Hi,
if you add on more than one server an SSD with an short lifetime, you
can run in real trouble (dataloss)!
Even if, all other SSDs are enterprise grade.
Ceph mix all data in PGs, which are spread over many disks - if one disk
fails - no poblem, but if the next two fails after that due high io
Hi,
On 16.07.2017 15:04, Phil Schwarz wrote:
> ...
> Same result, the OSD is known by the node, but not by the cluster.
> ...
Firewall? Or missmatch in /etc/hosts or DNS??
Udo
___
ceph-users mailing list
ceph-users@lists.ceph.com
Hi,
On 15.07.2017 16:01, Phil Schwarz wrote:
> Hi,
> ...
>
> While investigating, i wondered about my config :
> Question relative to /etc/hosts file :
> Should i use private_replication_LAN Ip or public ones ?
private_replication_LAN!! And the pve-cluster should use another network
(nics) if
Hi Mike,
On 30.05.2017 01:49, Mike Cave wrote:
>
> Greetings All,
>
>
>
> I recently started working with our ceph cluster here and have been
> reading about weighting.
>
>
>
> It appears the current best practice is to weight each OSD according
> to it’s size (3.64 for 4TB drive, 7.45 for
Hi,
ceph speeds up with more nodes and more OSDs - so go for 6 nodes with
mixed SSD+SATA.
Udo
On 23.03.2017 18:55, Alejandro Comisario wrote:
> Hi everyone!
> I have to install a ceph cluster (6 nodes) with two "flavors" of
> disks, 3 servers with SSD and 3 servers with SATA.
>
> Y will purchase
Hi,
thanks for the usefull infos.
On 11.03.2017 12:21, cephmailingl...@mosibi.nl wrote:
>
> Hello list,
>
> A week ago we upgraded our Ceph clusters from Hammer to Jewel and with
> this email we want to share our experiences.
>
> ...
>
>
> e) find /var/lib/ceph/ ! -uid 64045 -print0|xargs
Hi,
I don't use mds, but I thinks it's the same like with rdb - the readed
data are cached on the OSD-nodes.
The 4MB-chunks of the 3G-file fit completly in the cache, the other not.
Udo
On 18.01.2017 07:50, Ahmed Khuraidah wrote:
> Hello community,
>
> I need your help to understand a little
Hi Sam,
the webfrontend of an external ceph-dash was interrupted till the node
was up again. The reboot took app. 5 min.
But the ceph -w output shows some IO much faster. I will look tomorrow
at the output again and create an ticket.
Thanks
Udo
On 12.01.2017 20:02, Samuel Just wrote:
>
Hi,
but I assume you measure also cache in this scenario - the osd-nodes has
cached the writes in the filebuffer
(due this the latency should be very small).
Udo
On 12.12.2016 03:00, V Plus wrote:
> Thanks Somnath!
> As you recommended, I executed:
> dd if=/dev/zero bs=1M count=4096 of=/dev/rbd0
Hi,
unfortunately there are no Debian Jessie packages...
Don't know that an recompile take such an long time for ceph... I think
such an important fix should hit the repros faster.
Udo
On 09.12.2016 18:54, Francois Lafont wrote:
> On 12/09/2016 06:39 PM, Alex Evonosky wrote:
>
>> Sounds
Hi,
On 16.11.2016 19:01, Vincent Godin wrote:
> Hello,
>
> We now have a full cluster (Mon, OSD & Clients) in jewel 10.2.2
> (initial was hammer 0.94.5) but we have still some big problems on our
> production environment :
>
> * some ceph filesystem are not mounted at startup and we have to
>
Hi again,
and change the value with something like this
ceph tell osd.* injectargs '--mon_osd_full_ratio 0.96'
Udo
On 01.11.2016 21:16, Udo Lembke wrote:
> Hi Marcus,
>
> for a fast help you can perhaps increase the mon_osd_full_ratio?
>
> What values do you have?
> Plea
Hi Marcus,
for a fast help you can perhaps increase the mon_osd_full_ratio?
What values do you have?
Please post the output of (on host ceph1, because osd.0.asok)
ceph --admin-daemon /var/run/ceph/ceph-osd.0.asok config show | grep
full_ratio
after that it would be helpfull to use on all hosts
Hi Vincent,
On 12.07.2016 15:03, Vincent Godin wrote:
> Hello.
>
> I've been testing Intel 3500 as journal store for few HDD-based OSD. I
> stumble on issues with multiple partitions (>4) and UDEV (sda5, sda6,etc
> sometime do not appear after partition creation). And I'm thinking that
>
Hi Albert,
to free unused space you must enable trim (or do an fstrim) in the vm -
and all things in the storage chain must support this.
The normal virtio-driver don't support trim, but if you use scsi-disks
with virtio-scsi-driver you can use it.
Work well but need some time for huge
Hi Mike,
Am 21.04.2016 um 15:20 schrieb Mike Miller:
Hi Udo,
thanks, just to make sure, further increased the readahead:
$ sudo blockdev --getra /dev/rbd0
1048576
$ cat /sys/block/rbd0/queue/read_ahead_kb
524288
No difference here. First one is sectors (512 bytes), second one KB.
oops,
Hi Mike,
Am 21.04.2016 um 09:07 schrieb Mike Miller:
Hi Nick and Udo,
thanks, very helpful, I tweaked some of the config parameters along
the line Udo suggests, but still only some 80 MB/s or so.
this mean you have reached factor 3 (this are round about the value I
see with single thread on
these tests:
http://www.spinics.net/lists/ceph-devel/msg22416.html
Mark
On 04/20/2016 11:50 AM, Udo Lembke wrote:
Hi,
on an small test-system (3 nodes (mon + osd), 6 OSDs, ceph 0.94.6) I
compare with and without cephx.
I use fio for that inside an VM on an host, outside the 3 ceph-nodes
Hi,
on an small test-system (3 nodes (mon + osd), 6 OSDs, ceph 0.94.6) I
compare with and without cephx.
I use fio for that inside an VM on an host, outside the 3 ceph-nodes,
with this command:
fio --max-jobs=1 --numjobs=1 --readwrite=read --blocksize=4k --size=4G
--direct=1 --name=fiojob_4k
Hi Mike,
I don't have experiences with RBD mounts, but see the same effect with RBD.
You can do some tuning to get better results (disable debug and so on).
As hint some values from a ceph.conf:
[osd]
debug asok = 0/0
debug auth = 0/0
debug buffer = 0/0
debug client = 0/0
Hi Sage,
we run ext4 only on our 8node-cluster with 110 OSDs and are quite happy
with ext4.
We start with xfs but the latency was much higher comparable to ext4...
But we use RBD only with "short" filenames like
rbd_data.335986e2ae8944a.000761e1.
If we can switch from Jewel to K* and
Hi,
Am 24.02.2016 um 17:27 schrieb Alfredo Deza:
> On Wed, Feb 24, 2016 at 4:31 AM, Dan van der Ster wrote:
>> Thanks Sage, looking forward to some scrub randomization.
>>
>> Were binaries built for el6? http://download.ceph.com/rpm-hammer/el6/x86_64/
>
> We are no longer
--verify=0 --verify_fatal=0 --numjobs=4 --rw=randwrite --blocksize=4k
--group_reporting
Udo
On 22.11.2015 23:59, Udo Lembke wrote:
> Hi Zoltan,
> you are right ( but this was two running systems...).
>
> I see also an big failure: "--filename=/mnt/test.bin" (use simply
> c
ents clean tomorow.
Udo
On 22.11.2015 14:29, Zoltan Arnold Nagy wrote:
> It would have been more interesting if you had tweaked only one option
> as now we can’t be sure which changed had what impact… :-)
>
>> On 22 Nov 2015, at 04:29, Udo Lembke <ulem...@polarzone.de
>
Hi Sean,
Haomai is right, that qemu can have a huge performance differences.
I have done two test to the same ceph-cluster (different pools, but this
should not do any differences).
One test with proxmox ve 4 (qemu 2.4, iothread for device, and
cache=writeback) gives 14856 iops
Same test with
Hi,
for production (with enough OSDs) is three replicas the right choice.
The chance for data loss if two ODSs fails at one time is to high.
And if this happens most of your data ist lost, because the data is
spead over many OSDs...
And yes - two replicas is faster for writes.
Udo
On
Hi Jonas,
you can create an bond over multible NICs (depends on your switch which modes
are possible) to use one IP addresses but
more than one NIC.
Udo
On 21.10.2015 10:23, Jonas Björklund wrote:
> Hello,
>
> In the configuration I have read about "cluster network" and "cluster addr".
> Is it
Hi,
do you have changed the ownership like discribed in Sages mail about
"v9.1.0 Infernalis release candidate released"?
#. Fix the ownership::
chown -R ceph:ceph /var/lib/ceph
or set ceph.conf to use root instead?
When upgrading, administrators have two options:
#. Add
Hi Christian,
On 07.10.2015 09:04, Christian Balzer wrote:
>
> ...
>
> My main suspect for the excessive slowness are actually the Toshiba DT
> type drives used.
> We only found out after deployment that these can go into a zombie mode
> (20% of their usual performance for ~8 hours if not
Hi,
you can use this sources-list
cat /etc/apt/sources.list.d/ceph.list
deb http://gitbuilder.ceph.com/ceph-deb-jessie-x86_64-basic/ref/v0.94.3
jessie main
Udo
On 25.09.2015 15:10, Jogi Hofmüller wrote:
> Hi,
>
> Am 2015-09-11 um 13:20 schrieb Florent B:
>
>> Jessie repository will be available
Hi Vickey,
I had the same rados bench output after changing the motherboard of the
monitor node with the lowest IP...
Due to the new mainboard, I assume the hw-clock was wrong during
startup. Ceph health show no errors, but all VMs aren't able to do IO
(very high load on the VMs - but no traffic).
Hi Christian,
for my setup "b" takes too long - too much data movement and stress to all
nodes.
I have simply (with replica 3) "set noout", reinstall one node (with new
filesystem on the OSDs, but leave them in the
crushmap) and start all OSDs (at friday night) - takes app. less than one day
Hi,
some time ago I switched all OSDs from XFS to ext4 (step by step).
I had no issues during mixed osd-format (the process takes some weeks).
And yes, for me ext4 performs also better (esp. the latencies).
Udo
Am 07.08.2015 13:31, schrieb Межов Игорь Александрович:
Hi!
We do some
1) the default is relatime which has minimal impact on performance
2) AFAIK some ceph features actually use atime (cache tiering was it?) or at
least so I gathered from some bugs I saw
Jan
On 07 Aug 2015, at 16:30, Udo Lembke ulem...@polarzone.de wrote:
Hi,
I use the ext4-parameters like
Hi,
dropping debian wheezy are quite fast - till now there aren't packages
for jessie?!
Dropping of squeeze I understand, but wheezy at this time?
Udo
On 30.07.2015 15:54, Sage Weil wrote:
As time marches on it becomes increasingly difficult to maintain proper
builds and packages for older
Hi,
On 28.07.2015 12:02, Shneur Zalman Mattern wrote:
Hi!
And so, in your math
I need to build size = osd, 30 replicas for my cluster of 120TB - to get my
demans
30 replicas is the wrong math! Less replicas = more speed (because of
less writing).
More replicas less speed.
Fore data
osd?
How many osds meet this problems?
This assert failure means that osd detects a upgraded pg meta object
but failed to read(or lack of 1 key) meta keys from object.
On Thu, Jul 23, 2015 at 7:03 PM, Udo Lembke ulem...@polarzone.de wrote:
Am 21.07.2015 12:06, schrieb Udo Lembke:
Hi all
Am 21.07.2015 12:06, schrieb Udo Lembke:
Hi all,
...
Normaly I would say, if one OSD-Node die, I simply reinstall the OS and ceph
and I'm back again... but this looks bad
for me.
Unfortunality the system also don't start 9 OSDs as I switched back to the
old system-disk... (only three
Hi all,
we had an ceph cluster with 7 OSD-nodes (Debian Jessie (because patched
tcmalloc) with ceph 0.94) which we expand with
one further node.
For this node we use puppet with Debian 7.8, because ceph 0.92.2 doesn't
install on Jessie (upgrade 0.94.1 work on the
other nodes but 0.94.2 looks not
Hi,
I have just expand our ceph-cluster (7 nodes) with one 8TB HGST (change
from 4TB to 8TB) on each node (and 11 4TB HGST).
But I have set the primary affinity to 0 for the 8 TB-disks... in this
case my performance values are not 8-TB-disk related.
Udo
On 08.07.2015 02:28, Blair Bethwaite
Hi,
On 01.05.2015 10:30, Piotr Wachowicz wrote:
Is there any way to confirm (beforehand) that using SSDs for journals
will help?
yes SSD-Journal helps a lot (if you use the right SSDs) for write speed,
and I made the experiences that this also helped (but not too much) for
read-performance.
Hi,
Am 26.03.2015 11:18, schrieb 10 minus:
Hi ,
I 'm just starting on small Ceph implementation and wanted to know the
release date for Hammer.
Will it coincide with relase of Openstack.
My Conf: (using 10G and Jumboframes on Centos 7 / RHEL7 )
3x Mons (VMs) :
CPU - 2
Memory - 4G
could have specified enough PGs to make it impossible to form PGs out of
84 OSDs (I'm assuming your SSDs are in a separate root) but I have to ask...
-don-
-Original Message-
From: Udo Lembke [mailto:ulem...@polarzone.de]
Sent: 25 March, 2015 08:54
To: Don Doerner; ceph-us
Hi all,
due an very silly approach, I removed the cache tier of an filled EC pool.
After recreate the pool and connect with the EC pool I don't see any content.
How can I see the rbd_data and other files through the new ssd cache tier?
I think, that I must recreate the rbd_directory (and fill
, is to create new rbd-disks and copy
all blocks with rados get - file - rados put.
The problem is the time it's take (days to weeks for 3 * 16TB)...
Udo
-Greg
On Thu, Mar 26, 2015 at 8:56 AM, Udo Lembke ulem...@polarzone.de wrote:
Hi Greg,
ok!
It's looks like, that my problem is more
show up when listing on the cache pool.
-Greg
On Thu, Mar 26, 2015 at 3:43 AM, Udo Lembke ulem...@polarzone.de wrote:
Hi all,
due an very silly approach, I removed the cache tier of an filled EC pool.
After recreate the pool and connect with the EC pool I don't see any content.
How can I see
Hi,
due to two more hosts (now 7 storage nodes) I want to create an new
ec-pool and get an strange effect:
ceph@admin:~$ ceph health detail
HEALTH_WARN 2 pgs degraded; 2 pgs stuck degraded; 2 pgs stuck unclean; 2
pgs stuck undersized; 2 pgs undersized
pg 22.3e5 is stuck unclean since forever,
300 PGs...
Udo
Am 25.03.2015 14:52, schrieb Gregory Farnum:
On Wed, Mar 25, 2015 at 1:20 AM, Udo Lembke ulem...@polarzone.de wrote:
Hi,
due to two more hosts (now 7 storage nodes) I want to create an new
ec-pool and get an strange effect:
ceph@admin:~$ ceph health detail
HEALTH_WARN 2 pgs
Hi Don,
thanks for the info!
looks that choose_tries set to 200 do the trick.
But the setcrushmap takes a long long time (alarming, but the client have still
IO)... hope it's finished soon ;-)
Udo
Am 25.03.2015 16:00, schrieb Don Doerner:
Assuming you've calculated the number of PGs
Hi,
due to PG-trouble with an EC-Pool I modify the crushmap (step set_choose_tries
200) from
rule ec7archiv {
ruleset 6
type erasure
min_size 3
max_size 20
step set_chooseleaf_tries 5
step take default
step chooseleaf indep 0 type host
Hi Tony,
sounds like an good idea!
Udo
On 09.03.2015 21:55, Tony Harris wrote:
I know I'm not even close to this type of a problem yet with my small
cluster (both test and production clusters) - but it would be great if
something like that could appear in the cluster HEALTHWARN, if Ceph
could
Hi all,
we use an EC-Pool with an small cache tier in front of, for our
archive-data (4 * 16TB VM-disks).
The ec-pool has k=3;m=2 because we startet with 5 nodes and want to
migrate to an new ec-pool with k=5;m=2. Therefor we migrate one VM-disk
(16TB) from the ceph-cluster to an fc-raid with the
Hi Jeff,
is the osd /var/lib/ceph/osd/ceph-2 mounted?
If not, does it helps, if you mounted the osd and start with
service ceph start osd.2
??
Udo
Am 17.02.2015 09:54, schrieb Jeff:
Hi,
We had a nasty power failure yesterday and even with UPS's our small (5
node, 12 OSD) cluster is having
Hi,
your will get further trouble, because your weight is not correct.
You need an weight = 0.01 for each OSD. This mean, you OSD must be 10GB
or greater!
Udo
Am 10.02.2015 12:22, schrieb B L:
Hi Vickie,
My OSD tree looks like this:
ceph@ceph-node3:/home/ubuntu$ ceph osd tree
#
Hi,
use:
ceph osd crush set 0 0.01 pool=default host=ceph-node1
ceph osd crush set 1 0.01 pool=default host=ceph-node1
ceph osd crush set 2 0.01 pool=default host=ceph-node3
ceph osd crush set 3 0.01 pool=default host=ceph-node3
ceph osd crush set 4 0.01 pool=default host=ceph-node2
ceph osd crush
Am 06.02.2015 09:06, schrieb Hector Martin:
On 02/02/15 03:38, Udo Lembke wrote:
With 3 hosts only you can't survive an full node failure, because for
that you need
host = k + m.
Sure you can. k=2, m=1 with the failure domain set to host will survive
a full host failure.
Hi,
Alexandre
Hi Dan,
I mean qemu-kvm, also librbd.
But how I can kvm told to flush the buffer?
Udo
On 05.02.2015 07:59, Dan Mick wrote:
On 02/04/2015 10:44 PM, Udo Lembke wrote:
Hi all,
is there any command to flush the rbd cache like the
echo 3 /proc/sys/vm/drop_caches for the os cache?
Udo
Do you
Hi Josh,
thanks for the info.
detach/reattach schould be fine for me, because it's only for
performance testing.
#2468 would be fine of course.
Udo
On 05.02.2015 08:02, Josh Durgin wrote:
On 02/05/2015 07:44 AM, Udo Lembke wrote:
Hi all,
is there any command to flush the rbd cache like
Hi all,
is there any command to flush the rbd cache like the
echo 3 /proc/sys/vm/drop_caches for the os cache?
Udo
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Hi Marco,
Am 04.02.2015 10:20, schrieb Colombo Marco:
...
We choosen the 6TB of disk, because we need a lot of storage in a small
amount of server and we prefer server with not too much disks.
However we plan to use max 80% of a 6TB Disk
80% is too much! You will run into trouble.
Ceph
Hi Alexandre,
nice to meet you here ;-)
With 3 hosts only you can't survive an full node failure, because for
that you need
host = k + m.
And k:1 m:2 don't make any sense.
I start with 5 hosts and use k:3, m:2. In this case two hdds can fail or
one host can be down for maintenance.
Udo
PS:
Hi Howard,
I assume it's an typo with 160 + 250 MB.
Ceph OSDs must be min. 10GB to get an weight of 0.01
Udo
On 31.01.2015 23:39, Howard Thomson wrote:
Hi All,
I am developing a custom disk storage backend for the Bacula backup
system, and am in the process of setting up a trial Ceph system,
Hi Xu,
On 01.02.2015 21:39, Xu (Simon) Chen wrote:
RBD doesn't work extremely well when ceph is recovering - it is common
to see hundreds or a few thousands of blocked requests (30s to
finish). This translates high IO wait inside of VMs, and many
applications don't deal with this well.
this
Hi Bruce,
hmm, sounds for me like the rbd cache.
Can you look, if the cache is realy disabled in the running config with
ceph --admin-daemon /var/run/ceph/ceph-osd.0.asok config show | grep cache
Udo
On 30.01.2015 21:51, Bruce McFarland wrote:
I have a cluster and have created a rbd device -
verify if it’s disabled at the librbd level on the client. If
you mean on the storage nodes I’ve had some issues dumping the config.
Does the rbd caching occur on the storage nodes, client, or both?
*From:*Udo Lembke [mailto:ulem...@polarzone.de]
*Sent:* Friday, January 30, 2015 1:00 PM
Hi,
Am 29.01.2015 07:53, schrieb Christian Balzer:
On Thu, 29 Jan 2015 01:30:41 + Ramakrishna Nishtala (rnishtal) wrote:
* Per my understanding once writes are complete to journal then
it is read again from the journal before writing to data disk. Does this
mean, we have to do,
Hi Patrik,
Am 27.01.2015 14:06, schrieb Patrik Plank:
...
I am really happy, these values above are enough for my little amount of
vms. Inside the vms I get now for write 80mb/s and read 130mb/s, with
write-cache enabled.
But there is one little problem.
Are there some tuning
Hi Megov,
you should weight the OSD so it's represent the size (like an weight of
3.68 for an 4TB HDD).
cephdeploy do this automaticly.
Nevertheless also with the correct weight the disk was not filled in
equal distribution. For that purposes you can use reweight for single
OSDs, or automaticly
Hi again,
sorry for not threaded, but my last email don't came back on the mailing
list (often miss some posts!).
Just after sending the last mail, the first time another SSD fails - in
this case an cheap one, but with the same error:
root@ceph-04:/var/log/ceph# more ceph-osd.62.log
2015-01-13
Hi,
since last thursday we had an ssd-pool (cache tier) in front of an
ec-pool and fill the pools with data via rsync (app. 50MB/s).
The ssd-pool has tree disks and one of them (an DC S3700) fails four
times since that.
I simply start the osd again and the pool pas rebuilded and work again
for
Hi,
I had an similiar effect two weeks ago - 1PG backfill_toofull and due
reweighting and delete there was enough free space but the rebuild
process stopped after a while.
After stop and start ceph on the second node, the rebuild process runs
without trouble and the backfill_toofull are gone.
Hi Lindsay,
On 05.01.2015 06:52, Lindsay Mathieson wrote:
...
So two OSD Nodes had:
- Samsung 840 EVO SSD for Op. Sys.
- Intel 530 SSD for Journals (10GB Per OSD)
- 3TB WD Red
- 1 TB WD Blue
- 1 TB WD Blue
- Each disk weighted at 1.0
- Primary affinity of the WD Red (slow) set to 0
the
Hi Sage,
Am 23.12.2014 15:39, schrieb Sage Weil:
...
You can't reduce the PG count without creating new (smaller) pools
and migrating data.
does this also work with the pool metadata, or is this pool essential
for ceph?
Udo
___
ceph-users mailing
Hi,
for monitoring only I use the Ceph Dashboard
https://github.com/Crapworks/ceph-dash/
Fo me it's an nice tool for an good overview - for administration i use
the cli.
Udo
On 23.12.2014 01:11, Tony wrote:
Please don't mention calamari :-)
The best web interface for ceph that actually
an chooseleaf_vary_r 1 (from 0) take round about the same time
to finished??
Regards
Udo
On 04.12.2014 14:09, Udo Lembke wrote:
Hi,
to answer myself.
With ceph osd crush show-tunables I see a little bit more, but doesn't
know how far away from firefly-tunables I'm at the procuction cluster
at the same time.
On Sat, Dec 20, 2014 at 3:26 AM, Udo Lembke ulem...@polarzone.de
mailto:ulem...@polarzone.de wrote:
Hi,
for information for other cepher...
I switched from unknown crush tunables to firefly and it's takes 6
hour
(30.853% degration) to finisched on our
Hi Mark,
On 18.12.2014 07:15, Mark Kirkwood wrote:
While you can't do much about the endurance lifetime being a bit low,
you could possibly improve performance using a journal *file* that is
located on the 840's (you'll need to symlink it - disclaimer - have
not tried this myself, but will
Hi all,
I have some fileserver with insufficient read speed.
Enabling read ahead inside the VM improve the read speed, but it's
looks, that this has an drawback during lvm-operations like pvmove.
For test purposes, I move the lvm-storage inside an VM from vdb to vdc1.
It's take days, because it's
Hi Lindsay,
have you tried the different cache-options (no cache, write through,
...) which proxmox offer, for the drive?
Udo
On 18.12.2014 05:52, Lindsay Mathieson wrote:
I'be been experimenting with CephFS for funning KVM images (proxmox).
cephfs fuse version - 0.87
cephfs kernel module
Hi Mikaël,
I have EVOs too, what to you mean by not playing well with D_SYNC?
Is there something I can test on my side to compare results with you,
as I have mine flashed?
http://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/
described how
Hi Benjamin,
On 15.12.2014 03:31, Benjamin wrote:
Hey there,
I've set up a small VirtualBox cluster of Ceph VMs. I have one
ceph-admin0 node, and three ceph0,ceph1,ceph2 nodes for a total of 4.
I've been following this
guide: http://ceph.com/docs/master/start/quick-ceph-deploy/ to the
Hi,
see here:
https://www.mail-archive.com/ceph-users@lists.ceph.com/msg15546.html
Udo
On 16.12.2014 05:39, Benjamin wrote:
I increased the OSDs to 10.5GB each and now I have a different issue...
cephy@ceph-admin0:~/ceph-cluster$ echo {Test-data} testfile.txt
Hi all,
I have upgrade two LSI SAS9201-16i HBAs to the latest Firmware P20.00.00
and after that I got following syslog messages:
Dec 9 18:11:31 ceph-03 kernel: [ 484.602834] mpt2sas0: log_info(0x3108):
originator(PL), code(0x08), sub_code(0x)
Dec 9 18:12:15 ceph-03 kernel: [
Hi,
perhaps an stupid question, but why you change the hostname?
Not tried, but I guess if you boot the node with an new hostname, the
old hostname are in the crush map, but without any OSDs - because they
are on the new host.
Don't know ( I guess not) if the degration level stay also on 5% if
Hi all,
http://ceph.com/docs/master/rados/operations/crush-map/#crush-tunables
described how to set the tunables to legacy, argonaut, bobtail, firefly
or optimal.
But how can I see, which profile is active in an ceph-cluster?
With ceph osd getcrushmap I got not realy much info
(only tunable
Hi,
from one host to five OSD-hosts.
NIC Intel 82599EB; jumbo-frames; single Switch IBM G8124 (blade network).
rtt min/avg/max/mdev = 0.075/0.114/0.231/0.037 ms
rtt min/avg/max/mdev = 0.088/0.164/0.739/0.072 ms
rtt min/avg/max/mdev = 0.081/0.141/0.229/0.030 ms
rtt min/avg/max/mdev =
on the host?
Thanks.
Thu Nov 06 2014 at 16:57:36, Udo Lembke ulem...@polarzone.de
mailto:ulem...@polarzone.de:
Hi,
from one host to five OSD-hosts.
NIC Intel 82599EB; jumbo-frames; single Switch IBM G8124 (blade
network).
rtt min/avg/max/mdev = 0.075/0.114/0.231/0.037 ms
Hi German,
if i'm right the journal-creation on /dev/sdc1 failed (perhaps because
you only say /dev/sdc instead of /dev/sdc1?).
Do you have partitions on sdc?
Udo
On 31.10.2014 22:02, German Anders wrote:
Hi all,
I'm having some issues while trying to activate a new osd in a
new
Am 15.10.2014 22:08, schrieb Iban Cabrillo:
HI Cephers,
I have an other question related to this issue, What would be the
procedure to restore a server fail (a whole server for example due to a
mother board trouble with no damage on disk).
Regards, I
Hi,
- change serverboard.
-
Hi,
looks that some osds are down?!
What is the output of ceph osd tree
Udo
Am 25.09.2014 04:29, schrieb Aegeaner:
The cluster healthy state is WARN:
health HEALTH_WARN 118 pgs degraded; 8 pgs down; 59 pgs
incomplete; 28 pgs peering; 292 pgs stale; 87 pgs stuck inactive;
Hi again,
sorry - forgot my post... see
osdmap e421: 9 osds: 9 up, 9 in
shows that all your 9 osds are up!
Do you have trouble with your journal/filesystem?
Udo
Am 25.09.2014 08:01, schrieb Udo Lembke:
Hi,
looks that some osds are down?!
What is the output of ceph osd tree
Udo
Am
Hi Christian,
On 22.09.2014 05:36, Christian Balzer wrote:
Hello,
On Sun, 21 Sep 2014 21:00:48 +0200 Udo Lembke wrote:
Hi Christian,
On 21.09.2014 07:18, Christian Balzer wrote:
...
Personally I found ext4 to be faster than XFS in nearly all use cases
and the lack of full, real kernel
Hi Christian,
On 21.09.2014 07:18, Christian Balzer wrote:
...
Personally I found ext4 to be faster than XFS in nearly all use cases and
the lack of full, real kernel integration of ZFS is something that doesn't
appeal to me either.
a little bit OT... what kind of ext4-mount options do you
Hi list,
on the weekend one of five OSD-nodes fails (hung with kernel panic).
The cluster degraded (12 of 60 osds), but from our monitoring-host the
noout-flag is set in this case.
But around three hours later the kvm-guest, which used storage on the
ceph cluster (and use writes) are
Hi,
don't see an improvement with tcp_window_scaling=0 with my configuration.
More the other way: the iperf-performance are much less:
root@ceph-03:~# iperf -c 172.20.2.14
Client connecting to 172.20.2.14, TCP port 5001
TCP window size:
Hi Steve,
I'm also looking for improvements of single-thread-reads.
A little bit higher values (twice?) should be possible with your config.
I have 5 nodes with 60 4-TB hdds and got following:
rados -p test bench -b 4194304 60 seq -t 1 --no-cleanup
Total time run:60.066934
Total reads
Hi again,
forget to say - I'm still on 0.72.2!
Udo
___
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Hi,
which values are all changed with ceph osd crush tunables optimal?
Is it perhaps possible to change some parameter the weekends before the
upgrade is running, to have more time?
(depends if the parameter are available in 0.72...).
The warning told, it's can take days... we have an cluster
Hi Erich,
I'm also on searching for improvements.
You should use the right mountoptions, to prevent fragmentation (for XFS).
[osd]
osd mount options xfs = rw,noatime,inode64,logbsize=256k,delaylog,allocsize=4M
osd_op_threads = 4
osd_disk_threads = 4
With 45 OSDs per node you need an powerfull
Hi,
Am 25.06.2014 16:48, schrieb Aronesty, Erik:
I'm assuming you're testing the speed of cephfs (the file system) and not
ceph object storage.
for my part I mean object storage (VM disk via rbd).
Udo
___
ceph-users mailing list
1 - 100 of 123 matches
Mail list logo