Re: serious bug in Threaded I/O Translator

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Its not a bug just a new min value.

If you dig deep deep into the wiki you can find the new correct defaults:
http://gluster.org/docs/index.php/Translators_options#performance.2Fio-threads

Its best to just remove the "option thread-count" line and let it always default. http://www.solarisinternals.com/wiki/index.php/ZFS_Evil_Tuning_Guide#Tuning_is_Evil

Hopefully the gluster developers set the best default values.
Alpha Electronics wrote:
The latest version gluster 2.0.0 has a bug in I/O xlator:

if we have this:
volume iothreads
  type performance/io-threads
  option thread-count 8  # deault is 1
  subvolumes <x>
end-volume


it reported:
iothreads: '8' in 'option thread-count 8' is out of range [16 - 256]

it works fine when we were at gluster 2.0.0rc4. Looks some bugs introduced after rc4. Please let us know when it got fixed.


thanks
Doug



------------------------------------------------------------------------

_______________________________________________
Gluster-devel mailing list
Gluster-devel@xxxxxxxxxx
http://lists.nongnu.org/mailman/listinfo/gluster-devel





[Index of Archives]     [Gluster Users]     [Ceph Users]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Security]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux