For pure reads, there should be no significant difference. However, it
is extrememly difficult (with default mount options, anyway) to generate
pure read access to a normal file system (discounting raw devices used
for databases and such here), since every file access updates the at
least the inode atime of the file that's being read. So, a pure read
pattern (from the user perspective) still generates quite a few writes,
which can easily lead to a perceived degradation in performance.
If atime is not important for this particular file system, you might
want to consider turning it off (a la 'mount -o noatime').
tw
On 07/29/1999 01:10 -0400, Jan Edler wrote:
>> Can anyone explain why a software raid5 array of N disks has
>> significantly lower read performance than a raid0 array of N-1 disks?
>> I'm only considering the case where there are no drive failures.
>>
>> I'm using 8 Seagate ST317242A drives in UDMA-66 mode, with 4 Promise
>> Ultra-66 cards, one drive per channel. This is with linux-2.2.10
>> + 2.2.10.uniform-ide-6.20.eridanus.patch from http://www.kernel.dk/ide,
>> + raid0145-19990724-2.2.10.bz2 and raidtools-19990724-0.90.tar.bz2.
>> The only problem is that, for some reason, the system hangs in SMP mode,
>> but it works fine in uniprocessor mode. I don't know when I'll get
>> time to try fixing that problem, but for now uniprocessor is ok for
>> my testing.
>>
>> On a Pentium II/400 I get ~60MB/s reading a file with raid0 on 6 drives,
>> but <40MB/s with raid5 on 8 drives.
>>
>> Thanks,
>> Jan Edler
>> NEC Research Institute
End of included message
--
+------------------------------+--------------------------+
| Tim Walberg | Phone: 847-782-2472 |
| TERAbridge Technologies Corp | FAX: 847-623-1717 |
| 1375 Tri-State Parkway | [EMAIL PROTECTED] |
| Gurnee, IL 60031 | 800-SKY-TEL2 PIN 9353299 |
+------------------------------+--------------------------+
PGP signature
