On 15 May 2023, at 10:23, Roi Dayan wrote:
> From: Gavin Li
>
> Add TC offload support for vxlan encap with gbp option
>
> Signed-off-by: Gavin Li
> Reviewed-by: Gavi Teitz
> Reviewed-by: Roi Dayan
I have a couple of comments below, and some general ones.
1) Can we add some unit tests for
named
> struct and pass it entirely.
>
> Signed-off-by: Gavin Li
> Reviewed-by: Roi Dayan
> Reviewed-by: Simon Horman
This looks good to me! Thanks for cleaning this up, looks way better this way.
Acked-by: Eelco Chaudron
___
dev mai
On 26 May 2023, at 13:05, Simon Horman wrote:
> On Fri, May 26, 2023 at 12:43:52PM +0200, Eelco Chaudron wrote:
>>
>>
>> On 15 May 2023, at 10:23, Roi Dayan wrote:
>>
>>> From: Gavin Li
>>>
>>> Add TC offload support for filtering vxlan t
On 15 May 2023, at 10:23, Roi Dayan wrote:
> From: Gavin Li
>
> Add TC offload support for filtering vxlan tunnels with gbp option
>
> Signed-off-by: Gavin Li
> Reviewed-by: Gavi Teitz
> Reviewed-by: Roi Dayan
One comment below, the rest looks good to me.
//Eelco
> ---
>
ed by
> message policy. To avoid this, add NLA_F_NESTED explicitly for all
> nested netlink messages with a new function
> nl_msg_start_nested_with_flag().
>
> Signed-off-by: Gavin Li
> Reviewed-by: Roi Dayan
The changes look good
On 15 May 2023, at 10:23, Roi Dayan wrote:
> From: Gavin Li
>
> Extract vxlan gbp option encoding to odp_encode_gbp_raw to be used in
> following commits.
>
> Signed-off-by: Gavin Li
> Reviewed-by: Roi Dayan
> Reviewed-by: Simon Horman
> ---
> lib/odp-util.c | 2 +-
> lib/odp-util.h | 5
On 15 May 2023, at 10:23, Roi Dayan wrote:
> From: Gavin Li
>
> Extract vxlan gbp option decoding to odp_decode_gbp_raw to be used in
> following commits.
>
> Signed-off-by: Gavin Li
> Reviewed-by: Roi Dayan
> Reviewed-by: Simon Horman
The changes look good
support more vxlan
> options in the future, change the function arguments to pass tunnel
> entirely to it instead of keep adding new arguments.
>
> Signed-off-by: Gavin Li
> Reviewed-by: Roi Dayan
> Reviewed-by: Simon Horman
The changes look g
On 24 May 2023, at 21:05, Ilya Maximets wrote:
> On 5/23/23 15:11, Balazs Nemeth wrote:
>> The only way that stats->{n_packets,n_bytes} would decrease is due to an
>> overflow, or if there are bugs in how statistics are handled. In the
>> past, there were multiple issues that caused a jump
y: Balazs Nemeth
Thanks for all the re-work, this revision looks good to me.
Acked-by: Eelco Chaudron
Cheers,
Eelco
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
On 22 May 2023, at 12:32, Frode Nordahl wrote:
> On Mon, May 22, 2023 at 11:33 AM Eelco Chaudron wrote:
>>
>>
>>
>> On 19 May 2023, at 12:31, Frode Nordahl wrote:
>>
>>> On Fri, May 19, 2023 at 11:55 AM Eelco Chaudron wrote:
>>>>
>&g
On 19 May 2023, at 12:31, Frode Nordahl wrote:
> On Fri, May 19, 2023 at 11:55 AM Eelco Chaudron wrote:
>>
>>
>>
>> On 15 May 2023, at 10:04, Frode Nordahl wrote:
>>
>>> The tc module combines the use of the `tc_transact` helper
>>&g
On 17 May 2023, at 17:05, Balazs Nemeth wrote:
> The only way that stats->{n_packets,n_bytes} would decrease is due to an
> overflow, or if there are bugs in how statistics are handled. In the
> past, there were multiple issues that caused a jump backward. A
> workaround was in place to set
On 15 May 2023, at 10:04, Frode Nordahl wrote:
> The tc module combines the use of the `tc_transact` helper
> function for communication with the in-kernel tc infrastructure
> with assertions on the reply data by `ofpbuf_at_assert` on the
> received data prior to further processing.
>
>
On 31 Mar 2023, at 15:19, Eelco Chaudron wrote:
> On 31 Mar 2023, at 15:15, Ilya Maximets wrote:
>
>> On 3/31/23 15:06, Eelco Chaudron wrote:
>>>
>>>
>>> On 31 Mar 2023, at 12:38, Simon Horman wrote:
>>>
>>>> On Fri, Mar 31, 2023 at 1
On 16 May 2023, at 21:48, Ilya Maximets wrote:
> On 5/16/23 10:20, Eelco Chaudron wrote:
>>
>>
>> On 15 May 2023, at 17:47, Ilya Maximets wrote:
>>
>>> On 5/15/23 16:24, Eelco Chaudron wrote:
>>>>
>>>>
>>>> On 4 May 2023, a
On 15 May 2023, at 17:47, Ilya Maximets wrote:
> On 5/15/23 16:24, Eelco Chaudron wrote:
>>
>>
>> On 4 May 2023, at 0:55, Ilya Maximets wrote:
>>
>>> On 3/27/23 13:25, Eelco Chaudron wrote:
>>>> Make the read of the current seq->value atomic,
On 4 May 2023, at 0:55, Ilya Maximets wrote:
> On 3/27/23 13:25, Eelco Chaudron wrote:
>> Make the read of the current seq->value atomic, i.e., not needing to
>> acquire the global mutex when reading it. On 64-bit systems, this
>> incurs no overhead, and it will avoid t
On 12 May 2023, at 3:57, Peng He wrote:
> Hi,
>
>
> Eelco Chaudron 于2023年5月11日周四 15:04写道：
>
>>
>>
>> On 4 May 2023, at 9:50, Peng He wrote:
>>
>>> Hi,
>>>
>>> sorry for the late reply.
>>>
>>> Yes, basically
On 13 May 2023, at 9:25, Christophe JAILLET wrote:
> Use struct_size() instead of hand writing it.
> This is less verbose and more informative.
>
> Signed-off-by: Christophe JAILLET
Change looks good to me.
Acked-by: Eelco Chaudron
___
On 1 May 2023, at 13:33, mit...@outlook.com wrote:
> From: Lin Huang
>
> OvS has supported packet-per-second policer which can be set at ingress
> and egress side in kernel datapath. But the userspace datapath dosen't
> support for ingress and egress packet-per-second policing now.
>
> So,
On 1 May 2023, at 13:33, mit...@outlook.com wrote:
> From: Lin Huang
>
> OvS has supported packet-per-second policer which can be set at ingress
> and egress side in kernel datapath. But the userspace datapath dosen't
> support for ingress and egress packet-per-second policing now.
>
> So,
On 10 May 2023, at 23:41, Ilya Maximets wrote:
> On 5/9/23 16:29, Eelco Chaudron wrote:
>> When doing performance testing with OVS v3.1 we ran into a deadlock
>> situation with the netdev_hmap_rwlock read/write lock. After some
>> debugging, it was discovered that the ne
On 4 May 2023, at 9:50, Peng He wrote:
> Hi,
>
> sorry for the late reply.
>
> Yes, basically this means going back to v5, but with a minor difference.
>
> In the original v5, the INCONSISTENT to EVICTING change is in the
> revalidate_sweep__ phrase.
>
> However，since you have spot that doing
ich
> would insert datapath flows.
Thanks this looks good to me. Will try to review patch 1/2 next week.
Acked-by: Eelco Chaudron
> Signed-off-by: Peng He
> ---
> lib/dpif-netdev.c | 9 -
> 1 file changed, 4 insertions(+), 5 deletions(-)
>
> diff --git a/lib/dpif-n
On 27 Apr 2023, at 3:27, Chris Mi wrote:
>>> recirc_id(0),in_port(1),eth(src=06:9c:de:63:c9:40,dst=01:00:5e:00:00:fb),eth_type(0x0800),ipv4(tos=0/0x3,frag=no),
>>> packets:13, bytes:1883, used:5.700s,
>>>
On 26 Apr 2023, at 4:47, Chris Mi wrote:
>>> +
>>> +P0_IFINDEX=$(cat /sys/class/net/ovs-p0/ifindex)
>>> +m4_define([DUMP_SFLOW], [sed -e
>>> "s/used:[[0-9]].[[0-9]]*s/used:0.001s/;s/eth(src=[[a-z0-9:]]*,dst=[[a-z0-9:]]*)/eth(macs)/;s/pid=[[0-9]]*/pid=1/;s/output=$P0_IFINDEX/output=1/"])
>>>
On 26 Apr 2023, at 4:44, Chris Mi wrote:
>>> +
>>> +static int
>>> +offload_sample_init(struct offload_sample *sample,
>>> +const struct nlattr *next_actions,
>>> +size_t next_actions_len, bool tunnel,
>>> +const struct flow_tnl
On 26 Apr 2023, at 4:38, Chris Mi wrote:
> On 4/12/2023 10:07 PM, Eelco Chaudron wrote:
>> On 29 Mar 2023, at 13:42, Chris Mi wrote:
>>
>>> Iterate each registered offload API. It's not a problem for today
>>> since we only have one implementation.
>
On 26 Apr 2023, at 4:42, Chris Mi wrote:
>>> /* DPIF_UC_ACTION only. */
>>> struct nlattr *userdata;/* Argument to OVS_ACTION_ATTR_USERSPACE.
>>> */
>>> -struct nlattr *out_tun_key;/* Output tunnel key. */
>>> -struct nlattr *actions;/* Argument to
On 26 Apr 2023, at 4:36, Chris Mi wrote:
> On 4/12/2023 10:06 PM, Eelco Chaudron wrote:
>>> +{
>>> +new->type = old->type;
>>> +new->action = xmemdup(old->action, old->action->nla_len);
>>> +new->userspace_actions = old-&g
separate read/write
locks, with an order guarantee to avoid another potential deadlock.
Reported-at: https://bugzilla.redhat.com/show_bug.cgi?id=2182541
Fixes: 9fe21a4fc12a ("netdev-offload: replace netdev_hmap_mutex to
netdev_hmap_rwlock")
Reviewed-by: Simon Horman
Signed-off-by: Eelc
On 26 Apr 2023, at 23:54, Ilya Maximets wrote:
> On 4/20/23 09:39, Eelco Chaudron wrote:
>> When doing performance testing with OVS v3.1 we ran into a deadlock
>> situation with the netdev_hmap_rwlock read/write lock. After some
>> debugging, it was discovered that the ne
On 28 Apr 2023, at 9:01, Simon Horman wrote:
> On Mon, Apr 24, 2023 at 12:37:04PM +0200, Simon Horman wrote:
>> On Thu, Apr 20, 2023 at 09:39:28AM +0200, Eelco Chaudron wrote:
>>> When doing performance testing with OVS v3.1 we ran into a deadlock
>>> situation with
Rebase on top of current main.
> Address comment from Eelco about not removing the sctp
> module if it was already loaded before run.
Thanks for changing! Two nits below, but it looks good to me.
Acked-by: Eelco Chaudron
> ---
> tests/system-common-macros.at | 13
sing my comment. It looks good to me.
Acked-by: Eelco Chaudron
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
On 18 Apr 2023, at 8:50, Ales Musil wrote:
> Fix the outdated parts of SCTP test and
> allow it to be run on CI, in order to do that
> we just need to load sctp kernel module.
Hi Ales,
Thanks for looking into this. Some comments/questions inline…
> Reported-at:
On 21 Apr 2023, at 4:51, Yunjian Wang via dev wrote:
> An unnecessarily overflow would occurs when the 'value' is longer than
> 4294967295. So it's required to check ranges to avoid uint32_t overflow.
>
> Reported-by: Nan Zhou
> Signed-off-by: Yunjian Wang
> ---
> v2: fix patch code styles
>
separate read/write
locks, with an order guarantee to avoid another potential deadlock.
Reported-at: https://bugzilla.redhat.com/show_bug.cgi?id=2182541
Fixes: 9fe21a4fc12a ("netdev-offload: replace netdev_hmap_mutex to
netdev_hmap_rwlock")
Signed-off-by: Eelco Chaudron
---
lib/netdev
nger than 16 bytes, the thread
> name will fail to be set
Thanks for fixing this! Changes look good to me.
Acked-by: Eelco Chaudron
> Signed-off-by: Songtao Zhan
> ---
> lib/util.c | 6 ++
> 1 file changed, 6 insertions(+)
>
> diff --git a/lib/util.c b/lib/util.c
> ind
On 17 Apr 2023, at 8:54, Songtao Zhan wrote:
> To: d...@openvswitch.org,
> i.maxim...@ovn.org
>
> The name of the current thread consists of a name with a maximum
> length of 16 bytes and a thread ID. The final name may be longer
> than 16 bytes. If the name is longer than 16 bytes, the
ed ok
See some comments inline. This concluded the v26 review...
//Eelco
> Signed-off-by: Chris Mi
> Reviewed-by: Roi Dayan
> Acked-by: Eelco Chaudron
> ---
> tests/system-offloads-traffic.at | 125 +++
> 1 file changed, 125 insertions(+)
>
> diff -
On 29 Mar 2023, at 13:42, Chris Mi wrote:
> Create a unique group ID to map the sFlow info when offloading sample
> action to TC. When showing the offloaded datapath flows, translate the
> group ID from TC sample action to sFlow info using the mapping.
See comments inline.
//Eelco
>
On 29 Mar 2023, at 13:42, Chris Mi wrote:
> In thread handler 0, add netdev offload recv in normal recv upcalls.
> To avoid starvation, introduce a flag to alternate the order of
> receiving normal upcalls and offload upcalls based on that flag.
One small comment inline.
//Eelco
> Add similar
On 29 Mar 2023, at 13:42, Chris Mi wrote:
> Iterate each registered offload API. It's not a problem for today
> since we only have one implementation.
See comment inline.
//Eelco
> Signed-off-by: Chris Mi
> Reviewed-by: Roi Dayan
> ---
> lib/netdev-offload.c | 35
On 29 Mar 2023, at 13:42, Chris Mi wrote:
> Initialize psample socket. Add sample recv API to receive sampled
> packets from psample socket. Add sample recv wait API to add psample
> socket fd to poll list.
Thanks for the update, see comments inline.
//Eelco
> Signed-off-by: Chris Mi
>
On 29 Mar 2023, at 13:42, Chris Mi wrote:
> When offloading sample action to TC, userspace creates a unique ID
> to map sample action and tunnel info and passes this ID to kernel
> instead of the sample info. Kernel will send this ID and sampled
> packet to userspace. Using the ID, userspace
On 29 Mar 2023, at 13:42, Chris Mi wrote:
> Update kernel UAPI to support psample and the tc sample action.
>
> Signed-off-by: Chris Mi
> Reviewed-by: Roi Dayan
> Acked-by: Eelco Chaudron
> ---
Thanks for incorporating the requested changes. Explicitly acking v26:
Acked-
eviewed-by: Roi Dayan
> Acked-by: Eelco Chaudron
> ---
No changes in v26 for this patch, explicitly acking it:
Acked-by: Eelco Chaudron
On 12 Apr 2023, at 16:04, Eelco Chaudron wrote:
> On 29 Mar 2023, at 13:42, Chris Mi wrote:
>
>> Update kernel UAPI to support psample and t
On 29 Mar 2023, at 13:42, Chris Mi wrote:
> Update kernel UAPI to support psample and the tc sample action.
>
> Signed-off-by: Chris Mi
> Reviewed-by: Roi Dayan
> Acked-by: Eelco Chaudron
> ---
Thanks for incorporating the requested changes. Explicitly acking v26:
Acked-
reads this overflow does not likely happen.
However just to clarify it’s not the thread ID that gets added to the end, but
the internal thread number. So for example, if we truncate from the end, we can
no longer identify which revalidator thread is causing a problem from the log.
As they normal
switch to quay.io if that will ever become a problem
> in the future.
>
> Signed-off-by: Ilya Maximets
These changes look good to me, did a quick test, and works in my GitHub action.
Acked-by: Eelco Chaudron
___
dev mailing list
On 31 Mar 2023, at 10:11, Songtao Zhan wrote:
> To: d...@openvswitch.org,
> i.maxim...@ovn.org
>
> The name of the current thread consists of a name with a maximum
> length of 16 bytes and a thread ID. The final name may be longer
> than 16 bytes. If the name is longer than 16 bytes, the
On 30 Mar 2023, at 17:57, Jon Kohler wrote:
>> On Mar 28, 2023, at 1:32 PM, Mike Pattrick wrote:
>>
>> On Mon, Mar 27, 2023 at 7:25 AM Eelco Chaudron wrote:
>>>
>>> Make the read of the current seq->value atomic, i.e., not needing to
>>> acq
On 28 Mar 2023, at 19:32, Mike Pattrick wrote:
> On Mon, Mar 27, 2023 at 7:25 AM Eelco Chaudron wrote:
>>
>> Make the read of the current seq->value atomic, i.e., not needing to
>> acquire the global mutex when reading it. On 64-bit systems, this
>> incurs
look good to me, so if Simon’s tests pass over the weekend:
Acked-by: Eelco Chaudron
> +])
> +NS_CHECK_EXEC([at_ns0], [ping -q -c 2 -i 0.2 10.1.1.3 | FORMAT_PING], [0],
> [dnl
> +2 packets transmitted, 2 received, 0% packet loss, time 0ms
> +])
> +
> +AT_CHECK([ovs-ap
On 31 Mar 2023, at 15:15, Ilya Maximets wrote:
> On 3/31/23 15:06, Eelco Chaudron wrote:
>>
>>
>> On 31 Mar 2023, at 12:38, Simon Horman wrote:
>>
>>> On Fri, Mar 31, 2023 at 12:05:09PM +0200, Ilya Maximets wrote:
>>>> On 3/31/23 11:07, Simon H
t;>>>> On Fri, Mar 17, 2023 at 09:47:36PM +0100, Eelco Chaudron wrote:
>>>>>>> Op 17 mrt. 2023 om 21:11 heeft Marcelo Ricardo Leitner
>>>>>>> het volgende geschreven:
>>>>>>> Thu, Mar 16, 2023 at 09:51:34AM +0100, Eelco C
On 31 Mar 2023, at 14:47, Dumitru Ceara wrote:
> On 3/31/23 14:16, Eelco Chaudron wrote:
>> Add arping package so the "virtual port with floating IP -- ovn-northd"
>> tests are run.
>>
>> Signed-off-by: Eelco Chaudron
>> ---
>
> Hi Eel
Add arping package so the "virtual port with floating IP -- ovn-northd"
tests are run.
Signed-off-by: Eelco Chaudron
---
.github/workflows/test.yml |3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index
On 30 Mar 2023, at 4:17, Songtao Zhan wrote:
> To: d...@openvswitch.org,
> i.maxim...@ovn.org
>
> The name of the current thread consists of a name with a maximum
> length of 16 bytes and a thread ID. The final name may be longer
> than 16 bytes. If the name is longer than 16 bytes, the
On 29 Mar 2023, at 13:41, Chris Mi wrote:
> On 3/29/2023 6:03 PM, Eelco Chaudron wrote:
>>
>> On 23 Mar 2023, at 13:07, Eelco Chaudron wrote:
>>
>>> On 23 Mar 2023, at 12:24, Chris Mi wrote:
>>
>>
>>>>>> I ran it 100 times. All pa
On 23 Mar 2023, at 13:07, Eelco Chaudron wrote:
> On 23 Mar 2023, at 12:24, Chris Mi wrote:
>>>> I ran it 100 times. All passed.
>>> Visually inspecting this, it looks fine, however, is this failing without
>>> passing the actions parts?
>> Yes. O
dev-offload-tc.c:1276
> #1 in netdev_flow_dump_next lib/netdev-offload.c:303
> #2 in dpif_netlink_flow_dump_next lib/dpif-netlink.c:1921
> [...]
>
> Signed-off-by: Mike Pattrick
Change looks good to me!
Acked-by: Eelco Chaudron
__
On 10 Mar 2023, at 17:20, Simon Horman wrote:
> On Fri, Mar 10, 2023 at 10:15:44AM +0100, Simon Horman wrote:
>> On Thu, Mar 09, 2023 at 05:22:43PM +0100, Eelco Chaudron wrote:
>>>
>>>
>>> On 9 Mar 2023, at 15:42, Simon Horman wrote:
>>>
>>
On 27 Mar 2023, at 22:32, Mike Pattrick wrote:
> UB Sanitizer report:
>
> lib/netdev-offload-tc.c:1276:19: runtime error: load of misaligned
> address 0x7f74e801976c for type 'union ovs_u128', which requires 8 byte
> alignment
>
> #0 in netdev_tc_flow_dump_next lib/netdev-offload-tc.c:1276
ing the mutex, so the current behavior is not changing. The
seq_read() behavior is already defined as, "Returns seq's current
sequence number (which could change immediately)". So the change
should not impact the current behavior.
Signed-off-by: Eelco Chaudron
---
lib/ovs-rcu.c |2
On 16 Mar 2023, at 17:36, James Raphael Tiovalen wrote:
> This commit addresses several high and medium-impact Coverity defects by
> fixing several possible null-pointer dereferences and potentially
> uninitialized variables.
>
> There were cases when crashes were encountered when some null
On 23 Mar 2023, at 12:24, Chris Mi wrote:
> On 3/23/2023 5:47 PM, Eelco Chaudron wrote:
>>
>> On 23 Mar 2023, at 10:28, Chris Mi wrote:
>>
>>> On 3/22/2023 6:45 PM, Eelco Chaudron wrote:
>>>> On 22 Mar 2023, at 7:15, Chris Mi wrote:
>>>
On 23 Mar 2023, at 10:28, Chris Mi wrote:
> On 3/22/2023 6:45 PM, Eelco Chaudron wrote:
>>
>> On 22 Mar 2023, at 7:15, Chris Mi wrote:
>>
>>> On 3/20/2023 6:04 PM, Eelco Chaudron wrote:
>>>> On 20 Mar 2023, at 6:44, Chris Mi wrote:
>>>
d-off-by: Mike Pattrick
Change looks good to me.
Acked-by: Eelco Chaudron
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
On 22 Mar 2023, at 11:45, Eelco Chaudron wrote:
> On 22 Mar 2023, at 7:15, Chris Mi wrote:
>
>> On 3/20/2023 6:04 PM, Eelco Chaudron wrote:
>>> On 20 Mar 2023, at 6:44, Chris Mi wrote:
>>>
>>>> On 3/16/2023 5:09 PM, Eelco Chaudron wrote:
&g
On 22 Mar 2023, at 7:15, Chris Mi wrote:
> On 3/20/2023 6:04 PM, Eelco Chaudron wrote:
>> On 20 Mar 2023, at 6:44, Chris Mi wrote:
>>
>>> On 3/16/2023 5:09 PM, Eelco Chaudron wrote:
>>>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>>>
>>>
On 22 Mar 2023, at 7:34, Chris Mi wrote:
> On 3/16/2023 7:43 PM, Eelco Chaudron wrote:
>>
>> On 16 Mar 2023, at 10:24, Eelco Chaudron wrote:
>>
>>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>>
>>>> Add two sFlow offload test caes:
>>&g
On 22 Mar 2023, at 7:31, Chris Mi wrote:
> On 3/16/2023 5:23 PM, Eelco Chaudron wrote:
>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>
>>> Create a unique group ID to map the sFlow info when offloading sample
>>> action to TC. When showing the offloaded datapath
On 22 Mar 2023, at 7:21, Chris Mi wrote:
> On 3/16/2023 5:13 PM, Eelco Chaudron wrote:
>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>
>>> Initialize psample socket. Add sFlow recv API to receive sampled
>>> packets from psample socket. Add sFow recv wait API to
parse_tc_flower_to_actions() was not reporting errors, which would
cause parse_tc_flower_to_match() to ignore them.
Fixes: dd03672f7bbb ("netdev-offload-tc: Move flower_to_match action handling
to isolated function.")
Signed-off-by: Eelco Chaudron
---
lib/netdev-offload-t
200, Roi Dayan wrote:
>>>>>
>>>>>
>>>>> On 13/03/2023 14:16, Simon Horman wrote:
>>>>>> On Mon, Mar 13, 2023 at 12:31:49PM +0200, Roi Dayan wrote:
>>>>>>>
>>>>>>>
>>>>>&g
On 20 Mar 2023, at 6:44, Chris Mi wrote:
> On 3/16/2023 5:09 PM, Eelco Chaudron wrote:
>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>
>>> When offloading sample action to TC, userspace creates a unique ID
>>> to map sFlow action and tunnel info and pas
Send from my phone
> Op 17 mrt. 2023 om 21:11 heeft Marcelo Ricardo Leitner
> het volgende geschreven:
>
> On Thu, Mar 16, 2023 at 09:51:34AM +0100, Eelco Chaudron wrote:
>>
>>
>>> On 22 Dec 2022, at 13:32, Eelco Chaudron wrote:
>>>
>>
On 16 Mar 2023, at 13:02, Ilya Maximets wrote:
> On 3/16/23 12:49, Eelco Chaudron wrote:
>>
>>
>> On 16 Mar 2023, at 12:00, Ilya Maximets wrote:
>>
>>> On 3/16/23 10:16, Eelco Chaudron wrote:
>>>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>
On 16 Mar 2023, at 12:00, Ilya Maximets wrote:
> On 3/16/23 10:16, Eelco Chaudron wrote:
>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>
>>> In thread handler 0, add netdev offload recv in normal recv upcalls.
>>> To avoid starvation, introduce a flag to alt
On 16 Mar 2023, at 11:48, Ilya Maximets wrote:
> On 3/16/23 10:15, Eelco Chaudron wrote:
>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>
>>> Iterate each registered offload API. It's not a problem for today
>>> since we only have one implementation.
>
On 16 Mar 2023, at 10:24, Eelco Chaudron wrote:
> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>
>> Add two sFlow offload test caes:
>>
>> 3: sflow offloads with sampling=1 - ping between two ports - offloads
>> enabled ok
>> 4: sflow offloads with
ow. This completes my review of v24 of the series.
//Eelco
> Signed-off-by: Chris Mi
> Reviewed-by: Roi Dayan
> Acked-by: Eelco Chaudron
> ---
> tests/system-offloads-traffic.at | 101 +++
> 1 file changed, 101 insertions(+)
>
> diff --git a/t
On 1 Mar 2023, at 8:22, Chris Mi wrote:
> Create a unique group ID to map the sFlow info when offloading sample
> action to TC. When showing the offloaded datapath flows, translate the
> group ID from TC sample action to sFlow info using the mapping.
See some comments inline below.
//Eelco
>
On 1 Mar 2023, at 8:22, Chris Mi wrote:
> In thread handler 0, add netdev offload recv in normal recv upcalls.
> To avoid starvation, introduce a flag to alternate the order of
> receiving normal upcalls and offload upcalls based on that flag.
>
> Add similar change for recv_wait.
See some
On 1 Mar 2023, at 8:22, Chris Mi wrote:
> Iterate each registered offload API. It's not a problem for today
> since we only have one implementation.
See some comments inline below.
//Eelco
> Signed-off-by: Chris Mi
> Reviewed-by: Roi Dayan
> ---
> lib/netdev-offload.c | 35
On 1 Mar 2023, at 8:22, Chris Mi wrote:
> Initialize psample socket. Add sFlow recv API to receive sampled
> packets from psample socket. Add sFow recv wait API to add psample
> socket fd to poll list.
See some comments inline below. and one question for Ilya ;)
//Eelco
> Signed-off-by: Chris
On 1 Mar 2023, at 8:22, Chris Mi wrote:
> When offloading sample action to TC, userspace creates a unique ID
> to map sFlow action and tunnel info and passes this ID to kernel
> instead of the sFlow info. Psample will send this ID and sampled
> packet to userspace. Using the ID, userspace can
On 22 Dec 2022, at 13:32, Eelco Chaudron wrote:
> On 22 Dec 2022, at 10:26, Balazs Nemeth wrote:
>
>> The only way that stats->{n_packets,n_bytes} would decrease is due to an
>> overflow, or if there are bugs in how statistics are handled. In the
>> past, there wer
On 16 Mar 2023, at 7:51, Chris Mi wrote:
> On 3/16/2023 11:37 AM, Chris Mi via dev wrote:
>> On 3/16/2023 12:40 AM, Eelco Chaudron wrote:
>>>
>>> On 15 Mar 2023, at 11:07, Chris Mi wrote:
>>>
>>>> On 3/15/2023 5:28 PM, Eelco Chaudron wrot
On 15 Mar 2023, at 11:07, Chris Mi wrote:
> On 3/15/2023 5:28 PM, Eelco Chaudron wrote:
>>
>> On 15 Mar 2023, at 4:40, Chris Mi wrote:
>>
>>> On 3/10/2023 10:02 PM, Eelco Chaudron wrote:
>>>> On 10 Mar 2023, at 13:11, Eelco Chaudron wrote:
>>
On 15 Mar 2023, at 4:40, Chris Mi wrote:
> On 3/10/2023 10:02 PM, Eelco Chaudron wrote:
>>
>> On 10 Mar 2023, at 13:11, Eelco Chaudron wrote:
>>
>>> On 1 Mar 2023, at 8:22, Chris Mi wrote:
>>>
>>>> This patch set adds offload support
On 1 Mar 2023, at 8:22, Chris Mi wrote:
> Load kernel module psample to receive sampled packets from TC.
> Before removing kernel module psample, remove act_sample first.
>
> Signed-off-by: Chris Mi
> Reviewed-by: Roi Dayan
> Acked-by: Eelco Chaudron
> ---
Changes
On 1 Mar 2023, at 8:22, Chris Mi wrote:
> Update kernel UAPI to support psample and the tc sample action.
>
> Signed-off-by: Chris Mi
> Reviewed-by: Roi Dayan
> Acked-by: Eelco Chaudron
> ---
> include/linux/automake.mk| 4 ++-
> include/linux
this is hard to troubleshoot, but I guess this is happening due to flow
deletion right in the middle of a revalidator run. It sounds odd that a short
delay solves it, but if it is we might leave it in for now. Any other idea on
this Ilya/Simon?
//Eelco
> From: Eelco Chaudron
> Date: 2023
"conntrack: Properly unNAT inner header of related
traffic.")
Signed-off-by: Eelco Chaudron
---
tests/system-traffic.at |8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/tests/system-traffic.at b/tests/system-traffic.at
index 380372430..2558f3b24 100644
--- a/tes
On 13 Mar 2023, at 11:27, Roi Dayan wrote:
> From: Oz Shlomo
>
> Currently jumping over a output-to-port action is translated to tc
> mirror action and stolen control action.
> However, the tc control action is not propagated to the hw offload action,
> thus the hardware action will mirror
I do not see it.
//Eelco
> From: Eelco Chaudron
> Date: 2023-03-08 15:28:05
> To: Faicker Mo
> Cc: d...@openvswitch.org,i.maxim...@ovn.org,simon.hor...@corigine.com
> Subject: Re: [PATCH v8] netdev-offload-tc: del ufid mapping if device not
> exist>
>>
>
701 - 800 of 2699 matches
Mail list logo
