هذه الصفحة غير متوفرة حاليًا بلغتك المحلية. نحن نعمل جاهدين على إضافة المزيد من اللغات. شاكرين تفهمك ودعمك المستمر لنا.

Compute
Elastic Cloud Server
Huawei Cloud Flexus
Bare Metal Server
Auto Scaling
Image Management Service
Dedicated Host
FunctionGraph
Cloud Phone Host
Huawei Cloud EulerOS
Networking
Virtual Private Cloud
Elastic IP
Elastic Load Balance
NAT Gateway
Direct Connect
Virtual Private Network
VPC Endpoint
Cloud Connect
Enterprise Router
Enterprise Switch
Global Accelerator
Management & Governance
Cloud Eye
Identity and Access Management
Cloud Trace Service
Resource Formation Service
Tag Management Service
Log Tank Service
Config
OneAccess
Resource Access Manager
Simple Message Notification
Application Performance Management
Application Operations Management
Organizations
Optimization Advisor
IAM Identity Center
Cloud Operations Center
Resource Governance Center
Migration
Server Migration Service
Object Storage Migration Service
Cloud Data Migration
Migration Center
Cloud Ecosystem
KooGallery
Partner Center
User Support
My Account
Billing Center
Cost Center
Resource Center
Enterprise Management
Service Tickets
HUAWEI CLOUD (International) FAQs
ICP Filing
Support Plans
My Credentials
Customer Operation Capabilities
Partner Support Plans
Professional Services
Analytics
MapReduce Service
Data Lake Insight
CloudTable Service
Cloud Search Service
Data Lake Visualization
Data Ingestion Service
GaussDB(DWS)
DataArts Studio
Data Lake Factory
DataArts Lake Formation
IoT
IoT Device Access
Others
Product Pricing Details
System Permissions
Console Quick Start
Common FAQs
Instructions for Associating with a HUAWEI CLOUD Partner
Message Center
Security & Compliance
Security Technologies and Applications
Web Application Firewall
Host Security Service
Cloud Firewall
SecMaster
Anti-DDoS Service
Data Encryption Workshop
Database Security Service
Cloud Bastion Host
Data Security Center
Cloud Certificate Manager
Edge Security
Situation Awareness
Managed Threat Detection
Blockchain
Blockchain Service
Web3 Node Engine Service
Media Services
Media Processing Center
Video On Demand
Live
SparkRTC
MetaStudio
Storage
Object Storage Service
Elastic Volume Service
Cloud Backup and Recovery
Storage Disaster Recovery Service
Scalable File Service Turbo
Scalable File Service
Volume Backup Service
Cloud Server Backup Service
Data Express Service
Dedicated Distributed Storage Service
Containers
Cloud Container Engine
SoftWare Repository for Container
Application Service Mesh
Ubiquitous Cloud Native Service
Cloud Container Instance
Databases
Relational Database Service
Document Database Service
Data Admin Service
Data Replication Service
GeminiDB
GaussDB
Distributed Database Middleware
Database and Application Migration UGO
TaurusDB
Middleware
Distributed Cache Service
API Gateway
Distributed Message Service for Kafka
Distributed Message Service for RabbitMQ
Distributed Message Service for RocketMQ
Cloud Service Engine
Multi-Site High Availability Service
EventGrid
Dedicated Cloud
Dedicated Computing Cluster
Business Applications
Workspace
ROMA Connect
Message & SMS
Domain Name Service
Edge Data Center Management
Meeting
AI
Face Recognition Service
Graph Engine Service
Content Moderation
Image Recognition
Optical Character Recognition
ModelArts
ImageSearch
Conversational Bot Service
Speech Interaction Service
Huawei HiLens
Video Intelligent Analysis Service
Developer Tools
SDK Developer Guide
API Request Signing Guide
Terraform
Koo Command Line Interface
Content Delivery & Edge Computing
Content Delivery Network
Intelligent EdgeFabric
CloudPond
Intelligent EdgeCloud
Solutions
SAP Cloud
High Performance Computing
Developer Services
ServiceStage
CodeArts
CodeArts PerfTest
CodeArts Req
CodeArts Pipeline
CodeArts Build
CodeArts Deploy
CodeArts Artifact
CodeArts TestPlan
CodeArts Check
CodeArts Repo
Cloud Application Engine
MacroVerse aPaaS
KooMessage
KooPhone
KooDrive
On this page

Show all

Fine-Tuning obsutil Performance

Updated on 2025-02-10 GMT+08:00

By default, obsutil uploads, downloads, and copies files or objects whose size is greater than 50 MB in multiple parts. Table 1 details related parameters in the .obsutilconfig file.

Table 1 Multipart-related parameters

Parameter

Description

defaultBigfileThreshold

Indicates the threshold for triggering multipart tasks, in bytes. If the size of a file to be uploaded, downloaded, or copied is greater than the threshold, the file is uploaded, downloaded, or copied in multiple parts. The default value is 50MB.

defaultPartSize

Size of each part, in bytes. The default value is auto.

NOTE:
  • For multipart upload and copy, the value ranges from 100KB to 5GB.
  • For multipart download, the value is unrestricted.

defaultParallels

Maximum number of concurrent tasks in the multipart mode. The default value is 5.

Generally, multipart tasks not only speed up transmission but also allow you to resume failed tasks. By default, the part size of a multipart task can be automatically adjusted by the obsutil in the auto mode. In practice, however, to further improve the upload and download performance, you can adjust the part size according to the file size and the network conditions, to obtain the maximum transmission efficiency and ensure the successful completion of a transmission task.

Adjust the number of concurrent tasks in the multipart mode according to the following formula:

defaultParallels = Min(Number of CPUs x 2, Object size/defaultPartSize x 1.5)

In the upload, download, and copy commands, parameters -p and -ps are used to modify the number of concurrent tasks in the multipart mode and part size respectively, and then deliver the multipart task based on the parameter values configured in the command. The default values in the configuration file are used if you do not set them in a command.

Adjust the number of concurrent tasks in the multipart mode according to the following formula:

p = Min(Number of CPUs x 2, Object size/ps x 1.5)

For batch upload and download tasks, adjust the maximum number of concurrent tasks in a multipart upload, indicated by the parameter defaultJobs (-j), for better performance.

If you have a large number of small files (each is usually several MB) to be uploaded or downloaded, set defaultJobs (-j) to a larger value for better performance. In this case, adjusting defaultParallels (-p) and defaultPartSize (-ps) may be ineffective.

If you want to upload or download large files, set defaultParallels (-p) and defaultPartSize (-ps) to a larger value for better performance. However, if there are too many concurrent tasks (calculated from defaultJobs x defaultParallels), the upload and download performance may deteriorate because of resource switchover and preemption between threads, and some tasks may fail due to network fluctuations.

NOTE:
  • Resources of a running host are limited. Therefore, if the number of concurrent tasks in the multipart mode is set too large, the performance of obsutil upload, download, or copy may deteriorate due to resource switchover and preemption between threads. In this case, you need to adjust the values of defaultParallels (-p) and defaultPartSize (-ps) based on the actual file size and network status. To perform a pressure test, lower the two values at first, and then gradually increase them to determine the optimal values.
  • If the values of defaultParallels (-p) and defaultPartSize (-ps) are too large, an EOF error may occur due to network instability. In this case, set the two parameters to smaller values.
  • If a batch operation is performed, the destination object size can be set to the average size of the objects to be operated.
  • If a batch task fails due to timeout, EOF, and other common network issues, retry the task through an incremental operation (specifically, configuring parameter -u in the cp command). You can also restore the failed task (by configuring parameter -recover in the cp command) based on the generated task ID.

We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out more

Feedback

Feedback

Feedback

0/500

Selected Content

Submit selected content with the feedback