[Zed][Neutron][OVN] Severe VM Network Performance Degradation Compared to Host
Hi all, I'm running OpenStack Zed with OVN as the Neutron backend. I've encountered a severe VM network performance degradation issue and would appreciate any insights from the community. 馃敼 **Environment** - OpenStack version: Zed - Neutron backend: OVN - Two VMs (each 4 vCPUs, 8 GB RAM) launched on two different compute nodes - Multi-queue is enabled on the VM vNICs 馃敼 **Issue** The network performance inside the VMs is significantly worse than on the host nodes, with high packet retransmissions observed. 馃敼 **Test results** **Host-to-Host (VTEP IPs)** ``` $ iperf3 -c 192.168.152.152 Connecting to host 192.168.152.152, port 5201 [ 5] local 192.168.152.153 port 45352 connected to 192.168.152.152 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 1.38 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 1.00-2.00 sec 1.37 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 2.00-3.00 sec 1.42 GBytes 12.2 Gbits/sec 0 3.10 MBytes [ 5] 3.00-4.00 sec 1.39 GBytes 11.9 Gbits/sec 0 3.10 MBytes [ 5] 4.00-5.00 sec 1.38 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 5.00-6.00 sec 1.43 GBytes 12.3 Gbits/sec 0 3.10 MBytes [ 5] 6.00-7.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 7.00-8.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 8.00-9.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 9.00-10.00 sec 1.42 GBytes 12.2 Gbits/sec 0 3.10 MBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 14.0 GBytes 12.0 Gbits/sec 0 sender [ 5] 0.00-10.04 sec 14.0 GBytes 12.0 Gbits/sec receiver iperf Done. ``` **VM-to-VM (through overlay network)** ``` $ iperf3 -c 10.0.6.10 Connecting to host 10.0.6.10, port 5201 [ 5] local 10.0.6.37 port 56710 connected to 10.0.6.10 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 499 MBytes 4.19 Gbits/sec 263 463 KBytes [ 5] 1.00-2.00 sec 483 MBytes 4.05 Gbits/sec 467 367 KBytes [ 5] 2.00-3.00 sec 482 MBytes 4.05 Gbits/sec 491 386 KBytes [ 5] 3.00-4.00 sec 483 MBytes 4.05 Gbits/sec 661 381 KBytes [ 5] 4.00-5.00 sec 472 MBytes 3.95 Gbits/sec 430 391 KBytes [ 5] 5.00-6.00 sec 480 MBytes 4.03 Gbits/sec 474 350 KBytes [ 5] 6.00-7.00 sec 510 MBytes 4.28 Gbits/sec 567 474 KBytes [ 5] 7.00-8.00 sec 521 MBytes 4.37 Gbits/sec 565 387 KBytes [ 5] 8.00-9.00 sec 509 MBytes 4.27 Gbits/sec 632 483 KBytes [ 5] 9.00-10.00 sec 514 MBytes 4.30 Gbits/sec 555 495 KBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 4.84 GBytes 4.15 Gbits/sec 5105 sender [ 5] 0.00-10.05 sec 4.84 GBytes 4.14 Gbits/sec receiver iperf Done. ``` As you can see, there's a sharp drop in performance inside the VMs (from ~12 Gbps down to ~4 Gbps), with a lot of retransmissions in 10 seconds. Has anyone encountered a similar issue with OVN and VM networking performance? What could be the potential causes? Any suggestions or debugging tips are welcome. Thanks in advance! Best regards,
Did this work better with LXB plugin earlier? On Wed, 30 Jul 2025, 09:01 Jeff Yang, <yjf1970231893@gmail.com> wrote:
Hi all,
I'm running OpenStack Zed with OVN as the Neutron backend. I've encountered a severe VM network performance degradation issue and would appreciate any insights from the community.
馃敼 **Environment** - OpenStack version: Zed - Neutron backend: OVN - Two VMs (each 4 vCPUs, 8 GB RAM) launched on two different compute nodes - Multi-queue is enabled on the VM vNICs
馃敼 **Issue** The network performance inside the VMs is significantly worse than on the host nodes, with high packet retransmissions observed.
馃敼 **Test results**
**Host-to-Host (VTEP IPs)**
``` $ iperf3 -c 192.168.152.152 Connecting to host 192.168.152.152, port 5201 [ 5] local 192.168.152.153 port 45352 connected to 192.168.152.152 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 1.38 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 1.00-2.00 sec 1.37 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 2.00-3.00 sec 1.42 GBytes 12.2 Gbits/sec 0 3.10 MBytes [ 5] 3.00-4.00 sec 1.39 GBytes 11.9 Gbits/sec 0 3.10 MBytes [ 5] 4.00-5.00 sec 1.38 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 5.00-6.00 sec 1.43 GBytes 12.3 Gbits/sec 0 3.10 MBytes [ 5] 6.00-7.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 7.00-8.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 8.00-9.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 9.00-10.00 sec 1.42 GBytes 12.2 Gbits/sec 0 3.10 MBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 14.0 GBytes 12.0 Gbits/sec 0 sender [ 5] 0.00-10.04 sec 14.0 GBytes 12.0 Gbits/sec receiver
iperf Done. ```
**VM-to-VM (through overlay network)**
``` $ iperf3 -c 10.0.6.10 Connecting to host 10.0.6.10, port 5201 [ 5] local 10.0.6.37 port 56710 connected to 10.0.6.10 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 499 MBytes 4.19 Gbits/sec 263 463 KBytes [ 5] 1.00-2.00 sec 483 MBytes 4.05 Gbits/sec 467 367 KBytes [ 5] 2.00-3.00 sec 482 MBytes 4.05 Gbits/sec 491 386 KBytes [ 5] 3.00-4.00 sec 483 MBytes 4.05 Gbits/sec 661 381 KBytes [ 5] 4.00-5.00 sec 472 MBytes 3.95 Gbits/sec 430 391 KBytes [ 5] 5.00-6.00 sec 480 MBytes 4.03 Gbits/sec 474 350 KBytes [ 5] 6.00-7.00 sec 510 MBytes 4.28 Gbits/sec 567 474 KBytes [ 5] 7.00-8.00 sec 521 MBytes 4.37 Gbits/sec 565 387 KBytes [ 5] 8.00-9.00 sec 509 MBytes 4.27 Gbits/sec 632 483 KBytes [ 5] 9.00-10.00 sec 514 MBytes 4.30 Gbits/sec 555 495 KBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 4.84 GBytes 4.15 Gbits/sec 5105 sender [ 5] 0.00-10.05 sec 4.84 GBytes 4.14 Gbits/sec receiver
iperf Done. ```
As you can see, there's a sharp drop in performance inside the VMs (from ~12 Gbps down to ~4 Gbps), with a lot of retransmissions in 10 seconds.
Has anyone encountered a similar issue with OVN and VM networking performance? What could be the potential causes?
Any suggestions or debugging tips are welcome.
Thanks in advance!
Best regards,
Hello. I have a similar case: communication between VMs using the provider network works fine, but not with the self-service network. Using jumbo frames will improve performance significantly. Nguyen Huu Khoi On Wed, Jul 30, 2025 at 10:36鈥疉M engineer2024 <engineerlinux2024@gmail.com> wrote:
Did this work better with LXB plugin earlier?
On Wed, 30 Jul 2025, 09:01 Jeff Yang, <yjf1970231893@gmail.com> wrote:
Hi all,
I'm running OpenStack Zed with OVN as the Neutron backend. I've encountered a severe VM network performance degradation issue and would appreciate any insights from the community.
馃敼 **Environment** - OpenStack version: Zed - Neutron backend: OVN - Two VMs (each 4 vCPUs, 8 GB RAM) launched on two different compute nodes - Multi-queue is enabled on the VM vNICs
馃敼 **Issue** The network performance inside the VMs is significantly worse than on the host nodes, with high packet retransmissions observed.
馃敼 **Test results**
**Host-to-Host (VTEP IPs)**
``` $ iperf3 -c 192.168.152.152 Connecting to host 192.168.152.152, port 5201 [ 5] local 192.168.152.153 port 45352 connected to 192.168.152.152 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 1.38 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 1.00-2.00 sec 1.37 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 2.00-3.00 sec 1.42 GBytes 12.2 Gbits/sec 0 3.10 MBytes [ 5] 3.00-4.00 sec 1.39 GBytes 11.9 Gbits/sec 0 3.10 MBytes [ 5] 4.00-5.00 sec 1.38 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 5.00-6.00 sec 1.43 GBytes 12.3 Gbits/sec 0 3.10 MBytes [ 5] 6.00-7.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 7.00-8.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 8.00-9.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 9.00-10.00 sec 1.42 GBytes 12.2 Gbits/sec 0 3.10 MBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 14.0 GBytes 12.0 Gbits/sec 0 sender [ 5] 0.00-10.04 sec 14.0 GBytes 12.0 Gbits/sec receiver
iperf Done. ```
**VM-to-VM (through overlay network)**
``` $ iperf3 -c 10.0.6.10 Connecting to host 10.0.6.10, port 5201 [ 5] local 10.0.6.37 port 56710 connected to 10.0.6.10 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 499 MBytes 4.19 Gbits/sec 263 463 KBytes [ 5] 1.00-2.00 sec 483 MBytes 4.05 Gbits/sec 467 367 KBytes [ 5] 2.00-3.00 sec 482 MBytes 4.05 Gbits/sec 491 386 KBytes [ 5] 3.00-4.00 sec 483 MBytes 4.05 Gbits/sec 661 381 KBytes [ 5] 4.00-5.00 sec 472 MBytes 3.95 Gbits/sec 430 391 KBytes [ 5] 5.00-6.00 sec 480 MBytes 4.03 Gbits/sec 474 350 KBytes [ 5] 6.00-7.00 sec 510 MBytes 4.28 Gbits/sec 567 474 KBytes [ 5] 7.00-8.00 sec 521 MBytes 4.37 Gbits/sec 565 387 KBytes [ 5] 8.00-9.00 sec 509 MBytes 4.27 Gbits/sec 632 483 KBytes [ 5] 9.00-10.00 sec 514 MBytes 4.30 Gbits/sec 555 495 KBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 4.84 GBytes 4.15 Gbits/sec 5105 sender [ 5] 0.00-10.05 sec 4.84 GBytes 4.14 Gbits/sec receiver
iperf Done. ```
As you can see, there's a sharp drop in performance inside the VMs (from ~12 Gbps down to ~4 Gbps), with a lot of retransmissions in 10 seconds.
Has anyone encountered a similar issue with OVN and VM networking performance? What could be the potential causes?
Any suggestions or debugging tips are welcome.
Thanks in advance!
Best regards,
Hi, I had similar issue. I have tested ovn 24.03 and ovs 3.3 on ubuntu jammy and had better results. You can try it from ubuntu UCA caracal repo. Ammad On Wed, 30 Jul 2025 at 10:57鈥疉M, Nguy峄卬 H峄痷 Kh么i <nguyenhuukhoinw@gmail.com> wrote:
Hello. I have a similar case: communication between VMs using the provider network works fine, but not with the self-service network. Using jumbo frames will improve performance significantly.
Nguyen Huu Khoi
On Wed, Jul 30, 2025 at 10:36鈥疉M engineer2024 <engineerlinux2024@gmail.com> wrote:
Did this work better with LXB plugin earlier?
On Wed, 30 Jul 2025, 09:01 Jeff Yang, <yjf1970231893@gmail.com> wrote:
Hi all,
I'm running OpenStack Zed with OVN as the Neutron backend. I've encountered a severe VM network performance degradation issue and would appreciate any insights from the community.
馃敼 **Environment** - OpenStack version: Zed - Neutron backend: OVN - Two VMs (each 4 vCPUs, 8 GB RAM) launched on two different compute nodes - Multi-queue is enabled on the VM vNICs
馃敼 **Issue** The network performance inside the VMs is significantly worse than on the host nodes, with high packet retransmissions observed.
馃敼 **Test results**
**Host-to-Host (VTEP IPs)**
``` $ iperf3 -c 192.168.152.152 Connecting to host 192.168.152.152, port 5201 [ 5] local 192.168.152.153 port 45352 connected to 192.168.152.152 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 1.38 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 1.00-2.00 sec 1.37 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 2.00-3.00 sec 1.42 GBytes 12.2 Gbits/sec 0 3.10 MBytes [ 5] 3.00-4.00 sec 1.39 GBytes 11.9 Gbits/sec 0 3.10 MBytes [ 5] 4.00-5.00 sec 1.38 GBytes 11.8 Gbits/sec 0 3.10 MBytes [ 5] 5.00-6.00 sec 1.43 GBytes 12.3 Gbits/sec 0 3.10 MBytes [ 5] 6.00-7.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 7.00-8.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 8.00-9.00 sec 1.41 GBytes 12.1 Gbits/sec 0 3.10 MBytes [ 5] 9.00-10.00 sec 1.42 GBytes 12.2 Gbits/sec 0 3.10 MBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 14.0 GBytes 12.0 Gbits/sec 0 sender [ 5] 0.00-10.04 sec 14.0 GBytes 12.0 Gbits/sec receiver
iperf Done. ```
**VM-to-VM (through overlay network)**
``` $ iperf3 -c 10.0.6.10 Connecting to host 10.0.6.10, port 5201 [ 5] local 10.0.6.37 port 56710 connected to 10.0.6.10 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 499 MBytes 4.19 Gbits/sec 263 463 KBytes [ 5] 1.00-2.00 sec 483 MBytes 4.05 Gbits/sec 467 367 KBytes [ 5] 2.00-3.00 sec 482 MBytes 4.05 Gbits/sec 491 386 KBytes [ 5] 3.00-4.00 sec 483 MBytes 4.05 Gbits/sec 661 381 KBytes [ 5] 4.00-5.00 sec 472 MBytes 3.95 Gbits/sec 430 391 KBytes [ 5] 5.00-6.00 sec 480 MBytes 4.03 Gbits/sec 474 350 KBytes [ 5] 6.00-7.00 sec 510 MBytes 4.28 Gbits/sec 567 474 KBytes [ 5] 7.00-8.00 sec 521 MBytes 4.37 Gbits/sec 565 387 KBytes [ 5] 8.00-9.00 sec 509 MBytes 4.27 Gbits/sec 632 483 KBytes [ 5] 9.00-10.00 sec 514 MBytes 4.30 Gbits/sec 555 495 KBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 4.84 GBytes 4.15 Gbits/sec 5105 sender [ 5] 0.00-10.05 sec 4.84 GBytes 4.14 Gbits/sec receiver
iperf Done. ```
As you can see, there's a sharp drop in performance inside the VMs (from ~12 Gbps down to ~4 Gbps), with a lot of retransmissions in 10 seconds.
Has anyone encountered a similar issue with OVN and VM networking performance? What could be the potential causes?
Any suggestions or debugging tips are welcome.
Thanks in advance!
Best regards,
Hi, Sometimes disabling offloading on the host helps: ethtool -K <interface> tso off Cheers On Wed, 2025-07-30 at 12:57 +0700, Nguy峄卬 H峄痷 Kh么i wrote:
聽Hello. I have a similar case: communication between VMs using the provider network works fine, but not with the self-service network. Using jumbo frames will improve performance significantly.聽聽
Nguyen Huu Khoi
On Wed, Jul 30, 2025 at 10:36鈥疉M engineer2024 <engineerlinux2024@gmail.com> wrote:
Did this work better with LXB plugin earlier?聽
On Wed, 30 Jul 2025, 09:01 Jeff Yang, <yjf1970231893@gmail.com> wrote:
Hi all,
I'm running OpenStack Zed with OVN as the Neutron backend. I've encountered a severe VM network performance degradation issue and would appreciate any insights from the community.
馃敼 **Environment** - OpenStack version: Zed - Neutron backend: OVN - Two VMs (each 4 vCPUs, 8 GB RAM) launched on two different compute nodes - Multi-queue is enabled on the VM vNICs
馃敼 **Issue** The network performance inside the VMs is significantly worse than on the host nodes, with high packet retransmissions observed.
馃敼 **Test results**
**Host-to-Host (VTEP IPs)**
``` $ iperf3 -c 192.168.152.152 Connecting to host 192.168.152.152, port 5201 [ 聽5] local 192.168.152.153 port 45352 connected to 192.168.152.152 port 5201 [ ID] Interval 聽 聽 聽 聽 聽 Transfer 聽 聽 Bitrate 聽 聽 聽 聽 Retr 聽Cwnd [ 聽5] 聽 0.00-1.00 聽 sec 聽1.38 GBytes 聽11.8 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 1.00-2.00 聽 sec 聽1.37 GBytes 聽11.8 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 2.00-3.00 聽 sec 聽1.42 GBytes 聽12.2 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 3.00-4.00 聽 sec 聽1.39 GBytes 聽11.9 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 4.00-5.00 聽 sec 聽1.38 GBytes 聽11.8 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 5.00-6.00 聽 sec 聽1.43 GBytes 聽12.3 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 6.00-7.00 聽 sec 聽1.41 GBytes 聽12.1 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 7.00-8.00 聽 sec 聽1.41 GBytes 聽12.1 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 8.00-9.00 聽 sec 聽1.41 GBytes 聽12.1 Gbits/sec 聽 聽0 聽 3.10 MBytes [ 聽5] 聽 9.00-10.00 聽sec 聽1.42 GBytes 聽12.2 Gbits/sec 聽 聽0 聽 3.10 MBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval 聽 聽 聽 聽 聽 Transfer 聽 聽 Bitrate 聽 聽 聽 聽 Retr [ 聽5] 聽 0.00-10.00 聽sec 聽14.0 GBytes 聽12.0 Gbits/sec 聽 聽0 聽 聽 聽 聽 聽 聽 sender [ 聽5] 聽 0.00-10.04 聽sec 聽14.0 GBytes 聽12.0 Gbits/sec 聽 聽 聽 聽 聽 聽 聽 聽 聽receiver
iperf Done. ```
**VM-to-VM (through overlay network)**
``` $ iperf3 -c 10.0.6.10 Connecting to host 10.0.6.10, port 5201 [ 聽5] local 10.0.6.37 port 56710 connected to 10.0.6.10 port 5201 [ ID] Interval 聽 聽 聽 聽 聽 Transfer 聽 聽 Bitrate 聽 聽 聽 聽 Retr 聽Cwnd [ 聽5] 聽 0.00-1.00 聽 sec 聽 499 MBytes 聽4.19 Gbits/sec 聽263 聽 聽463 KBytes [ 聽5] 聽 1.00-2.00 聽 sec 聽 483 MBytes 聽4.05 Gbits/sec 聽467 聽 聽367 KBytes [ 聽5] 聽 2.00-3.00 聽 sec 聽 482 MBytes 聽4.05 Gbits/sec 聽491 聽 聽386 KBytes [ 聽5] 聽 3.00-4.00 聽 sec 聽 483 MBytes 聽4.05 Gbits/sec 聽661 聽 聽381 KBytes [ 聽5] 聽 4.00-5.00 聽 sec 聽 472 MBytes 聽3.95 Gbits/sec 聽430 聽 聽391 KBytes [ 聽5] 聽 5.00-6.00 聽 sec 聽 480 MBytes 聽4.03 Gbits/sec 聽474 聽 聽350 KBytes [ 聽5] 聽 6.00-7.00 聽 sec 聽 510 MBytes 聽4.28 Gbits/sec 聽567 聽 聽474 KBytes [ 聽5] 聽 7.00-8.00 聽 sec 聽 521 MBytes 聽4.37 Gbits/sec 聽565 聽 聽387 KBytes [ 聽5] 聽 8.00-9.00 聽 sec 聽 509 MBytes 聽4.27 Gbits/sec 聽632 聽 聽483 KBytes [ 聽5] 聽 9.00-10.00 聽sec 聽 514 MBytes 聽4.30 Gbits/sec 聽555 聽 聽495 KBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval 聽 聽 聽 聽 聽 Transfer 聽 聽 Bitrate 聽 聽 聽 聽 Retr [ 聽5] 聽 0.00-10.00 聽sec 聽4.84 GBytes 聽4.15 Gbits/sec 聽5105 聽 聽 聽 聽 聽 聽 sender [ 聽5] 聽 0.00-10.05 聽sec 聽4.84 GBytes 聽4.14 Gbits/sec 聽 聽 聽 聽 聽 聽 聽 聽 聽receiver
iperf Done. ```
As you can see, there's a sharp drop in performance inside the VMs (from ~12 Gbps down to ~4 Gbps), with a lot of聽retransmissions in 10 seconds.
Has anyone encountered a similar issue with OVN and VM networking performance? What could be the potential causes?
Any suggestions or debugging tips are welcome.
Thanks in advance!
Best regards, 聽
participants (5)
-
Ammad Syed
-
engineer2024
-
Jeff Yang
-
Konstantin Larin
-
Nguy峄卬 H峄痷 Kh么i