Network downtime has always had a big impact on business and revenue. But with an increase in the number of mission-critical workloads running on denser and faster datacenter infrastructures, businesses today stand to lose more than in the past.
Challenges with legacy telemetry
The sheer volume and variety of data over a typical network is growing all the time, creating a complex and noisy environment. Increases in network speeds also mean an increase in data that must be analyzed in shorter periods of time. Traditional network monitoring approaches and tools use a central collector for telemetry data. These traditional approaches present a growing challenge to the transportation, processing, and storage of telemetry data as even a small network can generate petabytes of data per day.
The network itself contains a wealth of information that can be used for smart decisions and to determine root-cause in the presence of a problem. So why can’t the ethernet switch -- which has visibility to each data packet that crosses the network -- be used to gather telemetry? The difficulty is that, in general, commodity ethernet switches can’t provide the critical telemetry data needed for root cause problem identification or issue resolution. This forces network administrators to process massive amounts of telemetry data centrally, creating an artificial bottleneck to problem resolution.
What just happened (WJH) telemetry
Imagine having easy access to all the information you need to avoid potential network and service disruptions before they happen. HPE M-series ethernet switches have the capability of providing rich, contextual and actionable insights on a variety of data. This includes layer-1 through layer-4, ACLs and buffer occupancy. Powerful agents collect and store network events to provide visibility and insights for critical questions in problem solving, answering who, what, when, why and where queries. We call this ‘What just happened’ and it is now available on every M-series switch platform that is running any network operating system, and can be integrated and extended with third party and open-source tools.
An improvement over traditional streaming and in-band network telemetry, WJH skips over much of the time-consuming data collection and manual sifting for network problems. With WJH, traffic inspection, filtering, and issue identification are done by the switch where the network context is readily available. As a result, relevant issue-related data is captured. For example, when packets are dropped, WJH implements the appropriate drop counter, as well as capturing the relevant header data from the packet so a more thorough analysis can be performed. With all of the relevant data at your fingertips, WJH helps network administrators to dramatically reduce meantime to issue resolution. Additionally, this information can also be used to provide insights to help improve resource utilization and capacity planning.
How does it work?
What Just Happened is an advanced streaming telemetry technology that provides real-time visibility into network-based problems. What Just Happened goes beyond conventional telemetry solutions by providing actionable details on abnormal network behavior. Traditional solutions try to extrapolate the root cause of network issues by simply analyzing network counters and statistical packet sampling. What WJH eliminates the guess-work from network troubleshooting by leveraging the unique hardware capabilities built into the M-series switch ASICs to inspect packets at multi-terabyte speeds. WJH inspects packets across all ports at line-rate and at-speeds.
For storage administrators, troubleshooting network and SAN issues has always been a challenge. The combination of WJH and HPE Network Orchestrator enhances HPE M-series solutions and simplifies SAN management and troubleshooting by providing advanced diagnostics that help keep everything running smoothly without performance degradation. With WJH, one can solve problems and easily debug severe network issues in minutes.
Summary
The HPE M-series ethernet switch family delivers the highest levels of performance at all the relevant speeds, including 1, 10, 25, 40, 50 and 100Gb/s. They have the lowest latency of any mainstream switch, featuring zero packet loss (no avoidable packet loss, for example due to traffic microbursts), and delivering that performance fairly and consistently across any packet size, mix of port speeds, or combination of ports.
Traditional network visibility methods fall short as datacenters adopt 25G, 50G and 100G ethernet speeds. What Just Happened provides an extensible and actionable telemetry that can help operators dramatically reduce mean-time to issue resolution, and improve infrastructure uptimes at even higher data rates. WJH leverages M-series Spectrum silicon level capabilities to provide granular, contextual and actionable telemetry information on datacenter networks.
What Just Happened can directly be used on the switch platforms via CLI. Alternatively, the WJH functionality is also available through a Web UI.
Storage Experts
Hewlett Packard Enterprise
twitter.com/HPE_Storage
linkedin.com/showcase/hpestorage/
hpe.com/storage
For more information, please check out the following:
Blogs
- Accelerating hyperconvergence with end-to-end 25GbE storage fabrics
- Driving data center transformation and innovation for AI, Machine Learning and Data Analytics
- HPE expands M-series offering with hight performance SN3000 series Ethernet Switch Family launch
- Game changer: HPE expands StoreFabric M-series Ethernet switch portfolio
- Enable high-performance Ethernet storage through StoreFabric M-series Ethernet switch family
White papers
Video
- HPE StoreFabric M-series Ethernet Switch Family
- NVMe over Ethernet Fabrics with HPE M-series Switch
- Resilient RoCE Enabled over Ethernet on HPE StorFabric M-series Switches
TekTalk webinars
Web
- HPE Storage Networking
- Quickspecs SN3000 (SN3700)
- Quickspecs SN2000 (SN2010, SN2100, SN2410, SN2700)
StorageExperts
Our team of Hewlett Packard Enterprise storage experts helps you dive deep into relevant data storage and data protection topics.
