This is a tangent on Paul Emmerich's response to "[ceph-users] Correct
Migration Workflow Replicated -> Erasure Code". I've tried Paul's method
before to migrate between 2 data pools. However I ran into some issues.
The first issue seems like a bug in RGW where the RGW for the new zone was
able to
Of the top of my head, if say your cluster might have the wrong tunables
for crush-compat. I know I ran into that when I first set up the balancer
and nothing obviously said that was the problem. Only researching find it
for me.
My real question, though, is why aren't you using upmap? It is
signif
Most times you are better served with simpler settings like
osd_recovery_sleep, which has 3 variants if you have multiple types of OSDs
in your cluster (osd_recovery_sleep_hdd, osd_recovery_sleep_sdd,
osd_recovery_sleep_hybrid).
Using those you can tweak a specific type of OSD that might be having
lly help with
bucket deletion.
On Thu, Jun 27, 2019 at 2:58 PM Sergei Genchev wrote:
> @David Turner
> Did your bucket delete ever finish? I am up to 35M incomplete uploads,
> and I doubt that I actually had that many upload attempts. I could be
> wrong though.
> Is there a way to
It's aborting incomplete multipart uploads that were left around. First it
will clean up the cruft like that and then it should start actually
deleting the objects visible in stats. That's my understanding of it
anyway. I'm int he middle of cleaning up some buckets right now doing this
same thing.
This was a little long to respond with on Twitter, so I thought I'd share
my thoughts here. I love the idea of a 12 month cadence. I like October
because admins aren't upgrading production within the first few months of a
new release. It gives it plenty of time to be stable for the OS distros as
we
You should be able to see all pools in use in a RGW zone from the
radosgw-admin command. This [1] is probably overkill for most, but I deal
with multi-realm clusters so I generally think like this when dealing with
RGW. Running this as is will create a file in your current directory for
each zone
Do you perhaps have anything in the ceph.conf files on the servers with
those OSDs that would attempt to tell the daemon that they are filestore
osds instead of bluestore? I'm sure you know that the second part [1] of
the output in both cases only shows up after an OSD has been rebooted. I'm
sure
Why do you think that it can't resolve this by itself? You just said that
the balancer was able to provide an optimization, but then that the
distribution isn't perfect. When there are no further optimizations,
running `ceph balancer optimize plan` won't create a plan with any
changes. Possibly
I can't speak to the rdma portion. But to clear up what each of these
does... the cluster network is only traffic between the osds for
replicating writes, reading EC data, as well as backfilling and recovery
io. Mons, mds, rgw, and osds talking with clients all happen on the public
network. The gen
Ceph has been getting better and better about prioritizing this sorry of
recovery, but free of those optimizations are in Jewel, which had been out
of the support cycle for about a year. You should look into upgrading to
mimic where you should see a pretty good improvement on this sorry of
prioriti
The problem with clients on osd nodes is for kernel clients only. That's
true of krbd and the kernel client for cephfs. The only other reason not to
run any other Ceph daemon in the same node as osds is resource contention
if you're running at higher CPU and memory utilizations.
On Sat, Mar 9, 201
n Fri, Mar 1, 2019, 6:28 PM solarflow99 wrote:
> It has to be mounted from somewhere, if that server goes offline, you need
> to mount it from somewhere else right?
>
>
> On Thu, Feb 28, 2019 at 11:15 PM David Turner
> wrote:
>
>> Why are you making the same rbd to multip
Have you used strace on the du command to see what it's spending its time
doing?
On Thu, Feb 28, 2019, 8:45 PM Glen Baars
wrote:
> Hello Wido,
>
> The cluster layout is as follows:
>
> 3 x Monitor hosts ( 2 x 10Gbit bonded )
> 9 x OSD hosts (
> 2 x 10Gbit bonded,
> LSI cachecade and write cache
Why are you making the same rbd to multiple servers?
On Wed, Feb 27, 2019, 9:50 AM Ilya Dryomov wrote:
> On Wed, Feb 27, 2019 at 12:00 PM Thomas <74cmo...@gmail.com> wrote:
> >
> > Hi,
> > I have noticed an error when writing to a mapped RBD.
> > Therefore I unmounted the block device.
> > Then
Those numbers look right for a pool only containing 10% of your data. Now
continue to calculate the pg counts for the remaining 90% of your data.
On Wed, Feb 27, 2019, 12:17 PM Krishna Venkata
wrote:
> Greetings,
>
>
> I am having issues in the way PGs are calculated in
> https://ceph.com/pgcalc
You can always set it in your ceph.conf file and restart the mgr daemon.
On Tue, Feb 26, 2019, 1:30 PM Alex Litvak
wrote:
> Dear Cephers,
>
> In mimic 13.2.2
> ceph tell mgr.* injectargs --log-to-stderr=false
> Returns an error (no valid command found ...). What is the correct way to
> inject m
The reason is that an osd still contributes to the host weight in the crush
map even while it is marked out. When you out and then purge, the purging
operation removed the osd from the map and changes the weight of the host
which changes the crush map and data moves. By weighting the osd to 0.0,
th
There is a scheduled birds of a feather for Ceph tomorrow night, but I also
noticed that there are only trainings tomorrow. Unless you are paying more
for those, you likely don't have much to do on Monday. That's the boat I'm
in. Is anyone interested in getting together tomorrow in Boston during th
One thing that's worked for me to get more out of nvmes with Ceph is to
create multiple partitions on the nvme with an osd on each partition. That
way you get more osd processes and CPU per nvme device. I've heard of
people using up to 4 partitions like this.
On Sun, Feb 24, 2019, 10:25 AM Vitaliy
Jewel is really limited on the settings you can tweak for backfilling [1].
Luminous and Mimic have a few more knobs. An option you can do, though, is
to use osd_crush_initial_weight found [2] here. With this setting you set
your initial crush weight for new osds to 0.0 and gradually increase them
t
luestore that does
> >> > it, but I'm seeing lower cpu usage when moving to bluestore + rocksdb
> >> > compared to filestore + leveldb .
> >> >
> >> >
> >> > On Wed, Feb 20, 2019 at 4:27 PM M Ranga Swami Reddy
> >> > wrot
Can you correlate the times to scheduled tasks inside of any VMs? For
instance if you have several Linux VMs with the updatedb command installed
that by default they will all be scanning their disks at the same time each
day to see where files are. Other common culprits could be scheduled
backups,
when moving to bluestore + rocksdb
> > compared to filestore + leveldb .
> >
> >
> > On Wed, Feb 20, 2019 at 4:27 PM M Ranga Swami Reddy
> > wrote:
> > >
> > > Thats expected from Ceph by design. But in our case, we are using all
> > > recomme
If I'm not mistaken, if you stop them at the same time during a reboot on a
node with both mds and mon, the mons might receive it, but wait to finish
their own election vote before doing anything about it. If you're trying
to keep optimal uptime for your mds, then stopping it first and on its own
It's also been mentioned a few times that when MDS and MON are on the same
host that the downtime for MDS is longer when both daemons stop at about
the same time. It's been suggested to stop the MDS daemon, wait for `ceph
mds stat` to reflect the change, and then restart the rest of the server.
HT
If your client needs to be able to handle the writes like that on its own,
RBDs might be the more appropriate use case. You lose the ability to have
multiple clients accessing the data as easily as with CephFS, but you would
gain the features you're looking for.
On Tue, Feb 12, 2019 at 1:43 PM Gr
You're attempting to use mismatching client name and keyring. You want to
use matching name and keyring. For your example, you would want to either
use `--keyring /etc/ceph/ceph.client.admin.keyring --name client.admin` or
`--keyring /etc/ceph/ceph.client.cephfs.keyring --name client.cephfs`.
Mix
[1] Here is a really cool set of slides from Ceph Day Berlin where Dan van
der Ster uses the mgr balancer module with upmap to gradually change the
tunables of a cluster without causing major client impact. The down side
for you is that upmap requires all luminous or newer clients, but if you
upgr
With a RACK failure domain, you should be able to have an entire rack
powered down without noticing any major impact on the clients. I regularly
take down OSDs and nodes for maintenance and upgrades without seeing any
problems with client IO.
On Tue, Feb 12, 2019 at 5:01 AM M Ranga Swami Reddy
w
et this up and running aswell. (But keep in
> mind that the help on their mailing list is not so good as here ;))
>
>
>
> -Original Message-
> From: David Turner [mailto:drakonst...@gmail.com]
> Sent: 18 February 2019 17:31
> To: ceph-users
> Subject: [ceph-users]
yone to migrate
their DB back off of their spinner which is what's happening to you. I
don't believe that sort of tooling exists yet, though, without compiling
the Nautilus Beta tooling for yourself.
On Tue, Feb 19, 2019 at 12:03 AM Konstantin Shalygin wrote:
> On 2/18/19 9:43 PM, Da
Everybody is just confused that you don't have a newer version of Ceph
available. Are you running `apt-get dist-upgrade` to upgrade ceph? Do you
have any packages being held back? There is no reason that Ubuntu 18.04
shouldn't be able to upgrade to 12.2.11.
On Mon, Feb 18, 2019, 4:38 PM Hello peo
Is this still broken in the 1-way direction where Slack users' comments do
not show up in IRC? That would explain why nothing I ever type (as either
helping someone or asking a question) ever have anyone respond to them.
On Tue, Dec 18, 2018 at 6:50 AM Joao Eduardo Luis wrote:
> On 12/18/2018 1
I'm getting some "new" (to me) hardware that I'm going to upgrade my home
Ceph cluster with. Currently it's running a Proxmox cluster (Debian) which
precludes me from upgrading to Mimic. I am thinking about taking the
opportunity to convert most of my VMs into containers and migrate my
cluster in
We have 2 clusters of [1] these disks that have 2 Bluestore OSDs per disk
(partitioned), 3 disks per node, 5 nodes per cluster. The clusters are
12.2.4 running CephFS and RBDs. So in total we have 15 NVMe's per cluster
and 30 NVMe's in total. They were all built at the same time and were
running
Also what commands did you run to remove the failed HDDs and the commands
you have so far run to add their replacements back in?
On Sat, Feb 16, 2019 at 9:55 PM Konstantin Shalygin wrote:
> I recently replaced failed HDDs and removed them from their respective
> buckets as per procedure.
>
> But
been there ever since.
On Sat, Feb 16, 2019 at 1:50 AM Konstantin Shalygin wrote:
> On 2/16/19 12:33 AM, David Turner wrote:
> > The answer is probably going to be in how big your DB partition is vs
> > how big your HDD disk is. From your output it looks like you have a
> >
The answer is probably going to be in how big your DB partition is vs how
big your HDD disk is. From your output it looks like you have a 6TB HDD
with a 28GB Blocks.DB partition. Even though the DB used size isn't
currently full, I would guess that at some point since this OSD was created
that it
I'm leaving the response on the CRUSH rule for Gregory, but you have
another problem you're running into that is causing more of this data to
stay on this node than you intend. While you `out` the OSD it is still
contributing to the Host's weight. So the host is still set to receive
that amount o
I have found that running a zap before all prepare/create commands with
ceph-volume helps things run smoother. Zap is specifically there to clear
everything on a disk away to make the disk ready to be used as an OSD.
Your wipefs command is still fine, but then I would lvm zap the disk before
conti
Ceph-users is the proper ML to post questions like this.
On Thu, Dec 20, 2018 at 2:30 PM Joao Eduardo Luis wrote:
> On 12/20/2018 04:55 PM, João Aguiar wrote:
> > I am having an issue with "ceph-ceploy mon”
> >
> > I started by creating a cluster with one monitor with "create-deploy
> new"… "cre
Ceph-users is the correct ML to post questions like this.
On Wed, Jan 2, 2019 at 5:40 PM Rishabh S wrote:
> Dear Members,
>
> Please let me know if you have any link with examples/detailed steps of
> Ceph-Safenet(KMS) integration.
>
> Thanks & Regards,
> Rishabh
>
> _
Ceph-users ML is the proper mailing list for questions like this.
On Sat, Jan 26, 2019 at 12:31 PM Meysam Kamali wrote:
> Hi Ceph Community,
>
> I am using ansible 2.2 and ceph branch stable-2.2, on centos7, to deploy
> the playbook. But the deployment get hangs in this step "TASK [ceph-mon :
>
The Ceph-users ML is the correct list to ask questions like this. Did you
figure out the problems/questions you had?
On Tue, Dec 4, 2018 at 11:39 PM Rishabh S wrote:
> Hi Gaurav,
>
> Thank You.
>
> Yes, I am using boto, though I was looking for suggestions on how my ceph
> client should get acc
This might not be a Ceph issue at all depending on if you're using any sort
of caching. If you have caching on your disk controllers at all, then the
write might have happened to the cache but never made it to the OSD disks
which would show up as problems on the VM RBDs. Make sure you have proper
Note that this format in fstab does require a certain version of util-linux
because of the funky format of the line. Pretty much it maps all command
line options at the beginning of the line separated with commas.
On Wed, Feb 13, 2019 at 2:10 PM David Turner wrote:
> I believe the fstab l
I believe the fstab line for ceph-fuse in this case would look something
like [1] this. We use a line very similar to that to mount cephfs at a
specific client_mountpoint that the specific cephx user only has access to.
[1] id=acapp3,client_mds_namespace=fs1 /tmp/ceph fuse.ceph
defaults,noat
Sorry for the late response on this, but life has been really busy over the
holidays.
We compact our omaps offline with the ceph-kvstore-tool. Here [1] is a
copy of the script that we use for our clusters. You might need to modify
things a bit for your environment. I don't remember which versio
I believe I fixed this issue by running `systemctl enable ceph-osd@n.service`
for all of the OSDs and then it wasn't a problem in future.
On Fri, Nov 9, 2018 at 9:30 PM wrote:
> Hi!
>
> I find a confused question about start/stop ceph cluster by systemd:
>
> - when cluster is on, restart ceph.ta
For this the procedure is generally to stop the osd, flush the journal,
update the symlink on the osd to the new journal location, mkjournal, start
osd. You shouldn't need to do anything in the ceph.conf file.
On Thu, Nov 8, 2018 at 2:41 AM wrote:
> Hi all,
>
>
>
> I have been trying to migrate
while
only using as much space as 2x replication.
On Thu, Nov 1, 2018 at 11:25 PM Wladimir Mutel wrote:
> David Turner wrote:
> > Yes, when creating an EC profile, it automatically creates a CRUSH rule
> > specific for that EC profile. You are also correct that 2+1 doesn&#
My big question is that we've had a few of these releases this year that
are bugged and shouldn't be upgraded to... They don't have any release
notes or announcement and the only time this comes out is when users
finally ask about it weeks later. Why is this not proactively announced to
avoid a pr
ic version of the tool to
update my omap backends.
On Mon, Nov 5, 2018 at 4:26 PM Pavan Rallabhandi <
prallabha...@walmartlabs.com> wrote:
> Not sure I understand that, but starting Luminous, the filestore omap
> backend is rocksdb by default.
>
>
>
> *From: *David Turn
y, this feature was supported in Jewel starting 10.2.11, ref
> https://github.com/ceph/ceph/pull/18010
>
>
>
> I thought you mentioned you were using Luminous 12.2.4.
>
>
>
> *From: *David Turner
> *Date: *Friday, November 2, 2018 at 5:21 PM
>
>
> *To: *Pavan Ra
other
tools as well that can be used to set up the omap backend db.
On Fri, Nov 2, 2018, 4:26 PM Pavan Rallabhandi
wrote:
> It was Redhat versioned Jewel. But may be more relevantly, we are on
> Ubuntu unlike your case.
>
>
>
> *From: *David Turner
> *Date: *Friday, No
.
>
> Thanks,
> -Pavan.
>
> From: David Turner
> Date: Monday, October 1, 2018 at 1:37 PM
> To: Pavan Rallabhandi
> Cc: ceph-users
> Subject: EXT: Re: [ceph-users] Any backfill in our cluster makes the
> cluster unusable and takes forever
>
> I tried m
Yes, when creating an EC profile, it automatically creates a CRUSH rule
specific for that EC profile. You are also correct that 2+1 doesn't really
have any resiliency built in. 2+2 would allow 1 node to go down while
still having your data accessible. It will use 2x data to raw as opposed
to the
What version of qemu-img are you using? I found [1] this when poking
around on my qemu server when checking for rbd support. This version (note
it's proxmox) has rbd listed as a supported format.
[1]
# qemu-img -V; qemu-img --help|grep rbd
qemu-img version 2.11.2pve-qemu-kvm_2.11.2-1
Copyright (
>From the balancer module's code for v 12.2.7 I noticed [1] these lines
which reference [2] these 2 config options for upmap. You might try using
more max iterations or a smaller max deviation to see if you can get a
better balance in your cluster. I would try to start with [3] these
commands/value
otstrap-osd/ceph.keyring
>>
>> ---
>> Alex
>>
>> On Tue, Oct 30, 2018 at 4:48 AM David Turner
>> wrote:
>> >
>> > Set noout, reinstall the OS without going the OSDs (including any
>> journal partitions and maintaining any dmcrypt keys if yo
Set noout, reinstall the OS without going the OSDs (including any journal
partitions and maintaining any dmcrypt keys if you have encryption),
install ceph, make sure the ceph.conf file is correct,zip start OSDs, unset
noout once they're back up and in. All of the data the OSD needs to start
is on
min_size should be at least k+1 for EC. There are times to use k for
emergencies like you had. I would suggest seeing it back to 3 once your
back to healthy.
As far as why you needed to reduce min_size, my guess would be that
recovery would have happened as long as k copies were up. Were the PG's
Which version of Ceph are you running? Do you have any kernel clients? If
yes, can which version kernel? These questions are all leading to see if
you can enable the Luminous/Mimic mgr module balancer with upmap. If you
can, it is hands down the best way to balance your cluster.
On Sat, Oct 27, 20
If your had a specific location for the wal it would show up there. If
there is no entry for the wal, then it is using the same seeing as the db.
On Sun, Oct 28, 2018, 9:26 PM Robert Stanford
wrote:
>
> Mehmet: it doesn't look like wal is mentioned in the osd metadata. I see
> bluefs slow, blu
It is indeed adding a placement target and not removing it replacing the
pool. The get/put wouldn't be a rados or even ceph command, you would do it
through an s3 client.
On Fri, Oct 26, 2018, 9:38 AM Matthew Vernon wrote:
> Hi,
>
> On 26/10/2018 12:38, Alexandru Cucu wrote:
>
> > Have a look at
Resharding a bucket won't affect the data in the bucket. After you change
the placement for a bucket, you could update where the data is by
re-writing all of the data in the bucket.
On Thu, Oct 25, 2018 at 8:48 AM Jacek Suchenia
wrote:
> Hi
>
> We have a bucket created with LocationConstraint s
There are no tools to migrate in either direction between EC and Replica.
You can't even migrate an EC pool to a new EC profile.
With RGW you can create a new data pool and new objects will be written to
the new pool. If your objects have a lifecycle, then eventually you'll be
to the new pool over
he DB + WAL on the NVMe? Is this "data disk"
> still an ssd?
>
>
>
> On Mon, Oct 22, 2018 at 3:34 PM David Turner
> wrote:
>
>> And by the data disk I mean that I didn't specify a location for the DB
>> partition.
>>
>> On Mon, Oct 22
ere is more utilization
> on the cluster than what's in the pools, the excess equal to about wal size
> * number of osds...
>
> On Mon, Oct 22, 2018 at 3:35 PM David Turner
> wrote:
>
>> My DB doesn't have a specific partition anywhere, but there's still a
>&g
master/rados/configuration/bluestore-config-ref/
>
> On Mon, Oct 22, 2018 at 3:13 PM Robert Stanford
> wrote:
>
>>
>> We're out of sync, I think. You have your DB on your data disk so your
>> block.db symlink points to that disk, right? There is however no wal
db points? I assumed that was a symlink for the db, but necessarily
> for the wal, because it can live in a place different than the db.
>
> On Mon, Oct 22, 2018 at 2:18 PM David Turner
> wrote:
>
>> You can always just go to /var/lib/ceph/osd/ceph-{osd-num}/ and look at
>&
And by the data disk I mean that I didn't specify a location for the DB
partition.
On Mon, Oct 22, 2018 at 4:06 PM David Turner wrote:
> Track down where it says they point to? Does it match what you expect?
> It does for me. I have my DB on my data disk and my WAL on a separate N
You can always just go to /var/lib/ceph/osd/ceph-{osd-num}/ and look at
where the symlinks for block and block.wal point to.
On Mon, Oct 22, 2018 at 12:29 PM Robert Stanford
wrote:
>
> That's what they say, however I did exactly this and my cluster
> utilization is higher than the total pool ut
I haven't had crush-compat do anything helpful for balancing my clusters.
upmap has been amazing and balanced my clusters far better than anything
else I've ever seen. I would go so far as to say that upmap can achieve a
perfect balance.
It seems to evenly distribute the PGs for each pool onto al
pressed_original=0.5? The
> second ratio does not look too impressive given the file contents.
>
> 4) Is there any way to get uncompressed data compressed as a background
> task like scrub?
>
> If you have the time to look at these questions, this would be great. Most
> import
>> 2018-10-13 20:58:53.750164 mon.a [WRN] Health check update: Reduced data
> >> availability: 3 pgs inactive (PG_AVAILABILITY)
> >> ...
> >>
> >> so there is a timeframe of > 90s whee PGs are inactive and unavail -
> >> this would at least ex
Not all pools need the same amount of PGs. When you get to so many pools
you want to start calculating how much data each pool will have. If 1 of
your pools will have 80% of your data in it, it should have 80% of your
PGs. The metadata pools for rgw likely won't need more than 8 or so PGs
each. If
Mgr and MDS do not use physical space on a disk. Mons do use the disk and
benefit from SSDs, but they write a lot of stuff all the time. Depending
why the SSDs aren't suitable for OSDs, they might not be suitable for mons
either.
On Mon, Oct 15, 2018, 7:16 AM ST Wong (ITSC) wrote:
> Hi all,
>
>
uot;ceph osd pool set" -
> commands, please let me know.
>
> Best regards,
>
> =
> Frank Schilder
> AIT Risø Campus
> Bygning 109, rum S14
>
>
> From: David Turner
> Sent: 12 October 2018 15:47:20
> T
What do you want to use these for? "5 Year or 0.2 DWPD" is the durability
of this drive which is absolutely awful for most every use in Ceph.
Possibly if you're using these for data disks (not DB or WAL) and you plan
to have a more durable media to host the DB+WAL on... this could work. Or
if you
The PGs per OSD does not change unless the OSDs are marked out. You have
noout set, so that doesn't change at all during this test. All of your PGs
peered quickly at the beginning and then were active+undersized the rest of
the time, you never had any blocked requests, and you always had 100MB/s+
provide a source or sample commands?
>
> Thanks and best regards,
>
> =
> Frank Schilder
> AIT Risø Campus
> Bygning 109, rum S14
>
> ____
> From: David Turner
> Sent: 09 October 2018 17:42
> To: Frank Schil
,d83df~1,d83e1~2,d83e5~1,d83e8~1,d83eb~4,d83f0~1,d83f2~1,d83f4~3,d83f8~3,d83fd~2,d8402~1,d8405~1,d8407~1,d840a~2,d840f~1,d8411~1,d8413~3,d8417~3,d841c~4,d8422~4,d8428~2,d842b~1,d842e~1,d8430~1,d8432~5,d843a~1,d843c~3,d8440~5,d8447~1,d844a~1,d844d~1,d844f~1,d8452~1,d8455~1,d8457~1,d8459~2,d845d~2,d84
My first guess is to ask what your crush rules are. `ceph osd crush rule
dump` along with `ceph osd pool ls detail` would be helpful. Also if you
have a `ceph status` output from a time where the VM RBDs aren't working
might explain something.
On Thu, Oct 11, 2018 at 1:12 PM Nils Fahldieck - Pro
As a part of a repair is queuing a deep scrub. As soon as the repair part
is over the deep scrub continues until it is done.
On Thu, Oct 11, 2018, 12:26 PM Brett Chancellor
wrote:
> Does the "repair" function use the same rules as a deep scrub? I couldn't
> get one to kick off, until I temporari
I have 4 other slack servers that I'm in for work and personal hobbies.
It's just easier for me to maintain one more slack server than have a
separate application for IRC.
On Thu, Oct 11, 2018, 11:02 AM John Spray wrote:
> On Thu, Oct 11, 2018 at 8:44 AM Marc Roos
> wrote:
> >
> >
> > Why slack
Not a resolution, but an idea that you've probably thought of. Disabling
logging on any affected OSDs (possibly just all of them) seems like a
needed step to be able to keep working with this cluster to finish the
upgrade and get it healthier.
On Wed, Oct 10, 2018 at 6:37 PM Wido den Hollander w
I would like an invite to. drakonst...@gmail.com
On Wed, Sep 19, 2018 at 1:02 PM Gregory Farnum wrote:
> Done. :)
>
> On Tue, Sep 18, 2018 at 12:15 PM Alfredo Daniel Rezinovsky <
> alfredo.rezinov...@ingenieria.uncuyo.edu.ar> wrote:
>
>> Can anyone add me to this slack?
>>
>> with my email alfr
There is a newer [1] feature to be able to set flags per OSD instead of
cluster wide. This way you can prevent a problem host from marking its
OSDs down while the rest ofthe cluster is capable of doing so. [2] These
commands ought to clear up your status.
[1]
http://docs.ceph.com/docs/master/rad
I know that it existed, but I've never bothered using it. In applications
like Python where you can get a different reaction by interacting with it
line by line and setting up an environment it is very helpful. Ceph,
however, doesn't have any such environment variables that would make this
more u
I would suggest trying to delete the bucket using radosgw-admin. If you
can't get that to work, then I would go towards deleting the actual RADOS
objects. There are a few threads on the ML that talk about manually
deleting a bucket.
On Thu, Sep 20, 2018 at 2:04 PM Sean Purdy wrote:
> Hi,
>
>
>
When I've tested compression before there are 2 places you need to
configure compression. On the OSDs in the configuration settings that you
mentioned, but also on the [1] pools themselves. If you have the
compression mode on the pools set to none, then it doesn't matter what the
OSDs configurati
Can you outline the process you're using to access the REST API? It's hard
to troubleshoot this without knowing how you were trying to do this.
On Mon, Sep 17, 2018 at 7:09 PM Michael Schäfer
wrote:
> Hi,
>
> We have a problem with the radosgw using the S3 REST API.
> Trying to create a new buc
Have you looked at your Garbage Collection. I would guess that your GC is
behind and that radosgw-admin is accounting for that space knowing that it
hasn't been freed up yet, whiles 3cmd doesn't see it since it no longer
shows in the listing.
On Tue, Sep 18, 2018 at 4:45 AM Luis Periquito wrote:
> It really seems to be something with RocksDB on centOS. I still think
> you can try removing “compression=kNoCompression” from the
> filestore_rocksdb_options And/Or check if rocksdb is expecting snappy to be
> enabled.
>
> Thanks,
> -Pavan.
>
> From: David Tur
. But other clients with only
> 1Gb nic will go through 140.109.0.0 (1Gb LAN) to ask mon or to read/write
> to osds. This is why my osds also have 1Gb and 10Gb nics with 140.109.0.0
> and 10.32.0.0 networking respectively.
>
> Cheers
> Joshua
>
> On Sun, Sep 30, 2018 at 12:09
The cluster/private network is only used by the OSDs. Nothing else in ceph
or its clients communicate using it. Everything other than osd to osd
communication uses the public network. That includes the MONs, MDSs,
clients, and anything other than an osd talking to an osd. Nothing else
other than os
ssion to be enabled, can you try
> removing “compression=kNoCompression” from the filestore_rocksdb_options?
> And/or you might want to check if rocksdb is expecting snappy to be enabled.
>
> From: David Turner
> Date: Tuesday, September 18, 2018 at 6:01 PM
> To: Pavan Rallabhand
> is reporting failure:1
>
> I'm working on getting things mostly good again with everything on mimic and
> will see if it behaves better.
>
> Thanks for your input on this David.
>
>
> [global]
> mon_initial_members = sephmon1, sephmon2, sephmon3
> mon_host = 10.
1 - 100 of 974 matches
Mail list logo
