If user run current script whthout argument, the script will search
config in default dir list, but output following message:
| # script/check-config.sh
| warning: /proc/config.gz seems not a kernel config, searching other paths for kernel config ...
^^^^^^^^^^^^^^^
| info: reading kernel config from /boot/config-4.7.0_HEAD_523d939ef98fd712632d93a5a2b588e477a7565e_ ...
| ...
We can make output better by restruct the code struct:
1: Specify nothing
Show info, and search default dir
2: Specify a config file
Use it directly
3: Specify a wrong config file
Show warning, and search default dir
4: Specify a dir
Info, and search specified dir
Test:
| # script/check-config.sh
| info: no config specified, searching for kernel config ...
| info: reading kernel config from /boot/config-4.7.0_HEAD_523d939ef98fd712632d93a5a2b588e477a7565e_ ...
|
| # script/check-config.sh /linux/.config
| info: reading kernel config from /linux/.config ...
|
| # script/check-config.sh /linux/.configgg
| warning: /linux/.configgg seems not a kernel config, searching other paths for kernel config ...
| info: reading kernel config from /boot/config-4.7.0_HEAD_523d939ef98fd712632d93a5a2b588e477a7565e_ ...
|
| # script/check-config.sh /linux
| info: input is a directory, searching for kernel config in this directory...
| info: reading kernel config from /linux/.config ...
|
Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Alternative of #895 , part of #892
The intension of current behavior if to create cgroup in
parent cgroup of current process, but we did this in a
wrong way, we used devices cgroup path of current process
as the default parent path for all subsystems, this is
wrong because we don't always have the same cgroup path
for all subsystems.
Signed-off-by: Qiang Huang <h.huangqiang@huawei.com>
This enables support for exec command argument starting with a '-'.
This uses the usual argument separator '--', for example:
runc exec containerid -- ps -afx
Without this, cli interprets command argument and fails with
'flag provided but not defined'.
Signed-off-by: Tristan Cacqueray <tdecacqu@redhat.com>
Signed-off-by: rajasec <rajasec79@gmail.com>
Error handling when container not exists
Signed-off-by: rajasec <rajasec79@gmail.com>
Error handling when container not exists
Signed-off-by: rajasec <rajasec79@gmail.com>
Error handling when container not exists
Signed-off-by: rajasec <rajasec79@gmail.com>
This keeps the flag but makes it hidden so that existing clients do not
encounter an error if we were to have removed the flag.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
This just moves everything to one function so we don't have to pass a
bunch of things to functions when there's no real benefit. It also makes
the API nicer.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
The original SETUID takes a 16 bit UID. Linux 2.4 introduced a new
syscall, SETUID32, with support for 32 bit UIDs. The setgid wrapper
already uses SETGID32.
Signed-off-by: Carl Henrik Lunde <chlunde@ifi.uio.no>
TestCaptureTestFunc failed in localunittest:
# make localunittest
=== RUN TestCaptureTestFunc
--- FAIL: TestCaptureTestFunc (0.00s)
capture_test.go:26: expected package "github.com/opencontainers/runc/libcontainer/stacktrace" but received "_/root/runc/libcontainer/stacktrace"
#
Reason: the path for stacktrace is a fixed string which
only valid for container environment.
And we can switch to relative path to make both in-container
and out-of-container test works.
After patch:
# make localunittest
=== RUN TestCaptureTestFunc
--- PASS: TestCaptureTestFunc (0.00s)
#
Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Removed a lot of clutter, improved the style of the code, removed
unnecessary complexity. In addition, made errors unique by making bail()
exit with a unique error code. Most of this code comes from the current
state of the rootless containers branch.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
Zhao Lei