305dc816525f461f9bfe640d87f671f53f0e0fc6

Doing an fsync per-record when receiving the complete HDB is a performance disaster. Among other things, if the HDB is very large, then one slave receving a full HDB can cause other slaves to timeout and, if HDB write activity is high enough to cause iprop log truncation, then also need full syncs, which leads to a cycle of full syncs for all slaves until HDB write activity drops. Allowing the iprop log to be larger helps, but improving receive_everything() performance helps even more.
Heimdal
Heimdal is a Kerberos 5 implementation.
For information how to install see here.
There are man pages for most of the commands.
Bug reports and bugs are appreciated. Use GitHub issues or send e-mail to heimdal-bugs@h5l.org.
For more information see the project homepage https://www.h5l.org/ or the mailing lists:
- heimdal-announce@sics.se low-volume announcement
- heimdal-discuss@sics.se high-volume discussion
Send e-mail to heimdal-announce-request@sics.se and heimdal-discuss-request@sics.se respectively to subscribe.
Build Status
Description
Languages
C
92.1%
Roff
2.8%
Shell
2.3%
Makefile
0.7%
M4
0.5%
Other
1.4%