I can't ceph file system in writing on file

2011-05-31 Thread biyan chen
When I mount ceph after the file system. I want to go to create a file, but hint permissions problem, cannot write In /var/log/ceph log information inside, didn't see more information [root@ceph_client /]# df Filesystem 1K-blocks Used Available Use% Mounted on /dev/sda1

Re: File only read, can't write, problem

2011-05-31 Thread biyan chen
I have mount on ceph file system, but, after entering directory cannot read documents. [root@ceph_client 1]# df Filesystem 1K-blocks Used Available Use% Mounted on /dev/sda1472658192 20199408 428449108 5% / tmpfs 1984548 0 1984548 0% /dev

Some thoughts about exceptions and Ceph

2011-05-31 Thread Colin Patrick McCabe
Ok. The exceptions issue. Flamewar in 3... 2... 1... Although most of Ceph is C++, a lot of the code in Ceph is written in a C-like style. Partly this is because we want to use the low-level features of C++ is gain some additional efficiency. Partly this is because we supply C APIs and interact wi

Re: cfuse and ceph.conf

2011-05-31 Thread Sage Weil
On Tue, 31 May 2011, Tommi Virtanen wrote: > On Wed, Jun 01, 2011 at 12:44:30AM +0300, Fyodor Ustinov wrote: > > As I understand with -m key cfuse should not require ceph.conf. > > It does need a config, to even know whether it should attempt > cryptographic authentication or not (and where to fin

ceph lock

2011-05-31 Thread biyan chen
HI Everybody! Who can give me some information about CEPH file locks CEPH files lock mechanism is how -- name:Riby mobile:+86 15280267642 company: 百大龙一 -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majord...@vger.kernel.org More majordomo

Re: cfuse and ceph.conf

2011-05-31 Thread Tommi Virtanen
On Wed, Jun 01, 2011 at 12:44:30AM +0300, Fyodor Ustinov wrote: > As I understand with -m key cfuse should not require ceph.conf. It does need a config, to even know whether it should attempt cryptographic authentication or not (and where to find the key, etc). It could be changed to do things mo

cfuse and ceph.conf

2011-05-31 Thread Fyodor Ustinov
Hi! As I understand with -m key cfuse should not require ceph.conf. But: root@st8:~# cfuse -m 10.5.51.230:6789 /stor01 common_init: unable to open config file. root@st8:~# Workaround: root@st8:~# cfuse -c /dev/null -m 10.5.51.230:6789 /stor01 failed to open log file '/var/log/ceph/client.admi

Re: compile error for ceph-0.28.*.tar.gz

2011-05-31 Thread Tommi Virtanen
On Tue, May 31, 2011 at 11:52:35AM -0600, Jim Schutt wrote: > FWIW, I believe I saw such errors on RHEL 5 due to it having > boost v1.33.1, while Ceph needs v1.34 or newer to get statechart. It seems we don't have a versioned dependency on libboost. I created a ticket to make it so. Like a captain

Re: compile error for ceph-0.28.*.tar.gz

2011-05-31 Thread Jim Schutt
Tommi Virtanen wrote: On Tue, May 31, 2011 at 02:23:10PM +0800, Simon Tian wrote: hi folks, When I make ceph after ./configure, error comes both in 0.28.1 and 0.28.2 like bellow: ./include/encoding.h:294: error: no matching function for call to ?.ecode(PG::Log::Entry&, ceph::buffer::list

Re: compile error for ceph-0.28.*.tar.gz

2011-05-31 Thread Tommi Virtanen
On Tue, May 31, 2011 at 02:23:10PM +0800, Simon Tian wrote: > hi folks, > > When I make ceph after ./configure, error comes both in 0.28.1 > and 0.28.2 like bellow: > > ./include/encoding.h:294: error: no matching function for call to > ?.ecode(PG::Log::Entry&, ceph::buffer::list::iterator&

Re: Quota function of radosgw

2011-05-31 Thread Brian Chrisman
On Tue, May 31, 2011 at 9:17 AM, Gregory Farnum wrote: > On Sat, May 28, 2011 at 7:45 PM, Sylar Shen wrote: >> Hi Gregory, >> Thanks for your information very much! >> Dropbox could limit the quota value of each user. >> Does Dropbox implement the quota function by recording every size of >> file

Re: Quota function of radosgw

2011-05-31 Thread Gregory Farnum
On Sat, May 28, 2011 at 7:45 PM, Sylar Shen wrote: > Hi Gregory, > Thanks for your information very much! > Dropbox could limit the quota value of each user. > Does Dropbox implement the quota function by recording every size of > file in its own database? > Or Dropbox just controls the quota of e

Re: read and write speed.

2011-05-31 Thread Fyodor Ustinov
On 05/31/2011 05:51 PM, Gregory Farnum wrote: Sage created an issue to track this: http://tracker.newdream.net/issues/1122 Based on the differences between the FUSE and kernel clients, it's probably just readahead settings. :) -Greg I'm not sure. rsize 10 times more than the default: root@gat

Re: read and write speed.

2011-05-31 Thread Gregory Farnum
Sage created an issue to track this: http://tracker.newdream.net/issues/1122 Based on the differences between the FUSE and kernel clients, it's probably just readahead settings. :) -Greg On Tue, May 31, 2011 at 3:01 AM, Fyodor Ustinov wrote: > On 05/31/2011 01:50 AM, Fyodor Ustinov wrote: >> >>

Re: read and write speed.

2011-05-31 Thread Fyodor Ustinov
On 05/31/2011 01:50 AM, Fyodor Ustinov wrote: Hi! Fresh 0.28.2 cluster. Why reading two times slower than the writing by dd, but rados show different. (Second question - why rados bench crash on read test?) root@gate0:/mnt# dd if=/dev/zero of=aaa bs=1024000 count=1 1+0 records in 10

Re: read and write speed.

2011-05-31 Thread djlee064
> Caching effect decreases as the writing size increases. Sure, when you > write 100GB+ data, the difference may be subtle. (It still depends on > your RAM size.) > RAM does no play when goes over 100gb+ too, I've gone mad and tried 4 8 12 18gb ram. Again, huge impact/differences at the start, but

Re: read and write speed.

2011-05-31 Thread Henry C Chang
2011/5/31 djlee064 : > From my (bad) memory, I've tried fsync, and the resulting was still > the same in the end, i.e., write 100gb+ and all will be the same. > Can't test it now as it is already running other tasks.. > > I think the small bs (4-8k) results to ~ KB/s level using fsync. and > large,