Hello,
Thanks for the heads-up. As someone who's currently maintaining a
Jewel cluster and are in the process of setting up a shiny new
Luminous cluster and writing Ansible roles in the process to make
setup reproducible. I immediately proceeded to look into ceph-volume
and I've some
Correct -- the optimization is in Luminous and not in Jewel.
On Mon, Nov 27, 2017 at 8:53 PM, Brendan Moloney wrote:
> Thanks Jason.
>
> I am running Jewel currently. I do have object-map enabled, but it sounds
> like the no-op discard optimization is specific to the newer
Thanks Jason.
I am running Jewel currently. I do have object-map enabled, but it sounds like
the no-op discard optimization is specific to the newer librbd?
Thanks again,
Brendan
From: Jason Dillaman [jdill...@redhat.com]
Sent: Monday, November 27,
My only possible suggestion would be to try a Luminous librbd client
and enable the object-map feature on the image. When the object map is
enabled, librbd will optimize away all the no-op discard requests. If
that doesn't work, it could be an issue in the OS / controller
interaction.
On Mon, Nov
Allocate disk space from where? If it's a physical device, then migration
still requires moving hardware. If it isn't a physical device, why are you
setting up OSDs without a physical device?
Who is the user in your scenario? If I'm the user, then I use a physical
device to create the OSD. If
Hi Patrick,
We are using the CentOS 7.4 kernel (3.10.0-693.5.2.el7.x86_64). The
nodes in question have a fairly large amount of RAM (512GB), I don't see
any evidence in any logs that the nodes ran out of memory (no OOM
killer, and we have a small amount of swap that is used to catch memory
Hello Andras,
On Mon, Nov 27, 2017 at 2:31 PM, Andras Pataki
wrote:
> After upgrading to the Luminous 12.2.1 ceph-fuse client, we've seen clients
> on various nodes randomly crash at the assert
> FAILED assert(0 == "failed to remount for kernel dentry
Hi,
Anyone have input on this? I am surprised there are not more people running
into this issue. I guess most people don't have multi-TB RBD images? I think
ext4 might also fair better since it does keep track of blocks that have been
discarded in the past and not modified so that they
Dear ceph users,
After upgrading to the Luminous 12.2.1 ceph-fuse client, we've seen
clients on various nodes randomly crash at the assert
FAILED assert(0 == "failed to remount for kernel dentry trimming")
with the stack:
ceph version 12.2.1
Hello,
Could someone please help me complete my botched upgrade from Jewel
10.2.3-r1 to Luminous 12.2.1. I have 9 Gentoo servers, 4 of which have 2
OSDs each.
My OSD servers were accidentally rebooted before the monitor servers
causing them to be running Luminous before the monitors. All
On Mon, Nov 27, 2017 at 12:55 PM Aristeu Gil Alves Jr
wrote:
> Hi.
>
> It's my first post on the list. First of all I have to say I'm new on
> hadoop.
>
> We are here a small lab and we have being running cephfs for almost two
> years, loading it with large files (4GB to
Why not use swift. The intergration has been around for a while, and may be
a better fit.
https://hadoop.apache.org/docs/stable/hadoop-openstack/index.html
On Mon, Nov 27, 2017 at 12:55 PM, Aristeu Gil Alves Jr wrote:
> Hi.
>
> It's my first post on the list. First of
Hi.
It's my first post on the list. First of all I have to say I'm new on
hadoop.
We are here a small lab and we have being running cephfs for almost two
years, loading it with large files (4GB to 4TB in size). Our cluster is
with approximately with 400TB with ~75% of usage, and we are planning
Hi Nick,
yeah, we are using the same nvme disk with an additional partition to use
as journal/wal. We double check the c-state and it was not configure to use
c1, so we change that on all the osd nodes and mon nodes and we're going to
make some new tests, and see how it goes. I'll get back as
Hi David,
Thanks a lot for the response. In fact, we first try to not use any
scheduler at all, but then we try kyber iosched and we notice a slightly
improve in terms of performance, that's why we actually keep it.
*German*
2017-11-27 13:48 GMT-03:00 David Byte :
> From the
From the benchmarks I have seen and done myself, I’m not sure why you are using
an i/o scheduler at all with NVMe. While there are a few cases where it may
provide a slight benefit, simply having mq enabled with no scheduler seems to
provide the best performance for an all flash, especially
Also what tuned profile are you using? There is something to be gained by
using a matching tuned profile for your workload.
On Mon, Nov 27, 2017 at 11:16 AM, Donny Davis wrote:
> Why not ask Red Hat? All the rest of the storage vendors you are looking
> at are not free.
>
Why not ask Red Hat? All the rest of the storage vendors you are looking at
are not free.
Full disclosure, I am an employee at Red Hat.
On Mon, Nov 27, 2017 at 10:16 AM, Nick Fisk wrote:
> *From:* ceph-users [mailto:ceph-users-boun...@lists.ceph.com] *On Behalf
> Of *German
Hi German,
We have similar config:
proxmox-ve: 5.1-27 (running kernel: 4.13.8-1-pve)
pve-manager: 5.1-36 (running version: 5.1-36/131401db)
pve-kernel-4.13.8-1-pve: 4.13.8-27
ceph: 12.2.1-pve3
system(4 nodes): Supermicro 2028U-TN24R4T+
2 port Mellanox connect x3pro 56Gbit
4 port intel 10GigE
From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of German
Anders
Sent: 27 November 2017 14:44
To: Maged Mokhtar
Cc: ceph-users
Subject: Re: [ceph-users] ceph all-nvme mysql performance tuning
Hi Maged,
Thanks a lot
Unfortunately, the latest EL 7.4 kernel does not have the necessary
bug fixes. We are trying to get the fixes included in a future 7.4
release, but in the meantime we are planning for EL 7.5.
We were also hoping to get the fixes included in upstream 4.14, but
there was a maintainer shuffle, so
On 27 Nov 2017 1:06 p.m., "Jens-U. Mozdzen" wrote:
Hi David,
Zitat von David C :
Hi Jens
>
> We also see these messages quite frequently, mainly the "replicating
> dir...". Only seen "failed to open ino" a few times so didn't do any real
>
Hi Maged,
Thanks a lot for the response. We try with different number of threads and
we're getting almost the same kind of difference between the storage types.
Going to try with different rbd stripe size, object size values and see if
we get more competitive numbers. Will get back with more
On 2017-11-27 15:02, German Anders wrote:
> Hi All,
>
> I've a performance question, we recently install a brand new Ceph cluster
> with all-nvme disks, using ceph version 12.2.0 with bluestore configured. The
> back-end of the cluster is using a bond IPoIB (active/passive) , and for the
>
(moving to ceph-users mailing list since this isn't development related)
Have you tried following the documentation located here [1]? Any
particular step you are having trouble with? There are no repos for
the Open-iSCSI packages of rtslib-fb and tcmu-runner since those will
eventually trickle
Hi Wido, thanks a lot for the quick response, regarding the questions:
Have you tried to attach multiple RBD volumes:
- Root for OS (the root partition has local SSDs)
- MySQL data dir (the idea is to have all the storage tests with the same
scheme, the first test is using one volume and put the
For the upcoming Luminous release (12.2.2), ceph-disk will be
officially in 'deprecated' mode (bug fixes only). A large banner with
deprecation information has been added, which will try to raise
awareness.
We are strongly suggesting using ceph-volume for new (and old) OSD
deployments. The only
> Op 27 november 2017 om 14:14 schreef German Anders :
>
>
> Hi Jason,
>
> We are using librbd (librbd1-0.80.5-9.el6.x86_64), ok I will change those
> parameters and see if that changes something
>
0.80? Is that a typo? You should really use 12.2.1 on the client.
Wido
> Op 27 november 2017 om 14:02 schreef German Anders :
>
>
> Hi All,
>
> I've a performance question, we recently install a brand new Ceph cluster
> with all-nvme disks, using ceph version 12.2.0 with bluestore configured.
> The back-end of the cluster is using a bond
Hi Jason,
We are using librbd (librbd1-0.80.5-9.el6.x86_64), ok I will change those
parameters and see if that changes something
thanks a lot
best,
*German*
2017-11-27 10:09 GMT-03:00 Jason Dillaman :
> Are you using krbd or librbd? You might want to consider "debug_ms
Are you using krbd or librbd? You might want to consider "debug_ms = 0/0"
as well since per-message log gathering takes a large hit on small IO
performance.
On Mon, Nov 27, 2017 at 8:02 AM, German Anders wrote:
> Hi All,
>
> I've a performance question, we recently install
Hi David,
Zitat von David C :
Hi Jens
We also see these messages quite frequently, mainly the "replicating
dir...". Only seen "failed to open ino" a few times so didn't do any real
investigation. Our set up is very similar to yours, 12.2.1, active/standby
MDS and
Hi All,
I've a performance question, we recently install a brand new Ceph cluster
with all-nvme disks, using ceph version 12.2.0 with bluestore configured.
The back-end of the cluster is using a bond IPoIB (active/passive) , and
for the front-end we are using a bonding config with active/active
Hi Jens
We also see these messages quite frequently, mainly the "replicating
dir...". Only seen "failed to open ino" a few times so didn't do any real
investigation. Our set up is very similar to yours, 12.2.1, active/standby
MDS and exporting cephfs through KNFS (hoping to replace with Ganesha
Yep, that did it! Thanks, Zheng. I should read release notes more carefully!
On Fri, Nov 24, 2017 at 7:09 AM, Yan, Zheng wrote:
> On Thu, Nov 23, 2017 at 9:17 PM, David C wrote:
> > Hi All
> >
> > I upgraded my 12.2.0 cluster to 12.2.1 a month or two
No, it doesn't. But I'll keep this commit in mind, thanks!
On 24 November 2017 at 03:33, Yan, Zheng wrote:
> On Thu, Nov 23, 2017 at 5:49 PM, Andrey Klimentyev
> wrote:
> > The workload is... really common. It's just a bunch of PHP scripts being
Hi,
Zitat von "Yan, Zheng" :
On Sat, Nov 25, 2017 at 2:27 AM, Jens-U. Mozdzen wrote:
[...]
In the log of the active MDS, we currently see the following two inodes
reported over and over again, about every 30 seconds:
--- cut here ---
2017-11-24
On Sat, Nov 25, 2017 at 2:27 AM, Jens-U. Mozdzen wrote:
> Hi all,
>
> with our Ceph Luminous CephFS, we're plaqued with "failed to open ino"
> messages. These don't seem to affect daily business (in terms of "file
> access"). (There's a backup performance issue that may
38 matches
Mail list logo