Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The option -p is used for testing page server
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

without this patch, fd will not be freeed

* Changelog from v1:
	* just free fd, no crt.ids
Signed-off-by: Libo Chen <libo.chen@huawei.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

when pb_read_one_eof faild, we should close fd
Signed-off-by: Libo Chen <libo.chen@huawei.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

when mntns_collect_root->readlinkat call faild, we should close pdf
Signed-off-by: Libo Chen <libo.chen@huawei.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

when is_blocked is seted, we should free file_lock
Signed-off-by: Libo Chen <libo.chen@huawei.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Libo Chen <libo.chen@huawei.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Currsntly this affects nothing, but xfer close should be called.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

If we have empty pagemap, the page server receives no
IO-s for one and doesn't create image file. Intoroduce
the OPEN command to say to page server, that we're about
to xfer and image so it can prepare.

https://bugzilla.openvz.org/show_bug.cgi?id=2584Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

First of all, 4 bits are not enough for type (shmem pagemap's is
28, which is 5 bits). Plus the encode trimmed bits from the id.

https://bugzilla.openvz.org/show_bug.cgi?id=2584Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Since commit 43ce038e -t is not required for restore,
plus a warning is printed if it is used. Let's remove
-t from criu restore in all test cases.
Signed-off-by: Kir Kolyshkin <kir@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

cr-check.c for some reason got x bit O_o
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Will be needed for parasite code.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

pages_scanned -- the amount of pages criu looked at for decision
pages_skipped_parent -- the amount of pages that were skipped, due to
                        they are present in parent image
pages_writted -- the amount of pages criu transfered into image
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Kir Kolyshkin <kir@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

-D is used for dump and restore, i.e. to read and write image files,
depending on the command, so let's put a read/write-neutral description.
Signed-off-by: Kir Kolyshkin <kir@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

A couple of fixes related to the fact.

This is an addition to commit 43ce038eSigned-off-by: Kir Kolyshkin <kir@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Kir Kolyshkin <kir@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

This patch

1. Replaces using argv[0] with criu literal. Using argv[0] is bad
because it can be a relative path, and it can be not "criu" but
say a symlink pointing to criu.

2. Reformats the source to print basic help test in justone call to
pr_msg(), same as commit 6ea0e002 did for extended help, for same
reasons: having it this way is easier to do further edits.
Signed-off-by: Kir Kolyshkin <kir@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

I'll need to modify this header so before anything
else lets beautify it

 - drop struct pstree_item declaration it's already in pstree.h
 - move struct cr_options to top
 - align members of struct ns_desc
 - move externs to top
 - add argument name to try_show_namespaces
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

#PSBM-19883
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The "*:<fmt>" describes format for everyone else in pretty.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Use <field>: format.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

1. clean the code
2. add support for <field-name>:<format> strings in pretty
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Now they seem to look OK.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The first is similar to existing snapshot test -- it calls
several pre-dumps on memory-changing zdtm test, then dumps
and check restore goes OK.

The second test is aimed at measuring frozen-time -- it
takes zdtm test with big mappings, dumps one, then start the
test again and calls one pre-dump plus dump. The sum of
frozen times in the 2nd dump (well, pre-dump + dump) should
be much smaller then the one of the 1st "just dump".
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

With this action criu will seize tasks, grab all its memory into
page-pipes, rest dirty tracker and will then release them. Writing
the memory from page-pipes would occur after tasks are unfreezed
and thus the frozen time should become reasonably small.

When pre-dump is in action, the dirty tracking is forcedly turned
off as well as tasks are resumed afterwards, not killed, by default.

This is a prerequisite for iterative migration.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Dumping memory is draining it from parasite, for pre-dump
this time would be reasonably small. _Writing_ the memory
would occur _after_ tasks unseize and resume.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

For pre-dump we'll need to cure the target task(s), but keep the
parasite_ctl (for its local args mapping) for memory image write.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

There will be more tests on memory snapshot.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>