On 09/05/2011 02:48 AM, Tomas Vondra wrote:
> On 3 Září 2011, 9:26, Gerhard Wohlgenannt wrote:
>> Dear list,
>>
>> we are encountering serious performance problems with our database.
>> Queries which took around 100ms or less last week now take several
>> seconds.
>> Results of Bonnie++
>>
>> Version 1.96 ------Sequential Output------ --Sequential Input-
>> --Random-
>> Concurrency 1 -Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
>> --Seeks--
>> Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
>> /sec %CP
>> voyager 95G 1400 93 27804 3 16324 2 2925 96 41636 3
>> 374.9 4
>> Latency 7576us 233s 164s 15647us 13120ms
>> 3302ms
>> Version 1.96 ------Sequential Create------ --------Random
>> Create--------
>> voyager -Create-- --Read--- -Delete-- -Create-- --Read---
>> -Delete--
>> files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP
>> /sec %CP
>> 16 141 0 +++++ +++ 146 0 157 0 +++++ +++
>> 172 0
>> Latency 1020ms 128us 9148ms 598ms 37us
>> 485ms
>>
>
> That seems a bit slow ... 27MB/s for writes and 41MB/s forreads is ait
> slow with 8 drives.
>
> Tomas
>
>
Agreed, that's really slow. A single SATA drive will get 60 MB/s. Did you run Bonnie while the VM's were up and
running?
root@host:~# vmstat
procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu----
r b swpd free buff cache si so bi bo in cs us sy id wa
0 0 0 308024 884812 40512932 0 0 464 168 353 92 4 2 84 9
Only one line? That does not help much. Can you run it as 'vmstat 2' and let it run while a few slow queries are
performed? Then paste all the lines?
-Andy
