Zhitao Li
Zhitao Li
Is it safe to **disable `CacheLocality` technique** by removing the "unable to load cache sharing info" exception at folly/concurrency/CacheLocality.cpp:L164 ? On our ppc64le machine, the cpu files maybe not as...
In our env, nfs-ganesha will take up too much memory if there is huge amount of data read/write IO load from some NFS client. Then OOM will happen. I think...
In our environment using nfs-ganesha, mount cmd got stuck without any response. Some info shows that nfs-ganesha does not handle data received from TCP connection established with some particular client...
### Case In my case, there are two NFS clients with the same hostname, and no nfs4_unique_id is given. It turns out that two clients have the same owner_id and...
In my case of nfs-ganesha, `mount` hangs. Ping does work, while `nc -zv ip 2049` fails with following output: It seems that [TCP Accept queue overflows ](https://www.alibabacloud.com/blog/tcp-syn-queue-and-accept-queue-overflow-explained_599203)for the NFS port...
I have tried many settings with `time_format` in LOG block of ganesha conf. Only following setting will print time with microseconds. ``` FORMAT { date_format = syslog_usec; time_format = syslog_usec;...
After seeing the implementation about state recovery, I understand as follows. 1. `EVENT_TAKE_IP` means that if some new IP is added to the nfs-ganesha node, then nfs-ganesha enters into grace...
Hi, community, I don't understand how to use `owner` and `state` parameters in lock_op2 in FSAL api. From the implementation, VFS FSAL does not use `owner`. CEPH FSAL does convert...
According to NFS 4.1 RFC 8881, [Section 8.4.3](https://www.rfc-editor.org/rfc/rfc8881#name-network-partitions-and-reco) > When a network partition is combined with a server restart, there are edge conditions that place requirements on the server in...