[sheepdog-users] Sheepdog 0.6.0 schedule and todos
aderumier at odiso.com
Tue Nov 6 09:10:21 CET 2012
>>- journaling to boost performance
One thing that could be great with journal, is something like slog device with zfs or nvram with netapp san.
random writes are going to a fast journal (ssd, nvram,...) then are flushed sequentially each X seconds to slower disks.
With these setup, I can achieve easily 12000iops of random write with around 10x 7200K drives.
----- Mail original -----
De: "MORITA Kazutaka" <morita.kazutaka at gmail.com>
À: sheepdog at lists.wpkg.org, sheepdog-users at lists.wpkg.org
Envoyé: Lundi 5 Novembre 2012 17:56:20
Objet: [sheepdog-users] Sheepdog 0.6.0 schedule and todos
I think of releasing 0.6.0 at the end of this month.
Major features expected for the release are:
- journaling to boost performance
- sheepkeeper: yet another cluster manager for large-scale cluster
- object reclaim based on reference counting
- flexible options to control backend cache
- variable object size
Let me know if there are any opinions.
sheepdog-users mailing lists
sheepdog-users at lists.wpkg.org
More information about the sheepdog-users