Batch, or out-of-band deduplication (happens after writes, not during).Send/receive of subvolume changes, efficient incremental filesystem mirroring and backup.Using copy on write, all modifications are stored on different devices the original is unchanged. The original filesystem and devices are included as a readonly starting point for the new filesystem. Create a (readonly) filesystem that acts as a template to seed other Btrfs filesystems. In-place conversion of existing ext2/3/4 and reiserfs file systems.Background scrub process for finding and repairing errors of files with redundant copies.This results in larger write operations and faster write throughput) avoiding unnecessary seek optimizations, sending writes in clusters, even if they are from unrelated files. TRIM/Discard for reporting free blocks for reuse.Single and Dual Parity implementations (experimental, not production-ready).Compression (ZLIB, LZO, ZSTD), heuristics.Checksums on data and metadata (crc32c, xxhash, sha256, blake2b).Subvolumes (separate internal filesystem roots).Writable snapshots, read-only snapshots.2^64 byte = 16 EiB maximum file size (practical limit is 8 EiB due to Linux VFS). Filesystems need to scale in their ability to address and manage large storage, and also in their ability to detect, repair and tolerate errors in the data stored on disk. Linux has a wealth of filesystems from which to choose, but we are facing a number of challenges with scaling to the large storage subsystems that are becoming common in today's data centers.
0 Comments
Leave a Reply. |