]>
git.proxmox.com Git - mirror_kronosnet.git/log
Fabio M. Di Nitto [Sat, 28 Nov 2015 13:42:16 +0000 (14:42 +0100)]
Update TODO
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 28 Nov 2015 08:13:33 +0000 (09:13 +0100)]
[PMTUd] Fix crash and calculation when using crypto
most of the problem was around incorrect typing of variables
and incorrect calculation when using signing without encryption.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Fri, 27 Nov 2015 16:38:18 +0000 (17:38 +0100)]
[libtap] automatic restore IPv6 address when recovering from MTU flapping
NOTE: if a user manually changes MTU < 1280, your IPv6 addresses
are gone for good.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Fri, 27 Nov 2015 14:33:09 +0000 (15:33 +0100)]
Update TODO list
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 26 Nov 2015 13:53:20 +0000 (14:53 +0100)]
Update TODO list
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 25 Nov 2015 19:15:22 +0000 (20:15 +0100)]
[crypto] align crypto_authenticate_and_decrypt API to crypto_encrypt_and_sign
2 issues solved by this change:
1) API were different and crypto_authenticate_and_decrypt would trash the
incoming packet, that we might want to keep for later usage
(re-switch for example)
2) By using an extre pre-allocated buffer while decrypting incoming packets
we save a whole memcpy and that reduces latency on crypto communications:
pre-patch:
[root@kronosnet-node1-br0 ~]# ping 192.168.12.2 -f -c 1000 -s 65000
PING 192.168.12.2 (192.168.12.2) 65000(65028) bytes of data.
--- 192.168.12.2 ping statistics ---
1000 packets transmitted, 1000 received, 0% packet loss, time 5302ms
rtt min/avg/max/mdev = 5.102/5.283/22.679/0.947 ms, pipe 3, ipg/ewma 5.307/5.223 ms
post-patch:
[root@kronosnet-node1-br0 ~]# ping 192.168.12.2 -f -c 1000 -s 65000
PING 192.168.12.2 (192.168.12.2) 65000(65028) bytes of data.
--- 192.168.12.2 ping statistics ---
1000 packets transmitted, 1000 received, 0% packet loss, time 5196ms
rtt min/avg/max/mdev = 4.997/5.154/6.661/0.129 ms, ipg/ewma 5.201/5.173 ms
(using aes256 and sha1)
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 22 Nov 2015 14:18:40 +0000 (15:18 +0100)]
[send/recv] init recv buffer array only once
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 22 Nov 2015 14:01:00 +0000 (15:01 +0100)]
[internal] define/use PCKT_FRAG_MAX instead of UINT8_MAX
makes the code more readable
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 22 Nov 2015 08:17:37 +0000 (09:17 +0100)]
Fix error message
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 22 Nov 2015 08:12:18 +0000 (09:12 +0100)]
[send/recv] use recvmmsg on network sockets
On my test systems this change reduces the latency of fragmented packets
from 0.27ms to 0.235ms in average. There are still some optimizations
on how buffers can be initialized that could shave some time on this code
path.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 22 Nov 2015 08:12:04 +0000 (09:12 +0100)]
Update TODO
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 18 Nov 2015 09:36:11 +0000 (10:36 +0100)]
Update copyright dates
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 18 Nov 2015 09:31:00 +0000 (10:31 +0100)]
[build] update configure.ac
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 16 Nov 2015 06:20:13 +0000 (07:20 +0100)]
[send/recv] fix data filling in the frag code
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 16 Nov 2015 06:11:34 +0000 (07:11 +0100)]
[send/recv] use sendmmsg to reduce latency
On my test systems this change reduces the latency from 0.7ms to 0.25ms
when sending 65000 bytes packet and using internal re-assembly code.
Internally use N buffers to split the incoming data and reduce by N frags
the amount of memcpy between kernel and userland.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 16 Nov 2015 04:16:25 +0000 (05:16 +0100)]
[internal] reduce memory footprint further down
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 20 Sep 2015 11:30:19 +0000 (13:30 +0200)]
[global] reduce memory footprint by a long shot
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 24 Oct 2015 05:23:31 +0000 (07:23 +0200)]
[send/recv] add simplistic packet re-assembly code
this will probably explode if you are using multiple links
in round-robin or active-active mode.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 21 Oct 2015 13:48:37 +0000 (15:48 +0200)]
Revert "[global] reduce memory footprint by a long shot"
This reverts commit
4b4290a2fafbeb4d08bf489caa35ea4c205b18b9 .
Fabio M. Di Nitto [Sun, 20 Sep 2015 11:30:19 +0000 (13:30 +0200)]
[global] reduce memory footprint by a long shot
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 20 Sep 2015 10:05:23 +0000 (12:05 +0200)]
[threads] cleanup header
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 20 Sep 2015 08:53:26 +0000 (10:53 +0200)]
[cleanup] remove unused headers around
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 20 Sep 2015 08:38:42 +0000 (10:38 +0200)]
[threads] split send recv threads in separate file
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 20 Sep 2015 08:34:10 +0000 (10:34 +0200)]
[threads] split dsthandler thread in separate file
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 20 Sep 2015 08:22:02 +0000 (10:22 +0200)]
[threads] split pmtud thread in separate file
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 20 Sep 2015 08:16:17 +0000 (10:16 +0200)]
[threads] split heartbeat thread in separate file
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 20 Sep 2015 06:36:38 +0000 (08:36 +0200)]
[threads] implement outgoing pckt fragmentation based on PMTUd
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 16 Sep 2015 05:01:20 +0000 (07:01 +0200)]
Update TODO list
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 16 Sep 2015 04:10:09 +0000 (06:10 +0200)]
[global] restrict max packet size to 65536 bytes
and apply workaround in data buf allocation while we cleanup
the whole buffer allocation handling situation
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 15 Sep 2015 18:34:33 +0000 (20:34 +0200)]
[test] disable crypto rekey test for now
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 15 Sep 2015 09:35:49 +0000 (11:35 +0200)]
[knetd] fix libqb logging filter
Thanks to Chrissie for the awesome work as usual
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 15 Sep 2015 09:11:23 +0000 (11:11 +0200)]
[test] fix ping_test data print and add some more info
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 13 Sep 2015 08:57:10 +0000 (10:57 +0200)]
[handle] add missing include
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 13 Sep 2015 08:01:58 +0000 (10:01 +0200)]
[handle] fix knet_send sock handling to use correct data flow
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 13 Sep 2015 07:56:34 +0000 (09:56 +0200)]
[handle] fix init order to have more debug in case of sockpair error
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 13 Sep 2015 07:45:50 +0000 (09:45 +0200)]
[commodity] add knet_send/knet_recv api calls
based on readv/writev man page, it is highly discouraged to mix
different kind of write/read operations on a given fd (for example
a read with a writev).
since not many finds using iovec that pleasent, those 2 functions
do wrap the more common buff/buff_len calls into iovec implementations.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 13 Sep 2015 06:26:01 +0000 (08:26 +0200)]
[handle] API change warning: add support for knet_handle_new to create proper sockpairs
this is a small facility for applications that don't want/need to create
socketpairs to read/write data to/from knet and avoids lots of duplicated
socket management on the client side.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 9 Sep 2015 04:34:11 +0000 (06:34 +0200)]
[threads] add warning on fragmented packets
also prepare ping_test for it
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 8 Sep 2015 13:52:49 +0000 (15:52 +0200)]
[ping] fix sockpair creation to deal with sequence of packets and not streaming
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 8 Sep 2015 13:34:43 +0000 (15:34 +0200)]
[threads] use iovec calls to read/write from datafd
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 8 Sep 2015 12:54:47 +0000 (14:54 +0200)]
[cosmetic] rename net_fd to datafd
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 6 Sep 2015 07:26:42 +0000 (09:26 +0200)]
[handle] add missing errno on failure
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 6 Sep 2015 05:55:57 +0000 (07:55 +0200)]
[libtap] change error check code to avoid a segfault and make it more readable
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 21 Apr 2015 08:23:38 +0000 (10:23 +0200)]
[listener] fix 2 cosmetic checks and keep around a useful debugging fn
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 21 Apr 2015 08:23:21 +0000 (10:23 +0200)]
[threads] make ping error message more verbose
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 21 Apr 2015 08:21:46 +0000 (10:21 +0200)]
Update TODO list
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Christine Caulfield [Tue, 21 Apr 2015 07:48:05 +0000 (08:48 +0100)]
libtap: don't close pipe fd twice
libtap was closing the parent's pipe() fd twice. Sometimes, between the
first and second close, that fd gets reopened by the logging thread as
PF_LOCAL, and used for logging.
Then libtap wakes up again after the fork and closes the fd thinking
it's its pipe fd. knet then opens it again as AF_INET for pinging.
libqb logging then errors on a sendto() and closes it AGAIN, and reopens
it as a PF_LOCAL logging fd. Ping then has a brain haemorrage next time
it comes round to calling sendto().
Signed-off-by: Christine Caulfield <ccaulfie@redhat.com>
Fabio M. Di Nitto [Fri, 20 Mar 2015 07:03:16 +0000 (08:03 +0100)]
Update TODO list
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 19 Mar 2015 12:29:01 +0000 (13:29 +0100)]
[host] move dst cache updates to the right logging subsystem
and return error codes
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 19 Mar 2015 05:52:02 +0000 (06:52 +0100)]
Update TODO list
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 19 Mar 2015 05:26:13 +0000 (06:26 +0100)]
[host] create dst_cache sync and async functions and fix link lookup race condition
Prior to this change, there was a potential race condition in which, when shutting
down a link, the destination cache would not be updated in time and pckts would
be lost in an invalid socket.
This change introduced a sync version of the dst cache update and protects
outgoing traffic socket lookup with a mutex.
The only downside of this change is that, in future, when we will introduce
complex switching algorithms, we might have to spend a bit more time
recalculating the network topology on link shutdown and halt traffic switching.
Pro is that we have a smaller gap in lost traffic when reconfiguring the local
node.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 18 Mar 2015 09:43:12 +0000 (10:43 +0100)]
[threads] simplify code to send data to links
in preparation to remove race condition in _dst_cache update,
simplify the access path to common code
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 18 Mar 2015 09:40:47 +0000 (10:40 +0100)]
[onwire] fix regression in macro expansions
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 12 Mar 2015 05:02:41 +0000 (06:02 +0100)]
[onwire] introduce khpi_link_status_ defines to make code simpler to parse
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 11 Mar 2015 11:19:18 +0000 (12:19 +0100)]
[onwire] add define for knet_hostinfo structures size
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 10 Mar 2015 17:13:45 +0000 (18:13 +0100)]
[onwire] rename kf_plink/kf_psize/kf_pdata to their respective more descriptive versions
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 10 Mar 2015 17:07:56 +0000 (18:07 +0100)]
[onwire] rename kf_link and kf_time to their respective more descriptive versions
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 10 Mar 2015 16:51:16 +0000 (17:51 +0100)]
[onwire] rename kf_seq_num and kf_data to their respective more descriptive versions
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 10 Mar 2015 16:47:39 +0000 (17:47 +0100)]
[onwire] add comment
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 10 Mar 2015 14:47:13 +0000 (15:47 +0100)]
[onwire] more cleanup around _SIZE define usage
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 9 Mar 2015 07:11:18 +0000 (08:11 +0100)]
[onwire] rename various KNET_FRAME_ definitions to KNET_HEADER_
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 9 Mar 2015 05:29:15 +0000 (06:29 +0100)]
[onwire] cleanup and use defines
make it easier to understand values and usage of other status info
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 9 Mar 2015 05:18:00 +0000 (06:18 +0100)]
[onwire] rename link_up_down struct to knet_hostinfo_payload_link_status
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 9 Mar 2015 05:10:09 +0000 (06:10 +0100)]
[onwire] rename knet_hinfo_data struct to knet_hostinfo
and add comments around the various fields
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 8 Mar 2015 08:50:43 +0000 (09:50 +0100)]
[onwire] add comment in ifout section
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 8 Mar 2015 06:39:49 +0000 (07:39 +0100)]
[onwire] start cleaning host_info data structures
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 8 Mar 2015 06:26:56 +0000 (07:26 +0100)]
[debug] add tool to print out network pckt header size
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 8 Mar 2015 06:05:05 +0000 (07:05 +0100)]
[onwire] clenaup knet_header_payload_data structure naming
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 8 Mar 2015 05:56:04 +0000 (06:56 +0100)]
[onwire] clenaup knet_header_payload_ping structure naming
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 21:53:03 +0000 (22:53 +0100)]
[cleanup] move some values from int to unsigned int
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 08:45:06 +0000 (09:45 +0100)]
[onwire] clenaup knet_header_payload_pmtud structure naming
and add more comments
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 08:40:46 +0000 (09:40 +0100)]
[onwire] add more comments
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 08:39:41 +0000 (09:39 +0100)]
[onwire] add extra comments
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 08:37:28 +0000 (09:37 +0100)]
[onwire] cleanup knet_header_payload union
use longer name to make it easier to identify nesting of structures
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 07:44:59 +0000 (08:44 +0100)]
[onwire] rename knet_frame_data to knet_header_payload
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 07:30:49 +0000 (08:30 +0100)]
[onwire] rename knet_frame to knet_header
also start renaming variables around to make it easier to understand
the level of nesting and add comments for each field
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 05:55:57 +0000 (06:55 +0100)]
[internal] start renaming things to make code look decent
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 7 Mar 2015 05:08:05 +0000 (06:08 +0100)]
[internals] Simplify code maintanance by shuffling around some variables
this allows creation of better #define to maintain some parts of the
code related to buffers allocations.
As a bonus, gcc does a better job at packing structs outside of a union
and we save 4 bytes onwire.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 5 Mar 2015 12:02:53 +0000 (13:02 +0100)]
[knetd] Fix internal MTU calculation to include tap ethernet frame
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 4 Mar 2015 06:56:43 +0000 (07:56 +0100)]
[PMTUd] fix mutex deadlock on socket error
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Wed, 4 Mar 2015 05:32:31 +0000 (06:32 +0100)]
[listeners] Use IP_FREEBIND options on sockets
this allows us to bind to IPs that are not yet on the system and
survive the infamous ifdown/ifup <device> test
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 3 Mar 2015 12:26:46 +0000 (13:26 +0100)]
[pingd] fix ping flood on sock errors
if we get an error on sendto, we would ping flood the link because
the ping_last timestamp was not being updated.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 3 Mar 2015 06:51:13 +0000 (07:51 +0100)]
[libknet] rename tap to send to link
plain and simple cleanup
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 2 Mar 2015 08:29:10 +0000 (09:29 +0100)]
Update TODO list
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 2 Mar 2015 08:24:13 +0000 (09:24 +0100)]
[knetd] add support for pmtud frequency
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 2 Mar 2015 08:23:30 +0000 (09:23 +0100)]
[PMUTd] add call to get pmtud interval value
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 2 Mar 2015 06:47:27 +0000 (07:47 +0100)]
[knetd] Use pmtud values to set tap device MTU
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 28 Feb 2015 07:47:45 +0000 (08:47 +0100)]
[PMTUd] fix notification callback to add private data
this is necessary to identify the callback when driving multiple
knet instances within the same daemon.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sat, 28 Feb 2015 05:25:15 +0000 (06:25 +0100)]
Update TODO list
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 1 Dec 2014 13:45:08 +0000 (14:45 +0100)]
[PMTUd] add support for pmtud_get for who doesn't want notifications
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 1 Dec 2014 05:07:28 +0000 (06:07 +0100)]
[PMTUd] add support for PMTUd changes notifications
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Sun, 30 Nov 2014 15:24:35 +0000 (16:24 +0100)]
[PMTUd] distinguish between link_mtu and data_mtu
link_mtu is the pure MTU over the link and doesn't account for knet headers.
data_mtu is what can be really transmitted onwire by the application.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 23 Oct 2014 05:26:11 +0000 (07:26 +0200)]
[PMTUd] add support for timer config and fix critical shutdown deadlock in condwait
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 23 Oct 2014 04:21:13 +0000 (06:21 +0200)]
[PMTUD] change error message
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 23 Oct 2014 04:18:23 +0000 (06:18 +0200)]
[PMTUd] fix scary message at startup
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Tue, 21 Oct 2014 10:12:30 +0000 (12:12 +0200)]
[PMTUD] fix threads to work with crypto
temporary disable re-keying test as it seems to be break PMTUd
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 20 Oct 2014 04:09:08 +0000 (06:09 +0200)]
[PMTUD] change variable names to make it easier to read
still doesn't work with crypto enable, but part of the code is getting
ready for it.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Fri, 29 Aug 2014 11:08:56 +0000 (13:08 +0200)]
[nss] fix calculation for crypto header to include SALT_SIZE
and propagate block size up in the layers to allow PMTUd thread
to round buffers and do crypted PMTUd packets.
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Thu, 28 Aug 2014 15:14:47 +0000 (17:14 +0200)]
[link] add rudimentary PMTUD support.
1) It won't work with crypto enable yet
2) values are not really used yet for anything
3) no API calls implemented yet
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
Fabio M. Di Nitto [Mon, 11 Aug 2014 17:39:56 +0000 (19:39 +0200)]
[listener] check setsockopts return codes
Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>