Blog · 2018-01-25 · MooseFS Team

MooseFS 3.0.100 Stable Release

MooseFS 3.0.100 lands as stable with Debian 9 (Stretch) and Ubuntu 16.04 LTS packages, a fix for a rare chunkserver segfault on master disconnection, and a big-endian data corruption patch – rolled up across three patch releases dating back to October 2017.

MooseFS 3.0.100-1 (2018-01-24)

  • (cs) fixed rare segfault during chunk sending to master after disconnection
  • (mount) added thread for cleaning released files with delay
  • (mount) added assertion for lru cache (sustained open files)
  • (master+mount) added chunks data cache invalidation after chunkserver disconnection
  • (mount) changed (lowered) number of connection retries (depends on I/O retry counter)

MooseFS 3.0.99-1 (2017-11-23)

  • (master) disconnect all clients when exports have changed
  • (mount) do not show the message about ‘negative travel time’ when the measured time is negative
  • (all) fixed get16bit function on big-endian machines

MooseFS 3.0.98-1 (2017-10-12)

  • (mount) changed default cache mode on OS X from ‘direct’ to ‘auto’ due to problems with OS X compatibility
  • (cgiserv) added seteuid to ‘mfs’ or ‘nobody’
  • (cs+tools) use readdir instead of readdir_r on glibc 2.24+
  • (debian) added support for systemd in debian packages
  • (all) fixed library dependencies (for libpcap, libz and libm)
  • (mount) fixed race between deferred ‘open’ and ‘locks’
  • (master) more chunk debugs and better handling chunk status change
  • (cs) fixed handling mark for removal (after reload sometimes cs could send chunks)
  • (master) added file with metadata checksums (for future use)
  • (master) fixed way of sending gids to changelog/follower
  • (master) added inode checksum for some changes sent to changelog/follower
  • (metadump) added ‘0x’ prefix for fields dumped as hex numbers
  • (master) fixed ACL mask synchronization issues (restoring from changelog/leader)

Star the project on GitHub and submit any issues you find.