This ensures that anything written to the logs are synced as they
happen.
This also changes the error message of the libcontainer error. The
original idea was to have this extra information in the message but it
makes it hard to parse and if the caller needed this information they
can just get it from the error type.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
The error handling on the runc cli is currenly pretty messy because
messages to the user are split between regular stderr format and logrus
message format. This changes all the error reporting to the cli to only
output on stderr and exit(1) for consumers of the api.
By default logrus logs to /dev/null so that it is not seen by the user.
If the user wants extra and/or structured loggging/errors from runc they
can use the `--log` flag to provide a path to the file where they want
this information. This allows a consistent behavior on the cli but
extra power and information when debugging with logs.
This also includes a change to enable the same logging information
inside the container's init by adding an init cli command that can share
the existing flags for all other runc commands.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
Closes#532
This requires the container id to always be passed to all runc commands
as arg one on the cli. This was the result of the last OCI meeting and
how operations work with the spec.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
By adding detach to runc the container process is the only thing running
on the system is the containers process.
This allows better usage of memeory and no runc process being long
lived. With this addition you also need a delete command because the
detached container will not be able to remove state and the left over
cgroups directories.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
I deleted possibility to specify config file from commands for now.
Until we decide how it'll be done. Also I changed runc spec interface to
write config files instead of output them.
Signed-off-by: Alexander Morozov <lk4d4@docker.com>
When any non-global-flag parameter appears on the command line make sure
there's a "command" even in the 'start' (run) case to ensure its not
ambiguous as to what the arg is. For example, w/o this fix its not
clear if
runc foo
means 'foo' is the name of a config file or an unknown command. Or worse,
you can't name a config file the same a ANY command, even future (yet to
be created) commands.
We should fix this now before we ship 1.0 and are forced to support this
ambiguous case for a long time.
Signed-off-by: Doug Davis <dug@us.ibm.com>
Should compile now without errors but changes needed to be added for each system so it actually works.
main_unsupported.go is a new file with all the unsupported commands
Fixes#9
Signed-off-by: Marianna <mtesselh@gmail.com>
We need this version check during our initial work so that runc does not
fail silently while make changes to runc to match the spec work going
on.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
1. Remove mention of nsinit (removed from the repo)
2. Make basic usage text a bit more informative; fix typo
3. Fix typo in panic() message (that should never be seen) :)
Docker-DCO-1.1-Signed-off-by: Phil Estes <estesp@linux.vnet.ibm.com> (github: estesp)
A couple minor changes to error handling in startup:
1. Don't dump full help/usage text when the only problem is `runc` wasn't started under
root privileges
2. Check for rootfs and make error clear to user when it doesn't exist
3. Change fatal to logrus.Fatal to get nicer output with simple error
message
Docker-DCO-1.1-Signed-off-by: Phil Estes <estesp@linux.vnet.ibm.com> (github: estesp)
Mrunal Patel
Michael Crosby
Mike Brown
Alexander Morozov
xlgao-zju
Tianon Gravi
Marcos Lilljedahl
Eric Myhre
Lai Jiangshan
Qiang Huang
Mrunal Patel
Doug Davis
Tonis Tiigi
rajasec
Marianna
John Howard
Alexander Morozov
Phil Estes