On Thu, Jul 15, 2021 at 4:57 PM Ben Pfaff wrote:
> On Thu, Jul 15, 2021 at 04:34:51PM -0700, Han Zhou wrote:
> > Fixes: 895e02ec0be6("ovn-sbctl.c Add logical flows count numbers")
> > Signed-off-by: Han Zhou
> > ---
> > tests/ovn-sbctl.at | 4 ++--
> > 1 file changed, 2 insertions(+), 2 deletio
On Thu, Jul 15, 2021 at 5:03 PM Ben Pfaff wrote:
> On Mon, Jul 12, 2021 at 10:08:10AM +0200, Dumitru Ceara wrote:
> > Whenever a Load_Balancer is updated, e.g., a VIP is added, the following
> > sequence of events happens:
> >
> > 1. The Southbound Load_Balancer record is updated.
> > 2. The Sout
Populate the in_out_port tag for logical switch pipeline flows wherever
possible.
Signed-off-by: Han Zhou
---
northd/ovn-northd.c | 272 ++--
northd/ovn_northd.dl | 495 +--
tests/ovn-northd.at | 21 ++
3 files changed, 470 insertion
With the help of logical_flow's in_out_port tag, we can skip parsing a
big portion of the logical flows in SB DB, which can largely improve
ovn-controller's performance whenever a full recompute is required.
With a scale test topology of 1000 chassises, 20 LSPs per chassis, 20k
lports in total spr
The column will provide information to help improve efficiency of
ovn-controller lflow parsing.
Signed-off-by: Han Zhou
---
ovn-sb.ovsschema | 7 +--
ovn-sb.xml | 23 +++
2 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/ovn-sb.ovsschema b/ovn-sb.ovss
When counting lsp specific flows, using format "table" for ovn-sbctl
output to make sure each record is counted at most once.
Signed-off-by: Han Zhou
---
tests/ovn-northd.at | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tests/ovn-northd.at b/tests/ovn-northd.at
index 11461d
With the help of logical_flow's in_out_port tag, we can skip parsing a
big portion of the logical flows in SB DB, which can largely improve
ovn-controller's performance whenever a full recompute is required.
With a scale test topology of 1000 chassises, 20 LSPs per chassis, 20k
lports in total spr
On Mon, Jul 12, 2021 at 10:08:10AM +0200, Dumitru Ceara wrote:
> Whenever a Load_Balancer is updated, e.g., a VIP is added, the following
> sequence of events happens:
>
> 1. The Southbound Load_Balancer record is updated.
> 2. The Southbound Datapath_Binding records on which the Load_Balancer is
I'm impressed by the improvement. I didn't really expect any.
On Tue, Jul 13, 2021 at 09:19:34AM +0100, Anton Ivanov wrote:
> I ran the revised patch series (v2) which addresses your comments on the
> ovn-heater benchmark.
>
> With 9 fake nodes, 50 fake pods per node I get ~ 2% reproducible imp
On Thu, Jul 15, 2021 at 04:34:51PM -0700, Han Zhou wrote:
> Fixes: 895e02ec0be6("ovn-sbctl.c Add logical flows count numbers")
> Signed-off-by: Han Zhou
> ---
> tests/ovn-sbctl.at | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tests/ovn-sbctl.at b/tests/ovn-sbctl.at
On Mon, Jul 12, 2021 at 04:42:27PM -0700, Ben Pfaff wrote:
> On Thu, Jul 08, 2021 at 08:59:24PM +0200, Dumitru Ceara wrote:
> > Hi Ben,
> >
> > As discussed earlier, during the OVN meeting, I've noticed a new
> > performance issue with ovn-northd-ddlog when running it against a
> > database from o
On Thu, Jul 15, 2021 at 4:34 PM Ihar Hrachyshka wrote:
>
> Recently, we stopped leaking localport traffic through localnet ports
> into fabric to avoid unnecessary flipping between chassis hosting the
> same localport.
>
> Despite the type name, in some scenarios localports are supposed to
> talk
On Tue, Jul 13, 2021 at 05:32:06PM +0200, Ilya Maximets wrote:
> There are 3 constraints for moving hashes from one member to another:
>
> 1. The load difference exceeds ~ 3% of the load of one member.
> 2. The difference in load between members exceeds 100,000 bytes.
> 3. Moving the hash re
Fixes: 895e02ec0be6("ovn-sbctl.c Add logical flows count numbers")
Signed-off-by: Han Zhou
---
tests/ovn-sbctl.at | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tests/ovn-sbctl.at b/tests/ovn-sbctl.at
index 16f5dabcc..dabf62d2b 100644
--- a/tests/ovn-sbctl.at
+++ b/tests/
On Tue, Jul 13, 2021 at 12:17:48PM -0400, Numan Siddique wrote:
> On Fri, Jul 2, 2021 at 5:36 PM Ben Pfaff wrote:
> >
> > These were part of the OVS tutorial, which isn't relevant for OVN.
> >
> > Signed-off-by: Ben Pfaff
>
> Acked-by: Numan Siddique
Thanks for the reviews. I pushed these com
On Thu, Jul 15, 2021 at 5:28 AM Mark Gray wrote:
>
> The Open vSwitch kernel module uses the upcall mechanism to send
> packets from kernel space to user space when it misses in the kernel
> space flow table. The upcall sends packets via a Netlink socket.
> Currently, a Netlink socket is created f
On 7/15/21 3:32 PM, Dumitru Ceara wrote:
> Hi Ilya,
>
> On 7/14/21 6:52 PM, Ilya Maximets wrote:
>> On 7/14/21 3:50 PM, Ilya Maximets wrote:
>>> Replication can be used to scale out read-only access to the database.
>>> But there are clients that are not read-only, but read-mostly.
>>> One of the
Bleep bloop. Greetings Rosemarie O'Riorden, I am a robot and I have tried out
your patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Line has trailing whitespace
#201 FILE: vswitchd/vswitch.xml:367:
DPD
Bleep bloop. Greetings Rosemarie O'Riorden, I am a robot and I have tried out
your patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Line is 80 characters long (recommended limit is 79)
#85 FILE: lib/dpdk.c:495:
This change removes the default values for EAL args socket-mem and
socket-limit. As DPDK supports dynamic memory allocation, there is no
need to allocate a certain amount of memory on start-up, nor limit the
amount of memory available, if not requested.
Currently, socket-mem has a default value of
This change removes the automatic memory limit on start-up of OVS with
DPDK. As DPDK supports dynamic memory allocation, there is no
need to limit the amount of memory available, if not requested.
Currently, if socket-limit is not configured, it is set to the value of
socket-mem. With this change,
Deprecate current OVS provided defaults for DPDK socket-mem and
socket-limit that are planned to be removed in OVS 2.17. At that point
DPDK defaults will be used instead. Warnings have been added to alert
users in advance.
Signed-off-by: Rosemarie O'Riorden
---
Version 3:
- Fixed typo and edited
Currently, there is a default value of 1024 for socket-mem if not
configured. socket-limit automatically takes on the value of socket-mem
unless otherwise specified. With these changes, memory allocation will
be dynamically managed by DPDK, meaning that by default, no memory will
be pre-allocated
On 15/07/2021 22:17, Ben Pfaff wrote:
On Mon, Jul 12, 2021 at 06:15:28PM +0100, anton.iva...@cambridgegreys.com wrote:
From: Anton Ivanov
If we are not obtaining any useful information out of the poll(),
such as is a fd busy or not, we do not need to do a poll() if
an immediate_wake() has been
On Mon, Jul 12, 2021 at 06:15:29PM +0100, anton.iva...@cambridgegreys.com wrote:
> From: Anton Ivanov
>
> time_poll() makes an excessive number of time_msec() calls
> which incur a performance penalty.
>
> 1. Avoid time_msec() call for timeout calculation when time_poll()
> is asked to skip poll
On Mon, Jul 12, 2021 at 06:15:28PM +0100, anton.iva...@cambridgegreys.com wrote:
> From: Anton Ivanov
>
> If we are not obtaining any useful information out of the poll(),
> such as is a fd busy or not, we do not need to do a poll() if
> an immediate_wake() has been requested.
>
> This cuts out
In addition to external port deleted scenario already covered in the
test scenario, also validate that HA group change or unset also
behaves properly (rules allowing external port traffic to leak into
localnet gone).
Related: 1148580290d0a ("Don't suppress localport traffic directed to
external po
Bleep bloop. Greetings Ihar Hrachyshka, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Unexpected sign-offs from developers who are not authors or co-authors
or committe
Bleep bloop. Greetings Ihar Hrachyshka, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
git-am:
error: Failed to merge in the changes.
hint: Use 'git am --show-current-patch' to see the failed
Mark Gray writes:
> The Open vSwitch kernel module uses the upcall mechanism to send
> packets from kernel space to user space when it misses in the kernel
> space flow table. The upcall sends packets via a Netlink socket.
> Currently, a Netlink socket is created for every vport. In this way,
> t
> On Thu, Jul 15, 2021 at 08:45:00PM +0200, Lorenzo Bianconi wrote:
> > > On Thu, Jul 15, 2021 at 11:18:12AM -0700, Han Zhou wrote:
> > > > On Wed, Jul 14, 2021 at 1:34 AM Lorenzo Bianconi <
> > > > lorenzo.bianc...@redhat.com> wrote:
> > > > > This should avoid some work by doing the cheapest chec
On 15/07/2021 20:49, Mark Michelson wrote:
Hi Anton,
Out of curiosity, has this change made a noticeable impact on
performance?
I can't pick it up on OVN heater.
That is not unexpected. It is "noise" compared to the compute time and
the number of syscalls used in one iteration in northd or
In addition to external port deleted scenario already covered in the
test scenario, also validate that HA group change or unset also
behaves properly (rules allowing external port traffic to leak into
localnet gone).
Related: 1148580290d0a ("Don't suppress localport traffic directed to
external po
Hi Han,
I finally got around to having a look at this, and honestly I'm really
happy at how simple the series is. For now, I'm not giving individual
notes on patches, but I'll comment on the series as a whole.
It seems that this is targeted at deployments where logical switches
have their po
Recently, we stopped leaking localport traffic through localnet ports
into fabric to avoid unnecessary flipping between chassis hosting the
same localport.
Despite the type name, in some scenarios localports are supposed to
talk outside the hosting chassis. Specifically, in OpenStack [1]
metadata
Recently, we stopped leaking localport traffic through localnet ports
into fabric to avoid unnecessary flipping between chassis hosting the
same localport.
Despite the type name, in some scenarios localports are supposed to
talk outside the hosting chassis. Specifically, in OpenStack [1]
metadata
On 7/15/21 8:31 PM, Dumitru Ceara wrote:
> On 7/15/21 7:37 PM, Han Zhou wrote:
>> On Thu, Jul 15, 2021 at 9:17 AM Ilya Maximets wrote:
>>>
>>> On 6/29/21 9:57 PM, Ilya Maximets wrote:
>> Regarding the current patch, I think it's better to add a test case to
>> cover the scenario and confir
> On 7/15/21 7:43 PM, Stokes, Ian wrote:
> >> Hi. As described in Documentation/internals/release-process.rst, we are
> >> in a "soft freeze" state:
> >>
> >>During the freeze, we ask committers to refrain from applying patches
> >> that
> >>add new features unless those patches were alre
On 7/15/21 7:43 PM, Stokes, Ian wrote:
>> Hi. As described in Documentation/internals/release-process.rst, we are
>> in a "soft freeze" state:
>>
>>During the freeze, we ask committers to refrain from applying patches that
>>add new features unless those patches were already being publicly
Hi Anton,
Out of curiosity, has this change made a noticeable impact on performance?
On 7/12/21 1:15 PM, anton.iva...@cambridgegreys.com wrote:
From: Anton Ivanov
time_poll() makes an excessive number of time_msec() calls
which incur a performance penalty.
1. Avoid time_msec() call for timeo
On Thu, Jul 15, 2021 at 11:29 AM Ben Pfaff wrote:
>
> On Thu, Jul 15, 2021 at 11:18:12AM -0700, Han Zhou wrote:
> > On Wed, Jul 14, 2021 at 1:34 AM Lorenzo Bianconi <
> > lorenzo.bianc...@redhat.com> wrote:
> > > This should avoid some work by doing the cheapest check (the one on
> > > UseLogicalD
On Thu, Jul 15, 2021 at 01:39:04PM +, Ferriter, Cian wrote:
>
>
> > -Original Message-
> > From: Flavio Leitner
> > Sent: Friday 9 July 2021 18:54
> > To: Ferriter, Cian
> > Cc: ovs-dev@openvswitch.org; i.maxim...@ovn.org
> > Subject: Re: [ovs-dev] [v15 06/10] dpif-netdev: Add a par
On Thu, Jul 15, 2021 at 08:45:00PM +0200, Lorenzo Bianconi wrote:
> > On Thu, Jul 15, 2021 at 11:18:12AM -0700, Han Zhou wrote:
> > > On Wed, Jul 14, 2021 at 1:34 AM Lorenzo Bianconi <
> > > lorenzo.bianc...@redhat.com> wrote:
> > > > This should avoid some work by doing the cheapest check (the one
On Wed, Jul 14, 2021 at 09:21:19AM +0200, Dumitru Ceara wrote:
> Fixes: 1b1d2e6daa56 ("ovsdb: Introduce experimental support for clustered
> databases.")
> Signed-off-by: Dumitru Ceara
Thanks! I pushed this. I noticed that the declaration could be moved
down to the first assignment, so I actua
On Thu, Jul 15, 2021 at 09:36:13PM +0530, kumar Amber wrote:
> From: Kumar Amber
>
> Tests:
> 6: OVS-DPDK - MFEX Autovalidator
> 7: OVS-DPDK - MFEX Autovalidator Fuzzy
> 8: OVS-DPDK - MFEX Configuration
>
> Added a new directory to store the PCAP file used
> in the tests and a script to ge
On Thu, Jul 15, 2021 at 09:36:16PM +0530, kumar Amber wrote:
> From: Harry van Haaren
>
> This commit adds AVX512 implementations of miniflow extract.
> By using the 64 bytes available in an AVX512 register, it is
> possible to convert a packet to a miniflow data-structure in
> a small quantity i
> On Thu, Jul 15, 2021 at 11:18:12AM -0700, Han Zhou wrote:
> > On Wed, Jul 14, 2021 at 1:34 AM Lorenzo Bianconi <
> > lorenzo.bianc...@redhat.com> wrote:
> > > This should avoid some work by doing the cheapest check (the one on
> > > UseLogicalDatapathGroups) before any joins. DDlog is probably
>
On Thu, Jul 15, 2021 at 04:28:12PM +0100, anton.iva...@cambridgegreys.com wrote:
> From: Anton Ivanov
>
> 1. Make latch behave as described and documented - clear all
> outstanding latch writes when invoking latch_poll().
> 2. Decrease the size of the latch buffer. Less stack usage,
> less cache
When adding two SB flows with the same vip but different protocols, only
the most recent flow will be added due to the `if` statement:
if (!sset_contains(&all_ips, lb_vip->vip_str)) {
sset_add(&all_ips, lb_vip->vip_str);
This can cause unexpected behaviour when two loa
Hi Anton,
From my perspective (i.e. a user of poll_immediate_wake()), this looks
fine by me. It results in the same return values and logging, and it
removes unnecessary overhead. It's probably best for someone on the OVS
team to give the final approval, but for me,
Acked-by: Mark Michelson
On 7/15/21 7:37 PM, Han Zhou wrote:
> On Thu, Jul 15, 2021 at 9:17 AM Ilya Maximets wrote:
>>
>> On 6/29/21 9:57 PM, Ilya Maximets wrote:
> Regarding the current patch, I think it's better to add a test case to
> cover the scenario and confirm that existing connections didn't
> reset. With
On Thu, Jul 15, 2021 at 11:18:12AM -0700, Han Zhou wrote:
> On Wed, Jul 14, 2021 at 1:34 AM Lorenzo Bianconi <
> lorenzo.bianc...@redhat.com> wrote:
> > This should avoid some work by doing the cheapest check (the one on
> > UseLogicalDatapathGroups) before any joins. DDlog is probably
> > factori
On Thu, Jul 15, 2021 at 09:36:12PM +0530, kumar Amber wrote:
> From: Kumar Amber
>
> This commit introduces additional command line paramter
> for mfex study function. If user provides additional packet out
> it is used in study to compare minimum packets which must be processed
> else a default
On Wed, Jul 14, 2021 at 1:34 AM Lorenzo Bianconi <
lorenzo.bianc...@redhat.com> wrote:
>
> From: Ben Pfaff
>
> This should avoid some work by doing the cheapest check (the one on
> UseLogicalDatapathGroups) before any joins. DDlog is probably
> factoring out the reference to the Flow relation, wh
On 7/15/21 7:04 PM, Mark Gray wrote:
> On 15/07/2021 15:29, Dumitru Ceara wrote:
>> On 7/15/21 3:54 PM, Mark Gray wrote:
>>> On 15/07/2021 14:16, Mark Michelson wrote:
Hi Mark,
>>
>> Hi Mark, Mark,
>>
I'm a bit curious about this change. Does the removal of the protocol
from th
> Hi. As described in Documentation/internals/release-process.rst, we are
> in a "soft freeze" state:
>
>During the freeze, we ask committers to refrain from applying patches that
>add new features unless those patches were already being publicly discussed
>and reviewed before the fre
On Thu, Jul 15, 2021 at 9:17 AM Ilya Maximets wrote:
>
> On 6/29/21 9:57 PM, Ilya Maximets wrote:
> >>> Regarding the current patch, I think it's better to add a test case to
> >>> cover the scenario and confirm that existing connections didn't
reset. With
> >>> that:
> >>> Acked-by: Han Zhou
> >
Mark Gray writes:
> Fixes: 1579cf677fcb ("dpif-linux: Implement the API functions to allow
> multiple handler threads read upcall.")
> Signed-off-by: Mark Gray
> Acked-by: Flavio Leitner
> ---
>
> Notes:
> v1 - Reworked based on Flavio's comments:
> * Added "Fixes" tag
>
> lib/dp
Mark Gray writes:
> 'n_handlers' and 'n_revalidators' are declared as type 'size_t'.
> However, dpif_handlers_set() requires parameter 'n_handlers' as
> type 'uint32_t'. This patch fixes this type mismatch.
>
> Signed-off-by: Mark Gray
> Acked-by: Flavio Leitner
> ---
>
> Notes:
> v1 - Rewo
On 15/07/2021 15:29, Dumitru Ceara wrote:
> On 7/15/21 3:54 PM, Mark Gray wrote:
>> On 15/07/2021 14:16, Mark Michelson wrote:
>>> Hi Mark,
>
> Hi Mark, Mark,
>
>>>
>>> I'm a bit curious about this change. Does the removal of the protocol
>>> from the match mean that traffic that is not of the p
On 14/07/2021 14:50, Ilya Maximets wrote:
> This will be used to apply update3 type updates to ovsdb tables
> while processing updates for future ovsdb 'relay' service model.
>
> 'ovsdb_datum_apply_diff' is allowed to fail, so adding support
> to return this error.
>
> Acked-by: Dumitru Ceara
>
On 14/07/2021 14:50, Ilya Maximets wrote:
> Main documentation for the service model and tutorial with the use case
> and configuration examples.
>
> Acked-by: Dumitru Ceara
> Signed-off-by: Ilya Maximets
> ---
> Documentation/automake.mk| 1 +
> Documentation/ref/ovsdb.7.rst
On 14/07/2021 14:50, Ilya Maximets wrote:
> It might be important for clients to know that relay lost connection
> with the relay remote, so they could re-connect to other relay.
>
> Signed-off-by: Ilya Maximets
> ---
> ovsdb/_server.xml| 17 +
> ovsdb/ovsdb-server.c | 3 ++-
On 14/07/2021 14:50, Ilya Maximets wrote:
> Current version of ovsdb relay allows to scale out read-only
> access to the primary database. However, many clients are not
> read-only but read-mostly. For example, ovn-controller.
>
> In order to scale out database access for this case ovsdb-server
On 14/07/2021 14:50, Ilya Maximets wrote:
> New database service model 'relay' that is needed to scale out
> read-mostly database access, e.g. ovn-controller connections to
> OVN_Southbound.
>
> In this service model ovsdb-server connects to existing OVSDB
> server and maintains in-memory copy of
On 14/07/2021 14:50, Ilya Maximets wrote:
> Replication can be used to scale out read-only access to the database.
> But there are clients that are not read-only, but read-mostly.
> One of the main examples is ovn-controller that mostly monitors
> updates from the Southbound DB, but needs to claim
> From: Kumar Amber
>
> Tests:
> 6: OVS-DPDK - MFEX Autovalidator
> 7: OVS-DPDK - MFEX Autovalidator Fuzzy
> 8: OVS-DPDK - MFEX Configuration
>
> Added a new directory to store the PCAP file used
> in the tests and a script to generate the fuzzy traffic
> type pcap to be used in fuzzy unit
> From: Kumar Amber
>
> This commit introduces additional command line paramter
> for mfex study function. If user provides additional packet out
> it is used in study to compare minimum packets which must be processed
> else a default value is choosen.
> Also introduces a third paramter for choo
From: Harry van Haaren
This commit adds 3 new traffic profile implementations to the
existing avx512 miniflow extract infrastructure. The profiles added are:
- Ether()/IP()/TCP()
- Ether()/Dot1Q()/IP()/UDP()
- Ether()/Dot1Q()/IP()/TCP()
The design of the avx512 code here is for scalability to ad
From: Harry van Haaren
This commit adds AVX512 implementations of miniflow extract.
By using the 64 bytes available in an AVX512 register, it is
possible to convert a packet to a miniflow data-structure in
a small quantity instructions.
The implementation here probes for Ether()/IP()/UDP() traff
From: Harry van Haaren
This commit adds a new counter to be displayed to the user when
requesting datapath packet statistics. It counts the number of
packets that are parsed and a miniflow built up from it by the
optimized miniflow extract parsers.
The ovs-appctl command "dpif-netdev/pmd-perf-sh
From: Harry van Haaren
This commit enables OVS to at runtime check for more detailed
AVX512 capabilities, specifically Byte and Word (BW) extensions,
and Vector Bit Manipulation Instructions (VBMI).
These instructions will be used in the CPU ISA optimized
implementations of traffic profile aware
From: Kumar Amber
Tests:
6: OVS-DPDK - MFEX Autovalidator
7: OVS-DPDK - MFEX Autovalidator Fuzzy
8: OVS-DPDK - MFEX Configuration
Added a new directory to store the PCAP file used
in the tests and a script to generate the fuzzy traffic
type pcap to be used in fuzzy unit test.
Signed-off-b
From: Kumar Amber
This commit introduces additional command line paramter
for mfex study function. If user provides additional packet out
it is used in study to compare minimum packets which must be processed
else a default value is choosen.
Also introduces a third paramter for choosing a particu
From: Kumar Amber
The study function runs all the available implementations
of miniflow_extract and makes a choice whose hitmask has
maximum hits and sets the mfex to that function.
Study can be run at runtime using the following command:
$ ovs-appctl dpif-netdev/miniflow-parser-set study
Sign
v14:
- fixed format and xmas order in patch 6
- added additonal negative test-cases for mfex commands
- added core mask for configuration test case
v13:
- add Acks from Flavio
- fixed atomic set and static var in study
- shotened null check in first patch
- added improvements to set command as per
From: Kumar Amber
This patch introduced the auto-validation function which
allows users to compare the batch of packets obtained from
different miniflow implementations against the linear
miniflow extract and return a hitmask.
The autovaidator function can be triggered at runtime using the
follo
From: Kumar Amber
This commit adds a new command to allow the user to enable
autovalidatior by default at build time thus allowing for
runnig unit test by default.
$ ./configure --enable-mfex-default-autovalidator
Signed-off-by: Kumar Amber
Co-authored-by: Harry van Haaren
Signed-off-by: Har
From: Kumar Amber
This patch introduces the MFEX function pointers which allows
the user to switch between different miniflow extract implementations
which are provided by the OVS based on optimized ISA CPU.
The user can query for the available minflow extract variants available
for that CPU by
From: Kumar Amber
This commit adds a section to the dpdk/bridge.rst netdev documentation,
detailing the added miniflow functionality. The newly added commands are
documented, and sample output is provided.
The use of auto-validator and special study function is also described
in detail as well a
On 6/29/21 9:57 PM, Ilya Maximets wrote:
>>> Regarding the current patch, I think it's better to add a test case to
>>> cover the scenario and confirm that existing connections didn't reset. With
>>> that:
>>> Acked-by: Han Zhou
>
> I'll work on a unit test for this.
Hi. Here is a unit test tha
For the record, there are some integration issues with the backport
that I am working now, please don't merge this version as-is.
Thanks,
Ihar
On Wed, Jul 14, 2021 at 10:07 PM Ihar Hrachyshka wrote:
>
> Recently, we stopped leaking localport traffic through localnet ports
> into fabric to avoid
> -Original Message-
> From: Flavio Leitner
> Sent: Thursday, July 15, 2021 4:26 PM
> To: Amber, Kumar
> Cc: ovs-dev@openvswitch.org; echau...@redhat.com; i.maxim...@ovn.org; Van
> Haaren, Harry ; Ferriter, Cian
> ; Stokes, Ian
> Subject: Re: [PATCH v13 07/11] test/sytem-dpdk: Add unit t
From: Anton Ivanov
1. Make latch behave as described and documented - clear all
outstanding latch writes when invoking latch_poll().
2. Decrease the size of the latch buffer. Less stack usage,
less cache thrashing.
Signed-off-by: Anton Ivanov
---
lib/latch-unix.c | 13 +++--
1 file cha
On Thu, Jul 15, 2021 at 06:12:13PM +0530, kumar Amber wrote:
> From: Kumar Amber
>
> Tests:
> 6: OVS-DPDK - MFEX Autovalidator
> 7: OVS-DPDK - MFEX Autovalidator Fuzzy
> 8: OVS-DPDK - MFEX Configuration
>
> Added a new directory to store the PCAP file used
> in the tests and a script to ge
On 15 Jul 2021, at 17:06, Stokes, Ian wrote:
>> Added some missing negative test cases, see below.
>>
>
> Thanks for these Eelco, would you like me to add you as a co-author for this
> patch as you have code that is part of the next revison?
Whatever is easiest for you, I’m fine either way.
>
Hi Flavio,
> -Original Message-
> From: Flavio Leitner
> Sent: Thursday, July 15, 2021 8:28 PM
> To: Eelco Chaudron
> Cc: Amber, Kumar ; ovs-dev@openvswitch.org;
> i.maxim...@ovn.org; Van Haaren, Harry ;
> Ferriter, Cian ; Stokes, Ian
> Subject: Re: [PATCH v13 06/11] dpif-netdev: Add pa
On 13/07/2021 20:15, Rosemarie O'Riorden wrote:
> This change removes the automatic memory limit on start-up of OVS with
> DPDK. As DPDK supports dynamic memory allocation, there is no
> need to limit the amount of memory available, if not requested.
>
> Currently, if socket-limit is not configure
> Added some missing negative test cases, see below.
>
Thanks for these Eelco, would you like me to add you as a co-author for this
patch as you have code that is part of the next revison?
Regards
Ian
> On 15 Jul 2021, at 14:42, kumar Amber wrote:
>
> > From: Kumar Amber
> >
> > Tests:
> >
On Thu, Jul 15, 2021 at 04:15:13PM +0200, Eelco Chaudron wrote:
>
> Some minor changes in output, maybe they can be done during the commit?
>
> On 15 Jul 2021, at 14:42, kumar Amber wrote:
>
> > From: Kumar Amber
> >
> > This commit introduces additional command line paramter
> > for mfex stud
Hi Eelco,
These seem straight forward and I agree. Let us re-spin with these changes and
I think this patch will be in a good to go state once these are addressed.
Reverse Xmas tree order for variables.
Standardize log errors to ‘miniflow extract’ (note lower case m and the word
extract).
Add ‘
On 13/07/2021 20:15, Rosemarie O'Riorden wrote:
> This change removes the default values for EAL args socket-mem and
> socket-limit. As DPDK supports dynamic memory allocation, there is no
> need to allocate a certain amount of memory on start-up, nor limit the
> amount of memory available, if not
On 7/15/21 3:54 PM, Mark Gray wrote:
> On 15/07/2021 14:16, Mark Michelson wrote:
>> Hi Mark,
Hi Mark, Mark,
>>
>> I'm a bit curious about this change. Does the removal of the protocol
>> from the match mean that traffic that is not of the protocol specified
>> in the load balancer will be ct_d
Added some missing negative test cases, see below.
On 15 Jul 2021, at 14:42, kumar Amber wrote:
> From: Kumar Amber
>
> Tests:
> 6: OVS-DPDK - MFEX Autovalidator
> 7: OVS-DPDK - MFEX Autovalidator Fuzzy
> 8: OVS-DPDK - MFEX Configuration
>
> Added a new directory to store the PCAP file use
Some minor changes in output, maybe they can be done during the commit?
On 15 Jul 2021, at 14:42, kumar Amber wrote:
From: Kumar Amber
This commit introduces additional command line paramter
for mfex study function. If user provides additional packet out
it is used in study to compare minimu
On 7/15/2021 4:35 PM, Ferriter, Cian wrote:
External email: Use caution opening links or attachments
-Original Message-
From: Eli Britstein
Sent: Wednesday 14 July 2021 16:21
To: Ferriter, Cian ; Ilya Maximets
; Gaëtan Rivet
; d...@openvswitch.org; Van Haaren, Harry
Cc: Majd Dibbi
On 15/07/2021 14:16, Mark Michelson wrote:
> Hi Mark,
>
> I'm a bit curious about this change. Does the removal of the protocol
> from the match mean that traffic that is not of the protocol specified
> in the load balancer will be ct_dnat()'ed? Does that constitute
> unexpected behavior?
>
Y
> -Original Message-
> From: Flavio Leitner
> Sent: Friday 9 July 2021 18:54
> To: Ferriter, Cian
> Cc: ovs-dev@openvswitch.org; i.maxim...@ovn.org
> Subject: Re: [ovs-dev] [v15 06/10] dpif-netdev: Add a partial HWOL PMD
> statistic.
>
>
>
> Hi,
>
> After rebasing, the performance
> -Original Message-
> From: Eli Britstein
> Sent: Wednesday 14 July 2021 16:21
> To: Ferriter, Cian ; Ilya Maximets
> ; Gaëtan Rivet
> ; d...@openvswitch.org; Van Haaren, Harry
>
> Cc: Majd Dibbiny ; Stokes, Ian ;
> Flavio Leitner
>
> Subject: Re: [ovs-dev] [PATCH 2/2] dpif-netdev:
Hi Ilya,
On 7/14/21 6:52 PM, Ilya Maximets wrote:
> On 7/14/21 3:50 PM, Ilya Maximets wrote:
>> Replication can be used to scale out read-only access to the database.
>> But there are clients that are not read-only, but read-mostly.
>> One of the main examples is ovn-controller that mostly monitor
1 - 100 of 131 matches
Mail list logo
