- 05 Jul, 2016 9 commits
-
-
Stanislav Kinsburskiy authored
This structures and helpers are needed to simplify autofs mounts reconfiguring during restore. Note: taken from automount package. Signed-off-by:
Stanislav Kinsburskiy <skinsbursky@virtuozzo.com> Signed-off-by:
Pavel Emelyanov <xemul@virtuozzo.com>
-
Stanislav Kinsburskiy authored
This helper is used by autofs restore to add temporary pipe structures. Signed-off-by:
-
Stanislav Kinsburskiy authored
This helpers will be used by autofs restore to create temporary pipe descriptors. Signed-off-by:
-
Stanislav Kinsburskiy authored
This list contains all per-process used file fdinfo's, sorted by fd number. Will be used to safely create new artificial file descriptors and also allow to recreate temporary descriptors with original number, if possible, like AutoFS tries to preserve original pipe write end descriptor, when it was closed. This patch also adds a couple of simple helpers to find unused file descriptor: 1) fd_is_used() does exactly what it is named 2) find_unused_fd() returns "hint_fd" if unused or last used descriptor plus one. Signed-off-by:
-
Stanislav Kinsburskiy authored
AutoFS mount point is managed by user space daemon, which receives requests from kernel via pipe, passed on mount operation. Kernel hold write end, while user space process - read end. Thus, for successful AutoFS migration, this connection has to be restored. During this stage, all the autofs parameters and parsed and collected in per-mount autofs structure. It also does check that autofs mounts is not in interim state. Below are major tricks to be performed to dump AutoFS mount: 1) Read end of the pipe in the process have to be discovered: it will be used to restore the pipe in case of write pipe end in closed in the process. Note: migration of AutoFS mounts, which process group leader doesn't have read pipe end opened is not supported. 2) Read pipe end has to be empty. Otherwise autofs is an interim state. Interim state is determined by control pipe contents: if it's not empty, then it means, that kernel requested some operation (mount/umount), which is in process right now. In case of pipe is not empty, dump is aborted. 3) Mount points are collected (parsed) from initial pid namespace, which leads to real pgrp value in AutoFS options instead of virtual one. This have to be fixed. Note: we don't care about virtual pgrp in case of catatonic mounts Signed-off-by:
-
Stanislav Kinsburskiy authored
Autofs uses packetized pipe (with O_DIRECT), migration of which is not supported. Luckely, because we support only empty autofs pipes, they can be collected into some list and then explicitly treated as normal pipes on dump. Note: packetized mode is set by kernel inself on mount operation. So, we don't need to carry the flag at all. Signed-off-by:
-
Stanislav Kinsburskiy authored
This entry will be used to carry all the autofs parameters, required to restore mount point. Signed-off-by:
-
Stanislav Kinsburskiy authored
This device doesn't support read or write operations and is expected to be created by external process. Thanks to that, regular dump options suits this device. Signed-off-by:
-
Stanislav Kinsburskiy authored
Signed-off-by:
-
- 04 Jul, 2016 4 commits
-
-
Andrei Tuicu authored
CRIU fails to dump processes that have a file descriptor pointing to the /proc folder, because check_path_remap returns error code in that case. Fix: return 0 instead. Signed-off-by:
Andrei Tuicu <andrei.tuicu@gmail.com> Signed-off-by:
-
Tycho Andersen authored
This is supposed to be an else if. CC: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
Tycho Andersen <tycho.andersen@canonical.com> Acked-by:
Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
-
Tycho Andersen authored
Signed-off-by:
-
Cyrill Gorcunov authored
Otherwise next strcat get confused | (00.024843) 26: Error (files-reg.c:1528): Can't open file dev/pts/g:��^?ptmx on restore: No such file or directory | (00.024846) 26: Error (files-reg.c:1470): Can't open file dev/pts/g:��^?ptmx: No such file or directory | (00.024849) 26: Error (tty.c:545): tty: Can't open dev/pts/g:��^?ptmx: No such file or directory Reported-by:
Dmitry Safonov <dsafonov@virtuozzo.com> Signed-off-by:
Cyrill Gorcunov <gorcunov@virtuozzo.com> Reviewed-by:
-
- 28 Jun, 2016 27 commits
-
-
Cyrill Gorcunov authored
In commit c6bc7259c we've started to carry @mode of the files we're opening on restore, implying they are static and should not be changed. This is true for regular files but the pty peers are created dynamically so if someone have set some special mode beore the checkpoint procedure we will fail on restore when regular file engine test it. So lets setup @mode unconditionally. https://travis-ci.org/xemul/criu/jobs/140011141Signed-off-by:
-
Dmitry Safonov authored
Otherwise on some older environments like RHEL7 it will fail to build with: CC pagemap.o pagemap.c: In function ‘punch_hole’: pagemap.c:54:40: error: ‘FALLOC_FL_PUNCH_HOLE’ undeclared (first use in this function) ret = fallocate(img_raw_fd(pr->pi), FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, pagemap.c:54:40: note: each undeclared identifier is reported only once for each function it appears in pagemap.c:54:63: error: ‘FALLOC_FL_KEEP_SIZE’ undeclared (first use in this function) ret = fallocate(img_raw_fd(pr->pi), FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, make[2]: *** [pagemap.o] Error 1 CC: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by:Adrian Reber <areber@redhat.com> Signed-off-by:
-
Andrew Vagin authored
It uses --manage-cgroup full and can dump and restore cgroup of other tests. Reported-by: Mr Jenkins Cc: Tycho Andersen <tycho.andersen@canonical.com> Signed-off-by:
Andrew Vagin <avagin@virtuozzo.com> Acked-by:
-
Mike Rapoport authored
Signed-off-by:
Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by:
-
Mike Rapoport authored
Signed-off-by:
-
Mike Rapoport authored
The deduplication code uses pagemap internal implementation details, so it's better to have this code in the pagemap.c Signed-off-by:
-
Mike Rapoport authored
Signed-off-by:
-
Andrew Vagin authored
Here is a race when someone umounted something and this operation isn't propagated into our namespace. CRIU | Another process ----------------------------------------------------------------- pivot_root(".", put_root) | mount(put_root, MS_REC|MS_PRIVATE) | | umount /xxx/yyy | umount /xxx -> EBUSY umount(put_root) We do this to not affect mounts in put_root, but we can mask these mounts as slave and this will work for us and for external users. Signed-off-by: -
Tycho Andersen authored
pids.current is the current number of pids, not the maximum number allowed (which is the thing we care about, that is set by the user). Signed-off-by:
-
Tycho Andersen authored
Signed-off-by:
-
Tycho Andersen authored
This property can't be written after there are children of the current cgroup or once it has tasks, similar to the cpuset properties. So, let's hoist this property into the "special" array. Signed-off-by:
-
Tycho Andersen authored
memory.oom_control when read displays something like: root@kernel:/sys/fs/cgroup/memory/zdtmtst# cat memory.oom_control oom_kill_disable 0 under_oom 0 but when setting it, it expects a "1" or "0" when written. Let's parse out this 1 or 0. Signed-off-by:
-
Tycho Andersen authored
Before, as long as we successfully closed the prop fd, the property write would succeed. Signed-off-by:
-
Tycho Andersen authored
Signed-off-by:
-
Tycho Andersen authored
CC: Andrey Vagin <avagin@openvz.org> Signed-off-by:
-
Mike Rapoport authored
Signed-off-by:
-
Adrian Reber authored
Signed-off-by:
-
Adrian Reber authored
For the previously added option to skip in-flight connections this adds that option to the RPC interface. The skip in-flight connections is also described in criu.txt. Signed-off-by:
-
Pavel Emelyanov authored
This was 1.2 when we merged all file-locks images together. I think it is good time to drop the legacy format. Signed-off-by: -
Pavel Emelyanov authored
Since 0.3 fdinfo image is ID-s based, so old ones are not used at all. Signed-off-by: -
Pavel Emelyanov authored
These are raw vaddr:page pairs, criu stopped generating this long before 1.0, nobody uses it now. Signed-off-by: -
Dmitry Safonov authored
Looks like it's the most appropriate place for those hooks. Didn't know about those helpers - maybe I should have used them in my code more widely instead of casts. Signed-off-by:
-
Cyrill Gorcunov authored
We will need it for NFS. While we're saving it into image, the test for mode change must be done in account with NFS. So put fixme there. CC: Pavel Emelyanov <xemul@virtuozzo.com> CC: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com> Signed-off-by:
-
Cyrill Gorcunov authored
These entries will be used for NFS support and we already test partial support in vz7 version of criu. So to make images compatible lets reserve some of them in advance. CC: Pavel Emelyanov <xemul@virtuozzo.com> CC: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com> Signed-off-by:
-
Nikita Spiridonov authored
Needed for container migration, where arguments are set via p.haul as rpc request. Signed-off-by:
Nikita Spiridonov <nspiridonov@virtuozzo.com> Signed-off-by:
-
Pavel Tikhomirov authored
1. First save/check all,default,lo together and only after - set them, as setting some sysctls can affect the others 2. Set "accept_redirects" after "forwarding" both for ipv4 and ipv6 3. Change order to "all", "default", "lo" *One can not set ipv6.conf.all.stable_secret, so don't even try, see: commit 622c81d57b39 ("ipv6: generation of stable privacy addresses for link-local and autoconf") Signed-off-by:Pavel Tikhomirov <ptikhomirov@virtuozzo.com> Signed-off-by:
-
Pavel Tikhomirov authored
Restore all/accept_redirects and default/forwarding after all/forwarding as the last can influence the former two. (see inet_forward_change in kernel) # sysctl -w net.ipv4.conf.all.forwarding=1 net.ipv4.conf.all.forwarding = 1 # sysctl -w net.ipv4.conf.default.forwarding=1 net.ipv4.conf.default.forwarding = 1 # sysctl -w net.ipv4.conf.all.forwarding=0 net.ipv4.conf.all.forwarding = 0 # sysctl net.ipv4.conf.default.forwarding net.ipv4.conf.default.forwarding = 0 Trigered with netns-dev test in VZ7CT with vzlinux-6-x86_64 template v2:quirk accept_redirects instead of duplicate entries in devconfs Signed-off-by:
-
