- 06 Mar, 2017 16 commits
-
-
Andrei Vagin authored
================= Run zdtm/static/socket-tcp-nfconntrack in h ================== Start test Test is SUID ./socket-tcp-nfconntrack --pidfile=socket-tcp-nfconntrack.pid --outfile=socket-tcp-nfconntrack.out Another app is currently holding the xtables lock. Perhaps you want to use the -w option? Makefile:331: recipe for target 'socket-tcp-nfconntrack.pid' failed make: *** [socket-tcp-nfconntrack.pid] Error 1 Reported-by: Mr Travis Signed-off-by:Andrei Vagin <avagin@virtuozzo.com>
-
Stanislav Kinsburskiy authored
"Check_fs_type" helper was repalce by "get_fs_type". This reference is a silly mistake. Signed-off-by:
Stanislav Kinsburskiy <skinsbursky@virtuozzo.com> Signed-off-by:
-
rbruno@gsd.inesc-id.pt authored
This is needed for the case when the target descriptor is image cache/proxy socket. Signed-off-by:
Rodrigo Bruno <rbruno@gsd.inesc-id.pt> Signed-off-by:
Katerina Koukiou <k.koukiou@gmail.com> Signed-off-by:
Pavel Emelyanov <xemul@virtuozzo.com>
-
rbruno@gsd.inesc-id.pt authored
This is needed for the case when we get data from image-cache/proxy socket. Signed-off-by:
-
Pavel Emelyanov authored
After fds restore set merge we no longer need two lists. Don't BUG in eventpoll when the tfd is not on the list. This situation means that it's restored, so it's safe to report OK from this place. Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Reviewed-by:
Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by:
-
Pavel Emelyanov authored
This is to avoid long item->pid->ns[0].virt for vpid(item). This is 1) for f in $(git grep -l 'ns\[0\]'); do sed -e 's/\([a-zA-Z0-9_]\+\)->pid->ns\[0\].virt/vpid(\1)/g' -i $f; done 2) adding of vpid() routine 3) some manual fixlets Reviewed-by: -
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
We should only get to the post-open stage for standalone sockets with peers. All the others return 0 from ->open which means "restore is over". This change avoids double calling or rst_file_params and restore_socket_opts for those ones. Signed-off-by:
-
Adrian Reber authored
Trying to use the FEATURE_CHECK RPC with criu_req->criu_opts set to NULL makes CRIU segfault. Technically there is no reason to have a valid criu_req->criu_opt during feature check. The only reason was to set the image directory for setproctitle(). This removes the segfault and the unnecessary requirement of setting criu_req->criu_opts. Another possible solution would have been to return an error if criu_req->criu_opts is NULL but so far it seems unnecessary to have criu_req->criu_opts during feature check. Signed-off-by:
Adrian Reber <areber@redhat.com> Signed-off-by:
-
Kir Kolyshkin authored
This will help us catch bugs where the arguments are not in line with the format string. Signed-off-by:
Kir Kolyshkin <kir@openvz.org> Signed-off-by:
-
Rodrigo Bruno authored
criu/sk-queue.c | 33 ++++++++++++--------------------- 1 file changed, 12 insertions(+), 21 deletions(-) In order to prepare for the use of sockets to transfer the image files lseek calls needs to be removed. For sk-queue, we now read the packet data at the same time than the header. This has the disadvantage to consume more memory between the image read and the packets restore, but should hopefully be affordable. Signed-off-by:
-
- 01 Mar, 2017 20 commits
-
-
Kir Kolyshkin authored
When criu is compiled with GCOV=1, .gc* files created are never cleaned. While 'git clean -dxf' does the job and is popular among the criu devs, it still feels good to have good ol' make clean doing the right thing. Reviewed-by:
Dmitry Safonov <dsafonov@virtuozzo.com> Signed-off-by:
-
Kir Kolyshkin authored
For most of the CLI tools I see, adding -v option increases their verbosity. Currently, this is not the case for criu. Default verbosity is set it 2, and using -v actually decreases the verbosity level to 1, so to increase verbosity you need to use -vvv (or -v3). To me, this behavior is quite counterintuitive. This patch changes the way -v works (but retains -vNUM as it was). Now, using -v increases verbosity by +1 from the default value (and e.g. -vvv increases it by +3). Surely, this changes user experience: for example someone who was using -v (rather than -v1 or -v0) to silent warnings, will now have verbosity increased. IMHO this is for the better. Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Andrei Vagin authored
"zdtm.py run -a" doesn't work on Alpine: find: unrecognized: -executable So run zdtm/static/env00 for now to be sure that it is not broken at all. travis-ci: success for travis: execute tests on Alpine Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by: -
Andrei Vagin authored
It works faster and allows to check exit codes. travis-ci: success for series starting with [1/2] page-server: don't return a server pid from page-server Signed-off-by:
-
Andrei Vagin authored
We see the "No space left on device" error on the current version, so let's try to use a newer version of Alpine, maybe this error has been fixed there. Signed-off-by: -
Cyrill Gorcunov authored
Signed-off-by:
Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
-
Andrei Vagin authored
travis-ci: success for A few fixes to c/r a docker container with a console (rev3) Signed-off-by:
-
Andrei Vagin authored
Here we check that a master of a bind-mounted slave was opened in the root mount namespace. The problem is that we restore all mounts in the root mount namespace. Only when all mounts are restored, we create other mount namespaces. So when we are restoring mounts, we can open files only in the root mount namespace. Signed-off-by: -
Andrei Vagin authored
Currently all mounts are restored in a one mount namespace, then this namespace is cloned to restore other mount namespaces and we need another copy of this namespace to clean link remap files. Let's define terms: A - the root mount namespace B - the mount namespace where link remap files are destroyed Currently we restore all mounts in the B namespace and then clone it into the A namespace. But it doesn't work in a case, when we have to open file descriptores to restore mounts (e g to restore bind-mount pty slaves), because a file descriptor has to be opened from a specified mount (which is one of restore mount namespaces). This patch reworks code so, that all mounts is restored in the A mount namespace and then the B mount namespace is created. In this case we can open files from the root mount namespace (A). $ ./zdtm.py run -t zdtm/static/pty-console --iter 5 ====================== Run zdtm/static/pty-console in ns ======================= Start test Test is SUID ./pty-console --pidfile=pty-console.pid --outfile=pty-console.out Run criu dump Run criu restore Run criu dump =[log]=> dump/zdtm/static/pty-console/36/2/dump.log ------------------------ grep Error ------------------------ (00.106521) Error (criu/files-reg.c:1132): Can't lookup mount=563 for fd=4 path=/ptmx (00.106585) Error (criu/cr-dump.c:1325): Dump files (pid: 70) failed with -1 (00.129041) Error (criu/cr-dump.c:1674): Dumping FAILED. ------------------------ ERROR OVER ------------------------ Signed-off-by: -
Andrei Vagin authored
If we can't create a temporary directory for a detached mount, we can clone a whole mount namespace, open a mount and release the created namespace. The result will be the same. https://jira.sw.ru/browse/PSBM-57135 https://github.com/opencontainers/runc/issues/1202 travis-ci: success for A few fixes to c/r a docker container with a console (rev3) Signed-off-by:
-
Andrei Vagin authored
Now we create pty pairs when file descriptors are restored. The problem is that a slave tty can be bind-mounted to somewhere and in this case we have to create this pair and hold a master file descritore before related file descriptors will not be restored. In this patch, a unix socket is used to hold file descriptros. And we use SK_PEEK_OFF and MSG_PEEK to get any of them. travis-ci: success for A few fixes to c/r a docker container with a console (rev3) Signed-off-by:
-
Andrei Vagin authored
When we need to get a file descriptor, we have to set peek offset and then to peek a message. There are two system calls, so we need to be sure that nobody changes a socket peek offset after we set it. Acked-by:
-
Andrei Vagin authored
We need a storage for file descriptors which is shared between processes and doesn't use a lot of file descriptors. We are going to use it on restore and if it will use file descriptors, we will have to find descriptors which don't used by all restored processes to not confilict with their descriptors. There are two solutions. The first one is a service (process) which handles to command push_fd(id, fd) and pop_fd(id, fd). Another solution is to save descriptros in a unix socket. It requires only one extra descriptor which we can register as a service fd. Each unix socket has a buffer and can fit a number of file descriptros. We can use SK_PEEK_OFF and MSG_PEEK to get file descriptros from a socket as many times as we need. This patch implements the second solution. v2: call recvmsg with MSG_PEEK travis-ci: success for A few fixes to c/r a docker container with a console (rev3) Signed-off-by:
-
Andrei Vagin authored
Now Docker creates a pty pair from a container devpts to use is as console. A slave tty is set as a control tty for the init process and bind-mounted into /dev/console. The master tty is handled externelly. Now CRIU can handle external resources, but here we have internal resources which are used externaly. https://github.com/opencontainers/runc/issues/1202 travis-ci: success for A few fixes to c/r a docker container with a console (rev3) Signed-off-by:
-
- 17 Feb, 2017 4 commits
-
-
Pavel Emelyanov authored
In 2.11 we've had several got bronek: - page-server start via RPC - Fedora build - ppc64le restorer switch Signed-off-by: -
Kir Kolyshkin authored
Recent Fedora releases add -Wp,-D_FORTIFY_SOURCE=2 to rpm builds, which breaks compiling pie code on some architectures due to its trying to use (absent) memcpy_chk() instead of usual memcpy(). We must stand strong against FORTIFY_SOURCE in pie code. No pasaran! Viva la resistance! NOTE: in tests, FORTIFY_SOURCE is disabled for completely different reasons (see commit d1a36cc9 for details), so we're not touching it. [v2: resend the correct (latest) version] Reported-by:
Reported-by: Adrian Reber <adrian@lisas.de> Signed-off-by:
-
Laurent Dufour authored
The JUMP_TO_RESTORER_BLOB assembly macro has been rewrote through the commit '89d6b39c ppc64: pie -- Add ppc64le relocation's processing', but the Clobber list hasn't been updated. This doesn't generate build neither runtime errors since the Clobber list was larger than needed but GCC 7 is now raising an error when an assembly macro is clobbering the r2 register. This patch fix the Clobber list to just modified registers. Fixes: 89d6b39c ("ppc64: pie -- Add ppc64le relocation's processing") Reported-by:
Laurent Dufour <ldufour@linux.vnet.ibm.com> Signed-off-by:
-
Pavel Emelyanov authored
Commit 10801f36 (page-server: don't return a server pid from page-server) broke page-server starting via RPC -- the latter code checks for return value being <=0 as failure. Signed-off-by:
-
