general:lisa15:s4_glusterfs
Differences
This shows you the differences between two versions of the page.
| general:lisa15:s4_glusterfs [2020/11/17 19:15] – created sunkan | general:lisa15:s4_glusterfs [2020/11/17 19:17] (current) – sunkan | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| extend attributes support needed from underlying fs | extend attributes support needed from underlying fs | ||
| - | Supports NFS, Samba or native FUSE mount (NFS-Ganesha, | + | Supports NFS, Samba or native FUSE mount (NFS-Ganesha, |
| Native apps can use libgfapi | Native apps can use libgfapi | ||
| - | NFSv3 supports natively and with Ganesha NFSv4 is also supported | + | NFSv3 supports natively and with Ganesha NFSv4 is also supported |
| NFS daemons run on each storage node and uses that is a pivot point for getting the data (LB can be used for NFS) | NFS daemons run on each storage node and uses that is a pivot point for getting the data (LB can be used for NFS) | ||
| - | Samba has VFS pluging that usus libgfapi | + | Samba has VFS pluging that usus libgfapi |
| - | Samba runs on each storage node | + | Samba runs on each storage node \\ |
| - | CTDB used for load balancing and clustering | + | CTDB used for load balancing and clustering |
| Samba also pivot' | Samba also pivot' | ||
| Line 16: | Line 16: | ||
| David-Meyer hash algo decided where storage is placed (hence no need for metadata DB) | David-Meyer hash algo decided where storage is placed (hence no need for metadata DB) | ||
| - | Links are used if a new brick is added and data has not been rebalanced yet | + | Links are used if a new brick is added and data has not been rebalanced yet \\ |
| First access is a two hop access but client caches information about the actual brick the data is stored at | First access is a two hop access but client caches information about the actual brick the data is stored at | ||
| Replicated volume is like RF2 | Replicated volume is like RF2 | ||
| - | Disperse volume use Erasure Coding | + | Disperse volume use Erasure Coding |
| Example is 11 nodes with redundancy 3 (8+3) | Example is 11 nodes with redundancy 3 (8+3) | ||
| Line 27: | Line 27: | ||
| pNFS support with NFS-Ganesha | pNFS support with NFS-Ganesha | ||
| - | + | | |
| - | Geo replication (async repl) does not support active/ | + | Geo replication (async repl) does not support active/ |
| Log is kept of changes and are synced in the background | Log is kept of changes and are synced in the background | ||
| - | ((S4 GlusterFS)) snapshot needs LVM2 thinly provisioned storage | + | S4 GlusterFS snapshot needs LVM2 thinly provisioned storage |
| Data tiering places data according to data access rate | Data tiering places data according to data access rate | ||
| Line 39: | Line 39: | ||
| Backups seems to need more work, data not available for delta changes for example. | Backups seems to need more work, data not available for delta changes for example. | ||
| - | Friday 9-10:30 evaluating distributed fs performance | + | Friday 9-10:30 evaluating distributed fs performance (S4 GlusterFS and Ceph) |
general/lisa15/s4_glusterfs.1605640520.txt.gz · Last modified: 2020/11/17 19:15 by sunkan