Ian Stokes [Fri, 22 Sep 2017 08:59:33 +0000 (01:59 -0700)]
docs: Use DPDK 17.05.2 release.
Modify docs and travis linux build script to use the DPDK 17.05.2
release branch to benefit from most recent bug fixes.
There are no new features introduced in the DPDK release, only back
ported bug fixes. For completeness these bug fixes have been documented
under the 17.05.2 section in the link below.
dpif-netdev: Avoid reading RSS hash when EMC is disabled.
When EMC is disabled the reading of RSS hash is skipped.
Also, for packets that are not recirculated it retrieves
the hash value without considering the recirc id.
Signed-off-by: Antonio Fischetti <antonio.fischetti@intel.com> Acked-by: Billy O'Mahony <billy.o.mahony@intel.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
ofproto: Include patch ports in mtu overriden check
When a patch port is deleted from the bridge (with no other ports
in the bridge) and if the bridge was set to an MTU by the user earlier, the
MTU of the bridge is overriden to 1500. Please see the below link for the
steps to reproduce the issue.
This patch fixes this issue.
Reported-at: https://mail.openvswitch.org/pipermail/ovs-dev/2017-September/338665.html Signed-off-by: Numan Siddique <nusiddiq@redhat.com> Signed-off-by: Ben Pfaff <blp@ovn.org>
Greg Rose [Thu, 21 Sep 2017 15:35:29 +0000 (08:35 -0700)]
acinclude: Add missing define
The final line of a conditional search for the nf_conntrack_helper_put
function does not actually define HAVE_NF_CONNTRACK_HELPER_PUT used
in datapath/linux/compat/include/net/netfilter/nf_conntrack_helper.h.
Fixes: ac8e3c6d14d2 ("datapath: introduce nf_conntrack_helper_put function") Signed-off-by: Greg Rose <gvrose8192@gmail.com> Signed-off-by: Ben Pfaff <blp@ovn.org>
Paul Blakey [Wed, 13 Sep 2017 14:04:58 +0000 (17:04 +0300)]
netdev-tc-offloads: Fix vxlan tunnel offloading
This commit fixes offloading when tunnel id is 0 by checking
for valid tunnel dst ipv4 or ipv6, like done in the normal flow.
Also need to reset the tunnel mask outside the condition
because in the special case, when adding a port with key=flow,
the match for tunnel_set gets a tunnel key id 0 with a mask.
If we don't reset the mask we'll fail later when we check
for unknown attributes that the mask was not reset.
Fixes: 8f283af89298 ("netdev-tc-offloads: Implement netdev flow put using tc interface") Signed-off-by: Paul Blakey <paulb@mellanox.com> Reviewed-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Simon Horman <simon.horman@netronome.com>
Russell Bryant [Fri, 15 Sep 2017 03:57:00 +0000 (21:57 -0600)]
ovn: Discard flows for non-local ports.
Discard some OpenFlow flows that will never match. This includes
flows that match on a non-local inport in the ingress pipeline or a
non-local outport in the egress pipeline of a logical switch.
This is most useful for networks with a large number of ports or ACLs
that use large address sets.
Signed-off-by: Russell Bryant <russell@ovn.org> Tested-by: Miguel Angel Ajo Pelayo <majopela@redhat.com> Acked-by: Han Zhou <zhouhan@gmail.com>
Andy Zhou [Wed, 6 Sep 2017 22:08:10 +0000 (15:08 -0700)]
bridge: Fix controller status update to passive connections
The bug can cause ovs-vswitchd to crash (due to assert) when it is
set up with a passive controller connection. Since only active
connections are kept, the passive connection status update should be
ignored and not trigger asserts.
Fixes: 85c55772a453 ("bridge: Fix controller status update") Reported-by: Josh Bailey <josh@faucet.nz> Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Joe Stringer <joe@ovn.org>
Fix C++ build issue when static_assert() is not available
This patch prevents compile errors if the C++ compiler does not support
C++11 or the support is not enabled.
VMWare-BZ: #1953215 Fixes: 994bfc298502 ("Automatically verify that OVS header files work OK in C++ also.") Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com> Signed-off-by: Ben Pfaff <blp@ovn.org>
Paul Blakey [Sun, 10 Sep 2017 05:00:06 +0000 (08:00 +0300)]
lib/odp: Fix handling of set masked action in parse_odp_action
If we find that we need to change from a SET to SET_MASKED action,
then we write the mask to the actions opfbuf. But if there was netlink
pad added to the buffer when writing the key, mask won't follow the
key data as per SET_MASKED spec.
Fix that by removing the padding before writing the mask, and
readding it if needed for alignment.
Fixes: 6d670e7f0d45 ("lib/odp: Masked set action execution and printing.") Signed-off-by: Paul Blakey <paulb@mellanox.com> Reviewed-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Simon Horman <simon.horman@netronome.com>
Alin Balutoiu [Fri, 25 Aug 2017 15:02:57 +0000 (15:02 +0000)]
windows,python: remove unnecessary code
At the moment we have WSAEventSelect in each if branch.
Since the call to the function is similar, we can move
it outside the if branch and create some local variables
which will be passed to WSAEventSelect.
This patch also remove the keyword argument passed when
the event for the connection overlapped structure is created.
The argument is not needed since it does not change the value
from the default one.
Signed-off-by: Alin Balutoiu <abalutoiu@cloudbasesolutions.com> Signed-off-by: Alin Gabriel Serdean <aserdean@ovn.org> Acked-by: Alin Gabriel Serdean <aserdean@ovn.org>
Alin Balutoiu [Fri, 25 Aug 2017 15:02:48 +0000 (15:02 +0000)]
windows, python: create a different event for sockets
At the moment the sockets on Windows use the same events
that are being created for the pipes.
This is not correct because they should be different events.
This patch introduces a new event which should be used for sockets.
The new event needs to be set on automatic reset with its initial
state not signaled.
Signed-off-by: Alin Balutoiu <abalutoiu@cloudbasesolutions.com> Co-authored-by: Alin Gabriel Serdean <aserdean@ovn.org> Signed-off-by: Alin Gabriel Serdean <aserdean@ovn.org> Tested-by: Alin Gabriel Serdean <aserdean@ovn.org> Acked-by: Russell Bryant <russell@ovn.org>
Commit d5c70d4bcc344ae10a644b83f1790a0235871efc fixed the MSVC issue
however, introduced a sparse error:
"tests/test-ovn.c:205:43: warning: Using plain integer as NULL pointer"
Use 'NULL' instead of '0'.
Signed-off-by: Alin Gabriel Serdean <aserdean@ovn.org> Acked-by: Shashank Ram <rams@vmware.com>
Mark Michelson [Mon, 11 Sep 2017 20:58:12 +0000 (15:58 -0500)]
test: Avoid using 'truncate' command
The 'truncate' command is not available on all platforms. Since the
command was being used to zero out a file, there are other easy options
available. In this case, I've replaced 'truncate' with a redirection.
Reported-by: Alin Gabriel Serdean <aserdean@ovn.org> Signed-off-by: Mark Michelson <mmichels@redhat.com> Tested-by: Alin Gabriel Serdean <aserdean@ovn.org> Acked-by: Alin Gabriel Serdean <aserdean@ovn.org> Signed-off-by: Alin Gabriel Serdean <aserdean@ovn.org>
Han Zhou [Sun, 10 Sep 2017 05:58:25 +0000 (22:58 -0700)]
ovn-controller: Fix empty address set parsing problem.
When an address set is empty, current implementation will generate
an ovs flow that matches random things (and in most cases matching
everything) due to a problem in expression parser of constant set.
This patch fixes it by replacing the expression by a boolean false
when the set is empty, and adds tests cases accordingly.
Reported-by: Guru Shetty <guru@ovn.org>
Reported-at: https://mail.openvswitch.org/pipermail/ovs-dev/2017-September/338441.html Signed-off-by: Han Zhou <zhouhan@gmail.com> Co-authored-by: Ben Pfaff <blp@ovn.org> Signed-off-by: Ben Pfaff <blp@ovn.org>
Stuart Cardall [Sun, 10 Sep 2017 19:11:04 +0000 (19:11 +0000)]
add libressl compatibility
fixes undefined reference to ASN1_STRING_get0_data
Submitted-at: https://github.com/openvswitch/ovs/pull/202 Signed-off-by: Stuart Cardall <developer@it-offshore.co.uk> Signed-off-by: Russell Bryant <russell@ovn.org>
Ben Pfaff [Wed, 6 Sep 2017 15:57:33 +0000 (08:57 -0700)]
dpif-netdev: Avoid side-effect in argument of atomic_store_relaxed().
Some of the implementations of atomic_store_relaxed() evaluate their
first argument more than once, so arguments with side effects cause
strange behavior. This fixes a problem observed on 64-bit Windows.
datapath-windows: Increment ct packet counters based on ct_state.
For a given packet, packet counters in conntrack should be accounted only
once, even if the packet is processed multiple times by conntrack.
When a packet is processed by conntrack, ct_state flag is set to
OVS_CS_F_TRACKED. Use this state to identify if a packet has been
processed previously by conntrack.
Also update the ct packet counters when ct entry is created.
With this patch, the conntrack's packet counters behavior is similar
to linux
netdev-dpdk: Execute QoS Checking before copying to mbuf.
In dpdk_do_tx_copy function, all packets were copied to mbuf first,
but QoS checking may drop some of them.
Move the QoS checking in front of copying data to mbuf, it helps to
reduce useless copy.
Jakub Sitnicki [Wed, 6 Sep 2017 13:50:55 +0000 (15:50 +0200)]
doc: Fix typo in ovn-sandbox tutorial
ovn-trace example refers to a non-existent output port. Correct it.
Fixes: 46a2dc58781a ("Document OVN support in ovs-sandbox.") Signed-off-by: Jakub Sitnicki <jkbs@redhat.com> Acked-By: Mark Michelson <mmichels@redhat.com> Signed-off-by: Russell Bryant <russell@ovn.org>
Russell Bryant [Fri, 1 Sep 2017 18:24:12 +0000 (14:24 -0400)]
ovn: Support chassis hostname in requested-chassis.
Previously, OVN expected the Chassis "name" in the "requested-chassis"
option for a Logical_Switch_Port. It turns out that in the two OVN
integrations I've checked with that plan to use this option,
specifying the Chassis "hostname" is much more convenient. This patch
extends the "requested-chassis" option to support both the Chassis
name or the hostname as a value.
Signed-off-by: Russell Bryant <russell@ovn.org> Acked-by: Lance Richardson <lrichard@redhat.com>
Reuse the atomics defined for x86 and add atomics for 64 bit reads/writes.
Before this patch the cmap test gives us:
$ ./tests/ovstest.exe test-cmap benchmark 10000000 3 1
Benchmarking with n=10000000, 3 threads, 1.00% mutations, batch size 1:
cmap insert: 20100 ms
cmap iterate: 2967 ms
batch search: 10929 ms
cmap destroy: 13489 ms
cmap insert: 20079 ms
cmap iterate: 2953 ms
cmap search: 10559 ms
cmap destroy: 13486 ms
hmap insert: 2021 ms
hmap iterate: 1162 ms
hmap search: 5152 ms
hmap destroy: 1158 ms
After this change we have:
$ ./tests/ovstest.exe test-cmap benchmark 10000000 3 1
Benchmarking with n=10000000, 3 threads, 1.00% mutations, batch size 1:
cmap insert: 2953 ms
cmap iterate: 267 ms
batch search: 2193 ms
cmap destroy: 2037 ms
cmap insert: 2909 ms
cmap iterate: 267 ms
cmap search: 2167 ms
cmap destroy: 2087 ms
hmap insert: 1853 ms
hmap iterate: 1086 ms
hmap search: 4395 ms
hmap destroy: 1140 ms
We should probably revisit this file and investigate it further to see if
we can squeeze more performance.
As a side effect fix tests on x64 because usage of `ovs-atomic-pthreads.h`
is currently broken.
Signed-off-by: Alin Gabriel Serdean <aserdean@ovn.org> Suggested-by: Ben Pfaff <blp@ovn.org> Acked-by: Ben Pfaff <blp@ovn.org>
Jakub Sitnicki [Wed, 6 Sep 2017 13:50:55 +0000 (15:50 +0200)]
doc: Fix typo in ovn-sandbox tutorial
ovn-trace example refers to a non-existent output port. Correct it.
Fixes: 46a2dc58781a ("Document OVN support in ovs-sandbox.") Signed-off-by: Jakub Sitnicki <jkbs@redhat.com> Acked-By: Mark Michelson <mmichels@redhat.com> Signed-off-by: Russell Bryant <russell@ovn.org>
Russell Bryant [Fri, 1 Sep 2017 18:24:12 +0000 (14:24 -0400)]
ovn: Support chassis hostname in requested-chassis.
Previously, OVN expected the Chassis "name" in the "requested-chassis"
option for a Logical_Switch_Port. It turns out that in the two OVN
integrations I've checked with that plan to use this option,
specifying the Chassis "hostname" is much more convenient. This patch
extends the "requested-chassis" option to support both the Chassis
name or the hostname as a value.
Signed-off-by: Russell Bryant <russell@ovn.org> Acked-by: Lance Richardson <lrichard@redhat.com>
Reuse the atomics defined for x86 and add atomics for 64 bit reads/writes.
Before this patch the cmap test gives us:
$ ./tests/ovstest.exe test-cmap benchmark 10000000 3 1
Benchmarking with n=10000000, 3 threads, 1.00% mutations, batch size 1:
cmap insert: 20100 ms
cmap iterate: 2967 ms
batch search: 10929 ms
cmap destroy: 13489 ms
cmap insert: 20079 ms
cmap iterate: 2953 ms
cmap search: 10559 ms
cmap destroy: 13486 ms
hmap insert: 2021 ms
hmap iterate: 1162 ms
hmap search: 5152 ms
hmap destroy: 1158 ms
After this change we have:
$ ./tests/ovstest.exe test-cmap benchmark 10000000 3 1
Benchmarking with n=10000000, 3 threads, 1.00% mutations, batch size 1:
cmap insert: 2953 ms
cmap iterate: 267 ms
batch search: 2193 ms
cmap destroy: 2037 ms
cmap insert: 2909 ms
cmap iterate: 267 ms
cmap search: 2167 ms
cmap destroy: 2087 ms
hmap insert: 1853 ms
hmap iterate: 1086 ms
hmap search: 4395 ms
hmap destroy: 1140 ms
We should probably revisit this file and investigate it further to see if
we can squeeze more performance.
As a side effect fix tests on x64 because usage of `ovs-atomic-pthreads.h`
is currently broken.
Signed-off-by: Alin Gabriel Serdean <aserdean@ovn.org> Suggested-by: Ben Pfaff <blp@ovn.org> Acked-by: Ben Pfaff <blp@ovn.org>
This patch fixes a trivial typo in vhost-user documentation:
the path to the second socket should be /tmp/dpdkvhostclient1
and not /tmp/dpdkvhostclient0.
Commit 72c84bc (dp-packet: Enhance packet batch APIs.) changed how the amount
of packets to be processed is retrieved. In the process, the patch used "size"
as the variable holding the amount of packets rather than "cnt". Change this
back to match with the "emc_processing()" comment.
Fix that by summing only stats that reflect match/not match.
It's decided to make direct summing of required values instead of
disabling some stats in a loop to make calculations more clear and
avoid similar issues in the future.
CC: Jan Scheurich <jan.scheurich@ericsson.com> Fixes: 3453b4d62a98 ("dpif-netdev: dpcls per in_port with sorted subtables") Signed-off-by: Ilya Maximets <i.maximets@samsung.com> Acked-by: Jan Scheurich <jan.scheurich@ericsson.com> Acked-by: Cian Ferriter <cian.ferriter@intel.com> Tested-by: Cian Ferriter <cian.ferriter@intel.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
netdev-dpdk: Create separate memory pool for each port.
Since it's possible to delete memory pool in DPDK
we can try to estimate better required memory size
when port is reconfigured, e.g. with different number
of rx queues.
CC: Kevin Traynor <ktraynor@redhat.com> CC: Aaron Conole <aconole@redhat.com> Signed-off-by: Robert Wojciechowicz <robertx.wojciechowicz@intel.com> Co-authored-by: Antonio Fischetti <antonio.fischetti@intel.com> Signed-off-by: Antonio Fischetti <antonio.fischetti@intel.com> Acked-by: Ian Stokes <ian.stokes@intel.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
wangzhike [Wed, 30 Aug 2017 06:12:03 +0000 (23:12 -0700)]
netdev-dpdk: update vhost user client port status.
After ovs-vswitchd reboots, vhost user client port status is displayed as
LINK DOWN though the traffic is OK.
The problem is that the port may be udpated while the vhost_reconfigured
is false. Then the vhost_reconfigured is updated to true. As a result,
the vhost port status is kept as LINK-DOWN.
daemon-windows: Set default error mode for services
Microsoft allows default process memory dumps via WER (Windows Error
Reporting).
WER can be set to collect dumps using in general using:
https://msdn.microsoft.com/en-us/library/windows/desktop/bb787181(v=vs.85).aspx
If a normal application crashes, the user will receive a pop-up dialog,
in which he will be asked of his consent on what will be the steps
after the dump was created (debug, close or send the dump to MSFT).
We disable the dump creation via WER in:
https://github.com/openvswitch/ovs/blob/master/lib/util.c#L492
because the idea is we don't want a pop-up if a OVS process (eg. ovs-vsctl)
has crashed.
(more information on the subject:
https://blogs.msdn.microsoft.com/oldnewthing/20040727-00/?p=38323)
Until we implement our own dump collection mechanism, we can set the default
error mode for services because there are no pop-ups allowed in that case.
The commit 7bc1aae71e89 ("rhel: make the selinux policy intermediate")
broke the centos RPM builds. This commit ensures that the centos rpmbuild
will first create the openvswitch-custom.te file, and then create the
final policy files.
Fixes: 7bc1aae71e89 ("rhel: make the selinux policy intermediate") Reported-by: Ansis Atteka <aatteka@ovn.org> Signed-off-by: Aaron Conole <aconole@redhat.com> Acked-by: Ansis Atteka <aatteka@ovn.org>
The selinux documentation mentions to check the selinux/openvswitch.te file
for any permissions that might need to be added. However, the commit 7bc1aae71e89 ("rhel: make the selinux policy intermediate") moved this
file to be generated from intermediate file selinux/openvswitch.te.in
instead.
Correct the documentation, so that users won't be trying to edit a generated
file.
Also, add a gitignore for the autogenerated file.
Fixes: 7bc1aae71e89 ("rhel: make the selinux policy intermediate") Reported-by: Ansis Atteka <aatteka@ovn.org> Signed-off-by: Aaron Conole <aconole@redhat.com> Acked-by: Ansis Atteka <aatteka@ovn.org>
Aaron Conole [Thu, 31 Aug 2017 23:22:45 +0000 (19:22 -0400)]
selinux: update policy to reflect non-root and dpdk support
The selinux policy that exists in the repository did not specify access to
all of the resources needed for Open vSwitch to properly function with
an enforcing selinux policy. This update allows Open vSwitch to operate
with selinux set to Enforcing mode, even while running as a non-root user.
Aaron Conole [Thu, 31 Aug 2017 23:22:44 +0000 (19:22 -0400)]
makefile: hook up dpdkstrip preprocessor
When building the openvswitch-custom.te file, it is important to have the
ability to filter out dpdk blocks depending on whether the system has been
configured with dpdk or not. This allows using all the standard .in file
blocks, as well as the dpdkstrip blocks, when constructing the selinux
policy file.
Additionally, this means any .in files which might want to change based on
configuration to exclude blocks based on dpdk can do so.
Ben Pfaff [Wed, 30 Aug 2017 16:33:14 +0000 (09:33 -0700)]
monitor: Simplify calculation of cond->conditional.
This removes n_true_cnd from struct ovsdb_monitor_session_condition.
It was an "optimization" that is not part of any inner loop, but
make the code harder to reason about.
Signed-off-by: Ben Pfaff <blp@ovn.org> Acked-by: Andy Zhou <azhou@ovn.org> Acked-by: Liran Schour <lirans@il.ibm.com>
Ben Pfaff [Wed, 30 Aug 2017 16:33:13 +0000 (09:33 -0700)]
monitor: Fix bad caching of conditional monitor_cond requests.
The current implementation of ovsdb-server caches only non-conditional
monitors, that is, monitors for every table row, not those that monitor
only rows that match some condition. To figure out which monitors are
conditional, the code track the number of tables that have conditions that
are uniformly true (cond->n_true_cnd) and compares that against the number
of tables in the condition (shash_count(&cond->tables)). If they are the
same, then every table has (effectively) no condition, and so
cond->conditional is set to false.
However, the implementation was buggy. The function that adds a new
table condition, ovsdb_monitor_table_condition_create(), only updated
cond->conditional if the table condition being added was true. This is
wrong; only adding a non-true condition can actually change
cond->conditional. This commit fixes the problem by always recalculating
cond->conditional.
The most visible side effect of cond->conditional being true when it
should be false, as caused by this bug, was that conditional monitors were
being mixed with unconditional monitors for the purpose of caching. This
meant that, if a client requested a conditional monitor that was the
same as an unconditional one, except for the condition, then the client
would receive the cached data previously sent for the unconditional one.
This commit fixes the problem.
Signed-off-by: Ben Pfaff <blp@ovn.org> Acked-by: Andy Zhou <azhou@ovn.org> Acked-by: Liran Schour <lirans@il.ibm.com>
Aaron Conole [Mon, 14 Aug 2017 20:18:14 +0000 (16:18 -0400)]
redhat: fix upgrades where group doesn't exist
The upgrade from older Open vSwitch versions on RHEL will try, as much as
possible, to preserve the system. This means no new users or groups are
created. As an effect, it's possible for the chown to fail, because the
hugetlbfs group may not exist. While it did on my systems, it was not
there on others.
This change allows the ExecStartPre commands to fail. In the case that the
user doesn't use DPDK, it won't matter anyway.
Fixes: e3e738a3d058 ('redhat: allow dpdk to also run as non-root user') Signed-off-by: Aaron Conole <aconole@redhat.com> Reported-by: Jean-Tsung Hsiao <jhsiao@redhat.com> Tested-by: Jean-Tsung Hsiao <jhsiao@redhat.com> Acked-by: Flavio Leitner <fbl@sysclose.org> Signed-off-by: Russell Bryant <russell@ovn.org>
Lance Richardson [Fri, 25 Aug 2017 21:35:31 +0000 (14:35 -0700)]
netdev-dpdk: use 64-bit arithmetic when converting rates.
Force 64-bit arithmetic to be used when converting uint32_t rate
and burst parameters from kilobits per second to bytes per second,
avoiding incorrect behavior for rates exceeding UINT_MAX bits
per second.
Lily Huang [Fri, 25 Aug 2017 20:39:00 +0000 (13:39 -0700)]
conntrack: Fix ct-clean thread crash bug.
Conn should be removed from the connection expiry list when
the connection tracker experiences NAT resource exhaustion
and the connection needing NAT mapping cannot get it.
If this is not done, the connection tracker can crash during
cleanup of expired connections by the clean thread.
This crash will be triggered when a established flow do ct(nat)
again, like
"ip,actions=ct(table=1)
table=1,in_port=1,ip,actions=ct(commit,nat(dst=5.5.5.5)),2
table=1,in_port=2,ip,ct_state=+est,actions=1
table=1,in_port=1,ip,ct_state=+est,actions=2"
Fixes: bd5e81a0e596 ("Userspace Datapath: Add ALG infra and FTP.") Signed-off-by: Lili Huang <huanglili.huang@huawei.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
Rxqs consumed processing cycles are used to improve the balance
of how rxqs are assigned to pmds. Currently some reconfiguration
is needed to perform a reassignment.
Add an ovs-appctl command to perform a new assignment in order
to balance based on the latest rxq processing cycle information.
Note: Jan requested this for testing purposes.
Suggested-by: Jan Scheurich <jan.scheurich@ericsson.com> Signed-off-by: Kevin Traynor <ktraynor@redhat.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
Kevin Traynor [Fri, 25 Aug 2017 07:51:18 +0000 (00:51 -0700)]
dpif-netdev: Change pmd selection order.
Up to his point rxqs are sorted by processing cycles they
consumed and assigned to pmds in a round robin manner.
Ian pointed out that on wrap around the most loaded pmd will be
the next one to be assigned an additional rxq and that it would be
better to reverse the pmd order when wraparound occurs.
In other words, change from assigning by rr to assigning in a forward
and reverse cycle through pmds.
Also, now that the algorithm has finalized, document an example.
Suggested-by: Ian Stokes <ian.stokes@intel.com> Signed-off-by: Kevin Traynor <ktraynor@redhat.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
Kevin Traynor [Fri, 25 Aug 2017 07:48:01 +0000 (00:48 -0700)]
dpif-netdev: Change rxq_scheduling to use rxq processing cycles.
Previously rxqs were assigned to pmds by round robin in
port/queue order.
Now that we have the processing cycles used for existing rxqs,
use that information to try and produced a better balanced
distribution of rxqs across pmds. i.e. given multiple pmds, the
rxqs which have consumed the largest amount of processing cycles
will be placed on different pmds.
The rxqs are sorted by their processing cycles and assigned (in
sorted order) round robin across pmds.
Signed-off-by: Kevin Traynor <ktraynor@redhat.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
Kevin Traynor [Fri, 25 Aug 2017 07:44:25 +0000 (00:44 -0700)]
dpif-netdev: Count the rxq processing cycles for an rxq.
Count the cycles used for processing an rxq during the
pmd rxq interval. As this is an in flight counter and
pmds run independently, also store the total cycles used
during the last full interval.
Signed-off-by: Kevin Traynor <ktraynor@redhat.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
Kevin Traynor [Fri, 25 Aug 2017 07:42:06 +0000 (00:42 -0700)]
dpif-netdev: Add rxq processing cycle counters.
Add counters to dp_netdev_rxq which will later be used for storing the
processing cycles of an rxq. Processing cycles will be stored in reference
to a defined time interval. We will store the cycles of the current in progress
interval, a number of completed intervals and the sum of the completed
intervals.
cycles_count_intermediate was used to count cycles for a pmd. With some small
additions we can also use it to count the cycles used for processing an rxq.
Signed-off-by: Kevin Traynor <ktraynor@redhat.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
Darrell Ball [Fri, 25 Aug 2017 05:09:58 +0000 (22:09 -0700)]
dp-packet: Refactor DPDK packet initialization.
DPDK uses dp-packet pools and manages the mbuf portion of
each packet. When a pool is created, partial initialization is
also done on the OVS portion (i.e. non-mbuf). Since packet
memory is reused, this is not very useful for transient
fields and is also misleading. Furthermore, some of these
transient fields are properly initialized for DPDK packets
entering OVS anyways, which is the only reasonable way to do this.
Another field, cutlen, is initialized in this manner in the pool
and intended to be reset when cutlen is applied on sending the
packet out. However, if cutlen context is set but the packet is
not sent out for some reason, then the packet header would be
corrupted in the memory pool. It is better to just reset the
cutlen in the packets when received. I did not detect a
degradation in performance, however, I would be willing to
have some degradation, since this is a proper way to handle
this. In addition to initializing cutlen in received packets,
the other OVS transient fields are removed from the DPDK pool
initialization.
Darrell Ball [Fri, 25 Aug 2017 04:46:51 +0000 (21:46 -0700)]
docs/dpdk: Consolidate pmd-cpu-mask references.
The DPDK introductory documentation has various references to
pmd-cpu-mask, including a section devoted to it. These parts of
the documentation seemed to have been written at different times
and look like they were individually ported from other sources.
They all include an example command which gets repeated several times.
Here, we consolidate those referenes to make the documentation
easier to maintain. At the same time, create linkages to the
pmd-cpu-mask section from other sections to provide some level of
coherence.
Reviewed-by: Greg rose <gvrose8192@gmail.com> Acked-by: Kevin Traynor <ktraynor@redhat.com> Signed-off-by: Darrell Ball <dlu998@gmail.com>
Gao Zhenyu [Sun, 20 Aug 2017 14:37:31 +0000 (14:37 +0000)]
ovn: Fix BFD error config on gateway
The bfd_calculate_chassis function calculates gateway's peer datapaths
to figure out which tunnel's BFD should be enabled to from the current chassis.
Existing algorithm only calculats peer datapaths at one hop, but multiple
logical switches and E/W routers could be in the path, making several hops
which were not considered on the calculation.
It may disable BFD on some gw's tunnel ports. Then a port on a remote ovs
cannot send packet out because it believes all remote gateways are down.
This patch will go through whole graph and visit all datapath's port
which has connection with gateways.
Yi-Hung Wei [Wed, 23 Aug 2017 00:52:30 +0000 (17:52 -0700)]
atlocal: Document find_l7_lib()
When a system traffic is skipped due to 'HAVE_FTP = no' or
'HAVE_TFTP = no', it takes some effort to figure out it is due to
missing the required python library. Add some comments around the
find_l7_lib(), so that user can figure that out by
$ git grep HAVE_FTP.
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com> Signed-off-by: Joe Stringer <joe@ovn.org>
Alin Balutoiu [Tue, 22 Aug 2017 10:47:21 +0000 (10:47 +0000)]
windows, python: Fix event type returned from poller
The function poll from poller should return a list of tuples
containing the events and their types.
On Windows the event type is not returned at the moment.
Instead of returning zero all the time, we check to see
the type of event and we set it accordingly before returning
the list.
This is used only for debugging purposes inside the function
"__log_wakeup" later on.
Signed-off-by: Alin Balutoiu <abalutoiu@cloudbasesolutions.com> Acked-by: Russell Bryant <russell@ovn.org> Acked-by: Alin Gabriel Serdean <aserdean@ovn.org> Signed-off-by: Alin Gabriel Serdean <aserdean@ovn.org>
Justin Pettit [Mon, 7 Aug 2017 21:44:02 +0000 (14:44 -0700)]
ofproto-dpif: Mark packets as "untracked" after call to ct().
Packet and Connection state is only available to the processing path
that follows the "recirc_table" argument of the ct() action. The
previous behavior made these states available until the end of the
pipeline. This commit changes the behavior so that the Packet and
Connection state are cleared for the current processing path whenever
ct() is called (in addition to reaching the end of the pipeline.)
A future commit will remove the behavior that a "send to controller"
action causes all packets for that flow to be handled via the slow-path.
The current behavior of connection tracking state makes that difficult
due to datapath actions containing multiple OpenFlow rules that may
contain different connection tracking states. This change will make
that future commit possible.
Signed-off-by: Justin Pettit <jpettit@ovn.org> Acked-by: Joe Stringer <joe@ovn.org>
Joe Stringer [Thu, 17 Aug 2017 21:26:27 +0000 (14:26 -0700)]
checkpatch: Enforce bracing around conditionals.
The coding style states that BSD-style brace placement should be used,
and even single statements should be enclosed. Add checks to checkpatch
for this, particularly for 'else' statements.
Signed-off-by: Joe Stringer <joe@ovn.org> Acked-by: Aaron Conole <aconole@redhat.com>
Lance Richardson [Sat, 19 Aug 2017 20:23:34 +0000 (16:23 -0400)]
ovn: support requested-chassis option for logical switch ports
This patch adds support for a "requested-chassis" option for logical
switch ports. If set, the only chassis that will claim this port is the
chassis identfied by this option; if already bound by another chassis,
it will be released.
The primary benefit of this enhancement is allowing a CMS to prevent
"thrashing" in the southbound database during live migration by keeping
the original chassis from attempting to re-bind a port that is in the
process of migrating.
This would also allow (with some additional work) RBAC to be applied
to the Port_Binding table for additional security.
Signed-off-by: Lance Richardson <lrichard@redhat.com> Signed-off-by: Russell Bryant <russell@ovn.org>
Roi Dayan [Thu, 17 Aug 2017 05:59:10 +0000 (08:59 +0300)]
dpif: Fix cleanup of netdev_ports map
Executing dpctl commands from userspace also calls to
dpif_open()/dpif_close() but not really creating another dpif
but using a clone.
As for netdev_ports map is global we avoid adding duplicate entries
but also need to make sure we are not removing needed entries.
With this commit we make sure only the last dpif close should clean
the netdev_ports map.
Fixes: 6595cb95a4a9 ("dpif: Clean up netdev_ports map on dpif_close().") Signed-off-by: Roi Dayan <roid@mellanox.com> Reviewed-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Joe Stringer <joe@ovn.org>
Alin Balutoiu [Wed, 16 Aug 2017 15:01:39 +0000 (15:01 +0000)]
python: fix python3 encode/decode on Windows
Fix double encoding/decoding on data, caused by
'get_decoded_buffer' and 'get_encoded_buffer'.
The functions 'get_decoded_buffer' and 'get_encoded_buffer'
from winutils have been removed. They are no longer
necessary since the buffers received/returned are already
in the right form.
The necessary encoding has been moved before any sending
function (this also includes named pipes send on Windows).
Anand Kumar [Tue, 15 Aug 2017 22:29:04 +0000 (15:29 -0700)]
datapath-windows: Do not modify port field for ICMP during SNAT/DNAT
During SNAT/DNAT, we should not be updating the port field of ct_endpoint
struct, as ICMP packets do not have port information. Since port and
icmp_id are overlapped in ct_endpoint struct, icmp_id gets changed.
As a result, NAT look up fails to find a matching entry.
This patch addresses this issue by not modifying icmp_id field during
SNAT/DNAT only for ICMP traffic
The current NAT module doesn't take the ICMP type/code into account
during the lookups. Fix this to make it similar with the other conntrack
module.
Acked-by: Shashank Ram <rams@vmware.com> Acked-by: Alin Gabriel Serdean <aserdean@ovn.org> Signed-off-by: Anand Kumar <kumaranand@vmware.com> Signed-off-by: Alin Gabriel Serdean <aserdean@ovn.org>
Joe Stringer [Tue, 15 Aug 2017 23:15:54 +0000 (16:15 -0700)]
tests: Put maximum timeout on netcat calls.
This was causing test script execution to hang forever on Ubuntu Zesty.
Make sure it times out within 5 seconds, so at least it will fail out
properly.
Signed-off-by: Joe Stringer <joe@ovn.org> Acked-by: Flavio Leitner <fbl@sysclose.org>
Joe Stringer [Fri, 11 Aug 2017 18:06:46 +0000 (11:06 -0700)]
ovsdb-idl: Avoid new expression.
In C++, 'new' is a keyword. If this is used as the name for a field,
then C++ compilers can get confused about the context and fail to
compile references to such fields. Rename the field to 'new_datum' to
avoid this issue.
Signed-off-by: Joe Stringer <joe@ovn.org> Acked-by: Ben Pfaff <blp@ovn.org>
Joe Stringer [Fri, 11 Aug 2017 18:06:45 +0000 (11:06 -0700)]
ovsdb-idl: Avoid mutable type specifier.
In C++, 'mutable' is a keyword. If this is used as the name for a field,
then C++ compilers can get confused about the context and fail to
compile references to such fields. Rename the field to 'is_mutable' to
avoid this issue.
Signed-off-by: Joe Stringer <joe@ovn.org> Acked-by: Ben Pfaff <blp@ovn.org>
Joe Stringer [Fri, 11 Aug 2017 18:06:44 +0000 (11:06 -0700)]
ovsdb-idl: Avoid class declaration.
In C++, 'class' is a keyword. If this is used as the name for a field,
then C++ compilers can get confused about the context and fail to
compile references to such fields. Rename the field to 'class_' to
avoid this issue.
Signed-off-by: Joe Stringer <joe@ovn.org> Acked-by: Ben Pfaff <blp@ovn.org>