Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Mellanox] [SKU] Mellanox-SN4700-C128 SKU added #24

Closed
wants to merge 10 commits into from

Conversation

vivekrnv
Copy link
Owner

@vivekrnv vivekrnv commented Jul 20, 2022

Signed-off-by: Vivek Reddy Karri vkarri@nvidia.com

Why I did it

Draft a new SKU for MSN-4700 Platform i.e. Mellanox-SN4700-C128

Requirements:

  • Breakout: Port 1-32: 4x100G
  • Downlinks: 120 (1-30)
  • Uplinks: 8 (31-32)
  • Shared Headroom: Enabled
  • Over Subscribe Ratio: 1:8
  • Default Topology: T2
  • Default Cable Length for T2: 1500m
  • VxLAN source port range set: yes
  • QoS params: The default ones defined in qos_config.j2 will be applied
  • Small Packet Percentage: Used 50% for traditional buffer model Note: For dynamic model, the value defined in LOSSLESS_TRAFFIC_PATTERN|AZURE|small_packet_percentage is used
Additional Details:
  • Switch Type has to be programmed as SpineRouter through config_db.json in DEVICE_METADATA|localhost|type field for the buffer values & cable lengths defined in the buffers_defaults_t2.j2 to apply on the device
  • Cable Lengths Used for generating buffer_defaults_{t0,t1,t2}.j2 values
 {
        "t2": {
            "up": "1500m",
            "down": "1500m",       
         },
        "t1": {
            "up": "300m",
            "down": "40m",
        },
        "t0": {
            "up": "40m",
            "down": "5m",
        }
}

How I did it

How to verify it

Which release branch to backport (provide reason below if selected)

  • 201811
  • 201911
  • 202006
  • 202012
  • 202106
  • 202111
  • 202205

Description for the changelog

Link to config_db schema for YANG module changes

A picture of a cute animal (not mandatory but encouraged)

vivekrnv added 5 commits July 20, 2022 06:48
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
@stephenxs
Copy link

stephenxs commented Jul 21, 2022

don't suggest exposing this Egress Mirroring: Disabled to the description as this is Mellanox's internal logic.
Over Subscribe Ratio: 1:8 this is provided by customer, right?

@vivekrnv
Copy link
Owner Author

don't suggest exposing this Egress Mirroring: Disabled to the description as this is Mellanox's internal logic.
Over Subscribe Ratio: 1:8 this is provided by customer, right?

Yeah

@@ -0,0 +1,41 @@
##
Copy link

@stephenxs stephenxs Jul 21, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the numbers are correct but we do not need the numbers for speed 200000 since there is no 200G port on this SKU.

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the numbers are correct but we do not need the numbers for speed 200000 since there is no 200G port on this SKU.

customer asked us to add it. Maybe for future use.

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

let's keep it then. 200G for 4x ports right?

Copy link
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah

Comment on lines 24 to 27
{% set ingress_lossless_pool_size = '36405216' %}
{% set ingress_lossless_pool_xoff = '11567088' %}
{% set egress_lossless_pool_size = '60817392' %}
{% set egress_lossy_pool_size = '36405216' %}

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As a convention, we round down by cell size for egress_lossless_pool only. For the rest sizes, we do not round them down.

Suggested change
{% set ingress_lossless_pool_size = '36405216' %}
{% set ingress_lossless_pool_xoff = '11567088' %}
{% set egress_lossless_pool_size = '60817392' %}
{% set egress_lossy_pool_size = '36405216' %}
{% set ingress_lossless_pool_size = '36405248' %}
{% set ingress_lossless_pool_xoff = '11567104' %}
{% set egress_lossless_pool_size = '60817392' %}
{% set egress_lossy_pool_size = '36405248' %}

Copy link
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated

@stephenxs
Copy link

don't suggest exposing this Egress Mirroring: Disabled to the description as this is Mellanox's internal logic. Over Subscribe Ratio: 1:8 this is provided by customer, right?

Just to double check, they do not use features like everflow, etc, right

@vivekrnv
Copy link
Owner Author

don't suggest exposing this Egress Mirroring: Disabled to the description as this is Mellanox's internal logic. Over Subscribe Ratio: 1:8 this is provided by customer, right?

Just to double check, they do not use features like everflow, etc, right

I think no. But Assaf, Can you confirm?

@assafho
Copy link

assafho commented Jul 21, 2022

don't suggest exposing this Egress Mirroring: Disabled to the description as this is Mellanox's internal logic. Over Subscribe Ratio: 1:8 this is provided by customer, right?

Just to double check, they do not use features like everflow, etc, right

I think no. But Assaf, Can you confirm?

Yes, customer asked for ratio of 1:8. Regarding everflow, i guess not, but its not part of hwsku questions.

@stephenxs
Copy link

don't suggest exposing this Egress Mirroring: Disabled to the description as this is Mellanox's internal logic. Over Subscribe Ratio: 1:8 this is provided by customer, right?

Just to double check, they do not use features like everflow, etc, right

I think no. But Assaf, Can you confirm?

Yes, customer asked for ratio of 1:8. Regarding everflow, i guess not, but its not part of hwsku questions.

Thanks @assafho . Better to know it. this is something we missed in hwsku questions.

Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
@vivekrnv
Copy link
Owner Author

@stephenxs, Apart from clarification on mirroring, is anything left for buffers?

@stephenxs
Copy link

@stephenxs, Apart from clarification on mirroring, is anything left for buffers?

No. all the rest LGTM.

vivekrnv added 2 commits July 22, 2022 10:22
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
@vivekrnv
Copy link
Owner Author

Mirroring is required and updated buffer defaults

@@ -0,0 +1,4 @@
SAI_VXLAN_SRCPORT_RANGE_ENABLE=1
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why do we need SAI_VXLAN_SRCPORT_RANGE_ENABLE? I believe this is removed in latest branches. Please check

Copy link
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, it was removed. Will update

Copy link
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated

<module>17</module>
<breakout-modes>3</breakout-modes>
<port-speed>1536</port-speed>
<split>4</split></port-info>
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The split and closing port info are not properly aligned. Can you please align?

Copy link
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated

vivekrnv added 2 commits July 25, 2022 17:31
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
@vivekrnv vivekrnv closed this Jul 28, 2022
vivekrnv pushed a commit that referenced this pull request Aug 10, 2022
Changes:

Update submodule branch to 202012
[sonic-linkmgrd][202012] submodule update

a8ddff5 Jing Zhang Fri Feb 25 11:38:28 2022 Incrementing tolerance on mux state inconsistency (#27)
a3f78a3 Jing Zhang Thu Feb 17 17:23:56 2022 Update log level for mux probing and mux state chance (#23)
05156fb Jing Zhang Thu Feb 17 17:21:01 2022 Handle xcvrd crashing scenarios (#22)
74529ef Longxiang Lyu Mon Feb 14 13:26:07 2022 [make] Enable make extra includes (#24)

sign-off: Jing Zhang zhangjing@microsoft.com
vivekrnv added a commit that referenced this pull request Mar 18, 2024
Signed-off-by: Vivek Reddy Karri <vkarri@nvidia.com>
Co-authored-by: Vivek Reddy Karri <vkarri@nvidia.com>
vivekrnv pushed a commit that referenced this pull request Dec 24, 2024
…sonic-net#21269)

#### Why I did it
src/dhcpmon
```
* e003522 - (HEAD -> master, origin/master, origin/HEAD) [Build] Update to buijld bookworm debian package (#24) (21 hours ago) [Yaqiang Zhu]
```
#### How I did it
#### How to verify it
#### Description for the changelog
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants