Parallelstore インスタンスは、Compute Engine VM または Google Kubernetes Engine クラスタにマウントできます。Parallelstore CSI ドライバを使用すると、Kubernetes API を使用して、ステートフル ワークロードのボリュームとしてファイル システムにアクセスできます。
Cloud Storage との間でのバッチデータ転送は、コマンドラインと REST API から使用できます。
[[["わかりやすい","easyToUnderstand","thumb-up"],["問題の解決に役立った","solvedMyProblem","thumb-up"],["その他","otherUp","thumb-up"]],[["わかりにくい","hardToUnderstand","thumb-down"],["情報またはサンプルコードが不正確","incorrectInformationOrSampleCode","thumb-down"],["必要な情報 / サンプルがない","missingTheInformationSamplesINeed","thumb-down"],["翻訳に関する問題","translationIssue","thumb-down"],["その他","otherDown","thumb-down"]],["最終更新日 2025-08-19 UTC。"],[],[],null,["# Parallelstore overview\n\nParallelstore is available by invitation only. If you'd like to request access to Parallelstore in your Google Cloud project, contact your sales representative.\n\nParallelstore is a fully managed, low-latency distributed file system\ndesigned to meet the demands of high performance computing (HPC) and\ndata-intensive applications.\n\nParallelstore is ideal for use cases where multiple clients need concurrent\naccess to shared files with data integrity.\n\nParallelstore supports the POSIX standard, ensuring\ncompatibility with a wide range of existing applications and tools,\nsimplifying migration and integration.\n\nParallelstore instances can be mounted to Compute Engine VMs or\nGoogle Kubernetes Engine clusters. The [Parallelstore CSI driver](/parallelstore/docs/csi-driver-overview) enables\ncustomers to use Kubernetes APIs to access the file system as volumes for\ntheir stateful workloads.\n\n[Batch data transfers](/parallelstore/docs/transfer-data) into and out of\nCloud Storage are available from the command line and the REST API.\n\nSpecifications\n--------------\n\n- Parallelstore is a \"scratch\" file system: it's backed by local SSD with\n 2+1 erasure coding, with a mean time to data loss (MTTDL) from 2 to 16\n months, depending on instance capacity. See the [Performance](#performance)\n table for details.\n\n- Usable capacity can be configured from 12TiB to 100TiB.\n\n- Supported in [multiple regions](/parallelstore/docs/locations).\n\nPerformance\n-----------\n\nExpected performance from Parallelstore is shown in the following table.\n\nThese numbers are measured using 256 client connections to a single\ninstance. Latency is measured from a single client. Directory and file\nstriping settings are optimized for each metric.\n\nUse Cases\n---------\n\n- **High-performance computing**: Parallelstore excels in HPC environments where\n multiple compute nodes need fast and consistent access to shared data for\n simulations, modeling, and analysis.\n\n- **Machine learning**: Parallelstore can handle the large datasets and high\n throughput requirements of machine learning workloads, enabling efficient\n training and inference.\n\nPricing\n-------\n\nSee the [Pricing](/parallelstore/pricing) page for details."]]