SPECstorage™ Solution 2020_swbuild Result
Copyright © 2016-2024 Standard Performance Evaluation Corporation
|
SPECstorage™ Solution 2020_swbuild ResultCopyright © 2016-2024 Standard Performance Evaluation Corporation |
| WekaIO, Inc. | SPECstorage Solution 2020_swbuild = 5000 Builds |
|---|---|
| Weka - Azure Public Cloud Reference | Overall Response Time = 0.25 msec |
|
|
| Weka - Azure Public Cloud Reference | |
|---|---|
| Tested by | WekaIO, Inc. | Hardware Available | September 2024 | Software Available | September 2024 | Date Tested | October 2024 | License Number | 4553 | Licensee Locations | Campbell, CA USA |
The WEKA Data Platform is purpose-built to seamlessly and sustainably deliver speed, simplicity, and scale that meets the needs of modern enterprises and research organizations without compromise. Its advanced, software-defined architecture supports next-generation workloads in virtually any location with cloud simplicity and on-premises performance.
| Item No | Qty | Type | Vendor | Model/Name | Description |
|---|---|---|---|---|---|
| 1 | 100 | Azure Virtual Machine | Azure | Standard L32s v3 | WEKA storage backends - Azure Standard L32s v3 Virtual Machine (32 vCPUs, 256 GiB memory, 16 Gbps networking, 4 x 1.92TB NVMe) |
| 2 | 64 | Azure Virtual Machine | Azure | Standard E32s v5 | Ubuntu clients with Weka POSIX-compliant file system driver - Azure Standard E32s v5 Virtual Machine (32 vCPUs, 256 GiB memory, 16 Gbps networking) |
| Item No | Component | Type | Name and Version | Description |
|---|---|---|---|---|
| 1 | WekaFS | File System | Version 4.3.5.109-azure | The WEKA filesystem (WekaFS) redefines storage solutions with its software-only approach, WekaFS addresses common storage challenges by removing performance bottlenecks, making it suitable for environments requiring low latency, high performance, and cloud scalability. |
| 2 | Weka Server | Storage OS | Ubuntu 20.04 | Operating System (OS) for 100 storage virtual machines using Azure L32s v3 instances |
| 3 | Clients | Client OS | Ubuntu 20.04 | Operating System (OS) for 64 client virtual machines using Azure E32s v5 instances |
| Component Name | Parameter Name | Value | Description |
|---|---|---|
| Accelerated Networking | Enabled | L32s and E32s virtual machines have 16 Gbps connectivity |
None
| Networking | Parameter Name | Value | Description |
|---|---|---|
| Jumbo Frames | 3900 | Enables Ethernet jumbo frames up to 3900 bytes |
The single filesystem was attached via a single mount per client. Four WEKA front ends (cores) were used on the clients. Note that this system was deployed entirely using WEKA's Terraform Module. You can create a Terraform template from WEKA's Cloud Deployment Manager at https://cloud.weka.io. Clients automount the WekaFS filesystem when the Terraform deployment completes.
None
| Item No | Description | Data Protection | Stable Storage | Qty |
|---|---|---|---|---|
| 1 | Weka Filesystem with 682TB of usable storage | WEKA 16+2 distributed data protection | Local 1.92TB NVMe Disk | 400 |
| Number of Filesystems | 1 | Total Capacity | 682 TB | Filesystem Type | WekaFS |
|---|
Each storage backend has four Azure SSDs attached to it, which are dedicated to the WEKA filesystem created. The storage cluster consisted of 100 storage servers with a single WEKA filesystem created in the cluster. Each client mounted the WEKA filesystem with a single mount.
Three cores assigned to the FE clients, which is specified in the Terraform configuration file.
| Item No | Transport Type | Number of Ports Used | Notes |
|---|---|---|---|
| 1 | 16 Gbps Virtual Nic | 100 | Used by Weka Backend Server Nodes |
| 2 | 16 Gbps Virtual Nic | 64 | Used by Weka Frontend Client Nodes |
None
| Item No | Switch Name | Switch Type | Total Port Count | Used Port Count | Notes |
|---|---|---|---|---|---|
| 1 | Azure | 16 Gbps Ethernet with Accelerated Networking | 100 | 100 | Used by Weka Backend Server Nodes |
| 2 | Azure | 16 Gbps Ethernet with Accelerated Networking | 64 | 64 | Used by Weka Frontend Client Nodes |
| Item No | Qty | Type | Location | Description | Processing Function |
|---|---|---|---|---|---|
| 1 | 3200 | vCPU | L32s v3 Weka Backend | 2.8 GHz Intel(R) Xeon(R) Platinum 8370C processors | WekaFS, Network Communications, Storage Functions |
| 2 | 2048 | vCPU | E32s v5 Weka Frontend | 2.8 GHz Intel(R) Xeon(R) Platinum 8370C processors | WekaFS, Network Communications, Storage Functions |
None
| Description | Size in GiB | Number of Instances | Nonvolatile | Total GiB |
|---|---|---|---|---|
| Azure L32s v3 Virtual Machine Memory | 256 | 100 | V | 25600 |
| Azure E32s v5 Virtual Machine Memory | 256 | 64 | V | 16384 | Grand Total Memory Gibibytes | 41984 |
None
WekaFS does not use any internal memory to temporarily cache write data to the underlying storage system. All writes are committed directly to the storage disks and protected via WekaFS Distributed Data Protection (16+2 in this case). There is no need for any RAM battery protection. In an event of a power failure a write in transit would not be acknowledged.
The solution under test was a standard distributed cluster built with Weka software. Weka clusters can handle large and small file I/O with intensive metadata operations for HPC applications with no tuning required.
None
None
None
None
Generated on Fri Oct 18 03:32:56 2024 by SpecReport
Copyright © 2016-2024 Standard Performance Evaluation Corporation
