eph client io and ceph ops seem to
> have dropped at cluster level (verified by looking at ceph status).
> Did our second pool got impacted too or we should take from granted
> that the pools are indeed isolated during remapping and there is a
> ceph status view granularity issue here?
&
It crashed on an OSD reply. What's the output of "ceph -s"?
-Greg
On Wednesday, July 9, 2014, Florent B wrote:
> Hi all,
>
> I run a Firefly cluster with a MDS server for a while without any problem.
>
> I would like to setup a second one to get a failover server.
>
> To minimize downtime in cas
On Thursday, July 10, 2014, Erik Logtenberg wrote:
>
> > Yeah, Ceph will never voluntarily reduce the redundancy. I believe
> > splitting the "degraded" state into separate "wrongly placed" and
> > "degraded" (reduced redundancy) states is currently on the menu for
> > the Giant release, but it's
On Thu, Jul 10, 2014 at 9:04 AM, Joe Hewitt wrote:
> Hi there
> Recently I got a problem triggered by rebooting ceph nodes, which eventually
> wound up by rebuilding from ground up. A too-long-don't-read question here
> is: is there suggested best practices for online/offline ceph node?
>
> Follow
On Mon, Jul 14, 2014 at 2:16 AM, Christian Balzer wrote:
>
> Hello,
>
> new firefly cluster, currently just 1 storage node with 8 OSDs (3TB HDDs,
> journals on 4 DC3700 SSDs), the rest of the storage nodes are in the queue
> and 3 mons. Thus replication of 1.
>
> Now this is the 2nd incarnation i
This is just the output if it fails to connect to the first monitor it
tries (in this case, the one that isn't running). If you let it run
for a while it should time out after 15 seconds or something, pick a
different monitor, and succeed.
-Greg
Software Engineer #42 @ http://inktank.com | http://c
It's generally recommended that you use disks in JBOD mode rather than
involving RAID.
-Greg
On Monday, July 14, 2014, 不坏阿峰 wrote:
> I have installed and test Ceph on VMs before, i know a bit about
> configuration and install.
> Now i want to use physic PC Server to install Ceph and do some Test
Are you saturating your network bandwidth? That's what it sounds like. :)
-Greg
On Monday, July 14, 2014, baijia...@126.com wrote:
> hi, everyone!
>
> I test RGW get obj ops, when I use 100 threads get one and the same
> object , I find that performance is very good, meadResponseTime is 0.1s.
You can't use erasure coded pools directly with RBD. They're only suitable
for use with RGW or as the base pool for a replicated cache pool, and you
need to be very careful/specific with the configuration. I believe this is
well-documented, so check it out! :)
-Greg
On Saturday, July 12, 2014, qix
What did ceph-fuse output to its log file or the command line?
On Tuesday, July 15, 2014, Jaemyoun Lee wrote:
> Hi All,
>
> I am using ceph 0.80.1 on Ubuntu 14.04 on KVM. However, I cannot connect
> to the MON from a client using ceph-fuse.
>
> On the client, I installed the ceph-fuse 0.80.1 and
Okay, first the basics: cls_rbd.cc operates only on rbd header
objects, so it's doing coordinating activities, not the actual data
handling. When somebody does an operation on an rbd image, they put
some data in the header object so that everybody else can coordinate
(if it's open) or continue (if
On Tue, Jul 15, 2014 at 10:15 AM, Jaemyoun Lee wrote:
> The output is nothing because ceph-fuse fell into an infinite while loop as
> I explain below.
>
> Where can I find the log file of ceph-fuse?
It defaults to /var/log/ceph, but it may be empty. I realize the task
may have hung, but I'm prett
68.122.166:0/3296 <==
> mon.0 192.168.122.106:6789/0 10 mon_subscribe_ack(300s) v1
> 20+0+0 (4226112827 0 0) 0x7f9a3c40 con 0x7f9a23c0dd30
> 2014-07-16 17:13:34.207622 7f9a177fe700 10 client.4705 renew_caps()
> 2014-07-16 17:13:54.209995 7f9a177fe700 10 client.4705 rene
On Wed, Jul 16, 2014 at 1:50 AM, James Harper wrote:
> Can you offer some comments on what the impact is likely to be to the data in
> an affected cluster? Should all data now be treated with suspicion and
> restored back to before the firefly upgrade?
I am under the impression that it's not ac
On Wed, Jul 16, 2014 at 9:20 AM, Scottix wrote:
> I wanted to update ceph-fuse to a new version and I would like to have
> it seamless.
> I thought I could do a remount to update the running version but came to a
> fail.
> Here is the error I got.
>
> # mount /mnt/ceph/ -o remount
> 2014-07-16 09
On Wed, Jul 16, 2014 at 6:21 AM, Pierre BLONDEAU
wrote:
> Hi,
>
> After the repair process, i have :
> 1926 active+clean
>2 active+clean+inconsistent
>
> This two PGs seem to be on the same osd ( #34 ):
> # ceph pg dump | grep inconsistent
> dumped all in format plain
> 0.2e4 0
On Wed, Jul 16, 2014 at 4:45 PM, Craig Lewis wrote:
> One of the things I've learned is that many small changes to the cluster are
> better than one large change. Adding 20% more OSDs? Don't add them all at
> once, trickle them in over time. Increasing pg_num & pgp_num from 128 to
> 1024? Go i
There's nothing built in to the system but I think some people have
had success with scripts that set nobackfill during the day, and then
trigger them regularly at night. Try searching the list archives. :)
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Fri, Jul 18, 2014 at
Hmm, this log is just leaving me with more questions. Could you tar up
the "/var/lib/ceph/mon/store.db" (substitute actual mon store path as
necessary) and upload it for me? (you can use ceph-post-file to put it
on our servers if you prefer.) Just from the log I don't have a great
idea of what's go
The config option change in the upgrade will prevent *new* scrub
errors from occurring, but it won't resolve existing ones. You'll need
to run a scrub repair to fix those up.
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Fri, Jul 18, 2014 at 2:59 PM, Randy Smith wrote:
>
Yes, that's expected behavior. Since the cluster can't move data
around on its own, and lots of things will behave *very badly* if some
of their writes go through but others don't, the cluster goes
read-only once any OSD is full. That's why nearfull is a warn
condition; you really want to even out
On Fri, Jul 18, 2014 at 3:29 PM, James Eckersall
wrote:
> Thanks Greg.
>
> Can I suggest that the documentation makes this much clearer? It might just
> be me, but I couldn't glean this from the docs, so I expect I'm not the only
> one.
>
> Also, can I clarify how many pg's you would suggest is
ick and
> we're back to HEALTH_OK.
>
> Cheers,
> Lincoln Bryant
>
> On Jul 18, 2014, at 4:15 PM, Gregory Farnum wrote:
>
>> Hmm, this log is just leaving me with more questions. Could you tar up
>> the "/var/lib/ceph/mon/store.db" (substitute actual mon
ring
> errors waiting for a scrub to find or just wait it out for a couple of days
> and hope that my data is safe?
>
>
> On Fri, Jul 18, 2014 at 4:01 PM, Gregory Farnum > wrote:
>
>> The config option change in the upgrade will prevent *new* scrub
>> errors from o
The heartbeat code is very careful to use the same physical interfaces as
1) the cluster network
2) the public network
If the first breaks, the OSD can't talk with its peers. If the second
breaks, it can't talk with the monitors or clients. Either way, the
OSD can't do its job so it gets marked do
nditions we'd like to gather more
information and figure out what happened!
-Greg
>
> From your points, it's easy to understand. And I see the code
> comments(src/ceph-osd.cc) claim the usage.
>
> Best Wishes!
>
>> 在 2014年7月20日，1:14，Gregory Farnum 写道：
>>
>
On Monday, July 21, 2014, Cristian Falcas wrote:
> Hello,
>
> We have a test project where we are using ceph+openstack.
>
> Today we had some problems with this setup and we had to force reboot the
> server. After that, the partition where we keep the ceph journal could not
> mount.
>
> When we c
On Monday, July 21, 2014, Jaemyoun Lee wrote:
> Hi all,
>
> I wonder that OSDs use system calls of Virtual File System (i.e. open,
> read, write, etc) when they access disks.
>
> I mean ... Could I monitor I/O command requested by OSD to disks if I
> monitor VFS?
>
Yes. The default configuration
>
>
> 18 jul 2014 kl. 20:04 skrev Gregory Farnum :
>
> There's nothing built in to the system but I think some people have
> had success with scripts that set nobackfill during the day, and then
> trigger them regularly at night. Try searching the list archives. :)
I'll see what I can do with this tomorrow, but it can be difficult to deal
with commits from an out-of-tree build, or even with commits that got
merged in following other changes (which is what happened with this
commit). I didn't see any obviously relevant commits in the git history, so
I want to
On Tue, Jul 22, 2014 at 8:38 AM, Aaron Ten Clay wrote:
> Hi Cephers,
>
> I'm trying to recover from an inconsistent object issue. I know which object
> is inconsistent across its two replicas, but I'm having difficulty
> determining which of the three copies is correct. Is there an easy way to
> d
On Thu, Jul 17, 2014 at 1:39 PM, Lincoln Bryant wrote:
> Hi all,
>
> I tried restarting my mon today, but I find that it no longer starts.
> Whenever I try to fire up the mon, I get errors of this nature:
>
>-3> 2014-07-17 15:12:32.738510 7f25b0921780 10 mon.a@-1(probing).auth
> v1537 update
Keep in mind that this coordination is largely happening above the
FileStore layer, so you are indeed not seeing any code within the
FileStore to support it. :) But operations within the OSD are ordered
on a per-PG basis, and while in-progress writes can overlap, a read
will be blocked until the wr
It still helps; the journal does just as much work. Less of the work
*can* be in the critical path for IO, but for most of the applications
it will be.
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Sat, Jul 26, 2014 at 2:18 AM, Cristian Falcas
wrote:
> Hello,
>
> I'm usin
On Mon, Jul 28, 2014 at 12:14 PM, Christian Balzer wrote:
> On Mon, 28 Jul 2014 14:24:02 + Edward Huyer wrote:
>
>> > > Ceph has a default pool size of 3. Is it a bad idea to run a pool of
>> > > size 2? What about size 2 min_size 1?
>> > >
>> > min_size 1 is sensible, 2 obviously won't protec
You could create a new root bucket which contains hosts 2 and 3; then
use it instead of "default" in your special rule. That's probably what
you want anyway (rather than potentially having two copies of the data
on host 1).
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Tue
On Thu, Jul 31, 2014 at 2:41 AM, yuelongguang wrote:
> hi,all
> 1.
> it seems that there are 2 kinds of function that get/set xattrs.
> one kind start with collection_*,the another one start with omap_*.
> what is the differences between them, and what xattrs use which kind of
> function?
IIRC,
Add a parameter to the OSD's config file
"osd crush update on start = false"
I'd recommend creating a section for just your SSD OSDs which sets this, as
that will let any of your other disks that move continue to be updated. :)
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
O
These sorts of questions are good for ceph-de...@vger.kernel.org,
which I've added. :)
On Thu, Jul 31, 2014 at 12:24 PM, yuelongguang wrote:
> hi,all
> recently i dive into the source code, i am a little confused about them,
> maybe because of many threads,wait,seq.
>
> 1. what does apply_manager
On Thu, Jul 31, 2014 at 2:35 PM, David Graham wrote:
> Question: I've not gone through a setup yet, just an interested lurker
> reading and interpreting capabilities at this time.
>
> my understanding of Ceph journal is that one can use a partition or a file
> on a Filesystem if i use a files
We appear to have solved this and then immediately re-broken it by
ensuring that the userspace daemons will set a new required feature
bit if there are any EC rules in the OSDMap. I was going to say
there's a ticket open for it, but I can't find one...
-Greg
On Fri, Aug 1, 2014 at 7:22 AM, Ilya Dr
The sst files are files used by leveldb to store its data; you cannot
remove them. Are you running on a very small VM? How much space are
the files taking up in aggregate?
Speaking generally, I think you should see something less than a GB
worth of data there, but some versions of leveldb under som
Check out http://ceph.com/docs/master/rados/operations/pools/#set-pool-values
"Hit sets" are bloom filters which we use to track which objects are
accessed ("hit") during a specific time period (hit_set_period). More
hit sets within a given time let us distinguish more fine-grained
accesses to the
On Wed, Aug 6, 2014 at 1:48 AM, Kenneth Waegeman
wrote:
> Hi,
>
> I did a test with 'rados -p ecdata bench 10 write' on an ECpool with a
> cache replicated pool over it (ceph 0.83).
> The benchmark wrote about 12TB of data. After the 10 seconds run, rados
> started to delete his benchmark
It's been a while since I worked on this, but let's see what I remember...
On Thu, Aug 14, 2014 at 11:34 AM, Craig Lewis wrote:
> In my effort to learn more of the details of Ceph, I'm trying to
> figure out how to get from an object name in RadosGW, through the
> layers, down to the files on dis
On Thu, Aug 14, 2014 at 12:40 PM, Robert LeBlanc wrote:
> We are looking to deploy Ceph in our environment and I have some musings
> that I would like some feedback on. There are concerns about scaling a
> single Ceph instance to the PBs of size we would use, so the idea is to
> start small like o
On Thu, Aug 14, 2014 at 6:32 PM, yuelongguang wrote:
> hi,all
>
> By reading the code , i notice everything of a OP is encoded into
> Transaction which is writed into journal later.
> does journal record everything(meta,xattr,file data...) of a OP.
> if so everything is writed into disk twice
Yes
On Mon, Aug 18, 2014 at 6:56 AM, Jasper Siero
wrote:
> Hi all,
>
> We have a small ceph cluster running version 0.80.1 with cephfs on five
> nodes.
> Last week some osd's were full and shut itself down. To help de osd's start
> again I added some extra osd's and moved some placement group director
On Thu, Aug 14, 2014 at 2:28 AM, NotExist wrote:
> Hello everyone:
>
> Since there's no cuttlefish package for 14.04 server on ceph
> repository (only ceph-deploy there), I tried to build cuttlefish from
> source on 14.04.
...why? Cuttlefish is old and no longer provided updates. You really
want
Hmm, you're not allowed to set real xattrs on the CephFS root and
we've had issues a few times with that and the layout xattrs. There
might have been a bug with that on v0.81 which is fixed in master, but
I don't remember exactly when it last happened.
-Greg
Software Engineer #42 @ http://inktank.c
On Tue, Aug 19, 2014 at 11:18 AM, Robert LeBlanc wrote:
> Greg, thanks for the reply, please see in-line.
>
>
> On Tue, Aug 19, 2014 at 11:34 AM, Gregory Farnum wrote:
>>
>>
>> There are many groups running cluster >1PB, but whatever makes you
>> comfort
On Tue, Aug 19, 2014 at 1:37 PM, Randy Smith wrote:
> Greetings,
>
> I'm creating a new ceph cluster for testing and it's reporting "192
> stale+incomplete" pgs.
>
> `ceph health detail` lists all of the pgs that are stuck. Here's a
> representative line.
>
> pg 2.2c is stuck stale for 3076.5109
; ruleset 0
> type replicated
> min_size 1
> max_size 10
> step take default
> step chooseleaf firstn 0 type osd
> step emit
> }
>
> This is a single host "cluster" as it's just for testing.
>
>
&
. Is there a way to force the mds
> to look at the 1832 epoch (or earlier) instead of 1833 (need osdmap epoch
> 1833, have 1832)?
>
> Thanks,
>
> Jasper
>
> Van: Gregory Farnum [g...@inktank.com]
> Verzonden: dinsdag 19 augustus
Yeah, that's fairly bizarre. Have you turned up the monitor logs and
seen what they're doing? Have you checked that the nodes otherwise
have the same configuration (firewall rules, client key permissions,
installed version of Ceph...)
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.c
Are the OSD processes still alive? What's the osdmap output of "ceph
-w" (which was not in the output you pasted)?
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Thu, Aug 21, 2014 at 7:11 AM, Bruce McFarland
wrote:
> I have 3 storage servers each with 30 osds. Each osd has
On Thu, Aug 21, 2014 at 8:29 AM, Jens-Christian Fischer
wrote:
> I am working with Cinder Multi Backends on an Icehouse installation and have
> added another backend (Quobyte) to a previously running Cinder/Ceph
> installation.
>
> I can now create QuoByte volumes, but no longer any ceph volumes
On Sat, Aug 23, 2014 at 11:06 PM, Bruce McFarland
wrote:
> I see osd’s being failed for heartbeat reporting > default
> osd_heartbeat_grace of 20 but the run time config shows that the grace is
> set to 30. Is there another variable for the osd or the mon I need to set
> for the non default osd_he
What's the output of "ceph osd tree"? And the full output of "ceph -s"?
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Mon, Aug 18, 2014 at 8:07 PM, Ripal Nathuji wrote:
> Hi folks,
>
> I've come across an issue which I found a "fix" for, but I'm not sure
> whether it's co
public_network = 209.243.160.0/24
> cluster_network = 10.10.50.0/24
> osd_journal_size = 96000
> osd_heartbeat_grace = 35
>
> [osd.0]
> .
> .
> .
> -Original Message-
> From: Gregory Farnum [mailto:g...@inktank.com]
> Sent: Monday, August 25, 2014 10:39 AM
> T
On Mon, Aug 25, 2014 at 10:56 AM, Bruce McFarland
wrote:
> Thank you very much for the help.
>
> I'm moving osd_heartbeat_grace to the global section and trying to figure out
> what's going on between the osd's. Since increasing the osd_heartbeat_grace
> in the [mon] section of ceph.conf on the
This is being output by one of the kernel clients, and it's just
saying that the connections to those two OSDs have died from
inactivity. Either the other OSD connections are used a lot more, or
aren't used at all.
In any case, it's not a problem; just a noisy notification. There's
not much you ca
In particular, we changed things post-Firefly so that the filesystem
isn't created automatically. You'll need to set it up (and its pools,
etc) explicitly to use it.
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Mon, Aug 25, 2014 at 2:40 PM, Sean Crosby
wrote:
> Hi James,
I don't think the log messages you're showing are the actual cause of
the failure. The log file should have a proper stack trace (with
specific function references and probably a listed assert failure),
can you find that?
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Tue,
jects degraded (50.000%)
> 832 active+degraded
>
>
> Thanks,
> Ripal
>
> On Aug 25, 2014, at 12:45 PM, Gregory Farnum wrote:
>
> What's the output of "ceph osd tree"? And the full output of "ceph -s"?
> -Greg
> Software E
ation on the newer versions? (we're doing
> evaluations at present, so I had wanted to work with newer versions, since it
> would be closer to what we would end up using).
>
>
> -Original Message-
> From: Gregory Farnum [mailto:g...@inktank.com]
> Sent: Tuesday,
This looks new to me. Can you try and start up the OSD with "debug osd
= 20" and "debug filestore = 20" in your conf, then put the log
somewhere accessible? (You can also use ceph-post-file if it's too
large for pastebin or something.)
Also, check dmesg and see if btrfs is complaining, and see what
On Tue, Aug 26, 2014 at 10:46 PM, John Morris wrote:
> In the docs [1], 'incomplete' is defined thusly:
>
> Ceph detects that a placement group is missing a necessary period of
> history from its log. If you see this state, report a bug, and try
> to start any failed OSDs that may contain th
There aren't too many people running RAID under Ceph, as it's a second
layer of redundancy that in normal circumstances is a bit pointless.
But there are scenarios where it might be useful. You might check the
list archives for the "anti-cephalopod question" thread.
-Greg
Software Engineer #42 @ ht
On Thu, Aug 28, 2014 at 10:36 AM, Brian C. Huffman
wrote:
> Is Ceph Filesystem ready for production servers?
>
> The documentation says it's not, but I don't see that mentioned anywhere
> else.
> http://ceph.com/docs/master/cephfs/
Everybody has their own standards, but Red Hat isn't supporting i
On Thu, Aug 28, 2014 at 10:41 AM, LaBarre, James (CTR) A6IT
wrote:
> Just out of curiosity, is there a way to mount a Ceph filesystem directly on
> a MSWindows system (2008 R2 server)? Just wanted to try something out from
> a VM.
Nope, sorry.
-Greg
___
eep_scrub_errors": 0,
> "num_objects_recovered": 0,
> "num_bytes_recovered": 0,
> "num_keys_recovered": 0},
> "stat_cat_sum": {},
> "up": [
> 7,
On Thu, Aug 28, 2014 at 9:52 PM, pragya jain wrote:
> I have some basic question about monitor and paxos relationship:
>
> As the documents says, Ceph monitor contains cluster map, if there is any
> change in the state of the cluster, the change is updated in the cluster
> map. monitor use paxos a
The clients are sending messages to OSDs which are not the primary for
the data. That shouldn't happen — clients which don't understand the
whole osdmap ought to be gated and prevented from accessing the
cluster at all. What version of Ceph are you running, and what
clients?
(We've seen this in dev
On Mon, Sep 8, 2014 at 10:08 AM, JIten Shah wrote:
> While checking the health of the cluster, I ran to the following error:
>
> warning: health HEALTH_WARN too few pgs per osd (1< min 20)
>
> When I checked the pg and php numbers, I saw the value was the default value
> of 64
>
> ceph osd pool ge
n Sep 8, 2014, at 10:31 AM, Gregory Farnum wrote:
>
>> On Mon, Sep 8, 2014 at 10:08 AM, JIten Shah wrote:
>>> While checking the health of the cluster, I ran to the following error:
>>>
>>> warning: health HEALTH_WARN too few pgs per osd (1< min 20)
>>
On Sun, Sep 7, 2014 at 4:28 PM, Alex Moore wrote:
> I recently found out about the "ceph --admin-daemon
> /var/run/ceph/ceph-osd..asok dump_historic_ops" command, and noticed
> something unexpected in the output on my cluster, after checking numerous
> output samples...
>
> It looks to me like "no
On Mon, Sep 8, 2014 at 1:42 AM, Francois Deppierraz
wrote:
> Hi,
>
> This issue is on a small 2 servers (44 osds) ceph cluster running 0.72.2
> under Ubuntu 12.04. The cluster was filling up (a few osds near full)
> and I tried to increase the number of pg per pool to 1024 for each of
> the 14 poo
On Mon, Sep 8, 2014 at 2:53 PM, Francois Deppierraz
wrote:
> Hi Greg,
>
> Thanks for your support!
>
> On 08. 09. 14 20:20, Gregory Farnum wrote:
>
>> The first one is not caused by the same thing as the ticket you
>> reference (it was fixed well before emperor), so
On Mon, Sep 8, 2014 at 6:33 AM, Eduard Kormann wrote:
> Hello,
>
> have I missed something or is it a feature: When I restart a osd on the
> belonging server so it restarts normally:
>
> root@cephosd10:~# service ceph restart osd.76
> === osd.76 ===
> === osd.76 ===
> Stopping Ceph osd.76 on cepho
On Tue, Sep 9, 2014 at 9:11 AM, Daniel Schneller
wrote:
> Hi list!
>
> Under
> http://lists.ceph.com/pipermail/ceph-users-ceph.com/2013-September/033670.html
> I found a situation not unlike ours, but unfortunately either
> the list archive fails me or the discussion ended without a
> conclusion,
The important bit there is actually near the end of the message output
line, where the first says "ack" and the second says "ondisk".
I assume you're using btrfs; the ack is returned after the write is applied
in-memory and readable by clients. The ondisk (commit) message is returned
after it's du
On Wednesday, September 10, 2014, Daniel Schneller <
daniel.schnel...@centerdevice.com> wrote:
> On 09 Sep 2014, at 21:43, Gregory Farnum > wrote:
>
>
> Yehuda can talk about this with more expertise than I can, but I think
> it should be basically fine. By creatin
On Tue, Sep 9, 2014 at 6:10 PM, Blair Bethwaite
wrote:
> Hi Sage,
>
> Thanks for weighing into this directly and allaying some concerns.
>
> It would be good to get a better understanding about where the rough
> edges are - if deployers have some knowledge of those then they can be
> worked around
tive"
with it until it has at least min_size copies that it knows about.
Once the OSD is doing any processing of the PG, it requires all
participating members to respond before it sends any messages back to
the client.
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
>
>
Presumably it's going faster when you have a deeper iodepth? So the reason
it's using more CPU is because it's doing more work. That's all there is to
it. (And the OSD uses a lot more CPU than some storage systems do, because
it does a lot more work than them.)
-Greg
On Thursday, September 11, 201
>
>
>
>
>
>
>
> At 2014-09-11 12:19:18, "Gregory Farnum" > wrote:
> >On Wed, Sep 10, 2014 at 8:29 PM, yuelongguang >> wrote:
> >>
> >>
> >>
> >>
> >> as for ack and ondisk, ceph has size and min_s
On Thu, Sep 11, 2014 at 4:13 AM, Kenneth Waegeman
wrote:
> Hi all,
>
> I am testing the tiering functionality with cephfs. I used a replicated
> cache with an EC data pool, and a replicated metadata pool like this:
>
>
> ceph osd pool create cache 1024 1024
> ceph osd pool set cache size 2
> ceph
On Thu, Sep 11, 2014 at 11:39 AM, Sage Weil wrote:
> On Thu, 11 Sep 2014, Gregory Farnum wrote:
>> On Thu, Sep 11, 2014 at 4:13 AM, Kenneth Waegeman
>> wrote:
>> > Hi all,
>> >
>> > I am testing the tiering functionality with cephfs. I used a replica
On Wed, Sep 10, 2014 at 4:24 PM, McNamara, Bradley
wrote:
> Hello,
>
> This is my first real issue since running Ceph for several months. Here's
> the situation:
>
> I've been running an Emperor cluster for several months. All was good. I
> decided to upgrade since I'm running Ubuntu 13.10 an
On Fri, Sep 12, 2014 at 1:53 AM, Kenneth Waegeman > wrote:
>
> - Message from Sage Weil > -
>Date: Thu, 11 Sep 2014 14:10:46 -0700 (PDT)
>From: Sage Weil >
> Subject: Re: [ceph-users] Cephfs upon Tiering
> To: Gregory Farnum >
> C
Ceph messages are transmitted using tcp, so the system isn't directly aware
of packet loss at any level. I suppose we could try and export messenger
reconnect counts via the admin socket, but that'd be a very noisy measure
-- it seems simplest to just query the OS or hardware directly?
-Greg
On Fr
On Fri, Sep 12, 2014 at 9:26 AM, brandon li wrote:
> Hi,
>
> I am new to ceph file system, and have got a newbie question:
>
> For a sparse file, how could ceph file system know the hole in the file was
> never created or some stripe was just simply lost?
CephFS does not keep any metadata to try
On Fri, Sep 12, 2014 at 6:49 AM, Florent Bautista wrote:
> Hi all,
>
> Today I have a problem using CephFS. I use firefly last release, with
> kernel 3.16 client (Debian experimental).
>
> I have a directory in CephFS, associated to a pool "pool2" (with
> set_layout).
>
> All is working fine, I ca
ject_t, pg_info_t const&,
>> std::map,
>> std::allocator> hobject_t> > >&, PGLog::IndexedLog&, pg_missing_t&,
>> std::basic_ostringstream,
>> std::allocator >&, std::set> string>, std::allocator >*)+0x16d4) [0x7d3ef4]
>>
You can turn off the MDS and create a new FS in new pools. The ability
to shut down a filesystem more completely is coming in Giant.
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Fri, Sep 12, 2014 at 1:16 PM, LaBarre, James (CTR) A6IT
wrote:
> We were building a tes
I don't know where the file came from, but likely/unlikely markers are the
kind of micro-optimization that isn't worth the cost in Ceph dev resources
right now.
-Greg
On Monday, September 15, 2014, Tim Zhang wrote:
> Hey guys,
> After reading ceph source code, I find that there is a file named
>
Not sure, but have you checked the clocks on their nodes? Extreme
clock drift often results in strange cephx errors.
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Sun, Sep 14, 2014 at 11:03 PM, Florian Haas wrote:
> Hi everyone,
>
> [Keeping this on the -users list for no
The pidfile bug is already fixed in master/giant branches.
As for the crashing, I'd try killing all the osd processes and turning
them back on again. It might just be some daemon restart failed, or
your cluster could be sufficiently overloaded that the node disks are
going unresponsive and they're
terested in the scenario of having a EC backed pool fronted by a
> replicated cache for use with cephfs.
>
> Thanks,
> Berant
>
> On Fri, Sep 12, 2014 at 12:37 PM, Gregory Farnum wrote:
>>
>> On Fri, Sep 12, 2014 at 1:53 AM, Kenneth Waegeman
>> wrote:
>> &g
101 - 200 of 2358 matches
Mail list logo
