timeout = config.getint("irs", "scsi_settle_timeout")
- udevadm.settle(timeout)
+ try:
+ udevadm.settle(timeout)
+ except udevadm.Timeout as e:
+ self.log.warning("Timeout waiting for udev events: %s", e)
def _match(self, session):
target = session.target
diff --git a/vdsm/storage/udevadm.py b/vdsm/storage/udevadm.py
index 4b4b54a..a2afd04 100644
--- a/vdsm/storage/udevadm.py
+++ b/vdsm/storage/udevadm.py
@@ -18,22 +18,39 @@
# Refer to the README and COPYING files for full details of the license
#
-import logging
+import errno
+import signal
+
from vdsm import utils
+from vdsm.infra import zombiereaper
_UDEVADM = utils.CommandPath("udevadm", "/sbin/udevadm", "/usr/sbin/udevadm")
class Error(Exception):
+ message = None
- def __init__(self, rc, out, err):
+ def __str__(self):
+ return self.message.format(self=self)
+
+
+class Failure(Error):
+ message = ("udevadm failed cmd={self.cmd} rc={self.rc} out={self.out!r} "
+ "err={self.err!r}")
+
+ def __init__(self, cmd, rc, out, err):
+ self.cmd = cmd
self.rc = rc
self.out = out
self.err = err
- def __str__(self):
- return "Process failed with rc=%d out=%r err=%r" % (
- self.rc, self.out, self.err)
+
+class Timeout(Error):
+ message = ("udevadm timed out cmd={self.cmd} timeout={self.timeout}")
+
+ def __init__(self, cmd, timeout):
+ self.cmd = cmd
+ self.timeout = timeout
def settle(timeout, exit_if_exists=None):
@@ -44,25 +61,35 @@
Arguments:
timeout Maximum number of seconds to wait for the event queue to
- become empty. A value of 0 will check if the queue is empty
- and always return immediately.
+ become empty.
exit_if_exists Stop waiting if file exists.
+
+ Raises Failure if udevadm failed, or Timeout if udevadm did not terminate
+ within the requested timeout.
"""
- args = ["settle", "--timeout=%s" % timeout]
+ cmd = [_UDEVADM.cmd, "settle"]
if exit_if_exists:
- args.append("--exit-if-exists=%s" % exit_if_exists)
+ cmd.append("--exit-if-exists=%s" % exit_if_exists)
- try:
- _run_command(args)
- except Error as e:
- logging.error("%s", e)
+ _run_command(cmd, timeout)
-def _run_command(args):
- cmd = [_UDEVADM.cmd]
- cmd.extend(args)
- rc, out, err = utils.execCmd(cmd, raw=True)
- if rc != 0:
- raise Error(rc, out, err)
+def _run_command(cmd, timeout=None):
+ proc = utils.execCmd(cmd, sync=False, deathSignal=signal.SIGKILL)
+
+ if not proc.wait(timeout):
+ try:
+ proc.kill()
+ except OSError as e:
+ if e.errno != errno.ESRCH:
+ raise
+ finally:
+ zombiereaper.autoReapPID(proc.pid)
+ raise Timeout(cmd, timeout)
+
+ if proc.returncode != 0:
+ out = "".join(proc.stdout)
+ err = "".join(proc.stderr)
+ raise Failure(cmd, proc.returncode, out, err)
--
To view, visit https://gerrit.ovirt.org/39740
To unsubscribe, visit https://gerrit.ovirt.org/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: Ia0a7380b1b181ec93399ea741122cfa2e98086fb
Gerrit-PatchSet: 1
Gerrit-Project: vdsm
Gerrit-Branch: master
Gerrit-Owner: Nir Soffer <nsoffer(a)redhat.com>