similar to: smbd's using up 100% of all cpu's and load avg slowly going up

In IRC today, someone who was hitting that same IB performance ceiling that occasionally gets reported had this to say [11:50] <nissim> first, I ran fedora which is not supported by Mellanox OFED distro [11:50] <nissim> so I moved to CentOS 6.3 [11:51] <nissim> next I removed all distibution related infiniband rpms and build the latest OFED package [11:52] <nissim>

Hi, I've been migrating data from an old striped 3.0.x gluster install to a 3.3 beta install. I copied all the data to a regular XFS partition (4K blocksize) from the old gluster striped volume and it totaled 9.2TB. With the old setup I used the following option in a "volume stripe" block in the configuration file in a client : volume stripe type cluster/stripe option

I'm about to do some testing with a an OSX 10.9 client connected to sernet samba 4.1.5 to see what things work and don't both from the finder and from the terminal with unix extensions = yes and no. Does anyone know of any show stopping issues that occur with unix extensions = yes and the latest samba (or 3.6.x, or 4.0.x a) and the latest OSX (or latest update with 10.7 & 10.8)?

Hi, Anyone know if the 1024 char limit for auth.allow still exists in the latest production version (seems to be there in 3.2.5). Also anyone know if the new versions check if auth.allow has been updated without having to restart glusterd? Is there anyway to restart glusterd without killing it and restarting the process, is kill -1 (HUP) possible with it (also with the version i'm running?)

Hi, I've got this strange problem where a striped endpoint will crash when I try to use cp to copy files off of it but not when I use rsync to copy files off: [user at gluster5 user]$ cp -r Python-2.6.4/ ~/tmp/ cp: reading `Python-2.6.4/Lib/lib2to3/tests/data/fixers/myfixes/__init__.py': Software caused connection abort cp: closing

Hi all, We're running gpfs 3.5.0.12 (5 total nsds & quorum servers, 2 nsds running samba), sernet-samba 4.1.4-7, and ctdb 1.0.114.7-1 and trying to get transparent failover to work from a windows 8 client. We have ctdb failover working, i.e. if I run mmshutdown on one of the nodes the IPs failover in a few seconds after the GPFS mount is unmounted. For our transparent failover test, I

Hi all, I have two rhel 6.3 servers running sernet samba 4.1.4-7 with winbind connecting to AD. They're also running ctdb. For some very strange reason I can't get one specific AD group to show up in the output of "id username" or the gid of that group to show up in "wbinfo -r username" for the user on one of the servers but it shows up fine on the other. The strange

Hi all, Does anyone have vfs_shadow_copy2 working with an alternate snapshot directory format? My snapshots look like this : drwxr-xr-x 55 root root 32768 Jan 10 12:37 20140113_12:00 drwxr-xr-x 55 root root 32768 Jan 10 12:37 20140114_12:00 drwxr-xr-x 55 root root 32768 Jan 10 12:37 20140115_12:00 drwxr-xr-x 55 root root 32768 Jan 10 12:37 20140116_12:00 drwxr-xr-x 55 root root 32768 Jan 10

Hi, Why does mkfs.ocfs2 take so long compared to gfs2 (pretty fast iirc), xfs (almost instantaneous), or ext3 (slow but still ok)? I'm using: # mkfs.ocfs2 -F -b 4k -C 4k -L san1 -T mail /dev/vg/san1 mkfs.ocfs2 1.3.9 Overwriting existing ocfs2 partition. WARNING: Cluster check disabled. Proceed (y/N): y Filesystem Type of mail Filesystem label=san1 Block size=4096 (bits=12) Cluster size=4096

Hi, I noticed that smbcontrol smbd reload-config or service smbd reload doesn't reload include files. Is there anyway to get a reload to reload files that have been included from the main smb.conf ? Otherwise it only looks like restart works, but that causes connections to reset, even in a ctdb/clustered environment . The only other option it looks like is to just put everything into the

I noticed that vfs_acl_xattr doesn't work unless all the inherit and map inherit acl parameters are set to yes. Which is fine but if I turn off inherit owner it completely breaks inheritance and security.NTACL never gets set for the file/directory that's created by the user. I want the uid of the user who's connected to be written and not the owner of the parent directory. Is there

Hi, Here is some output of "strace -ff -p" to the process using ~100% CPU writev(75, [{"\250\r\0\0\2\0\0\0S-1-5-21-2097307442-3435"..., 3496}], 1) = 3496 epoll_wait(9, {{EPOLLIN, {u32=2539833808, u64=140271876753872}}}, 1, 30000) = 1 readv(91, [{"\34\0\0\0\0\0\0\0rT\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 2092}], 1) = 2092 gettimeofday({1419854003, 222035},

Greetings, There are 2 imminent releases coming soon to a download server near you: 1. GlusterFS 3.2.6 - a maintenance release that fixes some bugs. 2. GlusterFS 3.3 beta 3 - the next iteration of the exciting new hotness that will be 3.3 You can find both of these in the "QA builds" server: http://bits.gluster.com/pub/gluster/glusterfs/ There are source tarballs and binary RPMs

On 29/12/14 12:02, Bruno Andrade wrote: > Hi again, > > Sorry, I forgot to include the fd used... > > 13 -> /var/lib/samba/private/sam.ldb.d/DC=EXAMPLE,DC=COM.ldb > 16 -> /var/lib/samba/private/sam.ldb.d/metadata.tdb > > the others refers to /var/run/samba/winbindd/pipe > > Regards, > Bruno Andrade. > > On 12/29/2014 11:56 AM, Bruno Andrade wrote:

On 29/12/14 14:58, Bruno Andrade wrote: > Hi, > > Yes, I already thought about it. > > I have the sernet repo installed.. Is possible to yum update and jump > from 4.1.6 to 4.1.14 directly, without problems or should I follow some > kind of procedure to avoid future problems? > > Regards, > Bruno Andrade. > > On 12/29/2014 01:46 PM, Rowland Penny wrote: >>

All, For our project, we bought 8 new Supermicro servers. Each server is a quad-core Intel cpu with 2U chassis supporting 8 x 7200 RPM Sata drives. To start out, we only populated 2 x 2TB enterprise drives in each server and added all 8 peers with their total of 16 drives as bricks to our gluster pool as distributed replicated (2). The replica worked as follows: 1.1 -> 2.1 1.2

Hi, I'm having problems in a second domain controller machine. Every time a restart samba, few time after a samba process starts using almost 100% cpu. It's a Centos 6.5 x86_64 with the following: sernet-samba-libsmbclient0-4.1.6-7.el6.x86_64 sernet-samba-ad-4.1.6-7.el6.x86_64 sernet-build-key-1.1-4.noarch sernet-samba-libs-4.1.6-7.el6.x86_64 sernet-samba-client-4.1.6-7.el6.x86_64

I have been reading through an old thread and to be honest confused.com root at zent1:~# samba-tool domain level show params.c:pm_process() - Processing configuration file "/etc/samba/shares.conf" ldb_wrap open of secrets.ldb Domain and forest function level for domain 'DC=office,DC=zentyal,DC=lan' Forest function level: (Windows) 2003 Domain function level: (Windows) 2003

Hi again, Sorry, I forgot to include the fd used... 13 -> /var/lib/samba/private/sam.ldb.d/DC=EXAMPLE,DC=COM.ldb 16 -> /var/lib/samba/private/sam.ldb.d/metadata.tdb the others refers to /var/run/samba/winbindd/pipe Regards, Bruno Andrade. On 12/29/2014 11:56 AM, Bruno Andrade wrote: > Hi, > > Here is some output of "strace -ff -p" to the process using ~100% CPU >

Dear All Can you please do me favor and let me know what is the equivalent of "iftop" command on CentOS 5.2 ? Please be informed that I couldn't find an rpm package for "iftop" on the www.pbone.net . Let me thank you in advance -------------- next part -------------- An HTML attachment was scrubbed... URL: