My only suggestion upon reading your client file is to remove the #commented lines in the translator section for volume writebehind and all of the commented out stat-prefetch and try that configuration. The fact that the comments "shouldn't" matter does not necessarily mean that they don't. Also - do make sure to push the changed client volfile out to all the clients and restart them - unless you're using the method of accessing a centralized volfile. James Burnash, Unix Engineering -----Original Message----- From: gluster-users-bounces at gluster.org [mailto:gluster-users-bounces at gluster.org] On Behalf Of Nikola Garafolic Sent: Wednesday, September 08, 2010 5:20 AM To: gluster-users at gluster.org Subject: gluster client problems I am having problems while testing gluster performance with bonnie++. Os used is centos 5.5 64bit. This is what the log says: ================================================================================ Version : glusterfs 3.0.5 built on Oct 10 2010 00:00:29 git: v3.0.5 Starting Time: 2010-09-08 10:42:45 Command line : /usr/sbin/glusterfs PID : 11029 System name : Linux Nodename : hostname.domain.com Kernel Release : 2.6.18-194.11.1.el5 Hardware Identifier: x86_64 Given volfile: +------------------------------------------------------------------------------+ 1: ## file auto generated by /usr/bin/glusterfs-volgen (mount.vol) 2: # Cmd line: 3: # $ /usr/bin/glusterfs-volgen --name=sh -t tcp glusterfs01:/data/ glusterfs02:/data/ 4: 5: # TRANSPORT-TYPE tcp 6: volume glusterfs01-1 7: type protocol/client 8: option transport-type tcp 9: option remote-host 192.168.32.101 10: option transport.socket.nodelay on 11: option remote-port 6996 12: option remote-subvolume brick1 13: end-volume 14: 15: volume glusterfs02-1 16: type protocol/client 17: option transport-type tcp 18: option remote-host 192.168.32.102 19: option transport.socket.nodelay on 20: option remote-port 6997 21: option remote-subvolume brick2 22: end-volume 23: 24: volume distribute 25: type cluster/distribute 26: subvolumes glusterfs01-1 glusterfs02-1 27: end-volume 28: 29: volume readahead 30: type performance/read-ahead 31: option page-count 4 32: subvolumes distribute 33: end-volume 34: 35: volume iocache 36: type performance/io-cache 37: option cache-size `echo $(( $(grep 'MemTotal' /proc/meminfo | sed 's/[^0-9]//g') / 5120 ))`MB 38: option cache-timeout 1 39: subvolumes readahead 40: end-volume 41: 42: volume quickread 43: type performance/quick-read 44: option cache-timeout 1 45: option max-file-size 64kB 46: subvolumes iocache 47: end-volume 48: 49: volume writebehind 50: type performance/write-behind 51: option cache-size 4MB 52: ### 53: # option aggregate-size 65035 54: subvolumes quickread 55: end-volume 56: 57: #volume statprefetch 58: # type performance/stat-prefetch 59: # subvolumes writebehind 60: #end-volume 61: +------------------------------------------------------------------------------+ [2010-09-08 10:42:45] W [write-behind.c:2479:init] writebehind: dangling volume. check volfile [2010-09-08 10:42:45] E [glusterfsd.c:673:glusterfs_graph_init] glusterfs: no valid translator loaded at the top or no mount point given. exiting [2010-09-08 10:42:45] E [glusterfsd.c:1395:main] glusterfs: translator initialization failed. exiting -- Nikola Garafolic SRCE, Sveucilisni racunski centar tel: +385 1 6165 804 email: nikola.garafolic at srce.hr _______________________________________________ Gluster-users mailing list Gluster-users at gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users DISCLAIMER: This e-mail, and any attachments thereto, is intended only for use by the addressee(s) named herein and may contain legally privileged and/or confidential information. If you are not the intended recipient of this e-mail, you are hereby notified that any dissemination, distribution or copying of this e-mail, and any attachments thereto, is strictly prohibited. If you have received this in error, please immediately notify me and permanently delete the original and any copy of any e-mail and any printout thereof. E-mail transmission cannot be guaranteed to be secure or error-free. The sender therefore does not accept liability for any errors or omissions in the contents of this message which arise as a result of e-mail transmission. NOTICE REGARDING PRIVACY AND CONFIDENTIALITY Knight Capital Group may, at its discretion, monitor and review the content of all e-mail communications. http://www.knight.com
