[Gluster-users] GlusterFS's HA: After one node is down, opened file can still be written without reopened

Liu, Dan liud.fnst at cn.fujitsu.com
Thu Dec 20 07:00:31 UTC 2018


Our team is investigating distributed file system.

We are confused about the following message that is written in GlusterFS¡¯s user guide.
¡°In a highly available active-active environment, if a NFS-Ganesha server that is connected to a NFS client running a particular application crashes,
the application/NFS client is seamlessly connected to another NFS-Ganesha server without any administrative intervention. ¡°
After ¡®LVS+CTDB+GlusterFS¡¯ cluster is created,
one node is down when one user is writing data to a file of a mounted directory.

At this time,
If NFS-Ganesha is used, current opened file can still be written without reopened. Is that right?
If NFS /Samba is used, it is possible that current opened file can still be written without reopened?

Best regards,

Liu Dan
PF Dept
Nanjing Fujitsu Nanda Software Tech.Co.,Ltd.(FNST)
EMail: liud.fnst at cn.fujitsu.com<mailto:liud.fnst at cn.fujitsu.com>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20181220/4795a234/attachment.html>

More information about the Gluster-users mailing list