Securing Data in Transit

Questions on Securing Data in Transit Answered

Data in transit provides a large attack surface for bad actors. Keeping data secure from threats and compromise while it’s being transmitted was the topic at our live SNIA Networking Storage Forum (NSF) webcast, Securing Data in Transit. Our presenters, Claudio DeSanti, Ariel Kit, Cesar Obediente, and Brandon Hoff did an excellent job explaining how to mitigate risks.

We had several questions during the live event. Our panel of speakers have been kind enough to answer them here.

Q. Could we control the most important point – identity, that is, the permission of every data transportation must have an identity label, so that we can control anomalies and misbehaviors easily?

A. That is the purpose of every authentication protocol: verify the identity of entities participating in the authentication protocol on the basis of some secret values or certificates associated with the involved entity. This is similar to verifying the identity of a person on the basis of an identity document associated with the person.

Q. What is BGP?

A. BGP stands for Border Gateway Protocol, it is a popular routing protocol commonly used across the Internet but also leveraged by many customers in their environments. BGP is used to exchange routing information and next hop reachability between network devices (routers, switches, firewall, etc.). In order to establish this communication among the neighbors, BGP creates a TCP session in port 179 to maintain and exchange BGP updates.

Q. What are ‘north-south’ and ‘east west’ channels?

A. Traditionally “north-south” is traffic up and down the application or solution “stack” such as from client to/from server, Internet to/from applications, application to/from database, application to/from storage, etc. East-West is between similar nodes–often peers in a distributed application or distributed storage cluster. For example, east-west could include traffic from client to client, between distributed database server nodes, between clustered storage nodes, between hyperconverged infrastructure nodes, etc. 

Q. If I use encryption for data in transit, do I still need a separate encryption solution for data at rest?

A. The encryption of data in transit protects the data as it flows through the network and blocks attack types such as eavesdropping, however, once it arrives to the target the data is decrypted and saved to the storage unencrypted unless data at rest encryption is applied. It is highly recommended to use both for best protection, data at rest protection protects the data in case the storage target is accessed by an attacker. The SNIA NSF did a deep dive on this topic in a separate webcast “Storage Networking Security Series: Protecting Data at Rest.”

Q. Will NVMe-oFÔ use 3 different encryption solutions depending upon whether it’s running over Fibre Channel, RDMA, or IP?

A. When referring to data in transit, the encryption type depends on the network type, hence, for different networks we will use different data-in-motion encryption protocols, nevertheless, they can all be based on Encapsulating Security Protocol (ESP) with same cipher suite and key exchange methods.

Q. Can NVMe-oF over IP already use Transport Layer Security (TLS) for encryption or is this still a work in progress? Is the NVMe-oF spec aware of TLS?

A. NVMe-oF over TCP already supports TLS 1.2. The NVM Express Technical Proposal TP 8011 is adding support for TLS 1.3.

Q. Are there cases where I would want to use both MACsec and IPSec, or use both IPSec and TLS?  Does CloudSec rely on either MACSec or IPSec?

A. Because of the number of cyber-attacks that are currently happening on a daily basis, it is always critical to create a secure environment in order to protect confidentially and integrity of the data. MACsec is enabled in a point-to-point Ethernet link and IPSec could be classified as to be end-to-end (application-to-application or router-to-router). Essentially you could (and should) leverage both technologies to provide the best encryption possible to the application.

These technologies can co-exist with each other without any problem. The same can be said if the application is leveraging TLS. To add an extra layer of security you can implement IPSec, for example site-to-site to IPSec VPN. This is true especially if the communication is leveraging the Internet.

CloudSec, on the other hand, doesn’t rely on MACsec because MACsec is a point-to-point Ethernet Link technology and CloudSec provides the transport and encryption mechanism to support a multi-site encryption communication. This is useful where more than one data center is required to provide an encryption mechanism to protect the confidentially and integrity of the data. The CloudSec session is a point-to-point encryption over Data Center Interconnect on two or more sites. CloudSec key exchange uses BGP to guarantee the correct information gets the delivered to the participating devices.

Q. Does FC-SP-2 require support from both HBAs and switches, or only from the HBAs?

A. For data that moves outside the data center, Fibre Channel Security Protocols (FC-SP-2) for Fibre Channel or IPsec for IP would need to be supported by the switches or routers. No support would be required in the HBA. This is most common use case for FC-SP-2.  Theoretically, if you wanted to support FC-SP-2 inside the secure walls of the data center, you can deploy end-to-end or HBA-to-HBA encryption and you won’t need support in the switches.  Unfortunately, this breaks some switch features since information the switch relies on would be hidden. You could also do link encryption from the HBA-to-the switch, and this would require HBA and switch support.  Unfortunately, there are no commercially available HBAs with FC-SP-2 support today, and if they become available, interoperability will need to be proven. This webcast from the Fibre Channel Industry Association (FCIA) goes into more detail on Fibre Channel security.

Q. Does FC-SP-2 key management require a centralized key management server or is that optional?

A. For switch-to-switch encryption, keys can be managed through a centralized server or manually. Other solutions are available and in production today. For HBAs, in most environments there would be thousands of keys to manage so a centralized key management solution would be required and FC-SP provides 5 different options. Today, there are no supported key management solutions for FC-SP-2 from SUSE, RedHat, VMware, Windows, etc. and there are no commercially available HBAs that support FC-SP-2.

This webcast was part of our Storage Networking Security Webcast Series and they are all available on demand. I encourage you to take a look at the other SNIA educational webcasts from this series:


Leave a Reply

Your email address will not be published. Required fields are marked *