>Groovy. Channel drives are IMHO a pain, though in the case of certain
>manufacturers it can be the only way to get firmware updates. Channel drives
>often only have a 3 year warranty, vs 5 for generic drives.
Yes, we have run into this with Kioxia as far as being able to find new
firmware.
By HBA I suspect you mean a non-RAID HBA?
Yes, something like the HBA355
NVMe SSDs shouldn’t cost significantly more than SATA SSDs. Hint: certain
tier-one chassis manufacturers mark both the fsck up. You can get a better
warranty and pricing by buying drives from a VAR.
We
nes server with 8-12 direct
attach NVMe?
On Fri, Jan 12, 2024 at 02:32:12PM +0000, Drew Weaver wrote:
> Hello,
>
> So we were going to replace a Ceph cluster with some hardware we had
> laying around using SATA HBAs but I was told that the only right way
> to build Ceph in 2023 i
Hello,
So we were going to replace a Ceph cluster with some hardware we had laying
around using SATA HBAs but I was told that the only right way to build Ceph in
2023 is with direct attach NVMe.
Does anyone have any recommendation for a 1U barebones server (we just drop in
ram disks and cpus)
, 2023 12:33 PM
To: Drew Weaver
Cc: ceph-users@ceph.io
Subject: Re: [ceph-users] Building new cluster had a couple of questions
Sorry I thought of one more thing.
I was actually re-reading the hardware recommendations for Ceph and it seems to
imply that both RAID controllers as well as HBAs
actually build a cluster with many disks 12-14
each per server without any HBAs in the servers.
Are there certain HBAs that are worse than others? Sorry I am just confused.
Thanks,
-Drew
-Original Message-
From: Drew Weaver
Sent: Thursday, December 21, 2023 8:51 AM
To: 'ceph-users@ceph.io
Howdy,
I am going to be replacing an old cluster pretty soon and I am looking for a
few suggestions.
#1 cephadm or ceph-ansible for management?
#2 Since the whole... CentOS thing... what distro appears to be the most
straightforward to use with Ceph? I was going to try and deploy it on Rocky
.
Thanks,
-Drew
-Original Message-
From: Dave Holland
Sent: Tuesday, February 14, 2023 11:39 AM
To: Drew Weaver
Cc: 'ceph-users@ceph.io'
Subject: Re: [ceph-users] iDRAC 9 version 6.10 shows 0% for write endurance on
non-dell drives, work around? [EXT]
On Tue, Feb 14, 2023 at 04:00
Hello,
After upgrading a lot of iDRAC9 modules to version 6.10 in servers that are
involved in a Ceph cluster we noticed that the iDRAC9 shows the write endurance
as 0% on any non-certified disk.
OMSA still shows the correct remaining write endurance but I am assuming that
they are working
Hello,
We had been using Intel SSD D3 S4610/20 SSDs but Solidigm is... having
problems Bottom line is they haven't shipped an order in a year.
Does anyone have any recommendations on SATA SSDs that have a fairly good mix
of performance/endurance/cost?
I know that they should all just work
of performance out of it.
So on a 4disk r10 you get about 30M/s when offloading.
-Original Message-
From: Konstantin Shalygin
Sent: Saturday, July 10, 2021 10:28 AM
To: Nathan Fish
Cc: Drew Weaver ; ceph-users@ceph.io
Subject: Re: [ceph-users] Re: RGW performance as a Veeam capacity tier
Hi,
I am going to migrate our ceph cluster to a new OS and I am trying to choose
the right one so that I won't have to replace it again when python4 becomes a
requirement mid-cycle [or whatever].
Has anyone seen any recommendations from the devs as to what distro they are
targeting for lets
Greetings.
I've begun testing using Ceph 14.2.9 as a capacity tier for a scale out backup
repository in Veeam 11.
The backup host and the RGW server are connected directly at 10Gbps.
It would appear that the maximum throughput that Veeam is able to achieve while
archiving data to this cluster
Hello,
I need to upgrade the OS that our Ceph cluster is running on to support new
versions of Ceph.
Has anyone devised a model for how you handle this?
Do you just:
Install some new nodes with the new OS
Install the old version of Ceph on the new nodes
Add those nodes/osds to the cluster
Hello,
I haven't needed to replace a disk in awhile and it seems that I have misplaced
my quick little guide on how to do it.
When searching the docs it is now recommending that you should use ceph-volume
to create OSDs when doing that it creates LV:
Disk /dev/sde: 4000.2 GB, 4000225165312
595d01e46e.74194.637.14 10413
.dir.2b67ef7c-2015-4ca0-bf50-b7595d01e46e.74194.637.9 10356
.dir.2b67ef7c-2015-4ca0-bf50-b7595d01e46e.74194.637.11 10410
-Original Message-
From: Benoît Knecht
Sent: Friday, March 5, 2021 12:00 PM
To: Drew Weaver
Cc: 'ceph-use
\n" $obj $(rados -p default.rgw.buckets.index listomapkeys
$obj | wc -l) done ```
returns this:
-bash: command substitution: line 4: syntax error: unexpected end of file
I figured perhaps you were using ``` to denote code so I tried running it
without that and also on one line and nei
whether or not it's enabled in
the running environment?
Thanks,
-Drew
-Original Message-
From: Benoît Knecht
Sent: Thursday, March 4, 2021 11:46 AM
To: Drew Weaver
Cc: 'ceph-users@ceph.io'
Subject: Re: [ceph-users] Resolving LARGE_OMAP_OBJECTS
Hi Drew,
On Thursday, March 4th, 2021
Howdy, the dashboard on our cluster keeps showing LARGE_OMAP_OBJECTS.
I went through this document
https://www.suse.com/support/kb/doc/?id=19698
I've found that we have a total of 5 buckets, each one is owned by a different
user.
>From what I have read on this issue it seems to flip flop
> As I understand it right now Ceph 14 is the last version that will run on
> CentOS/EL7 but CentOS8 was "killed off".
>This is wrong. Ceph 15 runs on CentOS 7 just fine, but without the dashboard.
Oh, what I should have said is that I want it to be fully functional.
Howdy,
After the IBM acquisition of RedHat the landscape for CentOS quickly changed.
As I understand it right now Ceph 14 is the last version that will run on
CentOS/EL7 but CentOS8 was "killed off".
So given that, if you were going to build a Ceph cluster today would you even
bother doing it
Nevermind didn't see that Octopus isn't really supported on C7 so I'll just
stick with what I have until I want to upgrade to C8.
Thanks,
-Drew
-Original Message-
From: Drew Weaver
Sent: Monday, June 8, 2020 1:38 PM
To: 'ceph-users@ceph.io'
Subject: [ceph-users] Trying to upgrade
Hi cluster is version 14.2.9
ceph-deploy v2.0.1
using command ceph-deploy install --release octopus mon0 mon1 mon2
result is this command being run:
sudo yum remove -y ceph-release
which removes this package:
ceph-releasenoarch1-1.el7 @/ceph-release-1-0.el7.noarch
Then it tries to
Not related to the original topic but the Micron case in that article is
fascinating and a little surprising.
With pretty much best in class hardware in a lab environment:
Potential 25,899,072 4KiB random write IOPs goes to 477K
Potential 23,826,216 4KiB random read IOPs goes to 2,000,000
I was told by someone at Red Hat that ISCSI performance is still several
magnitudes behind using the client / driver.
Thanks,
-Drew
-Original Message-
From: Nathan Fish
Sent: Thursday, October 24, 2019 1:27 PM
To: Ryan
Cc: ceph-users
Subject: [ceph-users] Re: iSCSI write
25 matches
Mail list logo