Why Zettar

Move a petabyte in 29 hours.

The fastest, petascale-proven, turnkey data mover — 10× typical commercial and freeware tools, wire speed the day it's racked. We don't sell AI. We move the data that powers it.

The difference

Fastest, petascale-proven, turnkey — at a lower TCO

Fastest

Never the bottleneck

Zettar moves data at the full speed your network and storage allow — using nearly all the bandwidth you have, sustained from first byte to last, not a peak.

Moving a petabyte for the U.S. DOE, it was capped at 80 Gbps to spare the shared network and still finished in 29 hours — on a full 100 Gbps link, that's a petabyte a day. Your infrastructure sets the ceiling; Zettar reaches it.

Petascale-proven

1 PB in 29 hours, 96% utilization

Proven at petabyte scale, on real networks.

With SLAC, ESnet, and the U.S. DOE, Zettar moved an actual petabyte over a 5,000-mile 100 Gbps loop in 29 hours at 96% bandwidth utilization — encrypted and checksummed. Winner, Supercomputing Asia 2019 Data Mover Challenge. Read the record → See the paper → Data Mover Challenge release →

Read the research →

Turnkey

Wire speed on day one

No integration project. No tuning team.

Pretuned and system-engineered — every component selected and matched to zx. The Core Appliance is built on the HPE ProLiant DL380 Gen 12.

Lower TCO

Lower total cost of ownership

Faster teams and freed-up engineers — 75% lower TCO in one replication deployment (case study).

HPE ProLiant enterprise servers with no proprietary lock-in — and none of the cost of a months-long DIY transfer project.

How it actually works

The network isn't the bottleneck — the whole path is.

Once a fast link is in place, throughput is set by storage I/O, the host, and the software — not the wire. Zettar co-designs all three, so a fast link actually delivers.

Co-design

Software, host, and hardware as one system

A fast link only pays off when everything behind it keeps up.

The data mover, tuned Linux host, and hardware are engineered together — no DIY tuning. CUBIC default congestion control is sufficient; packet loss stays negligible on R&E backbones.

Concurrency

Massive parallelism fills the pipe

A single stream can't fill a high-speed link — not even close.

zx moves data with many concurrent streams across cores and nodes at once, so the link runs full instead of half-empty — and throughput scales out as you add nodes.

Burst buffers

NVMe staging that keeps the link fed

A burst buffer absorbs slow storage so it doesn't throttle the WAN.

A high-speed NVMe burst buffer stages data between production storage and the WAN, keeping the link fed end to end.

Latency-insensitive

Distance barely matters

Move data across the building or across the planet at near line rate.

Validated across 10–100 ms paths, with real transfers spanning 5,000 and 12,375 miles.

Built for production

Fast is the start. Production-ready is the bar.

Speed only counts when every byte arrives intact, the pipeline keeps running, and it slots into the systems you already operate.

Data integrity & security

Verified every time

Trust what landed — no silent corruption, no clear-text exposure.

Unconditional end-to-end checksums plus TLS encryption verify and protect every transfer.

Enterprise resilience

Keeps moving under load

Pipelines that survive failures and busy windows.

Built-in high availability, load balancing, and scheduling keep data flowing around the clock.

Automation

Wire it into your data services

Make movement a service your platform calls, not a manual step.

RESTful APIs and an SDK let you script and embed zx directly into your workflows.

Less complexity

One validated system

Skip the months-long DIY tuning project.

One system-engineered appliance replaces a custom build across firewalls and heterogeneous hardware.

vs the alternatives

Why teams move with Zettar instead

  • rsync / scp — single-stream and serial by design, never built for petascale; throughput collapses long before your network is full. Zettar vs rsync →
  • Globus — grid-era orchestration that leaves throughput to the endpoints you tune; ESnet measured zx at 2×–7× Globus GridFTP on its DTNs. Zettar vs Globus →
  • Aspera / Signiant — closed, proprietary software with usage-based licensing. Zettar vs Aspera →
  • DIY on commodity servers — months of hand-tuning across firewalls and heterogeneous hardware, and the result rarely reaches wire speed.
CapabilityZettar zxrsync / scpGlobusAspera / SigniantDIY build
Linear scale-out across nodes✓—Partial—Partial
Turnkey, pretuned appliance✓————
End-to-end checksums + TLS✓Partial✓✓Partial
No proprietary lock-in✓✓Partial—✓
Build your business case

Put a number on it — and make your case.

FAQ

Common questions

Why not just use rsync, Globus, or Aspera?

Those tools were not built for petascale. zx is roughly 10× faster, unifies file, object, and streaming in one stack, and is petascale-proven and turnkey — one validated appliance instead of a months-long DIY tuning project or closed, proprietary software you still have to size, host, and tune.

Isn't the network the bottleneck, not the data mover?

Once a fast link is in place, the bottleneck is no longer the network — it is storage I/O, host architecture, and software design. zx is co-designed across the whole path, using NVMe burst buffers for staging and host-level optimization to reach line rate where general-purpose tools stall at a fraction of it.

How do we know it works at scale, not just in a benchmark?

It is proven at petascale on real networks, not a lab demo: 1 PB moved in 29 hours at 96% link utilization with SLAC (U.S. DOE) and ESnet, and winner of the Supercomputing Asia 2019 Data Mover Challenge. For more, see Fang et al., arXiv:2512.15028 (CC BY 4.0).

Will Zettar lock us in?

No. zx moves data in native file and object formats with no proprietary wrappers, so nothing is trapped. The appliance runs on HPE ProLiant enterprise servers — standard, well-supported hardware rather than a closed, proprietary box.

What does it cost compared with a DIY transfer stack?

Lower total cost of ownership: no months-long tuning project to staff, standard enterprise servers instead of a closed, proprietary stack, and far less ongoing engineering time — your team runs it without becoming data-transfer specialists. And it delivers results a DIY stack rarely matches.

Get started

See why teams move with Zettar.

Fastest, petascale-proven, turnkey, and co-designed — built on HPE ProLiant enterprise servers that scale out across nodes. Let us show you wire-speed data movement on your workload.