1 .. SPDX-License-Identifier: GPL-2.0 2 3 ============== 4 Fuse I/O Modes 5 ============== 6 7 Fuse supports the following I/O modes: 8 9 - direct-io 10 - cached 11 + write-through 12 + writeback-cache 13 14 The direct-io mode can be selected with the FOPEN_DIRECT_IO flag in the 15 FUSE_OPEN reply. 16 17 In direct-io mode the page cache is completely bypassed for reads and writes. 18 No read-ahead takes place. Shared mmap is disabled by default. To allow shared 19 mmap, the FUSE_DIRECT_IO_ALLOW_MMAP flag may be enabled in the FUSE_INIT reply. 20 21 In cached mode reads may be satisfied from the page cache, and data may be 22 read-ahead by the kernel to fill the cache. The cache is always kept consistent 23 after any writes to the file. All mmap modes are supported. 24 25 The cached mode has two sub modes controlling how writes are handled. The 26 write-through mode is the default and is supported on all kernels. The 27 writeback-cache mode may be selected by the FUSE_WRITEBACK_CACHE flag in the 28 FUSE_INIT reply. 29 30 In write-through mode each write is immediately sent to userspace as one or more 31 WRITE requests, as well as updating any cached pages (and caching previously 32 uncached, but fully written pages). No READ requests are ever sent for writes, 33 so when an uncached page is partially written, the page is discarded. 34 35 In writeback-cache mode (enabled by the FUSE_WRITEBACK_CACHE flag) writes go to 36 the cache only, which means that the write(2) syscall can often complete very 37 fast. Dirty pages are written back implicitly (background writeback or page 38 reclaim on memory pressure) or explicitly (invoked by close(2), fsync(2) and 39 when the last ref to the file is being released on munmap(2)). This mode 40 assumes that all changes to the filesystem go through the FUSE kernel module 41 (size and atime/ctime/mtime attributes are kept up-to-date by the kernel), so 42 it's generally not suitable for network filesystems. If a partial page is 43 written, then the page needs to be first read from userspace. This means, that 44 even for files opened for O_WRONLY it is possible that READ requests will be 45 generated by the kernel.
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.