Hi,
I attached one 500G block device to the vm, and test it in vm use
"dd if=/dev/zero of=myfile bs=1M count=1024" ,
Then I got a average io speed about 31MB/s. I thought that i
should have got 100MB/s，
cause my vm hypervisor has 1G nic and osd host has 10G nic。
Di
Hi,
I attached one 500G block device to the vm, and test it in vm use
"dd if=/dev/zero of=myfile bs=1M count=1024" ,
Then I got a average io speed about 31MB/s. I thought that i
should have got 100MB/s，
cause my vm hypervisor has 1G nic and osd host has 10G nic。
Di
Hey all-
Can anyone tell me, if I install the latest development release (looks like it
is 0.77) can I enable and test erasure coding? Or do I have to wait for the
actual Firefly release? I don't want to deploy anything for production,
basically I just want to do some lab testing to see what
Joe,
We¹re pushing to get 0.78 out this week, which will allow you to play with
EC.
Ian R. Colle
Director of Engineering
Inktank
Delivering the Future of Storage
http://www.linkedin.com/in/ircolle
http://www.twitter.com/ircolle
Cell: +1.303.601.7713
Email: i...@inktank.com
On 3/16/14, 8:11 PM, "
Great, thanks! I'll watch (hope) for an update later this week. Appreciate
the rapid response.
-Joe
From: Ian Colle [mailto:ian.co...@inktank.com]
Sent: Sunday, March 16, 2014 7:22 PM
To: Gruher, Joseph R; ceph-users@lists.ceph.com
Subject: Re: [ceph-users] erasure coding testing
Joe,
We're
Hi everyone,
I am using replicate 2, 3 for my data pools.
Anh, I want to stop recovering process when a data node be down. I
think mark "unout" downed osds or setting crushmap for down osd with
their weigh=0, Righ?
ceph-data-node-01:
70 1 osd.70 down0
[root@storage1 ~]# ceph osd perf
osdid fs_commit_latency(ms) fs_apply_latency(ms)
0 149 52
1 201 61
2 176 166
3 240 57
4
That seems a little high; how do you have your system configured? That
latency is how long it takes for the hard drive to durably write out
something to the journal.
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
On Sun, Mar 16, 2014 at 9:59 PM, wrote:
>
> [root@storage1 ~]#
Hi Gregory,
The latency is under my ceph test environment. It has only 1 host
with 16 2T SATA disks(16 OSDs) and 10Gb/s NIC，
journal and data are on the same disk which fs type is ext4.
my cluster config is like this. is it normal under this
configuration ? or how can i im
I'm not sure what's normal when you're sharing the journal and the data on
the same disk drive. You might do better if you partition the drive and put
the journals on an unformatted partition; obviously providing each journal
its own spindle/ssd/whatever would be progressively better.
There was a c
Hello,
I'm looking to build a full ssd cluster (I have mainly random io workload),
I would like to known how many iops can we expect, by osd ?
I have read on inktank doc, about 4000 iops by osd(that enough for me). Is is
true ?
What is the bottleneck ? osd cpu limited ?
Also, can we have othe
Hi all,
I have a question about the pool .rgw.buckets, when I upload a file(has been
stripped because it is bigger than 4M) through swift API, it is stored in
.rgw.buckets,
if I upload it again, why the objects in .rgw.buckets are not override? It is
stored again and have different name. and wh
Hi Alexandre,
Am 17.03.2014 07:03, schrieb Alexandre DERUMIER:
> Hello,
>
> I'm looking to build a full ssd cluster (I have mainly random io workload),
>
> I would like to known how many iops can we expect, by osd ?
>
> I have read on inktank doc, about 4000 iops by osd(that enough for me). Is
13 matches
Mail list logo
