[Date Prev][Date Next] [Chronological] [Thread] [Top]

Re: How to improve performance with MDB backend?



For second test I have changed I/O scheduler only
Nothing changed in terms of adding speed!

Test start    Test stop      Test duration        Num users    User/sec

19.4.2013     19.4.2013    min 5759,00            742837        128,99
14:37:45       16:13:34     sec 95,98333

[root@spr1 /]# cat /sys/block/sda/queue/scheduler
noop [anticipatory] deadline cfq

Total DISK READ: 0.00 B/s | Total DISK WRITE: 7.91 M/s
  TID  PRIO  USER     DISK READ  DISK WRITE  SWAPIN     IO>    COMMAND
 4165 be/4 root        0.00 B/s 1307.21 K/s  0.00 % 99.99 % [flush-8:0]
 2058 be/3 root        0.00 B/s    0.00 B/s  0.00 % 99.99 % [jbd2/sda3-8]
 4144 be/4 openldap    0.00 B/s    2.23 M/s  0.00 %  0.00 % slapd -h ldap:/// -F /opt/openldap/etc/openldap/slapd.d -g openldap -u openldap
 4145 be/4 openldap    0.00 B/s    2.18 M/s  0.00 %  0.00 % slapd -h ldap:/// -F /opt/openldap/etc/openldap/slapd.d -g openldap -u openldap
 4146 be/4 openldap    0.00 B/s    2.28 M/s  0.00 %  0.00 % slapd -h ldap:/// -F /opt/openldap/etc/openldap/slapd.d -g openldap -u openldap
 4157 be/4 openldap    0.00 B/s    2.19 M/s  0.00 %  0.00 % slapd -h ldap:/// -F /opt/openldap/etc/openldap/slapd.d -g openldap -u openldap
    1 be/4 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % init

   
On second server I/O is different

Total DISK READ: 0.00 B/s | Total DISK WRITE: 9.92 M/s
  TID  PRIO  USER     DISK READ  DISK WRITE  SWAPIN     IO>    COMMAND
 2141 be/3 root        0.00 B/s    0.00 B/s  0.00 % 99.99 % [jbd2/sda3-8]
 4284 be/4 root        0.00 B/s 1580.46 K/s  0.00 % 73.88 % [flush-8:0]
 4201 be/4 openldap    0.00 B/s   56.76 M/s  0.00 %  0.00 % slapd -h ldap:/// -F /opt/openldap/etc/openldap/slapd.d -g openldap -u openldap

 I/O difference?