Server Fault Stack Exchange
Server Fault Stack Exchange

Questions tagged [mdraid]

16 questions
4
votes
1 answer

XFS very slow on LVMed Raid 6

i have a new storage server with 6 x 8TB WD Red HDDs. They build a RAID 6 with mdadm and a chunk size of 256k. On top of that mdraid i have LVM which then holds the different filesystems. Initially i wanted to use XFS as filesystem, but the…
teissler
  • 738
  • 7
  • 11
3
votes
1 answer

Expanding ZFS on MDRaid?

I had a 4-disk mdraid of 8.12TB with zfsonlinux's ZFS: # zpool status pool: tank state: ONLINE scan: none requested config: NAME STATE READ WRITE CKSUM tank ONLINE 0 0 0 …
pascal
  • 221
  • 1
  • 9
3
votes
3 answers

RAID6 mdraid -> LVM -> EXT4 root with GRUB2?

2012-03-31 Debian Wheezy daily build in VirtualBox 4.1.2, 6 disk devices. My steps to reproduce so far: Setup one partition, using the entire disk, as a physical volume for RAID, per disk Setup a single RAID6 mdraid array out of all of those Use…
Rotonen
  • 71
  • 1
  • 9
2
votes
0 answers

Creating RAID 1 using mdadm for Root disk in Linux:

I recently found one of our production server (running RHEL7) doesn’t have the root disk mirrored. So, we thought of using one of the spare disks (which has some junk data) for mirroring the root disk using mdraid. I wanted to do it without…
Ram Kumar
  • 73
  • 1
  • 3
  • 8
2
votes
1 answer

One disk accessed more than others during md RAID6 rebuild

I am rebuilding one drive of an 8-drive RAID6 (using 'md' Linux software RAID), and have noticed that it doesn't seem to be going as fast as it could, presumably because one of the drives is being sent twice as many IOPS as the others: Device: …
jonny5532
  • 21
  • 2
2
votes
1 answer

What would be the ideal solution to sync 2 offline systems?

we are in a special case where we have 2 Ubuntu offline servers in 2 DCs and should be kept offline when not used. When we need to use them, we power up one of them, do whatever we want physically via KVM and then power it off again. Network…
thouvou
  • 43
  • 3
1
vote
1 answer

linux mdraid: sfdisk partition table copy fails

One of the disks in my MD RAID 1 failed, and I had it replaced. Now the system runs on /dev/sdb, /dev/sda is blank. Although the disks are not identical (SAMSUNG HD753LJ vs. SAMSUNG HD754JJ), I made sure they both have the exact same size: Disk…
Arno Schäfer
  • 401
  • 4
  • 5
1
vote
0 answers

SSD Temperture Increases during idle

I have 4 Samsung 850 EVO SSDs in a mdraid 10 array inside a high performance simple NAS. running Centos6.8 minimal. I have found that the SSD tempertures start to increase on their own without any disk io. this happens to only some of the drives at…
x422man
  • 11
  • 1
1
vote
1 answer

Why does md resync cause no iowait?

I've known the defintion of %iowait as Time the CPU spent idling/blocking, because it had to wait on an IO operation to complete. Now take a simple Linux system with an mdraid1 and two disks. /proc/mdstat shows that the resync is running at about…
dog
  • 168
  • 4
1
vote
1 answer

moving mdraid from failed Buffalo NAS

I've been tasked with restoring a RAID from a failed Buffalo NAS. the NAS box has failed, but our understanding at this point is that the drives are still functioning. I believe that Buffalo's NAS was using mdraid+Linux in a RAID5 of 4x1TB drives.…
neoice
  • 874
  • 4
  • 17
0
votes
0 answers

Poor disk performance on KVM guest

I have a server running Proxmox and some Linux VMs running on it. On the host, I get 200+ MB/s write to the disk On a VM, I only get around 50-60 MB/s Caching is disabled for all VMs. I'm using Virtio-SCSI as storage controller Specs of the…
patrick7
  • 1
  • 2
0
votes
0 answers

Server reverted to may after reboot

I just had a problem on a client's server, it wasn't responding to anything so I forced a reboot. The client called shortly after to say the website reverted to a version from May. Checked the backups we do every night, and indeed the backup from…
Ulrar
  • 367
  • 4
  • 22
0
votes
2 answers

Headless server with an mdraid array won't boot

I'm in a bit of a pickle. I have a headless server (Acer EasyStore) running Ubuntu 12.04.1, which, after an update, now refuses to boot. It has four disks, one of which holds the OS in a partition and the rest, along with the other three disks, is…
Stavros Korokithakis
  • 275
  • 1
  • 3
  • 12
0
votes
0 answers

Re-add physically removed hdd in mdraid having lvm

I have 4 raid6 devices on my server /dev/md0, /dev/md1,/dev/md2 and /dev/md3 each having 9 hdd. I accidently removed /dev/sda1 without removing it from raid md1. When I re-inserted it, raid md1 is not adding /dev/sda1 back, md1 shows it as…
ravinder saharan
  • 1
0
votes
1 answer

How do I maximize nvme raid0(md) performance (in linux)?

Nvme raid0 read(and write) performance is sometimes worse than the performance of one individual underlying drive. hdparm -t /dev/md0 : Timing buffered disk reads: 7054 MB in 3.00 seconds = 2350.46 MB/sec hdparm -t /dev/nvme0n1 : Timing…
Horatiu
  • 41
  • 5
1
2