Currently, both systemd cgroup drivers (v1 and v2) only set
"TasksMax" unit property if the value > 0, so there is no
way to update the limit to -1 / unlimited / infinity / max.
Since systemd driver is backed by fs driver, and both fs and fs2
set the limit of -1 properly, it works, but systemd still has
the old value:
# runc --systemd-cgroup update $CT --pids-limit 42
# systemctl show runc-$CT.scope | grep TasksMax
TasksMax=42
# cat /sys/fs/cgroup/system.slice/runc-$CT.scope/pids.max
42
# ./runc --systemd-cgroup update $CT --pids-limit -1
# systemctl show runc-$CT.scope | grep TasksMax=
TasksMax=42
# cat /sys/fs/cgroup/system.slice/runc-xx77.scope/pids.max
max
Fix by changing the condition to allow -1 as a valid value.
NOTE other negative values are still being ignored by systemd drivers
(as it was done before). I am not sure whether this is correct, or
should we return an error.
A test case is added.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
1. do not allow to set quota without period or period without quota, as we
won't be able to calculate new value for CPUQuotaPerSecUSec otherwise.
2. do not ignore setting quota to -1 when a period is not set.
3. update the test case accordingly.
Note that systemd value checks will be added in the next commit.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Such containers should remain paused after the update. This has
historically been true, but this helps ensure that the systemd cgroup
changes (freezing the container during SetUnitProperties) don't break
this behaviour.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
Unfortunately, runc update doesn't support setting devices rules
directly so we have to trigger it by modifying a different rule (which
happens to trigger a devices update).
Signed-off-by: Aleksa Sarai <asarai@suse.de>
1. The command `runc checkpoint --lazy-server --status-fd $FD` actually
accepts a file name as an $FD. Make it accept a file descriptor,
like its name implies and the documentation states.
In addition, since runc itself does not use the result of CRIU status
fd, remove the code which relays it, and pass the FD directly to CRIU.
Note 1: runc should close this file descriptor itself after passing it
to criu, otherwise whoever waits on it might wait forever.
Note 2: due to the way criu swrk consumes the fd (it reopens
/proc/$SENDER_PID/fd/$FD), runc can't close it as soon as criu swrk has
started. There is no good way to know when criu swrk has reopened the
fd, so we assume that as soon as we have received something back, the
fd is already reopened.
2. Since the meaning of --status-fd has changed, the test case using
it needs to be fixed as well.
Modify the lazy migration test to remove "sleep 2", actually waiting
for the the lazy page server to be ready.
While at it,
- remove the double fork (using shell's background process is
sufficient here);
- check the exit code for "runc checkpoint" and "criu lazy-pages";
- remove the check for no errors in dump.log after restore, as we
are already checking its exit code.
[v2: properly close status fd after spawning criu]
[v3: move close status fd to after the first read]
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
With the fix in the previous commit and criu patched with support for
cgroupv2, these tests should now pass.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Same test as the first one, just with cgroupns enabled.
Since in case of cgroupv2 `runc spec` enables cgroupns,
this case was already tested by the first checkpoint test,
so skip it.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Commit a9e15e7e0 adds a check that stdin/out/err pipes
are restored correctly. Commit ec260653b7 copy/pastes
the same code to one more another test.
Problem is (as pointed out in commit 5369f9ade3) these tests
sometimes hang. I have also seen them fail.
Apparently, the code used to create pipes and open them to fds
is racy:
```shell
cat $fifo | cat $fifo &
pid=$!
exec 50</proc/$pid/fd/0
exec 51>/proc/$pid/fd/0
```
Since `cat | cat` is spawned asynchronously, by the time exec is used,
the second cat process (i.e. $pid) is already fork'ed but it might
not be exec'ed yet. As a result, we get this (`ls -l /proc/self/fd`):
```
lr-x------. 1 root root 64 Apr 20 02:39 50 -> /dev/pts/1
l-wx------. 1 root root 64 Apr 20 02:39 51 -> /dev/pts/1
```
or, in some cases:
```
lr-x------. 1 root root 64 Apr 20 02:45 50 -> /dev/pts/1
l-wx------. 1 root root 64 Apr 20 02:45 51 -> 'pipe:[215791]'
```
instead of expected set of pipes:
```
> lr-x------. 1 root root 64 Apr 20 02:45 50 -> 'pipe:[215791]'
> l-wx------. 1 root root 64 Apr 20 02:45 51 -> 'pipe:[215791]'
```
One possible workaround is to add `sleep 0.1` or so after cat|cat,
but it is outright ugly (besides, we already have one sleep in
the test code).
The solution is to not use any external processes to create pipes.
I admit this still looks not very comprehensible, but at least it
is easier than before, and it works.
While at it, remove code duplication, moving the setup and check
code into a pair of functions.
Finally, since the tests are working now, remove the skip.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Since all the criu tests have the same requirements,
move them to setup().
While at it, remove an obviously redundant comment.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Introduce a special case for `testcontainer` to test
for container that is not present (checkpointed), use it.
Fix one place where testcontainer was not used.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
runc in this file is actually a function that does `run runc ...`,
and `run` sets variable `$status` as the exit code, so `$status`
is what should be checked.
If calling runc directly (as in `__runc ...`), then $? is legit.
While at it, remove an obsoleted comment, and an unneeded
`ret=$?` assignment (check `$?` directly).
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Run in the same environment as systemd tests.
Disable CRIU tests because:
- they all fail with cgroup v2;
- CRIU v3.14 is required and it's not yet released, and
rebuilding it from sources with patches applied (like
it is currently done in Dockerfile) is too much work.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Those needs to be run on the (Vagrant Fedora 31) host
(since we need real systemd running), and so we have
to have all the tools needed to compile runc and run
the tests.
The good news is Fedora packages a decent and recent release
of bats-core (1.1.0), which we can use (Debian does not),
and we can also use golang (currently 1.13.9) from Fedora.
The bad news are
1. Currently cgroups tests are only working with
RUNC_USE_SYSTEMD=yes (addressed by #2299, #2305)
2. Tests in events.bats do not work (need cgroupv2
memory.events support)
3. Fedora 31 image is 6 months old (and has broken
container-selinux policy) so we need `dnf update`,
which adds ~5 min to test time.
[v2: add -t to ssh to enforce pty]
[v3: disable events tests for cgroupv2]
[v4: update fedora packages, use a single dnf transation]
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
1. Add `cgroups_v1` and `cgroups_v2` options to `requires`.
2. Modify `check_cgroup_value` to be able to work with v2.
3. Split `test "update"` into two:
- (1) testing cgroupv1-only cpu shares and cfs
- (2) testing limits that are more or less common
between v1 and v2: memory/swap, pids, cpusets.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
... and add kmem-tcp to cgroups kmem test.
First, we already have a separate kmem test in cgroups.bats.
Second, making kmem a requirement leads to skipping all the other
test cases in the update.bats test.
Third, kmem limit is being removed from the kernel, so it makes sense
to handle it separately.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
This comment was added by commit 6cd425be2b (Allow update rt_period_us
and rt_runtime_us, Nov 4 2016), and the test case was added by commit
51baedf3f3 (Add integration for update rt period and runtime,
Nov 28 2016), making the comment obsolete.
Remove it.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
1. Consolidate all the cgroup-related initialization code to
a single place, init_cgroup_paths(), so we can see which
variables are set.
2. Lazily call init_cgroup_paths() from all places that require it.
3. Don't set globals KMEM and RT_PERIOD.
4. Slightly clarlify variables naming:
- use OCI_CGROUPS_PATH for cgroupsPath in config.json
- use REL_CGROUPS_PATH for relative cgroups path
5. Do not hardcode the list of cgroup subsystems -- get it from
/proc/cgroup.
6. Preliminary support for cgroupv2 unified hierarchy (not yet working).
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Consolidate two implementations of check_cgroup_value()
into one, putting it into helpers.
Remove the first parameter, deducing the variable to get
the path from by the parameter name.
This should help in future cgroupv2 support.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
If container's config.json have `"terminal": true` setting in its
"process" section, runc exec assumes that stdin (fd 0) is a terminal
and tries to use it.
This leads to the following error in case stdin is not a terminal:
> ERRO[0000] exec failed: provided file is not a console
So, even if -t/--tty is not set, exec uses stdin as a terminal.
It does not help that urfave/cli v1 parser we use does not allow
to use `-t no` or `-t false`.
Since the settings in config.json is probably for the container run/start,
not for the auxiliary process started inside a container with exec, do
not use a setting from there, only treating stdin as a terminal in case
`-t` is explicitly given.
Tests that use runc exec with a terminal are amended with -t.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Currently, the id verification in integration test failed on arm
platform due to the inconsistent /etc/group in the busybox images
for arm and x86. To be specific, the nogroup id in x86 is 99 while
that in arm is 65534.
99 is old id for nogroup, and no longer be used in recent system,
so sync the busybox image for arm and x86 to the image in busybox
github. Also change the id verification rule in integration test.
Signed-off-by: Howard Zhang <howard.zhang@arm.com>
Minor refactoring to use the filePair struct for both init sock and log pipe
Co-authored-by: Julia Nedialkova <julianedialkova@hotmail.com>
Signed-off-by: Georgi Sabev <georgethebeatle@gmail.com>
These tests sometimes hang, so let's skip them for now.
Tested:
$ sudo make localintegration TESTPATH='/checkpoint.bats' RUNC_USE_SYSTEMD=1
The 5 tests in this test suite will be skipped.
Signed-off-by: Filipe Brandenburger <filbranden@google.com>
When $RUNC_USE_SYSTEMD is set, then use a systemd syntax for the
cgroupsPath. Also fix $CGROUPS_PATH to look under the actual path to the
slice/scope created by systemd.
Tested:
$ sudo make localintegration TESTPATH='/cgroups.bats' RUNC_USE_SYSTEMD=1
That test will fail without this commit.
Signed-off-by: Filipe Brandenburger <filbranden@google.com>
This allows us to test runc using libcontainer's systemd driver, by
passing an extra `--systemd-cgroup` argument to the calls to runc.
Tested:
$ sudo make localintegration TESTPATH='/exec.bats' RUNC_USE_SYSTEMD=1
And confirmed that systemd was in use by looking at creation and removal
of libcontainer_<pid>_systemd_test_default.slice test slices. Also
introduced a breakage in systemd cgroup driver and confirmed that the
tests failed as expected.
Signed-off-by: Filipe Brandenburger <filbranden@google.com>
This removes unnecessary lines from checkpoint.bats like:
sed -i 's;"readonly": true;"readonly": false;' config.json
and adds (and corrects) comments which are leftover from older
versions of checkpoint.bats.
Signed-off-by: Adrian Reber <areber@redhat.com>
This adds a new CRIU based checkpoint/restore test to check if
the restored container runs in the same network namespace as before.
Signed-off-by: Adrian Reber <areber@redhat.com>
Upstream renamed the feature check for lazy migration support from
'lazy_pages' to 'uffd'. The lazy migration test case was therefore
not running at all. This enables the lazy migration test case in runc
again.
The test will, however, not run in travis as the kernel is too old.
But it works again locally.
Signed-off-by: Adrian Reber <areber@redhat.com>
Kir Kolyshkin
Mrunal Patel
Aleksa Sarai
Akihiro Suda
lifubang
Kir Kolyshkin
Odin Ugedal
Jordan Liggitt
Sebastiaan van Stijn
Howard Zhang
Georgi Sabev
Filipe Brandenburger
Giuseppe Scrivano
Adrian Reber
Yan Zhu
Kenta Tada