raid array seek performance

Поиск
Список
Период
Сортировка
От Samuel Gendler
Тема raid array seek performance
Дата
Msg-id CAEV0TzAT0rJ2rWdpkwavVQBsvt9gf-EqVn9Fh9Ee2H-rArDm+Q@mail.gmail.com
обсуждение исходный текст
Ответы Re: raid array seek performance
Re: raid array seek performance
Список pgsql-performance
I'm just beginning the process of benchmarking and tuning a new server.  Something I really haven't done before.  I'm using Greg's book as a guide.  I started with bonnie++ (1.96) and immediately got anomalous results (I think).

Hardware is as follows:

2x quad core xeon 5504 2.0Ghz, 2x4MB cache
192GB DDR3 1066 RAM
24x600GB 15K rpm SAS drives
adaptec 52445 controller

The default config, being tested at the moment, has 2 volumes, one 100GB and one 3.2TB, both are built from a stripe across all 24 disks, rather than splitting some spindles out for one volume and another set for the other volume.  At the moment, I'm only testing against the single 3.2TB volume.

The smaller volume is partitioned into /boot (ext2 and tiny) and / (ext4 and 91GB).  The larger volume is mounted as xfs with the following options (cribbed from an email to the list earlier this week, I think): logbufs=8,noatime,nodiratime,nobarrier,inode64,allocsize=16m

Bonnie++ delivered the expected huge throughput for sequential read and write.  It seems in line with other benchmarks I found online.  However, we are only seeing 180 seeks/sec, but seems quite low.  I'm hoping someone might be able to confirm that and. hopefully, make some suggestions for tracking down the problem if there is one.

Results are as follows:

1.96,1.96,newbox,1,1315935572,379G,,1561,99,552277,46,363872,34,3005,90,981924,49,179.1,56,16,,,,,19107,69,+++++,+++,20006,69,19571,72,+++++,+++,20336,63,7111us,10666ms,14067ms,65528us,592ms,170ms,949us,107us,160us,383us,31us,130us


Version      1.96   ------Sequential Output------ --Sequential Input- --Random-
                    -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
newzonedb.z1.p 379G  1561  99 552277  46 363872  34  3005  90 981924  49 179.1  56
Latency              7111us   10666ms   14067ms   65528us     592ms     170ms
                    ------Sequential Create------ --------Random Create--------
                    -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
files:max:min        /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
newbox            16 19107  69 +++++ +++ 20006  69 19571  72 +++++ +++ 20336  63
Latency               949us     107us     160us     383us      31us     130us

Also, my inclination is to default to the following volume layout:

2 disks in RAID 1 for system
4 disks in RAID 10 for WAL (xfs)
18 disks in RAID 10 for data (xfs)

Use case is minimal OLTP traffic, plus a fair amount of data warehouse style traffic - low connection count, queries over sizeable fact tables (100s of millions of rows) partitioned over time, insert-only data loading, via COPY, plus some tables are populated via aggregation queries over other tables.  Basically, based on performance of our current hardware, I'm not concerned about being able to handle the data-loading load, with the 4 drive raid 10 volume, so emphasis is on warehouse query speed.  I'm not best pleased by the 2 Ghz CPUs, in that context, but I wasn't given a choice on the hardware.

Any comments on that proposal are welcome.  I've got only a week to settle on a config and ready the box for production, so the number of iterations I can go through is limited.


В списке pgsql-performance по дате отправления:

Предыдущее
От: Stefan Keller
Дата:
Сообщение: Re: Postgres for a "data warehouse", 5-10 TB
Следующее
От: Scott Marlowe
Дата:
Сообщение: Re: Postgres for a "data warehouse", 5-10 TB