File glb.changes of Package glb
1
-------------------------------------------------------------------2
Tue Feb 12 19:53:19 UTC 2013 - cs@linux-administrator.com3
4
- update to release 0.9.2 5
6
-------------------------------------------------------------------7
Mon Jan 14 20:43:53 UTC 2013 - cs@linux-administrator.com8
9
- update to release 0.9.1 10
11
-------------------------------------------------------------------12
Sat Dec 22 09:58:32 UTC 2012 - cs@linux-administrator.com13
14
- update to release 0.9.015
* created subpackage for libglb0 and libglb-devel 16
17
-------------------------------------------------------------------18
Thu Dec 6 13:55:22 UTC 2012 - cs@linux-administrator.com19
20
- update to release 0.8.221
* hotfix to slow a connection initialization issue introduced in 0.8.122
* adds a 'random' balancing policy23
24
-------------------------------------------------------------------25
Tue Dec 4 20:44:22 UTC 2012 - cs@linux-administrator.com26
27
- update to release 0.8.128
* fixes connection loss when too many connections were attempted at once29
* significantly improves performance under certain kinds of load (like sysbench)30
* adds a max connections option31
* implements basic "source tracking" capability32
* adds a start/stop service script and is generally much more suitable to be run as a "service" 33
34
-------------------------------------------------------------------35
Fri May 18 19:02:53 UTC 2012 - cs@linux-administrator.com36
37
- update to release 0.7.538
* list of backend servers is configurable in runtime.39
* supports server "draining", i.e. does not allocate new connections40
to server, but does not kill existing ones, waiting for them to end gracefully.41
* on Linux 2.6 and higher glb uses epoll API for ultimate performance.42
* glb is multithreaded, so it can utilize multiple CPU cores.43
In fact even on a single core CPU using several threads can44
significantly improve performance when using poll()-based IO.45
* connections are distributed proportionally to weights assigned to backend servers. 46
47