Hi all,

I'm running a set of three 389-ds servers with about 50 databases with replication on each server.

No I'm encounter a constant very hight disk write rate (about 300 write io/sec.).

In the audit-log there is nothing what would explain this. But in iotop I see a lot of threads like:

1621 be/4 dirsrv 0.00 B/s 3.95 K/s 0.00 % 0.46 % ns-slapd -D /etc/dirsrv/slapd-ldap0 -i /var/run/dirsrv/slapd-ldap0.pid -w /var/run/dirsrv/slapd-ldap0.startpid 1628 be/4 dirsrv 0.00 B/s 7.90 K/s 0.00 % 0.46 % ns-slapd -D /etc/dirsrv/slapd-ldap0 -i /var/run/dirsrv/slapd-ldap0.pid -w /var/run/dirsrv/slapd-ldap0.startpid

....

1631 be/4 dirsrv 0.00 B/s 892.18 K/s 0.00 % 0.00 % ns-slapd -D /etc/dirsrv/slapd-ldap0 -i /var/run/dirsrv/slapd-ldap0.pid -w /var/run/dirsrv/slapd-ldap0.startpid 1463 be/4 dirsrv 0.00 B/s 580.31 K/s 0.00 % 0.00 % ns-slapd -D /etc/dirsrv/slapd-ldap0 -i /var/run/dirsrv/slapd-ldap0.pid -w /var/run/dirsrv/slapd-ldap0.startpid 1462 be/4 dirsrv 0.00 B/s 363.19 K/s 0.00 % 0.00 % ns-slapd -D /etc/dirsrv/slapd-ldap0 -i /var/run/dirsrv/slapd-ldap0.pid -w /var/run/dirsrv/slapd-ldap0.startpid

I configured caching and have entrycachehits about 99 - but anyway this would have only impact to read-operations.