Messages in this thread | | | Date | Wed, 15 Sep 1999 01:39:01 -0700 (PDT) | From | Chris Cooney <> | Subject | SW Raid test platform? |
| |
In the near future i'm going to be playing around with software raid as a personal research project. The hardware will probably look like this:
K6-2 processor ~300Mhz, 64 MB ram 4-6 atapi disks ~6GB or so running off of the motherboard and an add-in card (probably ata-66 pci cards)
Questions:
Is this system likely to be cpu limited (for raid levels 3, 5) or does it have enough power to expect that the disks will be fully utilized?
is the raidable component large enough to reasonably expect that i will encounter the effects of raid (increased read capacity, increased latency, potential for degraded write speed, cpu loading from parity calculations and so on)? rephrase: will this hit scalability issues inherent to raid and not be dwarfed by other factors (atapi weirdness for example)?
Are there any changes you would make (aside from a scsi implementation, due to money) to reduce outside factors?
thanks, -chris
"We returned the General to El Salvador, or maybe Guatemala, it's difficult to tell from 10,000 feet"
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |