Content deleted Content added
rm excess whitespace |
→Performance: Correct capitalization of GitHub |
||
Line 51:
Zimbra has tested back-mdb vs back-hdb performance in OpenLDAP, with LMDB clearly outperforming the BDB based back-hdb.<ref>{{cite web | url=http://wiki.zimbra.com/wiki/OpenLDAP_MDB_vs_HDB_performance|title=OpenLDAP MDB vs HDB performance|publisher=Zimbra, Inc.}}</ref> Many other OpenLDAP users have observed similar benefits.<ref>{{cite web|url=https://mishikal.wordpress.com/2013/05/16/openldap-a-comparison-of-back-mdb-and-back-hdb-performance/|title=OpenLDAP: A comparison of back-mdb and back-hdb performance|date=16 May 2013|accessdate=8 May 2017}}</ref>
Since the initial benchmarking work done in 2012, multiple follow-on tests have been conducted with additional database engines for both in-memory <ref>{{cite web|last1=Chu|first1=Howard|title=In-Memory Microbenchmark|url=http://symas.com/mdb/inmem/|publisher=Symas Corp.|access-date=2014-12-06|archive-url=https://web.archive.org/web/20141209233002/http://symas.com/mdb/inmem/|archive-date=2014-12-09|url-status=dead}}</ref> and on-disk <ref>{{cite web|last1=Chu|first1=Howard|title=On-Disk Microbenchmark|url=http://symas.com/mdb/ondisk/|publisher=Symas Corp.|access-date=2014-12-06|archive-url=https://web.archive.org/web/20141209233807/http://symas.com/mdb/ondisk/|archive-date=2014-12-09|url-status=dead}}</ref> workloads characterizing the performance across multiple CPUs and record sizes. These tests show that LMDB performance is unmatched on all in-memory workloads, and excels in all disk-bound read workloads, as well as disk-bound write workloads using large record sizes. The benchmark driver code was subsequently published on
== Reliability ==
| |||