|
1 | 1 | Dear Users, |
2 | 2 |
|
3 | | -LizardFS 3.10.2 is out! |
| 3 | +here comes LizardFS 3.11.0! |
4 | 4 | Featuring: |
5 | 5 |
|
6 | | -master: redesign in-memory representation of file system objects - at least 30% reduction in RAM usage |
7 | | -master: name storage: a possibility to keep all file names in BerkeleyDB, thus saving even more RAM |
8 | | -master: redesign of trash - increased performance, reduced RAM usage and CPU pressure |
9 | | -master: huge boost of responsiveness - lengthy operations split into asynchronous bits |
10 | | -master: OPERATIONS_DELAY* config entries, which allow postponing metadata operations on restart/disconnect |
11 | | -master, mount: make big snapshot, setgoal and settrashtime operations asynchronous to improve responsiveness |
12 | | -master: fix improper handling of endangered chunks |
13 | | -chunkserver: memory optimizations - at least 60% reduction in RAM usage |
14 | | -chunkserver: introduce smart descriptor management |
15 | | -tools: brand new `lizardfs` command, a unified replacement for mfs* tools with prompt and bash completion |
16 | | -all: various fixes and community requests |
| 6 | +master: improve ACL implementation |
| 7 | +master: add option to avoid same-ip chunkserver replication |
| 8 | +master: add minimal goal configuration option |
| 9 | +master: reimplement directory entry cache for faster lookups |
| 10 | +master: add whole-path lookups |
| 11 | +master: chunkserver add chunkserver load awareness |
| 12 | +mount: add readahead to improve sequential read perfromance |
| 13 | +mount: add secondary groups support |
| 14 | +tools: add correct-only flag to filerepair |
| 15 | +tools: add -s and -i options to snapshot command |
| 16 | +tools: add recursive remove operations (for removing large directories and snapshots) |
| 17 | +tools: add tool for stopping execution of tasks (snapshot, recursive remove, etc.) |
| 18 | +all: change to semantic versioning system |
| 19 | +all: many fixes |
17 | 20 |
|
18 | 21 | Detailed information: |
19 | 22 |
|
20 | | -Master’s memory and CPU |
21 | | -With 3.10.2, master is much more memory-efficient and responsive. RAM usage reduction was accomplished through redesigning the way it keeps metadata in memory, adding a possibility to keep some metadata in on-disk database (see USE_BDB_FOR_NAME_STORAGE in mfsmaster.cfg file for reference). Responsiveness was dramatically increased by recognizing all potentially lengthy operations and splitting their execution in smaller time bits. It applied to both in-master maintenance procedures and client’s requests like snapshotting/changing goal of very big directories. |
| 23 | +Readahead |
| 24 | +Clients can now benefit from integrated readahead mechanism. |
| 25 | +In order to enable readahead, please mount with the following options: |
| 26 | + -o cacheexpirationtime={MSEC} |
| 27 | + -o readaheadmaxwindowsize={KB} |
| 28 | +Example: |
| 29 | + mfsmount -o cacheexpirationtime=1000 -o readaheadmaxwindowsize=8192 |
| 30 | + |
| 31 | +Recursive remove |
| 32 | +A tool for removing large directories/snapshots is finally implemented. |
| 33 | +Example: |
| 34 | + lizardfs rremove big_directory/ |
| 35 | + lizardfs rremove -h |
| 36 | + |
| 37 | +Tools for managing tasks |
| 38 | +Two administration tools are available for managing long tasks: |
| 39 | + lizardfs-admin list-tasks |
| 40 | + lizardfs-admin stop-task |
| 41 | +Run above commands for detailed usage information. |
| 42 | + |
| 43 | +Secondary groups support |
| 44 | +LizardFS is now able to fully recognize secondary groups of users |
| 45 | +and take them into account while evaluating permissions. |
22 | 46 |
|
23 | | -`lizardfs` tool: |
24 | | -3.10.2 comes with new client tool: `lizardfs` utility. See `man lizardfs`, `lizardfs -h` for details. Aside from known functionalities like setting/getting goals, making snapshots, etc. it comes with bash-like prompt and bash completion. |
25 | | -Examples: |
26 | | - |
27 | | -lizardfs setgoal -r ec32 a/ |
28 | | - |
29 | | -lizardfs makesnapshot dira/ dirb/ |
30 | | - |
31 | | -lizardfs fileinfo a/* |
32 | | - |
33 | | -lizardfs <<EOF |
34 | | -fileinfo a/* |
35 | | -setgoal -r 3 a |
36 | | -getgoal a/2 |
37 | | -EOF |
38 | | - |
39 | | -Future plans: |
40 | | -In next release, paths and build system is to be unified with the one from official Debian repository (e.g. configuration directory will officially become /etc/lizardfs). Also, more asynchronous client commands are coming (including awaited recursive-remove operation). A so called “minimal goal setting”, which will probably be named MIN_REDUNDANCY_LEVEL is being implemented as well. Finally, more news on native HA (μRaft) will appear. |
41 | 47 |
|
42 | 48 | Best, |
6D40
43 | 49 | Piotr Sarna |
|
0 commit comments