|
Home > Archive > Data Storage > September 2007 > Adaptec 2810SA extremely fast or extremely slow?
You are viewing an archived Text-only version of the thread.
To view this thread in it's original format and/or if you want to reply to
this thread please [click here]
| Author |
Adaptec 2810SA extremely fast or extremely slow?
|
|
| Fondazione Distrofici Onlus 2007-09-05, 1:19 pm |
| Hi, sorry for bad english..
I've got a Tyan Thunder S2885 and an Adaptec 2810SA, configured as
follows:
- 5 Maxtor 300gb hard disks on adaptec card
- 1 Maxtor 160gb hard disk attached to the motherboard
- 3 RAID5 volumes (partitions) on adaptec card
- 1 partition 1TB
- 1 partition 160 GB
- 1 partition 5GB
After executing a benchmark test, the results surprised me...
All the volumes of the Adaptec card showed the same results:
________________________________________
____________________
READ
- sequential read (large files):
- random read (large files):
- sequential read (small files):
- random read (small files):
________________________________________
____________________
WRITE
- sequential write (large files):
- random write(large files):
- sequential write(small files):
- random write(small files):
Aren't these results strange for what is said to be an "ideal cost-
effective solution for applications where high levels of sustained
read and write performance are required, including video streaming,
web content, reference data and fixed content storage" ??
Thanks a lot,
Marco
| |
| moojit 2007-09-07, 1:14 am |
|
"Fondazione Distrofici Onlus" <info@disys.it> wrote in message
news:1189011253.327390.256380@g4g2000hsf.googlegroups.com...
> Hi, sorry for bad english..
> I've got a Tyan Thunder S2885 and an Adaptec 2810SA, configured as
> follows:
>
> - 5 Maxtor 300gb hard disks on adaptec card
> - 1 Maxtor 160gb hard disk attached to the motherboard
> - 3 RAID5 volumes (partitions) on adaptec card
> - 1 partition 1TB
> - 1 partition 160 GB
> - 1 partition 5GB
>
> After executing a benchmark test, the results surprised me...
>
> All the volumes of the Adaptec card showed the same results:
> ________________________________________
____________________
> READ
> - sequential read (large files):
> - random read (large files):
>
> - sequential read (small files):
> - random read (small files):
>
> ________________________________________
____________________
> WRITE
> - sequential write (large files):
> - random write(large files):
>
> - sequential write(small files):
> - random write(small files):
>
>
>
> Aren't these results strange for what is said to be an "ideal cost-
> effective solution for applications where high levels of sustained
> read and write performance are required, including video streaming,
> web content, reference data and fixed content storage" ??
>
> Thanks a lot,
> Marco
>
Try DataMover For Windows (http://www.moojit.net/Networking/downloads.shtml)
it may provide better benchmark data. Random I/O is a purely subjective
implementation, DataMover only performs sequential I/O. It tests many
different transfer sizes between 512B and 4MB in half and full duplex
operation.
Moojit
|
|
|
|
|