- 19 Jun, 2012 35 commits
-
-
Andrey Vagin authored
Now the most part of test cases may be executed in pidns. By default all test cases are executed in current pidns, then they are executed in new pidns again. v2: remove the hard coded path to test_init Signed-off-by:
Andrey Vagin <avagin@openvz.org> Signed-off-by:
Pavel Emelyanov <xemul@parallels.com>
-
Andrey Vagin authored
Add a small program, which clones a process in new PIDNS and executes a test. Signed-off-by:
-
Andrey Vagin authored
Create a tmp directory and mount proc from a target pid ns. This proc will show pid-s from the target pid ns. crtools uses map_files for restoring sharing mappings. the tmp directory is removed after restore. Signed-off-by:
-
Andrey Vagin authored
open_proc_rw knows that proc may be mounted not in /proc, it's used for restoring tasks in pid ns. Signed-off-by:
-
Andrey Vagin authored
v2: rework this by using openat() and service fds for proc root. Signed-off-by:
-
Andrey Vagin authored
Now pid is dumped from pid ns, it's gotted from parasite. v2: fail if a zombie is in PIDNS Signed-off-by:
-
Andrey Vagin authored
It uses pid for create image file and real_pid for dumping ns-s. Signed-off-by:
-
Andrey Vagin authored
because in collect_pstree we don't know pid-s of processes inside pidns Signed-off-by:
-
Andrey Vagin authored
because a pid in a target pid ns is got from parasite. Signed-off-by:
-
Andrey Vagin authored
A pid namespace is created if a pid of the first task is 1. Signed-off-by:
-
Andrey Vagin authored
When we dump pid ns, dump_pstree is called after dump_tasks Signed-off-by:
-
Andrey Vagin authored
If we try to dump a process from another pid ns, we have not another way to get its pid. Signed-off-by:
-
Andrey Vagin authored
Add struct pid and use it everywhere. This struct contains two fields: pid and real_pid. real_pid is a pid outside of the target pid namespace. pid is in the target pid namespace Signed-off-by:
-
Cyrill Gorcunov authored
Otherwise its value might be taken from heap (it's xmalloc'ed). Signed-off-by:
Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
- align members - comment with empty line No func changes. Signed-off-by:
-
Cyrill Gorcunov authored
It's static function near the file_desc_ops, no need for a long name. Signed-off-by:
-
Cyrill Gorcunov authored
Checkpoint and restore do use fdtype_ops and file_desc_ops intensively so reorder pipes functions, this allow us to make them static and drop additional declarations. No func changes. Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
There is no need to make it xmalloc'ed, it's global for all processes dumped. Signed-off-by:
-
Cyrill Gorcunov authored
xemul: Why we haven't done this earlier? Because the pe entry contained the amount of bytes in the pipe and this value had to be calculated before we wrote this entry into the image. Now the pipe data is stored in another img file and we can happily split pe dump and pde dump into two calls. Signed-off-by:
-
Cyrill Gorcunov authored
Will need it for fifo data dumping. At moment the helper is pushed out of compilation procedure for easier review, and will be real used in next patch. Signed-off-by:
-
Cyrill Gorcunov authored
Will need it for pipes data dumping. Signed-off-by:
-
Cyrill Gorcunov authored
And make it dep. on PIPE_DEF_BUFFERS, this points to a limit from kernel side. Signed-off-by:
-
Cyrill Gorcunov authored
| Restoring fd 5 (state -> create) | Create fd for 5 | Going to dup 5 into 5 | Restoring fd 0 (state -> receive) Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
Andrew Vagin <avagin@parallels.com> Signed-off-by:
-
Andrey Vagin authored
sys_exit() takes down only the currect thread. exit_group() should be used to take down all threads. Signed-off-by:
-
Victor Konyashkin authored
If address already in use then need increase port. The problem occured because the socket_listen.c и socket_aio.c can try to use the same address. Signed-off-by:
Victor Konyashkin <vkonyashkin@parallels.com> Acked-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
That is what it is -- a hash for file descriptors based on their ID. Signed-off-by:
-
Andrey Vagin authored
* Create fifo and two descriptors rw and ro * Write data and close rw descriptor * Suspend/resume * Read data from ro descriptor Signed-off-by:
-
Andrey Vagin authored
Signed-off-by:
-
Cyrill Gorcunov authored
Use them explicitly. This fixes problem | LINK crtools | /usr/lib/librt.so: could not read symbols: File in wrong format | collect2: ld returned 1 exit status | make[1]: *** [crtools] Error 1 | make: *** [all] Error 2 Signed-off-by:
Kinsbursky Stanislav <skinsbursky@openvz.org> Signed-off-by:
-
- 04 Jun, 2012 3 commits
-
-
Andrey Vagin authored
Signed-off-by:
-
Cyrill Gorcunov authored
Ad addition to commit 63000f5b, this place was missed to fix. Signed-off-by:
-
Cyrill Gorcunov authored
- add test for flags recovery - drop sockets, not needed - simplify test for owners and signumber v2: remove polling (by avagin@) Signed-off-by:
-
- 01 Jun, 2012 1 commit
-
-
Andrey Vagin authored
SIGABRT may be blocked. We do that in the restorer. Signed-off-by:
-
- 31 May, 2012 1 commit
-
-
Kinsbursky Stanislav authored
v5: 1) make change directory messages supressed. v4: 1) Fixed apply conflicts. v3: 1) "crtools" goal dependences fixed. v2: 1) wrong "protobuf/tmp.pb-c.h" inclusion removed from cr-dump.c Without this patch "touch parasite.c" will lead to rebuild of the whole project. This patch also introduces "pie" goal as a subsystem. This will be usefull, when other subsystems will apper, because it allows to build them in parallel. "all" becomes default goal. This allows to skip deps inclusion for empty, "all", "zdtm" and "test-legacy" goals. Signed-off-by:
-
