Release Candidate of LizardFS 3.13 with built in High Availability finally out!

Dear Users,

3.13.0-rc1 (release candidate) is officially out!

Featuring:

  • uRaft High Availability
  • fixes to EC handling
  • nfs-ganesha plugin changed to use only C code
  • reduced number of secondary group retrievals
  • new fuse3 client
  • many fixes

Detailed info:

  • uRaft HA *

uRaft is HA solution designed for use with LizardFS. It allows for seamless switching of  the master server in case of hardware failure. More information about uRaft is available in LizardfFS Handbook.

  • fixes to EC handling *

After extensive tests, we decided to improve the mechanism of calculating parities greater than 4 e.g EC( 6,5). After this upgrade, the system will show chunks of parities as endangered until the system automatically recalculates.

  • nfs-ganesha plugin changed to use only C code *

In preparation for moving LizardFS nfs-ganesha plugin to official nfs-ganesha repository, we had to remove all occurrences of C++ code and replace it with plain C.

  • reduced number of secondary group retrievals *

In LizardFS we introduced the handling of secondary groups. Unfortunately, the function to retrieve secondary groups in FUSE library used a lot of CPU resources. Thanks to removing unnecessary calls to this function, mount performance increased significantly.

  • added fuse3 client *

LizardFS now includes mount3 client which uses FUSE3 library. Thanks to new features in FUSE3, now the mount performs much better in many scenarios. Here are the most important changes visible to LizardFS users:

  • big_writes option is now enabled by default (not recognized as a parameter anymore).
  • added writeback_cache option which with kernel 3.14 and later improves performance significantly
  • increased read/write performance (especially for small operations)

Because most of the Linux distributions don’t include FUSE3 library, we have build FUSE3 packages and made them available on the LizardFS website.