2
0
mirror of https://github.com/checkpoint-restore/criu synced 2025-08-22 01:51:51 +00:00
criu/include
Pavel Emelyanov 505652ef86 page-server: Fine grained corking control (v3)
When live migrating a container with large amount of processes
inside the time to do page-server-ed dump may be up to 10 times
slower than for the local dump.

The delay is always introduced in the open_page_server_xfer()
when criu negotiates the has_parent bit on the 2nd task. This
likely happens because of the Nagel algo taking place -- after
the write() of the OPEN2 command happened kernel delays this
command sending waiting for more data.

v2:
Fix this by turning on CORK option on memory transfer sockets
on send side, and NODELAY one once on urgent data. Receive
side is always NODELAY-ed. According to Alexey Kuznetsov this
is the best mode ever for such type of transfers.

v3:
Push packets in pre-dump's check_parent_server_xfer too.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Andrew Vagin <avagin@odin.com>

Conflicts:
	include/util.h
	util.c
2015-11-11 19:13:57 +03:00
..
2014-12-26 18:13:40 +03:00
2014-02-21 16:27:16 +04:00
2014-08-19 12:58:36 +04:00
2013-02-15 17:34:38 +04:00
2014-09-30 21:48:13 +04:00
2013-04-02 20:27:51 +04:00
2014-02-25 23:38:35 +04:00
2014-09-30 21:48:10 +04:00
2015-08-18 18:17:31 +03:00
2014-09-19 17:42:48 +04:00
2015-07-29 17:53:36 +03:00
2014-09-30 21:48:13 +04:00
2015-08-18 18:17:31 +03:00
2013-11-14 22:13:59 +04:00
2014-01-14 09:33:19 +04:00
2015-04-14 15:18:32 +03:00
2015-10-22 17:13:31 +04:00
2015-06-08 23:34:58 +03:00
2015-04-02 20:20:01 +03:00
2013-11-15 16:59:57 +04:00
2014-09-03 20:48:36 +04:00
2015-02-10 16:54:31 +03:00
2015-08-06 14:31:06 +03:00
2014-09-30 21:48:10 +04:00
2015-07-16 14:24:13 +03:00
2014-09-30 21:48:10 +04:00
2015-08-03 17:06:19 +03:00
2014-02-04 14:03:10 +04:00
2015-07-23 15:17:54 +03:00
2015-05-12 15:58:58 +03:00
2014-08-21 18:35:22 +04:00
2015-04-02 20:20:01 +03:00
2013-12-12 10:03:07 +04:00
2015-08-03 17:14:18 +03:00