PeerCache2018-11-29T13:18:22+00:00

PeerCache – Overview

HPC
Scale Out

Application
Acceleration

Keep Existing
Enterprise Storage

Hybrid Cloud
Bursting

Data
Logging & Search

Storage
Reduction

High Performance Computing Scale Out IO

Extreme File Performance

IC Manage PeerCache helps deliver HPC scale out with  extreme file performance through peer-to-peer caching.

The lines between file I/O and memory I/O are blurring. PeerCache uses NVME, but instead of building NVMe-based file system, it make your local filesystem look like a cache.

Further, it provides a shared storage model for that cache using a peer-to-peer network, enabling high-performance compute in the cloud. By using peer-to-peer between multiple readers and writers, we can now do everything in parallel.

Most filesystems today are serialized. The alternative parallel filesystems that are often used in HPC compute have been been optimized for a high concurrent I/O workload.

PeerCache uses flash as cache, not storage, resulting in extreme file performance with only 1 to 2 terabytes of NVME per node.

.

Advantages of IC Manage PeerCache HPC Scale Out IO

HPC
Scale Out IO

.

PeerCache utilizing a peer-to-peer cache fabric to deliver high-performance computing I/O. It is scaled out simply by adding additional peers.

You simply run additional PeerCache peer nodes as part of your cloud auto-scale groups. It ensures consistent low latency and high bandwidth parallel performance, eliminating traditional storage bottlenecks. As your needs evolve, you can expand to 1000s of nodes .

PeerCache behaves like your NFS filer, with the same high resiliency, but with full horizontal scaling.  It runs RAFT distributed consensus between databases, so that if one unit fails, the coherency is still maintained.

The scale out architecture allows additional peers to be added in the cloud or at your remote site into your infrastructure, giving you a fully elastic cache fabric to go with your elastic compute. Because it is file based, PeerCache works with all applications in any domain.

See HPC Scale Out IO video >>

Application
Acceleration

.

PeerCache speeds up your application tool I/O by 10x. It does this by creating a peer-to-peer flash cache network from the flash in your existing compute farm, typically using only 500 GB to 1 TB per node. All nodes in the compute grid then share the local data– both bare metal and virtual machines.

By using P2P networking, PeerCache gives teams close to the 1 GB+/sec speed of direct attached storage, removing the NFS I/O bottleneck. It particularly impacts non-CPU bound jobs and interactive applications.

Keep Existing
Enterprise
Storage

.

PeerCache is 100% software, and will plug-and-play into existing flows.

PeerCache takes your existing compute farm and gives you smart grid computing by sharing the flash storage.  The authoritative data is still saved to your filer, preserving your existing reliability, uptime, backup and disaster recovery.

It offers cloud bursting and cloud caching, and abstracts any file-based database, such as MySQL and Apache.

PeerCache presents a regular file system interface, working all your EDA tools, from physical design to RTL simulation regressions.

Hybrid
Cloud
Bursting

.

By using PeerCache to deliver hybrid cloud bursting, development teams can quickly extend their existing on-premise compute to burst into the cloud for elastic compute power. Your on-premise workflows will run identically in the cloud, without the need for  retooling, and the workflow is then moved back to your on-premises servers until the next time you have a peak load.

Finally, you also reduce your costs with PeerCache, as it enables the absolute minimum data transfer between on-premise and the cloud and back. It’s cache fabric also reduces your cloud storage requirements, as well as on-premise discussed above.

By using PeerCache to deliver hybrid cloud bursting, design and verification teams can extend their existing on-premise compute to burst into the cloud for elastic compute power – in a matter of minutes. Your on-premise workflows will run identically in the cloud, without the need for  retooling, and the workflow is then moved back to your on-premises servers until the next time you have a peak load.

Finally, you also reduce your costs with PeerCache, as it enables the absolute minimum data transfer between on-premise and the cloud and back. It’s cache fabric also reduces your cloud storage requirements, as well as on-premise discussed above.

Learn more on PeerCache for Hybrid Cloud Bursting >>

Data Logging
& Elastic
Search

.

Audit Logs with File Data and  Metadata — Detailed design and verification information is automatically logged for all your data — both managed and unmanaged — as part of the meta-data translation described in the virtual workspace section.  Audit logs are generated for all operations on every file. Built-in data anonymization separates the analytics data from the individual users, requiring that certain protocols occur before the data-user link can be accessed.

Search queries on File History — PeerCache interfaces to the Elasticsearch open source engine for fast search queries on the large volume of log data.  You can identify which changes were made to every file, and drill down  to explore in detail.

Big Data Analytics — You can link the data to IC Manage Envision for big data analytics based on the activity generated by a project over time. Your search data is also available to any other big data analytics and visualization tools you may have.

Storage
Reduction

PeerCache allows you to dramatically reduce your expensive NFS filer storage disk space, by eliminating the unnecessary duplication of physical copies on the filer, which contain both the common data and the meta data in each copy. PeerCache separates the common file content from the descriptive file metadata containing the file name, size, owner, group, mask, and times of creation, access and modification. Only the metadata changes and per-workspace changes require additional storage; once either of those changes are checked into the filer, the space is freed up on  PeerCache’s P2P caching networks.

With PeerCache’s Zero-Time Sync,  you can immediately access your work files — making copies takes only seconds or minutes, vs hours.

PeerCache also dramatically reduces storage requirements for cloud storage. The shared peer caches eliminate duplicate storage because the copies are in PeerCache’s “cache fabric” rather than in your cloud back-end storage or your on-premise storage.  You no longer pay  for data copies in the cloud, including those that are never used —  a number that would only grow over time.

.

.