Hello there,
I'm installing HP DL180 G6 with 12-disk front bay.
Internals:
one Xeon E5520 CPU, 6GB RAM,
SmartArray P212 controller with 256MB cache. Disk cage is loaded with 2x 146GB SAS disks and 4x 2GB SATA disks.
Controller is running latest available firmware (3.66) and has two logical disks configured:
- RAID1 volume based on 146GB SAS disks, visible to underlaying linux system as /dev/cciss/c0d0
- RAID5 volume based on 2TB SATA disks, /dev/cciss/c0d1
hpacucli shows everything is fine, and I can see the real size of RAID devices:
# cat /proc/partitions
major minor #blocks name
104 0 143338560 cciss/c0d0
104 1 96358 cciss/c0d0p1
104 2 143235540 cciss/c0d0p2
104 16 5860445272 cciss/c0d1
104 17 5860444160 cciss/c0d1p1
(Partition 1, c0d1p1 was created with parted after initializing the GPT label)
However, my block write attempts fail.
I cannot write to the partition, it fails right away:
# dd if=/dev/zero of=/dev/c0d1p1 bs=1M count=10240
dd: writing `/dev/c0d1p1': No space left on device
1+0 records in
0+0 records out
4096 bytes (4.1 kB) copied, 0.000534731 s, 7.7 MB/s
If I would write to the disk itself, it would give me a headroom of 3.1GB:
# dd if=/dev/zero of=/dev/c0d1 bs=1M count=10240
dd: writing `/dev/c0d1': No space left on device
2978+0 records in
2977+0 records out
3122606080 bytes (3.1 GB) copied, 1.32505 s, 2.4 GB/s
Some technical information:
Debian Linux version 6.0 (squeeze)
Linux hostname 2.6.32-5-amd64 #1 SMP Wed Jan 12 03:40:32 UTC 2011 x86_64 GNU/Linux
dmesg does not show anything strange
# modinfo cciss | grep version:
version: 3.6.20
srcversion: 9DE0C3ECDF1A8C9C0467DBF
Ideas anyone?
Regards,
Vlad
I'm installing HP DL180 G6 with 12-disk front bay.
Internals:
one Xeon E5520 CPU, 6GB RAM,
SmartArray P212 controller with 256MB cache. Disk cage is loaded with 2x 146GB SAS disks and 4x 2GB SATA disks.
Controller is running latest available firmware (3.66) and has two logical disks configured:
- RAID1 volume based on 146GB SAS disks, visible to underlaying linux system as /dev/cciss/c0d0
- RAID5 volume based on 2TB SATA disks, /dev/cciss/c0d1
hpacucli shows everything is fine, and I can see the real size of RAID devices:
# cat /proc/partitions
major minor #blocks name
104 0 143338560 cciss/c0d0
104 1 96358 cciss/c0d0p1
104 2 143235540 cciss/c0d0p2
104 16 5860445272 cciss/c0d1
104 17 5860444160 cciss/c0d1p1
(Partition 1, c0d1p1 was created with parted after initializing the GPT label)
However, my block write attempts fail.
I cannot write to the partition, it fails right away:
# dd if=/dev/zero of=/dev/c0d1p1 bs=1M count=10240
dd: writing `/dev/c0d1p1': No space left on device
1+0 records in
0+0 records out
4096 bytes (4.1 kB) copied, 0.000534731 s, 7.7 MB/s
If I would write to the disk itself, it would give me a headroom of 3.1GB:
# dd if=/dev/zero of=/dev/c0d1 bs=1M count=10240
dd: writing `/dev/c0d1': No space left on device
2978+0 records in
2977+0 records out
3122606080 bytes (3.1 GB) copied, 1.32505 s, 2.4 GB/s
Some technical information:
Debian Linux version 6.0 (squeeze)
Linux hostname 2.6.32-5-amd64 #1 SMP Wed Jan 12 03:40:32 UTC 2011 x86_64 GNU/Linux
dmesg does not show anything strange
# modinfo cciss | grep version:
version: 3.6.20
srcversion: 9DE0C3ECDF1A8C9C0467DBF
Ideas anyone?
Regards,
Vlad