chrislusf
1b6ab2f6af
Add boltdb for volume needle map
...
boltdb is fairly slow to write, about 6 minutes for recreating index
for 1553934 files. Boltdb loads 1,553,934 x 16 = 24,862,944bytes from
disk, and generate the boltdb as large as 134,217,728 bytes in 6
minutes.
To compare, for leveldb, it recreates index in leveldb as large as
27,188,148 bytes in 8 seconds.
For in memory version, it loads the index in
To test the memory consumption, the leveldb or boltdb index are
created. And the server is restarted. Using the benchmark tool to read
lots of files. There are 7 volumes in benchmark collection, each with
about 1553K files.
For leveldb, the memory starts at 142,884KB, and stays at 179,340KB.
For boltdb, the memory starts at 73,756KB, and stays at 144,564KB.
For in-memory, the memory starts at 368,152KB, and stays at 448,032KB.
2015-03-29 11:04:32 -07:00
chrislusf
020ba6c9a8
add leveldb support for needle map
...
This supposedly should reduce memory consumption. However, for tests
with millions of, this shows consuming more memories. Need to see
whether this will work out. If not, later boltdb will be tested.
2015-03-27 16:34:58 -07:00
chrislusf
b07d81fb08
follow golint suggestions
2015-03-10 00:20:34 -07:00
chrislusf
f511b507a5
Add read only public port on volume server
...
Add read only public port on volume server
2015-03-09 01:10:04 -07:00
chrislusf
b2f636ab8c
set default volume admin port
2015-02-25 23:59:44 -08:00
chrislusf
eff83a87d1
Add publicUrl for master server
2015-02-11 21:04:43 -08:00
Chris Lu
f7998f8652
merge conflicts
2015-02-07 15:35:28 -08:00
chrislusf
09f98630c0
Avoid checking folder if not using filer. fix #80
...
Fix https://github.com/chrislusf/weed-fs/issues/80
2015-02-05 10:12:35 -08:00
chrislusf
1791de4ae4
Avoid creating filer folder if not starting it.
2015-02-02 16:26:12 -08:00
chrislusf
e381356af9
change CLI option from publicIp to publicUrl
...
Now the publicUrl is free style text.
2015-02-02 15:51:25 -08:00
Chris Lu
7b4a53b2c1
Add optional admin port to volume server, to seperate admin operations from normal file operations.
2015-01-18 17:03:38 -08:00
Chris Lu
af416189f1
Cleanup error printing.
2015-01-13 17:04:41 -08:00
Chris Lu
5afdc469a3
Separate into admin and public mux for volume servers.
2015-01-13 00:45:26 -08:00
Brian McQueen
cec2b3724c
add server options to set redis and cassandra in the filer and corrected filer option description text
2015-01-08 00:41:27 -08:00
Chris Lu
e4531fc1e6
Add Redis support for Distributed Filer store.
2015-01-06 20:15:13 -08:00
Chris Lu
cceb5768c7
Adjust function name.
2015-01-06 19:26:48 -08:00
Chris Lu
49784d7f28
Add support for distributed filer metadata store.
2015-01-05 23:03:27 -08:00
Chris Lu
a3e4145e8a
refactoring for later security changes
2015-01-05 14:20:04 -08:00
Brian McQueen
d56c748fa8
switch it back to chris's repo
2014-12-14 00:35:26 -08:00
Brian McQueen
57ec736941
make it turn on the filer when filer.redirectOnRead is set
2014-12-14 00:33:16 -08:00
Brian McQueen
c0dfdf4392
switch to my forked repo
2014-12-14 00:20:21 -08:00
chrislusf
ba972694c7
Add filer option to redirect instead of proxying to volume server on file GET requests.
2014-12-08 20:27:26 -08:00
Chris Lu
8af4753002
Write request id to first 8 bytes of a file, instead of whole file, for
...
better write performance.
2014-11-28 16:34:03 -08:00
Chris Lu
179d36ba0e
formatting code by: goimports -w=true .
2014-10-26 11:34:55 -07:00
wyy
4126280d55
use github.com/chrislusf instead of github.com/aszxqw
2014-09-25 16:57:22 +08:00
wyy
1cd19447e3
use github.com/aszxqw instead of code.google.com/p
2014-09-25 00:47:09 +08:00
Chris Lu
a2f8d985fb
Fix typo.
2014-09-20 23:34:13 -07:00
Chris Lu
ba179b1542
Add "-ip.bind" option when starting volume servers.
...
Also some Weed->Seaweed changes.
2014-09-20 23:30:35 -07:00
Chris Lu
794b755f1d
rename to Seaweed File System
2014-09-20 21:18:26 -07:00
Chris Lu
625f880b15
Adjust "weed server" parameters.
2014-05-26 17:34:54 -07:00
Chris Lu
8ff0d17d6a
defauting images.fix.orientation option to true
2014-05-15 01:16:56 -07:00
Chris Lu
dcd12576c6
Add option to auto fix jpg orientation
2014-05-15 01:08:00 -07:00
Chris Lu
dac95464b8
better handling of os signals
2014-05-13 15:04:04 -07:00
Chris Lu
029923329d
add os.Kill signal to handle.
...
go fmt some code.
2014-05-13 11:32:10 -07:00
Chris Lu
982aaa41b9
Add control+c or INT handling
2014-05-13 00:03:10 -07:00
Chris Lu
729716ab7a
Add cpu profiling option.
2014-05-07 10:17:06 -07:00
Chris Lu
d344e87de0
Adjust command line options.
...
1. switch to use -publicIp instead of -publicUrl
2. -ip can be empty. It will listen to all available interfaces.
3. For "weed master", these options are changed:
-masterPort => -master.port
-peers => -master.peers
-mdir => -master.dir
-volumeSizeLimitMB => -master.volumeSizeLimitMB
-conf => -master.conf
-defaultReplicaPlacement => -master.defaultReplicaPlacement
-port => -volume.port
-max => -volume.max
2014-04-25 22:09:42 -07:00
Chris Lu
3b5035c468
1. v0.54
...
2. go vet found many printing format errors
2014-04-17 00:16:44 -07:00
Chris Lu
51939efeac
1. volume server now sends master server its max file key, so that
...
master server does not need to store the sequence on disk any more
2. fix raft server's failure to init cluster during bootstrapping
2014-04-16 23:43:27 -07:00
Chris Lu
67be8a5af8
adding filer!!!
2014-03-30 20:57:25 -07:00
Chris Lu
2861275fb6
working filer server!
2014-03-30 11:28:04 -07:00
Chris Lu
39b774a131
1. adding statistics reporting
...
2. refactor version to util package
2014-03-25 13:46:59 -07:00
Chris Lu
7c5c94785c
switch to idle timeout instead of read timeout
2014-03-20 11:07:15 -07:00
Chris Lu
92afbb858a
adjusting volumeSizeLimitMB default value and descriptions
2014-03-17 15:10:12 -07:00
Chris Lu
41143b3b78
toughen weedfs clustering, adding synchronizing max volume id among
...
peers in order to avoid the same volume id being assigned twice
1. moving raft.Server to topology
2. adding max volume id command for raft
2014-03-15 23:03:49 -07:00
Chris Lu
097aac2328
adjusting default read time out
2014-03-12 15:05:07 -07:00
Chris Lu
27c74a7e66
Major:
...
change replication_type to ReplicaPlacement, hopefully cleaner code
works for 9 possible ReplicaPlacement
xyz
x : number of copies on other data centers
y : number of copies on other racks
z : number of copies on current rack
x y z each can be 0,1,2
Minor:
weed server "-mdir" default to "-dir" if empty
2014-03-02 22:16:54 -08:00
Chris Lu
e7585548a4
working auto fail-over master node
2014-02-05 01:54:52 -08:00
Chris Lu
1d5c44e2df
adjust description text
2014-02-05 00:13:25 -08:00
Chris Lu
260fcd8e1e
reduce the default volume size to 32000MB from 32768MB
...
this avoids problems with busy writing systems from having too many file
id assigned while the volume is close to the overflow limit.
2014-01-29 13:34:46 -08:00