Server Fault Stack Exchange
Server Fault Stack Exchange

Questions tagged [nvme]

112 questions
5
votes
2 answers

How to explain these fio bandwidth results?

Been running a couple of fio tests on a new server with the following setup: 1x Samsung PM981a 512GB M.2 NVMe drive. Proxmox installed with ZFS on root. 1x VM with 30GB space created and Debian 10 installed. 6x Intel P4510 2TB U.2 NVMe drives…
Woodgnome
  • 203
  • 1
  • 8
4
votes
2 answers

Cannot connect to EC2 instance after converting Ubuntu 16 PV to Ubuntu 16 HVM

So it's been a few days and I still can not connect to my new HVM instance with EC2 running Ubuntu 16. For reference, I am trying to upgrade our server from an m3 instance running Ubuntu 16, to a C5 instance running Ubuntu 16. For almost every…
Alex
  • 221
  • 2
  • 8
4
votes
1 answer

Encrypt disks using SED and store keys in TPM?

I'm buying servers lately and all of them have disks that support TCG Opal full-disk encryption (aka SED). What I'd like to do is: Store data encrypted-at-rest on the disks (NVMe & SAS). Not be required to enter a password/passphrase at server…
Evan
  • 307
  • 1
  • 4
  • 12
4
votes
1 answer

Is it worse to go with Samsung 960 EVO instead of Pro version in terms of price to perforamce measure?

We are about to deploy shared storage researching for ultra-fast storage to implement Microsoft SQL Server Failover Cluster (FCI). So far the project goes, we would to start with 500K IOPS and have ability of grows up to 2M IOPS in a year or so, due…
Joshua Turnwell
  • 530
  • 3
  • 12
4
votes
1 answer

NVMe latency monitoring

Is there a way to get read/write queue latencies from NVMe devices? If it's not split for read/write that's better than nothing but ideally I could see these separately. I'd like to go below the usual millisecond level and haven't found anything so…
Zoltán
  • 155
  • 11
4
votes
3 answers

Get exact SMART error from Intel RST (Rapid Storage Technology)

On one system I use dual NVMe m.2 drives on an Intel Z170 board in RAID0 with Intel RST. After about 6 months of light use the Intel RST Tool gives me a SMART error. The only option I have is to suppress the error. Instead of suppressing I would…
user643011
  • 139
  • 1
  • 10
4
votes
2 answers

nvme device dropouts - I/O 0 QID 0 timeout, controller disabled

We have 6 Supermicro servers all of the same (or very similar spec), Over the last two weeks one of them has been dropped an NVMe disk at random times due to: [ 66.856719] nvme 0000:03:00.0: I/O 0 QID 0 timeout, disable controller [ 66.957911]…
s_mcleod
  • 41
  • 1
  • 3
4
votes
1 answer

NVMe drives write performance in software RAID 1

We have just received two brand new Supermicro servers 1028U-TN10RT+ with 10 NVMe slots, two of them with Intel DC P3600 800gb hard drives. We were eager to test the performance of the drives as the specification is promising very good read (up to…
markz
  • 173
  • 1
  • 4
4
votes
2 answers

Map PCIe slot number (or BDF) to device number or vice versa

Is there any way to know the drive number from BDF or slot number of a PCIe or vice versa? Suppose I have four PCIe drives attached to my system. And I know their BDF's, I want to know each of the drives corresponding drive number in OS.…
kate
  • 41
  • 1
  • 2
4
votes
1 answer

pacemaker agent nvmet-subsystem missing

I tried to follow the drbd Howto "Highly Available NVMe Over Fabrics (NVMe-oF) on RHEL 9", but run into the error `Error: Unable to find agent 'nvmet-subsystem', try specifying its full name` `Error: Errors have occurred, therefore pcs is unable to…
kumpel4
  • 41
  • 2
4
votes
2 answers

How does hardware RAID handle firmware updates for the underlying drives?

My SuperMicro X13SAE has hardware raid for the three m.2 NVME drives that it supports. My question is how does it handle firmware updates for these drives? If the drives aren't being exposed to the operating system, then I assume fwupdmgr and…
Evan Carroll
  • 2,373
  • 10
  • 34
  • 53
4
votes
0 answers

AWS: Can't mount my restored volume (EBS snapshot)

I restored an EBS volume from AWS Backup and attached it to a new EC2 instance. When I lsblk I can see it under the name /dev/nvme1n1. More specifically the output of lsblk is: NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT loop0 7:0 0 …
HelloWorld
  • 137
  • 4
4
votes
3 answers

How can I override IRQ affinity for NVME devices

I am trying to move all interrupts over to cores 0-3 to keep the rest of my cores free for high speed, low latency virtualization. I wrote a quick script to set IRQ affinity to 0-3: #!/bin/bash while IFS= read -r LINE; do echo "0-3 ->…
Hubro
  • 1,138
  • 4
  • 16
  • 35
3
votes
1 answer

Intel NVME performance on Linux

I have an Intel 760P NVME drive hooked up to a Supermicro X11SRM-F with a Xeon W-2155 and 64GB of ddr4-2400 RAM. The specs for this drive claim 205K-265K IOPS (whatever 8GB span means) with about 3G/s random-read and 1.3G/s random write. I've…
Server Fault
  • 3,714
  • 12
  • 54
  • 89
3
votes
0 answers

How to setup nvmetcli for FC loopback mode?

I have a NVMe SSD, KC1000, from Kingston and a HBA, QLE2672 2-port 16Gb Fibre Channel Adapter, from QLogic and are installed on Linux kernel 4.16.6. Then I would like to set up a scenario which has a fc loop mode which is to use the sole FC HBA as…
codexplorer
  • 181
  • 5
1
2
3 4 5 6 7 8