Rafi KC
Rafi KC
upcall notification expects the upcall data struct gf_upcall_cache_invalidation as the main argument. While AFR requires another argument to identify the child xlator who send the upcall. As of now, afr_notify...
**Description of problem:** In our cluster, the heal info shows entries with pending heal. When I check the gfid on the backend, the entry is a regular file but it...
We are running NFS-Ganesha's latest version 3.5.11 with gluster vfs. We are experiencing high memory usage with mainly write fops, our file size ranges from 1-64k. 3 Client machine is...
### Observed behavior Log flooding in glusterd2 ### Expected/desired behavior Log file should not increase when a brick is down, as glusterfs designed to work as a highly available ###...
### Observed behavior ` glustercli heal info` command failed with `Client.Timeout exceeded while awaiting headers` when I had lot of entries to heal (almost 3k) ``` [root@dhcp42-161 glusterfs]# glustercli volume...
Labels are used to tag different object, and perform collective operation based on label configuration values More information on issue #1094 Signed-off-by: Mohammed Rafi KC
**Description of problem:** The order in which the arguments are sent to the afr_notify and the way they process the arguments while handling UPCALL notifications are wrong. The upcall data...
While an entry heal is on going, if there is a pending metadata set on the source dentry, then the recreation of soft link will fail to create on the...
Brick log is reporting an error message that the inode is linked as link when it is actually a directory in the backend. This error message is reported when trying...
On our 2*3 cluster with arbiter setup, we have observed split-brain. We had some issues at the brick which caused write operation failures. Here is the log snippet from the...