Интересная презентация на тему пригдоности Экзадаты и ODA для OLTP-задач:
Презентация немного устаревшая – еще про Х2-2 и не учитывает WriteBack Smart Flash Cache, но тем не менее весьма полезная.
Showing posts with label ODA. Show all posts
Showing posts with label ODA. Show all posts
Wednesday, May 15, 2013
Wednesday, February 27, 2013
ODA X3-2
Вышла ODA Х3-2. Изменения:
Было Стало Всего в новой ODA
------ --------------- -------------------- -----------------
CPU: 12 core/server 16 core/server 32 core
2*6core 2*8core
RAM: 96g 256g/server 512g
Disks:
Hard: 20* 600g 20* 900g 18T
SSD: 4* 73g 4* 200g 800g
------ --------------- -------------------- -----------------
Не сбылись наши мечты о :
- HCC на ODA
- Standard Edition на ODA.
Однако, поскольку на ODA возможна виртуализация, то есть возможность поднять виртуалку с SE и вообще любыми версиями СУБД и (да и вообще с любым софтом). Также с учетом виртуализации можно поднять на ODA и сервера приложений.
Было Стало Всего в новой ODA
------ --------------- -------------------- -----------------
CPU: 12 core/server 16 core/server 32 core
2*6core 2*8core
RAM: 96g 256g/server 512g
Disks:
Hard: 20* 600g 20* 900g 18T
SSD: 4* 73g 4* 200g 800g
------ --------------- -------------------- -----------------
Не сбылись наши мечты о :
- HCC на ODA
- Standard Edition на ODA.
Однако, поскольку на ODA возможна виртуализация, то есть возможность поднять виртуалку с SE и вообще любыми версиями СУБД и (да и вообще с любым софтом). Также с учетом виртуализации можно поднять на ODA и сервера приложений.
Sunday, March 11, 2012
ODA IO performance summary
Oracle Database Appliance IO performance was measured with different tools: Orion, Calibrate, oakcli.
Here is summary:
Despite of ORION documentation examples showed against raw (character) devices I used block devices (first column) because Linux deprecated raw devices.
SAS Disks were tested with 8K block size.
SSD columns:
Because of 512b redo log block size I wanted to measure SSD performance for 512 bytes blocks. But ORION don't have the 512 bytes block size. The 1K is minimum.The steps are:
- 1K - because it nearest to the 512b
- 4K - because it is default SSD block size, so this size is optimal for IO operations
- 8K - for comparison purposes. If you put db file on SSD.
Calibrate IO:
I thinks that number of IOPS=14238 is double measured mistake .
The more real number is an half of this value 7119 ( theoretical value is: 20 disks * 320 IOPS = 6400 IOPS) . Calibrate_IO uses database block size, the 8K in our case.
Here is summary:
Despite of ORION documentation examples showed against raw (character) devices I used block devices (first column) because Linux deprecated raw devices.
SAS Disks were tested with 8K block size.
SSD columns:
Because of 512b redo log block size I wanted to measure SSD performance for 512 bytes blocks. But ORION don't have the 512 bytes block size. The 1K is minimum.The steps are:
- 1K - because it nearest to the 512b
- 4K - because it is default SSD block size, so this size is optimal for IO operations
- 8K - for comparison purposes. If you put db file on SSD.
Calibrate IO:
I thinks that number of IOPS=14238 is double measured mistake .
The more real number is an half of this value 7119 ( theoretical value is: 20 disks * 320 IOPS = 6400 IOPS) . Calibrate_IO uses database block size, the 8K in our case.
Subscribe to:
Posts (Atom)