All Products
Search
Document Center

Object Storage Service:ossfs 2.0 mount options

Last Updated:Dec 26, 2025

When you create an ossfs 2.0 configuration file, you can set various parameters to meet your specific mount requirements. This file lets you mount an OSS bucket as a file system in different ways to meet various business needs.

Basic configuration items

Category

Configuration item

Required

Description

Default value

Supported versions

Bucket basic configuration

oss_endpoint

Yes

The endpoint to access the bucket.

None

v2.0.0 and later

oss_bucket

Yes

The name of the bucket.

None

v2.0.0 and later

Access credential configuration

oss_access_key_id

Conditionally required

The AccessKey ID. This parameter is required for AccessKey authentication.

None

v2.0.0 and later

oss_access_key_secret

Conditionally required

The AccessKey secret. This parameter is required for AccessKey authentication.

None

v2.0.0 and later

ram_role

Conditionally required

The ECS RAM role. This parameter is required for ECS RAM role authentication.

None

v2.0.2 and later

credential_process

Conditionally required

The command to run an external process to obtain access credentials.

This parameter is required for external process authentication.

None

v2.0.5 and later

Common configuration items

Category

Configuration item

Required

Description

Default value

Supported versions

Bucket configuration

oss_bucket_prefix

No

Mounts a specific folder in the bucket.

Empty

v2.0.0 and later

oss_region

No

The region ID of the bucket. This is used for the OSS V4 signature algorithm. If you do not specify this parameter, the OSS V1 signature algorithm is used.

Empty

v2.0.0 and later

Cache configuration

attr_timeout

No

The time-to-live (TTL) for file metadata cache, in seconds.

60

v2.0.0 and later

negative_timeout

No

The TTL for invalid directory entry cache, in seconds.

0

v2.0.0 and later

readdirplus

No

Enables the readdirplus feature. When enabled, the file metadata cache is built synchronously during the readdir operation. This consumes more memory.

true

v2.0.0 and later

Log configuration

log_level

No

The log level. Valid values are info and debug.

info

v2.0.0 and later

log_dir

No

The folder where log files are stored.

/tmp/ossfs2

v2.0.0 and later

log_file_max_size

No

The maximum size of a single log file, in bytes.

67108864

v2.0.3 and later

log_file_max_count

No

The maximum number of log files to retain.

8

v2.0.3 and later

Running mode

f

No

Specifies whether to run in the foreground.

false

v2.0.0 and later

d

No

Specifies whether to run in the foreground and enable FUSE debug logs.

false

v2.0.0 and later

Mount mode

ro

No

Mounts the file system in read-only mode.

false

v2.0.0 and later

Permission configuration

gid

No

If configured, the GID property of all files and folders under the mount target is set to this value.

The GID of the user who mounts the file system

v2.0.1 and later

uid

No

If configured, the UID property of all files and folders under the mount target is set to this value.

The UID of the user who mounts the file system

v2.0.1 and later

file_mode

No

If configured, the permission property of all files under the mount target is set to this value.

0777

v2.0.1 and later

dir_mode

No

If configured, the permission property of all folders under the mount target is set to this value.

0777

v2.0.1 and later

allow_other

No

If you set `allow_other` to `true`, non-root users can access files under the mount target. Access is verified based on file permissions.

true

v2.0.1 and later

Advanced configuration

Category

Configuration item

Required

Description

Default value

Supported versions

Network configuration

bind_ips

No

Binds a list of specified IP addresses as the source IPs for accessing OSS. Separate the IP addresses with commas. For example, 192.168.0.1,192.168.0.2. By specifying a list of IP addresses, you can control which network interface card (NIC) is used to access OSS. This can increase the total throughput in a multi-NIC environment.

Empty

v2.0.3 and later

Upload configuration

upload_buffer_size

No

The size of the multipart upload buffer, in bytes. This is also the part size. This parameter determines the maximum size of a file that can be written. The maximum file size is calculated as `upload_buffer_size` × 10,000.

8388608

v2.0.0 and later

upload_concurrency

No

The concurrency for multipart uploads.

64

v2.0.0 and later

sync_upload

No

If enabled, the system waits for the file to be completely uploaded before returning when the file is closed.

true

v2.0.0 and later

Download/Prefetch configuration

prefetch_concurrency

No

The global concurrency for download prefetching.

256

v2.0.0 and later

prefetch_concurrency_per_file

No

The concurrency for download prefetching per file handle.

64

v2.0.0 and later

prefetch_chunk_size

No

The size of a prefetch chunk, in bytes.

8388608

v2.0.0 and later

prefetch_chunks

No

The number of prefetch chunks. If not set, the default value is three times the value of `prefetch_concurrency`. If set to -1, prefetch memory is not limited. Each file handle can acquire enough memory for prefetching.

0 (automatically configured based on prefetch_concurrency)

v2.0.0 and later

Memory management configuration

total_mem_limit

No

The total memory limit, in bytes. If set, the concurrency for uploads and prefetching is automatically adjusted based on this limit.

If you do not configure this option, a buffer of prefetch_chunk_size * prefetch_chunks is used for data read prefetching, and a buffer of upload_buffer_size * upload_concurrency is used for data writing. Read and write operations can allocate up to approximately 8 GB of memory. Make sure your device has enough memory resources to avoid potential out-of-memory (OOM) issues.

For environments with 16 GB of memory or less, the default value of `total_mem_limit` is half of the system memory. For environments with more than 16 GB of memory, there is no limit.

0

v2.0.0 and later

max_inode_cache_count

No

Enables active control over the number of cached metadata entries.

  • The default value is 0, which means metadata count is not actively controlled. The operating system automatically evicts metadata.

  • If you set this to a positive integer, active control is enabled. When the number of cache entries exceeds the set value, ossfs 2.0 evicts the excess entries based on specific rules.

0

v2.0.4 and later

File verification/Metadata configuration

enable_crc64

No

Specifies whether to enable cyclic redundancy check (CRC) for file writes.

true

v2.0.0 and later

close_to_open

No

Supports close-to-open semantics. If you enable this option, a GetObjectMeta request is sent to get file information from OSS when a file is opened. This ensures real-time metadata.

By default, this option is disabled. When a file is opened, the system decides whether to send a request to OSS for the latest file properties based on the metadata cache TTL. If you enable this option, a request is always sent to OSS when a file is opened. This significantly increases access latency when reading many small files.

false

v2.0.0 and later

File operation configuration

rename_dir_limit

No

The maximum total number of descendant files and folders in a source folder for a single rename operation. If the actual number exceeds this limit, the rename operation fails.

2000000

v2.0.0 and later

enable_appendable_object

No

If enabled, the AppendObject operation is used for file writes. This mode supports reading a file while it is being written.

false

v2.0.0 and later

appendable_object_autoswitch_threshold

No

When `enable_appendable_object` is enabled, non-appendable objects in OSS that are smaller than or equal to this size (in bytes) are automatically converted to appendable objects when data is appended.

0

v2.0.5 and later

Request timeout configuration

oss_request_timeout_ms

No

The timeout period for requests sent to OSS, in milliseconds.

60000

v2.0.0 and later

Cache configuration

oss_negative_cache_timeout

No

The TTL for cached OSS 404 request items, in seconds.

0

v2.0.2 and later

oss_negative_cache_size

No

The number of cached OSS 404 request items.

10000

v2.0.2 and later

memory_data_cache_size

No

In this mode, a fixed amount of memory is pre-allocated for the read cache. This is mainly used to solve the prefetch amplification issue when reading files concurrently. It can effectively improve performance when loading large models on multiple GPUs.

0

v2.0.5 and later

References