DOCA Management Service Guide
This guide provides instructions on how to use the DOCA Management Service on top of NVIDIA® BlueField® networking platform or NVIDIA® ConnectX® SmartNICs.
DOCA DMS service is currently supported at the alpha level. Exercise caution when running dmsd
over an external interface, as it may pose security risks. Apply appropriate mitigations and restrict access to the DMS accordingly. Use at your own risk.
DOCA Management Service (DMS) is a centralized solution for configuring and operating NVIDIA® BlueField® and ConnectX® devices.
DMS consolidates NVIDIA’s internal scripts and tools under a streamlined, industry-standard API based on OpenConfig. Users can configure BlueField or ConnectX devices either locally (via SSH) or remotely (via gRPC).
DMS exposes configurable parameters for BlueField and ConnectX over the external interface, enabling automated configuration from a management station. The interface offers a consistent and unified approach to device configuration while abstracting away the underlying tools used to manage individual features.
DMS follows a client-server architecture. The server component, DMS Daemon (dmsd
), is responsible for resource discovery and for processing incoming commands from clients. These clients can be either the provided DMS Client (dmsc
) or a custom-built client using the same API.
Open Config and YANG Models
OpenConfig is a standard that defines and implements a common, vendor-independent software layer for managing and monitoring network devices.
It utilizes YANG data models to represent device configurations and operational states in a consistent and standardized format.
Most gNMI/gNOI protocols used in DMS are aligned with the OpenConfig community and rely on the gRPC protocol for command transmission.
YANG (Yet Another Next Generation) is a data modeling language used to describe the structure and content of network configuration and state data.
It represents data hierarchically, similar to an XML tree, and defines schemas for configuration, operational state, and remote procedure calls (RPCs). YANG models serve as the foundation for implementing the OpenConfig standard.
The DOCA YANG model is currently experimental.
The gNMI Subscribe mechanism for streaming telemetry is not yet supported
DMS can run either on the host machine where BlueField or ConnectX devices are installed, or directly on the BlueField Arm cores when operating in DPU mode .
To operate the DMS, DOCA must be installed on the system where DMS will run.
DMS on Host – The DOCA for Host package must be installed on the host system. It should be installed using either the
doca-networking
ordoca-all
profile.DMS on DPU (BlueField Arm) – A compatible DOCA image must be installed on the BlueField Arm processor.
Consult the DOCA Installation Guide for Linux to correctly set up the required DOCA components prior to deploying DMS.
Supported operating systems are Linux-based environments.
DMS has 3 major components:
DMSD – Server – DMS server can run on the BlueField ARM or on the host with an NVIDIA PCIe device
DMSC – Client – DOCA provided OpenConfig client. Customers can choose to use this client, any other open-source client, or develop their own (gRPC-based) client.
Yang files – Yang model files contain the data model used to configure the device, using NVIDIA-specific extension to common OpenConfig YANG Models.
OpenConfig consists of 2 main protocols:
gNMI – gRPC Network Management Interface, protocol to configure of network device.
gNOI – gRPC Network Operations Interface, a protocol to perform operational commands on network devices (i.e., provision, upgrade, reboot).
Service Connectivity
The following is an architectural diagram of DMS:

The following diagram presents the DMS modes of operation, as the DMS client can operate from different location:
Both DMS client and server components are deployed on the Host.
Both DMS client and server components are deployed on DPU (BlueField Arm).
DMS server component is deployed on the Host, while DMS client is deployed remotely (connecting to DMS server over management network).
DMS server component is deployed on DPU (BlueField Arm), while DMS client is deployed remotely (connecting to DMS server over management network).

DMS Daemon Launch Options
Option 1: SystemD Service (Recommended)
On the DPU, the DMS Daemon (dmsd
) runs as a systemd
service and comes pre-installed with the BlueField BFB-Bundle.
It should be running locally by default as a systemd
service, bound to localhost:9339
.
To check if
dmsd
is running:ps -ef | grep dms
To manage the service:
sudo systemctl status dmsd sudo systemctl start dmsd sudo systemctl stop dmsd
To interact with
dmsd
using the built-in client (requires user-password authentication; the default is the OS root password):dmscli
A template
systemd
service file is included in the DOCA package:/opt/mellanox/doca/services/dms/dmsd.service/dmsd.service
Notedmsd
runs automatically as asystemd
service only on the DPU, not on the host.
Option 2: Manual Launch
You can start the dmsd
daemon manually with a variety of authentication methods.
Localhost with username/password:
/opt/mellanox/doca/services/dms/dmsd \ --bind_address localhost:
9339
\ --auth credentials \ --username my_username \ --password my_passwordRemote host with shadow file:
/opt/mellanox/doca/services/dms/dmsd \ --bind_address <ip>:<port> \ --auth shadow \ --username my_username \ --shadow /etc/shadow
TLS certificate-based authentication:
/opt/mellanox/doca/services/dms/dmsd \ --bind_address localhost:
9339
\ --auth cert \ --ca <ca.pem> \ --tls_key_file <key.pem> \ --tls_cert_file <cert.pem>Specific PCIe device (for a host with multiple DPUs):
/opt/mellanox/doca/services/dms/dmsd \ --bind_address localhost:
9339
\ --auth credentials \ --username my_username \ --password my_password \ --target_pci0000
:08
:00
Provide a list of PCIe devices (for a host with multiple DPUs):
/opt/mellanox/doca/services/dms/dmsd \ --bind_address localhost:
9339
\ --auth credentials \ --username my_username \ --password my_password \ --target_pci0000
:08
:00
,0000
:09
:00
DMS Server Flags
To see the full list of flags, use the help flag (i.e., dmsd --help
, dmsd -h
).
General Flags
--bind_address <string>
– Bind to<address>:<port>
or just:<port>
(default is:9339
). Can be localhost for the local use case, or an IP address for the remote use case.-v <value>
– log level for V logs--target_pci <string>
– One or multiple target PCIe addresses (i.e.,0000:03:00, 0000:03:00,0000:04:00
). Auto-select if only one NVIDIA network device is present; otherwise, one or more PCIe addresses must be specified.
Provisioning Flags
--image_folder <string>
– Specify the image install folder. Can copy images directly to the folder to avoid transfer over the net. Default create folder:/tmp/dms
.--chunk_size_ack <uint>
– The chunk size of the image to respond with a transfer response in bytes (default: 12000000)--exec_timeout <uint>
– The maximum execution timeout in seconds for a command if not responding (not printing tostdout
); 0 (default) is unlimited
Config Flags
--init_config <string>
– File containing gNMI requests to run on DMS start. By default, DMS adds any gNMI set request to a file (file format is req.json).
Authentication Method Flags
The --auth <string>
flag specifies one of the following three authentication methods, each with its own set of required flags:
Shadow
Zero-touch setup – no need to create a dedicated DMS user (reuses existing OS user)
The server reads the hashed password from the shadow file in real time for each client request
Required flags:
--username <string>
and--shadow <string>
Example:
--auth shadow --username root --shadow /etc/shadow
To disable authentication:
--noauth
Credentials
Requires the admin to define a strong password.
Required flags:
--username <string>
and optionally--password <string>
Example:
--auth credentials --username root --password
123456
To prompt for password input interactively at startup, leave the
--password
flag empty.To disable authentication:
--noauth
Certificate (TLS)
The most secure option, using Transport Layer Security (TLS) for both encryption and mutual authentication.
Authentication is based on digital certificates, ensuring only trusted clients can connect.
Required flags:
--auth cert
--ca <path/to/ca.crt>
--tls_key_file <path/to/target.key>
--tls_cert_file <path/to/target.crt>
Example:
--auth cert --ca /path/to/certs/ca.crt --tls_key_file /path/to/certs/target.key --tls_cert_file /path/to/certs/target.crt
To disable TLS:
--tls_enabled=
false
Security Flags
TLS Encryption and Authentication
DMS uses TLS (Transport Layer Security) by default to secure communication. TLS is a widely adopted cryptographic protocol that provides the following guarantees:
Encryption – Protects transmitted data from eavesdropping.
Authentication – Verifies the identity of the server and optionally the client via digital certificates.
Integrity – Ensures transmitted data is not tampered with.
TLS relies on a public/private key pair and a digital certificate issued by a Certificate Authority (CA). These elements ensure secure, authenticated communication.
DMS supports TLS for both gNMI and gNOI interfaces, and works with either self-signed or CA-signed certificates.
To enable TLS, both server and client must provide:
--ca <string>
– Path to the CA certificate used to validate the remote party’s certificate.--tls_cert_file <string>
– Path to the public certificate presented during the TLS handshake.--tls_key_file <string>
– Path to the corresponding private key used to sign the handshake and decrypt messages.NoteThe private key must be protected. If compromised, it can be used to impersonate the server or client.
TLS Communication Modes
Mutual TLS Authentication (mTLS)
Both the server and client present certificates and verify each other during the TLS handshake.
# Server:
/opt/mellanox/doca/services/dms/dmsd <flags> --auth cert \
--ca /path/to/certs/client_ca.crt \
--tls_cert_file /path/to/certs/target.crt \
--tls_key_file /path/to/certs/target.key
# Client:
/opt/mellanox/doca/services/dms/dmsc <flags> \
--tls-ca /path/to/certs/target_ca.crt \
--tls-cert /path/to/certs/client.crt \
--tls-key /path/to/certs/client.key <command>
Highlights:
Provides the highest level of security.
Ensures both sides are authenticated and trusted.
All traffic is encrypted.
TLS (Server Authentication Only)
Only the server presents its certificate during the handshake. The client verifies the server but does not present a certificate.
# Server:
/opt/mellanox/doca/services/dms/dmsd <flags> --auth cert \
--tls_cert_file /path/to/certs/target.crt \
--tls_key_file /path/to/certs/target.key
# Client:
/opt/mellanox/doca/services/dms/dmsc <flags> \
--tls-ca /path/to/certs/target_ca.crt \
--skip-verify <command>
Highlights:
Client authenticity is not verified.
Use
--skip-verify
if a root CA is not provided.Traffic remains encrypted.
Insecure Mode (No TLS)
TLS is disabled entirely on both server and client. No encryption or authentication is performed.
# Server:
/opt/mellanox/doca/services/dms/dmsd <flags> --auth cert --tls_enabled=false
# Client:
/opt/mellanox/doca/services/dms/dmsc <flags> --insecure <command>
To achieve insecure communication (no encryption), configure:
Server – use
--tls_enabled=false
paramClient – use
--insecure
flag'
Highlights:
Not recommended for production.
Use only in fully isolated, trusted environments for testing or development.
To see the full list of flags, use the help flag (i.e., dmsc --help
, dmsc -h
).
DMS Client Flags
General Flags
--address <string>
– Bind to<address>:<port>
or just:<port>
(default is:9339
). Can be localhost for the local use case, or an IP address for the remote use case.--target <string>
– Target PCIe address to interact with. Mandatory if the server is running for multiple PCIe addresses.-d, --debug
– Debug mode.
Authentication Flags
-u, --username <string>
– username.-p, --password <string>
– password.
Security Flags
--tls-ca <string>
– path to server CA certificate.--tls-key <string>
– path to the client TLS private key.--tls-cert <string>
– path to the client TLS certificate, containing the public key.--skip-verify
– tells the client to skip verifying the server's certificate during the TLS handshake. TLS is enabled, and the connection is encrypted.--insecure
– Disable TLS. The client connects over plain TCP, with no encryption or authentication.
gNMI Command
gNMI (gRPC Network Management Interface) is a standardized network management protocol to configure and monitor network devices via gRPC and Protocol Buffers. It enables interaction with devices using models such as OpenConfig.
Core gNMI commands:
Get – Retrieves device data (e.g., operational state, configuration).
Set – Modifies device configuration.
Capabilities – Queries the device’s capabilities (e.g., supported models, versions, encodings).
Subscribe – Streams data from the device to the client.
NoteDMS currently does not support the Subscribe command.
In DMSC, the gNMI functionality is powered by the GNMIC project. For additional details, refer to the GNMIC documentation.
Prompt mode with autocomplete can be invoked using the prompt
command. To access it, run dmscli
and authenticate with the dmsd
user password (by default, the root OS password).
Get Request
Get requests happen in real-time without a cache. Get command requires providing the YANG Xpath as described in the following:
/opt/mellanox/doca/services/dms/dmsc <flags> get --path /interfaces/interface[name=p0]/config/mtu
[
{
"source"
: "localhost:9339"
,
"timestamp"
: 1712485149723248511,
"time"
: "2024-04-07T10:19:09.723248511Z"
,
"updates"
: [
{
"Path"
: "interfaces/interface[name=p0]/config/mtu"
,
"values"
: {
"interfaces/interface/config/mtu"
: "1500"
}
}
]
}
]
To insert params in the path, as an indication of the interface name (p0).
Get request also work on subtree (subPath) as follows:
/opt/mellanox/doca/services/dms/dmsc <flags> get --path /nvidia/roce
[
{
"source"
: "127.0.0.1:9339"
,
"timestamp"
: 1728471432988295603,
"time"
: "2024-10-09T13:57:12.988295603+03:00"
,
"updates"
: [
{
"Path"
: "nvidia/roce"
,
"values"
: {
"nvidia/roce"
: {
"config"
: {
"adaptive-routing"
: "false"
,
"multipath-dscp"
: "MULTIPATH_DSCP_DEFAULT"
,
"tx-sched-locality-mode"
: "TX_SCHED_LOCALITY_ACCUMULATIVE"
}
}
}
}
]
}
]
Failing to provide a mandatory parameter for decoding a leaf leads to that leaf being skipped. The entire request fails when the first leaf fails.
Set Request
Set requests happen immediately, invoking tools to configure the OS.
Set commands require providing Yang Xpath as described in the following:
/opt/mellanox/doca/services/dms/dmsc <flags> set
--update /interfaces/interface[name=p0]/config/mtu:::int:::9216
{
"source"
: "localhost:9339"
,
"time"
: "1970-01-01T00:00:00Z"
,
"results"
: [
{
"operation"
: "UPDATE"
,
"path"
: "interfaces/interface[name=p0]/config/mtu"
}
]
}
To insert params in the path, as an indication of the interface name (p0).
The value provided must be separated by value type and char.
Currently, only the --update
flag is supported in Set.
The update of some leaves only takes effect after the system reboot. Refer to gNOI system reboot for information.
It is also possible to invoke a command JSON list:
/opt/mellanox/doca/services/dms/dmsc <flags> set
--request-file
req.json
req.json
example:
{
"updates"
:
[
{
"path"
: "/interfaces/interface[name=p0]/config/mtu"
,
"value"
: 9216
,
"encoding"
: "uint"
},
{
"path"
: "/interfaces/interface[name=p0]/config/enabled"
,
"value"
: true
,
"encoding"
: "bool"
}
]
}
List of DMS Supported Path Entries for Get/Set Commands
To get the list of supported paths for get/set commands, run the following command:
dmsc --file
/opt/mellanox/doca/service/dms/yang path --types --descr
Path | Type | Description |
/interfaces/interface[name=*]/config/enabled | boolean | This leaf contains the configured, desired state of the interface. Systems that implement the IF-MIB use the value of this leaf in the 'running' datastore to set IF-MIB.ifAdminStatus to 'up' or 'down' after an ifEntry has been initialized, as described in RFC 2863. Changes in this leaf in the 'running' datastore are reflected in ifAdminStatus, but if ifAdminStatus is changed over SNMP, this leaf is not affected. |
/interfaces/interface[name=*]/config/mtu | uint16 | Set the maximum transmission unit size in octets for the physical interface. If this is not set, the mtu is set to the operational default -- e.g., 1514 bytes on an Ethernet interface. |
/interfaces/interface[name=*]/config/name | string | The name of the interface. A device MAY restrict the allowed values for this leaf, possibly depending on the type of the interface. For system-controlled interfaces, this leaf is the device-specific name of the interface. The 'config false' list interfaces/interface[name]/state contains the currently existing interfaces on the device. If a client tries to create a configuration for a system-controlled interface that is not present in the corresponding state list, the server MAY reject the request if the implementation does not support pre-provisioning of interfaces or if the name refers to an interface that can never exist in the system. A NETCONF server MUST reply with an rpc-error with the error-tag 'invalid-value' in this case. The IETF model in RFC 7223 provides YANG features for the following (i.e., pre-provisioning and arbitrary names), However they are omitted here: If the device supports pre-provisioning of the interface configuration, the 'pre-provisioning' feature is advertised. If the device allows an arbitrarily named user-controlled interfaces, the 'arbitrary-names' feature is advertised. When a configured user-controlled interface is created by the system, it is instantiated with the same name in the /interfaces/interface[name]/state list. |
/interfaces/interface[name=*]/config/type | identityref | The type of the interface. When an interface entry is created, a server MAY initialize the type leaf with a valid value, e.g., if it is possible to derive the type from the name of the interface. If a client tries to set the type of an interface to a value that can never be used by the system, e.g., if the type is not supported, or if the type does not match the name of the interface, the server MUST reject the request. A NETCONF server MUST reply with an rpc-error with the error-tag 'invalid-value' in this case. |
/interfaces/interface[name=*]/ethernet/nvidia/config/inter-packet-gap | uint8 | Inter packet gap configuration, in 4B unit |
/interfaces/interface[name=*]/ethernet/nvidia/config/rate-limit | uint16 | The percentage of bandwidth, in permile units, to be used on the port. |
/interfaces/interface[name=*]/name | leafref | References the name of the interface |
/interfaces/interface[name=*]/nvidia/cc/config/priority[id=*]/id | leafref | |
/interfaces/interface[name=*]/nvidia/cc/config/priority[id=*]/np_enabled | boolean | Enable CC NP for a given priority on the interface |
/interfaces/interface[name=*]/nvidia/cc/config/priority[id=*]/rp_enabled | boolean | Enable CC RP for a given priority on the interface |
/interfaces/interface[name=*]/nvidia/cc/slot[id=*]/config/counter_enable | boolean | Enable the counter while enabling tha CC algo according to the algo_slot |
/interfaces/interface[name=*]/nvidia/cc/slot[id=*]/config/enabled | boolean | Enable a CC algo slot execution. |
/interfaces/interface[name=*]/nvidia/cc/slot[id=*]/config/id | algo_slot_id | CC algo slot id. |
/interfaces/interface[name=*]/nvidia/cc/slot[id=*]/id | leafref | CC algo slot ID. |
/interfaces/interface[name=*]/nvidia/cc/slot[id=*]/param[id=*]/config/id | algo_param_id | CC algo param id. |
/interfaces/interface[name=*]/nvidia/cc/slot[id=*]/param[id=*]/config/value | algo_param_value | Parameter value within the CC algo slot. |
/interfaces/interface[name=*]/nvidia/cc/slot[id=*]/param[id=*]/id | leafref | Parameter ID within the CC algo slot. |
/interfaces/interface[name=*]/nvidia/qos/config/pfc | boolean | Enables PFC |
/interfaces/interface[name=*]/nvidia/qos/config/priority[id=*]/id | prio | Priority ID. |
/interfaces/interface[name=*]/nvidia/qos/config/trust-mode | identityref | Trust mode for the interface QoS. |
/interfaces/interface[name=*]/nvidia/roce/config/adaptive-retransmission | boolean | Enable adaptive retransmission |
/interfaces/interface[name=*]/nvidia/roce/config/adaptive-routing-force | boolean | Force adaptive routing even if the feature was not negotiated between the requestor and responder. |
/interfaces/interface[name=*]/nvidia/roce/config/rtt-resp-dscp | uint8 | Defines the DSCP fixed value used if mode is set to FIXED. |
/interfaces/interface[name=*]/nvidia/roce/config/rtt-resp-dscp-mode | identityref | Defines the method for setting DSCP in RTT response packets. |
/interfaces/interface[name=*]/nvidia/roce/config/slow-restart | boolean | Enable slow restart when congestion |
/interfaces/interface[name=*]/nvidia/roce/config/slow-restart-idle | boolean | Enable slow restart when idle |
/interfaces/interface[name=*]/nvidia/roce/config/tos | tos | ToS value for RoCE traffic. |
/interfaces/interface[name=*]/nvidia/roce/config/tx-window | boolean | Enable transmission window |
/interfaces/interface[name=*]/state/admin-status | enumeration | The desired state of the interface. In RFC 7223, this leaf has the same read semantics as ifAdminStatus. Here, it reflects the administrative state as set by enabling or disabling the interface. |
/interfaces/interface[name=*]/state/oper-status | enumeration | The current operational state of the interface. This leaf has the same semantics as ifOperStatus. |
/nvidia/cc/config/user-programmable | boolean | Enables user-programmable CC functionality. |
/nvidia/command[run=*]/run | string | The command to run. |
/nvidia/mode/config/mode | identityref | Mode can take one of several predefined values representing operational modes of DPU. |
/nvidia/roce/config/adaptive-routing | boolean | Enable adaptive routing between a requestor and responder. |
/nvidia/roce/config/multipath-dscp | identityref | Multipath on transmit, set the DSCP bit to hold the MP eligible info |
/nvidia/roce/config/tx-sched-locality-mode | identityref | Transmission scheduler adaptation to locality |
gNOI Commands
gNOI (gRPC Network Operations Interface) is a protocol designed for operational tasks, such as installing software, managing certificates, and troubleshooting.
It complements gNMI by focusing on operational and administrative functions.
In DMSc, the gNOI part is powered by GNOIC project, for full docs refer to GNOIC docs.
/opt/mellanox/doca/services/dms/dmsc -a localhost --port 9339 --tls-cert client.crt --tls-key client.key <command
>
Prompt mode with autocomplete options can be invoked using the command prompt
.
All commands are blocked unless specified otherwise.
Currently, gNOI commands are only supported on the host (not the BlueField).
OS
The following subsections present actions for provisioning a new DOCA image (BFB) or firmware on BlueField.
Install
This command transmits the file from the client to the server and authenticates the file's validity:
# Command Format:
/opt/mellanox/doca/services/dms/dmsc <flags> os install
--version <free_text_version> --pkg <bfb|cfg|fw path>
# Install BFB:
/opt/mellanox/doca/services/dms/dmsc <flags> os install
--version 2_9_0 --pkg DOCA_2.9.0_Ubuntu.bfb
# Install cfg:
/opt/mellanox/doca/services/dms/dmsc <flags> os install
--version 0_0_1.cfg --pkg bf.cfg
# Install FW
/opt/mellanox/doca/services/dms/dmsc <flags> os install
--version 24_29_0046.fw --pkg fw-BlueField.bin
The file is saved to the folder specified in the -image_folder
flag (default /tmp/dms
) given to the server. if the file authenticates successfully. The file's extension is autodetected and is written automatically if none
is provided in the --version
field. Users may copy the file to the folder manually and invoke the command with file extension to authenticate the file. No file transfer is initiated if the file already exists in the folder and the version specified with the extension.
Activate
This command deploys the BFB bundle/firmware to the hardware:
/opt/mellanox/doca/services/dms/dmsc <flags> os activate --version 2_9_0 # Invoke all files under 2_9_0 name
/opt/mellanox/doca/services/dms/dmsc <flags> os activate --version "2_9_0.bfb;0_0_1.cfg;24_29_0046.fw"
The --version
flag provides a version to search for in the folder specified by the -image_folder
flag (default /tmp/dms
). If no extension is provided, the command uses all files under the version name.
To activate separate files, use the --version
flag separated by semi-colon.
Deploying the BFB bundle is only supported when running from the host.
After running the command to activate firmware, firmware reset is automatically invoked.
Verify
Verify command retrieves the firmware and BFB bundle version:
/opt/mellanox/doca/services/dms/dmsc <flags> os verify
The return value consists of both versions separated by a semi-colon:
+-----------------+---------------------------------------------------------------+-----------------------------+
| Target Name | Version | Activation Fail Msg |
+-----------------+---------------------------------------------------------------+-----------------------------+
| 127.0.0.1:19999 | FW: 32.42.1000;BFB: bf-bundle-2.8.0-98_24.07-ubuntu-22.04_dev | |
| | | |
+-----------------+---------------------------------------------------------------+-----------------------------+
Currently, the BFB bundle can only be retrieved if it was installed via DMS.
System
The following subsections provide actions for rebooting the BFB bundle/firmware on the BlueField.
Reboot Status
To verify that BFB is rebooting:
/opt/mellanox/doca/services/dms/dmsc <flags> system reboot-status
The value returned is false
if the system is active. It is true
if the system is rebooting. If the status cannot be retrieved, the status appears as a failure and the message field indicates what the issue is.
The flag --reboot_status_check <string>
checks if firmware reboot is needed:
If set to
fast
(default), a quick test occurs but is not accurate (any config can trigger this flag)If set to
strict
, a more accurate test occurs, but it is slower.If set to
none
, then the firmware check is skipped.
Reboot
To reboot the BlueField Arm and firmware:
/opt/mellanox/doca/services/dms/dmsc <flags> system reboot --delay <uint>s --subcomponent <string> --method <string>
This command is non-blocking and returns immediately.
The flag --delay
specifies the time interval to wait before invoking the reset.
The subcomponent and method are optional. By default, the reboot executes with the lowest reset level and type available.
Currently, DMS supports --subcomponent ARM --method <WARM|POWERDOWN>
flags.
Factory-Reset (Alias: Reset)
The following subsection provides an action for performing a factory reset on a target node.
Start
Performs reset operation on each PF on the given target node.
This operation resets the device configurations to their default values:
/opt/mellanox/doca/services/dms/dmsc <flags> factory-reset start
/opt/mellanox/doca/services/dms/dmsc <flags> reset start
Reset to Golden Image (pre-configured, ideal state version) is not supported.
File
The generic interface to perform file operational tasks.
Stat
Returns metadata about files on the target device.
/opt/mellanox/doca/services/dms/dmsc <flags> file
stat --path /path/to/file
/opt/mellanox/doca/services/dms/dmsc <flags> file
stat --path /path/to/dir --recursive
Command output:
+----------------+---------------------+----------------------+------------+------------+------+
| Target Name | Path | LastModified | Perm | Umask | Size |
+----------------+---------------------+----------------------+------------+------------+------+
| 127.0.0.1:9339 | /path/to/dir/file_1 | 2025-04-10T09:05:37Z | -rw-r--r-- | -----w--w- | 0 |
| | /path/to/dir/file_2 | 2025-04-10T09:05:37Z | -rw-r--r-- | -----w--w- | 0 |
+----------------+---------------------+----------------------+------------+------------+------+
Get
Streams the contents of a file from the target device to the client.
To allow this operation, the DMSD server must be started with a list of directories permitted for read access, using the --allow_list_read
flag.
# Server
/opt/mellanox/doca/services/dms/dmsd <flags> --allow_list_read dir1,dir2,dir3
# Client
/opt/mellanox/doca/services/dms/dmsc <flags> file
get --file
/tmp/debug/file_to_get
Put
Streams a file from the client to the target device.
To allow this operation, the DMSD server must be started with a list of directories permitted for write access, using the --allow_list_write
flag.
# Server
/opt/mellanox/doca/services/dms/dmsd <flags> --allow_list_write dir1,dir2,dir3
# Client
/opt/mellanox/doca/services/dms/dmsc <flags> file
put --file
/tmp/debug/file_to_send --dst /tmp/output/path_on_remote_host
Containerz
This deployment model aligns with the DOCA container deployment methodology described in the DOCA Container Deployment Guide .
Containerz enables remote management and monitoring of containers running on the host or DPU. It supports the following backend modes:
Docker Backend - default
In this mode, Containerz interacts with the Docker daemon (dockerd
) running on the host.
Ensure that the Docker daemon is active:
systemctl start docker
Kubelet Backend
In this mode, Containerz uses the Kubelet daemon to manage containers on the BlueField DPU via static pod definitions.
This does not require a full Kubernetes cluster. Instead, static pod manifests placed in /etc/kubelet.d
are automatically handled by the Kubelet.
Add a pod: Create a YAML file in
/etc/kubelet.d
– the pod will be started automatically.Remove a pod: Delete the corresponding YAML file – the pod will be stopped and removed.
This is the default mode for DMSD running by systemd on the DPU.
Kubelet daemon is not running by default on the host (DOCA for host).
This mode is available when DMSD is running on the DPU only.
For DOCA for Host, use the default Docker backend.

To set the container backend mode, use the --container_interface
flag when launching the DMSD server:
/opt/mellanox/doca/services/dms/dmsd <flags> --container_interface <kubelet|docker>
Container Operations
These operations manage the lifecycle, images, and persistent volumes associated with containers.
Container Start
Starts a container using the specified image and tag.
Docker mode – The image must already be available in the local registry.
Kubelet mode – Pass a YAML file that defines the container. The file will be copied to the Kubelet manifest directory, triggering the daemon to start the container.
# Docker mode
/opt/mellanox/doca/services/dms/dmsd <flags> containerz container start --image <image_name>
# Kubelet mode
/opt/mellanox/doca/services/dms/dmsd <flags> containerz container start --image path/to/yaml/file.yaml
Container List
Lists all running containers.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz container list
Container Stop
Stops a running container. The container is preserved and can be restarted later.
Kubelet mode – This deletes the YAML file from the manifest directory, which automatically stops the container.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz container stop --instance <container name>
Container Remove
Stops and removes the specified container.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz container remove --instance <container name>
Image Operations
These commands manage container images—pulling, pushing, listing, and removing them.
Image Pull
Downloads an image from a container registry.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz image pull --image ubuntu
Image Push
Uploads an image (in tar file format) from the client to the device. The image is streamed via gRPC and stored locally.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz image push --file
/path/to/tarfile.tar
Image List
Displays all available container images on the device.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz image list
Image Remove
Deletes a specific image from the device.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz image remove --image ubuntu
Volume Operations
These commands manage persistent storage volumes for containers.
In Kubelet mode, volumes are created under /var/dms/volume
.
Volume Create
Creates a new named volume.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz volume create --name my_volume
Volume Remove
Deletes a specified volume.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz volume remove --name volume_name
Volume list
Lists all named volumes and their mount points.
/opt/mellanox/doca/services/dms/dmsd <flags> containerz volume list