I have mikrotik chr 6.42.7 router on my esxi 6.0 u3 hypervisor with P10 licence, which connect to couple subnets.All my virtual machines use VMXNET3 adapter with 10Gb speed, speed between hosts in one subnet(network) 4-5Gb, but I see that when I send traffic betweent subnets speed is going down and became to 2Gb.I have pretty simple config of my microtik
/interface ethernet
set [ find default-name=ether2 ] mtu=1500
set [ find default-name=ether3 ] mtu=1500
/ip address
add address=10.10.10.1/24 interface=ether2 network=10.10.10.0
add address=10.10.11.1/24 interface=ether3 network=10.10.11.0
To measuge speed I use iperf.
And I do not understand why it happend, please help me.

What is the CPU usage? How many cores have you assigned to CHR?

Finally have you enabled FastTrack?

https://wiki.mikrotik.com/wiki/Manual:IP/Fasttrack

CPU usage 10-15%, virtual machine use 4 core, on my hypervisor I have two Xeon X5670 processor
Yes I try to use fasttrack but it did not bring any results

A method to get more speed out of a very busy CHR router:

On the physical computer , in the BIOS , disable hyper-threading & set for maximum performance.
On the hyper-visor (VmWare ESXi , set for performance.
Then on the virtual CHR router , enable 8 processors.
Limit other virtual hosted servers on the hyper-visor.

Note - with hyper-threading disabled, the guest hosted CHR now actually has twice the power (providing you are using the same processor count). And - also of note - now your processor CPU cache is more efficient and will have more CPU cache hits.

FYI - With a CHR, you should be able to perform a udp btest (send or receive) to 127.0.0.1 and acheive around 20-Gig.
If you can only acheive 15 Gig or less , then you are running on an old-slow-tired physical computer.
If you can acheive 21 Gig or faster, then you are running on a normal decent physical server.
If you can acheive over 25 Gig, then you are probable running on a newer high-end physical server.

FYI - My CHR systems btest to 127.0.0.1 at 23.6 Gbps.
I have never seen any mikrotik board even come close to 1/3 to 1/2 these speeds on a btest to 127.0.0.1

North Idaho Tom Jones

Hi guys,

I am new to this forum, I was wondering if anyone got better performance by disabling hyper threading. I will need to take down production routers to do this. We have a 9 core cloud core router doing 5x more traffic and the CPU usage is around 40-50% at peak. I have 2x CHR routers with 8 cores of 2.6GHZ Xeon processor, doing around 15Mbps of traffic per interface (WAN and LAN) and the CPU is sitting around 15-25% which I feel is very high for the CPU spec.

These are VM's running on ESXi 6.0.0, similarly, I have used VMXNET3 and the Licence is P1, I won't need more than 1Gbps. My firewall rules are limited to dropping invalid connections and anything that doesn't match my allow rules, there are 11 rules. No NAT rules, no Mangle rules.

I am keen to find a solution to this issue, anyone input would be appreciated. I have attached some screenshots below:

Hi guys,

I am new to this forum, I was wondering if anyone got better performance by disabling hyper threading. I will need to take down production routers to do this. We have a 9 core cloud core router doing 5x more traffic and the CPU usage is around 40-50% at peak. I have 2x CHR routers with 8 cores of 2.6GHZ Xeon processor, doing around 15Mbps of traffic per interface (WAN and LAN) and the CPU is sitting around 15-25% which I feel is very high for the CPU spec.

These are VM's running on ESXi 6.0.0, similarly, I have used VMXNET3 and the Licence is P1, I won't need more than 1Gbps. My firewall rules are limited to dropping invalid connections and anything that doesn't match my allow rules, there are 11 rules. No NAT rules, no Mangle rules.

I am keen to find a solution to this issue, anyone input would be appreciated. I have attached some screenshots below:

do you use virtio-net of you VM
it may reduce cpu useage

I don't see that setting, are you sure it is available in ESXi 6.0.0?

I don't see that setting, are you sure it is available in ESXi 6.0.0?

i am not sure,but you can check it online.i use the Virtualbox, when i use virto-net ,the cpu usage reduce 20%.
It's a virtualization technology.
General virtual machines have this function
It can significantly improve network performance and reduce cpu usage

Thanks I will try and find a way to do it, I saw a post regarding setting it up on ESXi, it helps with allowing the tx and rx to use multiple CPU's thus helping the I/O queuing.
I am also going to try a bandwidth test between two CHR's, I want to see where the load is coming in, I don't think it is on the firewall side but I will try enable fast track and disable the Conntrack to lessen the load.

Hi guys,

I am new to this forum, I was wondering if anyone got better performance by disabling hyper threading. I will need to take down production routers to do this. We have a 9 core cloud core router doing 5x more traffic and the CPU usage is around 40-50% at peak. I have 2x CHR routers with 8 cores of 2.6GHZ Xeon processor, doing around 15Mbps of traffic per interface (WAN and LAN) and the CPU is sitting around 15-25% which I feel is very high for the CPU spec.

These are VM's running on ESXi 6.0.0, similarly, I have used VMXNET3 and the Licence is P1, I won't need more than 1Gbps. My firewall rules are limited to dropping invalid connections and anything that doesn't match my allow rules, there are 11 rules. No NAT rules, no Mangle rules.

I am keen to find a solution to this issue, anyone input would be appreciated. I have attached some screenshots below:

Re: I was wondering if anyone got better performance by disabling hyper threading

YES - BIG time.
Also , on your physical hypervisor server (in my case , VMware ESXi ) , there are some more things you can do to give it more throughput power.
- Configure your hypervisor to use delayed_ack = 1 ( nstead of the defualt delayed_ack = 0 )
- Increase your hypervisor network buffer sizes ( helps give you more throughput )
- If you are using a NFS , disable sync ( and also set your NFS server for delayed_ack = 1 )
- Your hypervisor should always have extra un-assigned ram memory and at least 1 free CPU. This gives you some processing power for hypervisor overhead tasks such as snapshots and/or copying/moving datastores.
- When ever possible , use 10-Gig physical network cards
- When ever possible , use paravirtulized devices ( example vmxnet-3 )
- On your physical and on your virtual machines , disable and remove as many devices as possible. You want to keep you interrupts low and free up resources.

North Idaho Tom Jones

I don't see that setting, are you sure it is available in ESXi 6.0.0?

Disable hyper-threading on the physical computer in the BIOS.

Thanks for the feedback, will give it a try.

I did try a Bandwidth test from one router to the other last night, from LAN interface to LAN interface I got just under a Gbps both ways which is acceptable, the CPU was under 10% which is confusing. I'm still not sure if the issue is with the firewall or with the routing of packets between two interfaces on two different subnets. Will investigate further and post results.

Thanks again!

Just an update, I have not yet hanged BIOS settings, however, we are using these routers to cross-connect with voice network providers. I noticed that SIP direct media was enabled, I have previously had issues with this setting, do you think it could have been causing load? we only push SIP traffic over these routers.

That (voip) explains the high packet rate but low bandwidth I saw on your screenshots.
Unless you use NAT, you don't need the SIP direct media helper (and I think it doesn't even get involved in forwarded traffic when there is no NAT).

Also, connection tracking in general, with lots of connections and/or packet rate can cause high load. If you can, disable it altogether, or if you don't need the voip traffic to be tracked, then apply no-track rules in the Raw table for that particular traffic.

Doing a bandwidth test can yield high bandwidth numbers with low CPU usage because the bandwidth test uses just a few connections and large sized packets.
Whereas having 14Kpps in voip traffic, must mean you have tons of simultaneous calls/connections - which is more heavy for connection-tracking.

A method to get more speed out of a very busy CHR router:

On the physical computer , in the BIOS , disable hyper-threading & set for maximum performance.

That's official Intel recommendation, if virtualization is used. HyperThreading does more harm than good, in this case.

A method to get more speed out of a very busy CHR router:

On the physical computer , in the BIOS , disable hyper-threading & set for maximum performance.

That's official Intel recommendation, if virtualization is used. HyperThreading does more harm than good, in this case.

Isn't that mainly because of security (Meltdown & co)?

A method to get more speed out of a very busy CHR router:

On the physical computer , in the BIOS , disable hyper-threading & set for maximum performance.

That's official Intel recommendation, if virtualization is used. HyperThreading does more harm than good, in this case.

Isn't that mainly because of security (Meltdown & co)?

No. This is from far earlier than that. It's about performance: it is better without HyperThreading (this kind of workload is).

Why disable hyper-threading ?

Hyper-Threading is a CPU trick to make a CPU core appear and function as if it were two CPU cores.
Some teckie info on Hyper-Threading - - - What is actually happening when Hyper-Threading is enabled is this:

- There is a software configured SMI interrupt (System Management Interrupt) that
A) Stops the CPU
B) POPs the stack (It copies the contents of CPU registers to a temporary memory location).
C) It then PUSHes the stack (It copies the contents of a different temporary memory location into the CPU registers)
D) It then allows the CPU to resume running.
E) After a few clock cycles, another SMI event occurs and this time the SMI process POPs and PUSHes the stacks then resumes running the original CPU contents. This process constantly repeats which to make it appear as if a CPU core is is two CPU cores.

There are two big problems with Hyper-Threading:
1) Hyper-Threading is a waste of CPU clock cycles in the SMI process which could be used to keep programs running when Hyper-Threading is disabled.
2) Hyper-Threading chews up built-in CPU cache memory and often creates CPU cache MISSes. A CPU cache MISS forces the CPU to slow down to RAM memory speed instead using the faster built-in CPU CACHE memory speed.

For a faster CHR running on a Hyper-Visor system (like VmWare ESXi):
- Disable Hyper-Threading
- Use Physical 10-Gig network cards (with 10-Gig switches)
- Use ParaVirtual devices (HyperVisor optomised drivers such as VMXNET-3 network interfaces and when possible also use "VMware Paravirtual" SCSI controllers)
- Remove any unnecesary devices not needed (such as CD-Drives, serial-ports, floppy disk drives ...)
- Do not over assign the physical CPUs and memory to virtual machines. Try to keep at least one free CPU
- When possible, move non-essential non-high-speed virtual machines to a different slower Hyper-Visor system (keep your core running fast).

Hey, let me just get into this thread because we're experiencing the same issue.
Don't want to hijack but maybe it gives more insight to the problem and we can pinpoint more?

Our setup is the following:
Tyan Server: GT62F-B8026 with firmware R3.00
Processors: AMD EPYC 7551P 32-Core Processor
Hypervisor: VMware ESXi, 6.5.0, 7967591
NICs: Mellanox MT27630 (ConnectX-4 LX)
Storage: Full Flash Dorado 5000v3

So the following has been tested and applied:

• Disabled SMT
• Paravirtualisation Enabled
• Delayed Ack on HBA inheritance off and manually Enabled
• CPU is 8 sockets with 1 core for this test device
• Storage is on IDE
• VMXNet3 adapter with DirectIO enabled

This is the result when testing to its own BTest: (This is the ONLY VM running on this host while doing the test)
And CPU is on 12% stable

Pirlet ,

FYI - I assume you are running a Mikrotik CHR (64-Bit ROS).

Heads up - I don't think you need the "SCSI controller 0" in your configuration. If I am correct , the CHR does not even have SCSI drivers and the virtual CHR hard disk is actually IDE.
By removing the SCSI controller , you free up some resources and at least one interrupt.

Here is my configuration on my CHR which happens to be one of my BGP routers:

Pirlet ,

FYI - I assume you are running a Mikrotik CHR (64-Bit ROS).

Heads up - I don't think you need the "SCSI controller 0" in your configuration. If I am correct , the CHR does not even have SCSI drivers and the virtual CHR hard disk is actually IDE.
By removing the SCSI controller , you free up some resources and at least one interrupt.

Here is my configuration on my CHR which happens to be one of my BGP routers:
CHR-NoScsi.png

Hey Tom,
Are you on an AMD platform or Intel platform?

Can I PM you so maybe we could compare configs? That would really help me out massively.

Pirlet ,

FYI - I assume you are running a Mikrotik CHR (64-Bit ROS).

Heads up - I don't think you need the "SCSI controller 0" in your configuration. If I am correct , the CHR does not even have SCSI drivers and the virtual CHR hard disk is actually IDE.
By removing the SCSI controller , you free up some resources and at least one interrupt.

Here is my configuration on my CHR which happens to be one of my BGP routers:
CHR-NoScsi.png

Hey Tom,
Are you on an AMD platform or Intel platform?

Can I PM you so maybe we could compare configs? That would really help me out massively.

I use only Intel Xeon processors.

Re: Can I PM you so maybe we could compare configs?
Sure

Getting the most performance out of a CHR (in my case , two CHRs on a single physical computer with two Intel Xeon CPUs (10 cores each) with Hyper-Threading disabled)

OK - so I have been blabbing quite alot about CPU cache. Well , here is another trick to get even more out of a couple of CHRs running on the same physical box.

Use CPU affinity (specify which CPU cores a hosted CHR can use

Info: I have a SuperMicro box , two 10-core Xeon processors (Cores 0 through 19) , Hyper-Threading disabled , I am using VMware ESXi for my Hyper-Visor.

CHR#1 - Set host CPU affinity to 1-9 ( 9 cores reserved on physical CPU1 )
CHR #2 - Set host CPU affinity to 11-19 ( 9 cores reserved on physical CPU2 )

CHR #1 does not share any CPU cache with CHR #2 (Both CHRs have their own semi-private CPU cache and dedicated cores to each running CHR)

The results , both CHRs now run faster.
Note: CHR #2 might be a little faster because it is likely not sharing any CPU cache with the VmWare ESXi hosing Hyper-Visor operating system.
Note: CHR #1 might share some CPU cache with the host VmWare ESXi Hyper-Visor operating system.

Note: If you do not define CPU affinity , you can potentially end up with some CPU cores doing nothing at almost zero percent CPU usage and other CPU cores running at 50 to 100 percent CPU usage handeling multiple hosts at the same time (swapping jobs).

One thing I have not tried yet is to define what CPU cores the actual VmWare ESXi system can use for it's own processes.


North Idaho Tom Jones


EDIT - additional info added

If you have more than 1 physical CPU on your Hyper-Visor system (example two 10-core CPUs with 30-Meg CPU cache per Xeon CPU), and you only run a single HOST CHR with no other hosts running - you can also do this:

--> use CPU affinity 6-14 (you end up with 60-Meg of CPU cache on your single CHR host)

Getting the most performance out of a CHR (in my case , two CHRs on a single physical computer with two Intel Xeon CPUs (10 cores each) with Hyper-Threading disabled)

OK - so I have been blabbing quite alot about CPU cache. Well , here is another trick to get even more out of a couple of CHRs running on the same physical box.

Use CPU affinity (specify which CPU cores a hosted CHR can use

Info: I have a SuperMicro box , two 10-core Xeon processors (Cores 0 through 19) , Hyper-Threading disabled , I am using VMware ESXi for my Hyper-Visor.

CHR#1 - Set host CPU affinity to 1-9 ( 9 cores reserved on physical CPU1 )
CHR #2 - Set host CPU affinity to 11-19 ( 9 cores reserved on physical CPU2 )

CHR #1 does not share any CPU cache with CHR #2 (Both CHRs have their own semi-private CPU cache and dedicated cores to each running CHR)

The results , both CHRs now run faster.
Note: CHR #2 might be a little faster because it is likely not sharing any CPU cache with the VmWare ESXi hosing Hyper-Visor operating system.
Note: CHR #1 might share some CPU cache with the host VmWare ESXi Hyper-Visor operating system.

Note: If you do not define CPU affinity , you can potentially end up with some CPU cores doing nothing at almost zero percent CPU usage and other CPU cores running at 50 to 100 percent CPU usage handeling multiple hosts at the same time (swapping jobs).

One thing I have not tried yet is to define what CPU cores the actual VmWare ESXi system can use for it's own processes.


North Idaho Tom Jones


EDIT - additional info added

If you have more than 1 physical CPU on your Hyper-Visor system (example two 10-core CPUs with 30-Meg CPU cache per Xeon CPU), and you only run a single HOST CHR with no other hosts running - you can also do this:

--> use CPU affinity 6-14 (you end up with 60-Meg of CPU cache on your single CHR host)

How much traffic/users do you run on system like this? What do you do on on it? QoS, Firewall, NAT, BGP...?

Getting the most performance out of a CHR (in my case , two CHRs on a single physical computer with two Intel Xeon CPUs (10 cores each) with Hyper-Threading disabled)

OK - so I have been blabbing quite alot about CPU cache. Well , here is another trick to get even more out of a couple of CHRs running on the same physical box.

Use CPU affinity (specify which CPU cores a hosted CHR can use

Info: I have a SuperMicro box , two 10-core Xeon processors (Cores 0 through 19) , Hyper-Threading disabled , I am using VMware ESXi for my Hyper-Visor.

CHR#1 - Set host CPU affinity to 1-9 ( 9 cores reserved on physical CPU1 )
CHR #2 - Set host CPU affinity to 11-19 ( 9 cores reserved on physical CPU2 )

CHR #1 does not share any CPU cache with CHR #2 (Both CHRs have their own semi-private CPU cache and dedicated cores to each running CHR)

The results , both CHRs now run faster.
Note: CHR #2 might be a little faster because it is likely not sharing any CPU cache with the VmWare ESXi hosing Hyper-Visor operating system.
Note: CHR #1 might share some CPU cache with the host VmWare ESXi Hyper-Visor operating system.

Note: If you do not define CPU affinity , you can potentially end up with some CPU cores doing nothing at almost zero percent CPU usage and other CPU cores running at 50 to 100 percent CPU usage handeling multiple hosts at the same time (swapping jobs).

One thing I have not tried yet is to define what CPU cores the actual VmWare ESXi system can use for it's own processes.


North Idaho Tom Jones


EDIT - additional info added

If you have more than 1 physical CPU on your Hyper-Visor system (example two 10-core CPUs with 30-Meg CPU cache per Xeon CPU), and you only run a single HOST CHR with no other hosts running - you can also do this:

--> use CPU affinity 6-14 (you end up with 60-Meg of CPU cache on your single CHR host)

How much traffic/users do you run on system like this? What do you do on on it? QoS, Firewall, NAT, BGP...?

Re: How much traffic/users do you run on system like this & BGP
Answer: I have about 16 Class C networks , two BGP feeds (primary BGP is 2-Gig burstable to 4-Gig & secondary-fallback BGP is 512-Meg), during busy hours we average about 1.5 Gig sustained traffic.

Re: What do you do on on it?
Answer: We have over 1,000+ customers , 2/3s of them on Mikrotik wireless and 1/3 on fiber.

Re: QoS
Answer: We are in the process of changing from PfSense bandwidth management per MAC address to CHR based systems bandwidth management per customer IP address. We just are 1/2 the way migrating to the Sonar ISP system (billing & BW management)

Re: Firewall & NAT
Answer: As for our internal office networks, we use PfSense. As for customers , each customer gets a live IP address to our customer located equipment. Our customer located equipment (Mikrotik for wireless customers - Non Mikrotik for fiber customers) perform NAT and firewall at each customer location.

Our goal is to eventually move the bulk of our wireless customers to fiber (mostly GPON fiber). Wireless we generally offer up to 25-Meg accounts , with fiber customers we offer just about any speed a customer may want (mostly 100 Meg customers but some are 256 & 512 & 1-Gig customers). Wireless networks for hundreds to thousands of customers will never have the throughput that fiber customers can acheive.

Because the network is somewhat big and complex for bandwidth management per customer, we have been beefing up our CHR systems so that they can handle 10-Gig throughputs under heavy CPU loads.

North Idaho Tom Jones

im on my way too switch to chr... Im in my testing so what i learn so far is single thread performance is a big fact to obtain bandwidth speed and convergence ... I do a small bandwidth test on hyper-v with my station 2600x and i got around 40 gbps... So im looking to go to the intel 8600k wich have the best price ratio on single thread performance. I order it today so i will test it and give you results as soon i got it. Second i found on google on a mum document that you get more performance with hyper-v then esxi or proxmox kvm.https://mum.mikrotik.com/presentations/ ... 562405.pdf

im on my way too switch to chr... Im in my testing so what i learn so far is single thread performance is a big fact to obtain bandwidth speed and convergence ... I do a small bandwidth test on hyper-v with my station 2600x and i got around 40 gbps... So im looking to go to the intel 8600k wich have the best price ratio on single thread performance. I order it today so i will test it and give you results as soon i got it. Second i found on google on a mum document that you get more performance with hyper-v then esxi or proxmox kvm.https://mum.mikrotik.com/presentations/ ... 562405.pdf

i have simmilar opinion, single core performance is critical

will be interesting to know how it has gone with 8600k, i agree is the best single core performance cpu available

Pirlet ,

FYI - I assume you are running a Mikrotik CHR (64-Bit ROS).

Heads up - I don't think you need the "SCSI controller 0" in your configuration. If I am correct , the CHR does not even have SCSI drivers and the virtual CHR hard disk is actually IDE.
By removing the SCSI controller , you free up some resources and at least one interrupt.

Here is my configuration on my CHR which happens to be one of my BGP routers:
CHR-NoScsi.png

CHR support PVSCSI

hello

I have same problem.

I have found a solution repeating 8 times the same interface ...

this way, one cpu for each interface .... and balance like magic.

i`m using just nat ....

the other configuration was: 2 interfaces: one for in and another for out ...

using 2 cpus ... high cpu in 90%

its bad for using all cpus to process all bandwidth ...

CHR its desappointing me...

I`ll replicate this for pppoe server

Has another way to balance cpus, without "replicate" the same interface to use all cpus?

I`ve tried everything...

Hi Guys,

Im seeing a similar issues where our Voip services start seeing a drop is Voice Quality once the CHR goes above 100000PPS, We have tried VMware and Proxmox 6.3 KVM and the latest long term stable 6.47.9 CHR , from my side it seems we are getting better performance on Proxmox and using VirIO nics

The host is a AMD EPYC Rome 7302P 16 core with HT/SMT disabled in the BIOS with 128GB RAM and 3 x 4 port 10G Intel X710 network Cards, 8 ports are is a LACP bond to 2 switches in MLAG and 4ports per switch for the iBGP traffic, and the last 4 ports are used for peering with upstream providers eBGP traffic

The CHR is configured with 14 vCPU's and 8GB Ram and 3 Nics at the moment, 1 for iBGP and 2 to Upstream eBGP

Bandwidth test to 127.0.0.1 is giving about 180Gbps with 14 vCPU, strange enough with only 2vCPU I get 800Gbps

What is the brand/model of the server? I happened to me once that the PCIe slot was x8 but in the specs I found out it was wired as x4, so the card was not able to use its full bandwidth

What is the brand/model of the server? I happened to me once that the PCIe slot was x8 but in the specs I found out it was wired as x4, so the card was not able to use its full bandwidth

Hi,
Chassis is a supermicro "2014TP-HTR" and the board "H12SST-PS" based on the web page the slots are PCI-E 4.0 x16 slots

https://www.supermicro.com/en/Aplus/sys ... TP-HTR.cfm
https://www.supermicro.com/en/products/ ... /H12SST-PS

Bandwidth test to 127.0.0.1 is giving about 180Gbps with 14 vCPU, strange enough with only 2vCPU I get 800Gbps

Your CPU has 4 CCD, 8 CCX and two active cores per CCX. ( https://en.wikipedia.org/wiki/Epyc#Seco ... pyc_(Rome) )

I have 4 ideas, about this.
1) With just two vCPUs, the OS puts all the VM on the same CCX. This will allow them to share L3 cache and speed up the communication.
2) Bandwidth test will use a fair chunk of the CPU, just to manage everything. Maybe using just 12 cores to the CPU, and leaving the rest for the host server?
3) If I'm not mistaken, the Epyc CPU uses 4 memory channels. You do have 4 (or 8) memory sticks (and in the right slots), don't You?
4) Have You looked into the CPU usage, while dropping packets? Just to make sure the machine is CPU bound?

Bandwidth test to 127.0.0.1 is giving about 180Gbps with 14 vCPU, strange enough with only 2vCPU I get 800Gbps

Your CPU has 4 CCD, 8 CCX and two active cores per CCX. ( https://en.wikipedia.org/wiki/Epyc#Seco ... pyc_(Rome) )

I have 4 ideas, about this.
1) With just two vCPUs, the OS puts all the VM on the same CCX. This will allow them to share L3 cache and speed up the communication.
2) Bandwidth test will use a fair chunk of the CPU, just to manage everything. Maybe using just 12 cores to the CPU, and leaving the rest for the host server?
3) If I'm not mistaken, the Epyc CPU uses 4 memory channels. You do have 4 (or 8) memory sticks (and in the right slots), don't You?
4) Have You looked into the CPU usage, while dropping packets? Just to make sure the machine is CPU bound?

Hi Paternot,

We have 4 memory sticks, and I have checked and no CPU core on the host is maxing during production traffic yet we still see packetloss

The servers we pre-assembled by supermicro so Im sure it will be configure correctly in regards to memory sticks in correct channels

We have 4 memory sticks, and I have checked and no CPU core on the host is maxing during production traffic yet we still see packetloss

Have You tried to pass traffic through the host server, to check if it's just the VM or both loosing packets? Have You pinned the VM CPUs to the host CPU cores?

We have 4 memory sticks, and I have checked and no CPU core on the host is maxing during production traffic yet we still see packetloss

Have You tried to pass traffic through the host server, to check if it's just the VM or both loosing packets? Have You pinned the VM CPUs to the host CPU cores?

I have not seen how its possible to PIN cpu core on a VM with PROXMOX

We have 4 memory sticks, and I have checked and no CPU core on the host is maxing during production traffic yet we still see packetloss

Have You tried to pass traffic through the host server, to check if it's just the VM or both loosing packets? Have You pinned the VM CPUs to the host CPU cores?

I have not seen how its possible to PIN cpu core on a VM with PROXMOX

The problem with packet loss is definitely not from the side of Internet lags? Sometimes it happens.

We have 4 memory sticks, and I have checked and no CPU core on the host is maxing during production traffic yet we still see packetloss

Have You tried to pass traffic through the host server, to check if it's just the VM or both loosing packets? Have You pinned the VM CPUs to the host CPU cores?

I have not seen how its possible to PIN cpu core on a VM with PROXMOX

The problem with packet loss is definitely not from the side of Internet lags? Sometimes it happens.

Hi ,

It is not, we are getting packetloss on the internal network aswell, we have a support ticket open with Mikrotik, they have given us a development version to load, and we have sent them .rif files which they have sent to the developers,

Seems there is packet loss once we start seeing high pps on the interfaces