Re: [Gluster-users] Transport endpoint not connected
Hey guys, Any clues or pointers with this problem? It's occurring every 6 hours or so.. Anything else I can do to help debug it? Kind regards -- joe. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users- boun...@gluster.org] On Behalf Of Joe Warren-Meeks Sent: 26 April 2010 12:31 To: Vijay Bellur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Transport endpoint not connected Here is the relevant crash section: patchset: v3.0.4 signal received: 11 time of crash: 2010-04-23 21:40:40 configuration details: argp 1 backtrace 1 dlfcn 1 fdatasync 1 libpthread 1 llistxattr 1 setfsid 1 spinlock 1 epoll.h 1 xattr.h 1 st_atim.tv_nsec 1 package-string: glusterfs 3.0.4 /lib/libc.so.6[0x7ffd0d809100] /usr/local/lib/glusterfs/3.0.4/xlator/performance/read- ahead.so(ra_fstat +0x82)[0 x7ffd0c968d22] /usr/local/lib/libglusterfs.so.0(default_fstat+0xcb)[0x7ffd0df7411b] /usr/local/lib/glusterfs/3.0.4/xlator/performance/quick- read.so(qr_fstat +0x113)[ 0x7ffd0c5570a3] /usr/local/lib/glusterfs/3.0.4/xlator/performance/write- behind.so(wb_fst at_helpe r+0xcb)[0x7ffd0c346adb] /usr/local/lib/libglusterfs.so.0(call_resume+0x390)[0x7ffd0df7cf60] /usr/local/lib/glusterfs/3.0.4/xlator/performance/write- behind.so(wb_res ume_othe r_requests+0x58)[0x7ffd0c349938] /usr/local/lib/glusterfs/3.0.4/xlator/performance/write- behind.so(wb_pro cess_que ue+0xe1)[0x7ffd0c348251] /usr/local/lib/glusterfs/3.0.4/xlator/performance/write- behind.so(wb_fst at+0x20a )[0x7ffd0c34a87a] /usr/local/lib/libglusterfs.so.0(default_fstat+0xcb)[0x7ffd0df7411b] /usr/local/lib/glusterfs/3.0.4/xlator/mount/fuse.so[0x7ffd0bf23a36] /usr/local/lib/glusterfs/3.0.4/xlator/mount/fuse.so[0x7ffd0bf246b6] /lib/libpthread.so.0[0x7ffd0db3f3f7] /lib/libc.so.6(clone+0x6d)[0x7ffd0d8aeb4d] And Startup section: - === = Version : glusterfs 3.0.4 built on Apr 19 2010 16:37:50 git: v3.0.4 Starting Time: 2010-04-26 10:00:59 Command line : /usr/local/sbin/glusterfs --log-level=NORMAL --volfile=/etc/glust erfs/repstore1-tcp.vol /data/import PID : 5910 System name : Linux Nodename : w2 Kernel Release : 2.6.24-27-server Hardware Identifier: x86_64 Given volfile: +-- - ---+ 1: ## file auto generated by /usr/local/bin/glusterfs-volgen (mount.vol) 2: # Cmd line: 3: # $ /usr/local/bin/glusterfs-volgen --name repstore1 --raid 1 10.10.130.11:/data/export 10.10.130.12:/data/export 4: 5: # RAID 1 6: # TRANSPORT-TYPE tcp 7: volume 10.10.130.12-1 8: type protocol/client 9: option transport-type tcp 10: option remote-host 10.10.130.12 11: option transport.socket.nodelay on 12: option transport.remote-port 6996 13: option remote-subvolume brick1 14: end-volume 15: 16: volume 10.10.130.11-1 17: type protocol/client 18: option transport-type tcp 19: option remote-host 10.10.130.11 20: option transport.socket.nodelay on 21: option transport.remote-port 6996 22: option remote-subvolume brick1 23: end-volume 24: 25: volume mirror-0 26: type cluster/replicate 27: subvolumes 10.10.130.11-1 10.10.130.12-1 28: end-volume 29: 30: volume readahead 31: type performance/read-ahead 32: option page-count 4 33: subvolumes mirror-0 34: end-volume 35: 36: volume iocache 37: type performance/io-cache 38: option cache-size `echo $(( $(grep 'MemTotal' /proc/meminfo | sed 's/[^0-9]//g') / 5120 ))`MB 39: option cache-timeout 1 40: subvolumes readahead 41: end-volume 42: 43: volume quickread 44: type performance/quick-read 45: option cache-timeout 1 46: option max-file-size 64kB 47: subvolumes iocache 48: end-volume 49: 50: volume writebehind 51: type performance/write-behind 52: option cache-size 4MB 53: subvolumes quickread 54: end-volume 55: 56: volume statprefetch 57: type performance/stat-prefetch 58: subvolumes writebehind 59: end-volume 60: -Original Message- From: Vijay Bellur [mailto:vi...@gluster.com] Sent: 22 April 2010 18:40 To: Joe Warren-Meeks Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Transport endpoint not connected Hi Joe, Can you please share the complete client log file? Thanks, Vijay Joe Warren-Meeks wrote: Hey guys, I've recently implemented gluster to share webcontent read-write between two servers. Version : glusterfs 3.0.4 built on Apr 19 2010 16:37:50 Fuse: 2.7.2-1ubuntu2.1 Platform: ubuntu 8.04LTS I used the following command to generate my configs: /usr/local/bin/glusterfs-volgen --name repstore1
Re: [Gluster-users] heavy metadata issues?
Hi Joe, We've been seeing the same thing here with several GlusterFS setups. It is really bad with GigE under load. From looking at our setups, it appears to be a network latency/contention issue. It is definitely not a disk contention issue as there is not a lot of load on the disks at the time of the metadata performance issues. Like you, we've tried a number of different combinations to help improve the performance. statprefetch will help with subsequent accesses to the same metadata, but it doesn't help with the initial access. We have not tried Infiniband yet to see if it improves the performance, but I am concerned that in a high IOps environment (like we run here), that even IB will not be able to sustain performance. - Mike Michael Moore Staff Engineer - Network SOLiD Advanced Research and Collaborations 500 Cummings Center Suite 2400 Beverly, MA 01915 T: 978-232-7886 michael.mo...@lifetech.com mike.mo...@appliedbiosystems.com -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Joe Landman Sent: Tuesday, April 27, 2010 7:19 PM To: gluster-users@gluster.org Subject: [Gluster-users] heavy metadata issues? Hi folks Seeing some metadata slowdowns in some cases on GlusterFS 3.0.3. These metadata slowdowns manifest in terms of long ls, long stat, long rm times for directories with a few thousand files. We tried statprefetch at the end of the stack, as well as right after the protocol/client, tried increasing read-ahead, etc. Is there anything in particular we should be looking to do, in order to get reasonable metadata performance under load? Thanks! Joe -- Joseph Landman, Ph.D Founder and CEO Scalable Informatics Inc. email: land...@scalableinformatics.com web : http://scalableinformatics.com http://scalableinformatics.com/jackrabbit phone: +1 734 786 8423 x121 fax : +1 866 888 3112 cell : +1 734 612 4615 ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] server ver 3.0.4 crashes
Did a strait install and the ibverbs instance will crash after a single connection attempt. Are there any bugs that would cause this behavior? All the log tells me is: pending frames: frame : type(2) op(SETVOLUME) patchset: v3.0.4 signal received: 11 time of crash: 2010-04-28 10:41:08 configuration details: argp 1 backtrace 1 dlfcn 1 fdatasync 1 libpthread 1 llistxattr 1 setfsid 1 spinlock 1 epoll.h 1 xattr.h 1 st_atim.tv_nsec 1 package-string: glusterfs 3.0.4 /lib64/tls/libc.so.6[0x33c0a2e2b0] /usr/local/lib/libglusterfs.so.0(dict_unserialize+0x111)[0x2b662221d281] /usr/local/lib/glusterfs/3.0.4/xlator/protocol/server.so(mop_setvolume+0xa2)[0x2b6622f246e2] /usr/local/lib/glusterfs/3.0.4/xlator/protocol/server.so(protocol_server_interpret+0x1aa)[0x2b6622f25a0a] /usr/local/lib/glusterfs/3.0.4/xlator/protocol/server.so(protocol_server_pollin+0x8b)[0x2b6622f268cb] /usr/local/lib/glusterfs/3.0.4/xlator/protocol/server.so(notify+0x100)[0x2b6622f26aa0] /usr/local/lib/libglusterfs.so.0(xlator_notify+0x94)[0x2b661b24] /usr/local/lib/glusterfs/3.0.4/transport/ib-verbs.so[0x2aaaf048] /lib64/tls/libpthread.so.0[0x33c1906137] /lib64/tls/libc.so.6(__clone+0x73)[0x33c0ac7113] - -- ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] server ver 3.0.4 crashes
Hi Mickey, Please open a defect in bugzilla. Someone from the dev team will have a look at it soon. Regards, Tejas. - Original Message - From: Mickey Mazarick m...@digitaltadpole.com To: Gluster Users gluster-users@gluster.org Sent: Wednesday, April 28, 2010 8:14:53 PM Subject: [Gluster-users] server ver 3.0.4 crashes Did a strait install and the ibverbs instance will crash after a single connection attempt. Are there any bugs that would cause this behavior? All the log tells me is: pending frames: frame : type(2) op(SETVOLUME) patchset: v3.0.4 signal received: 11 time of crash: 2010-04-28 10:41:08 configuration details: argp 1 backtrace 1 dlfcn 1 fdatasync 1 libpthread 1 llistxattr 1 setfsid 1 spinlock 1 epoll.h 1 xattr.h 1 st_atim.tv_nsec 1 package-string: glusterfs 3.0.4 /lib64/tls/libc.so.6[0x33c0a2e2b0] /usr/local/lib/libglusterfs.so.0(dict_unserialize+0x111)[0x2b662221d281] /usr/local/lib/glusterfs/3.0.4/xlator/protocol/server.so(mop_setvolume+0xa2)[0x2b6622f246e2] /usr/local/lib/glusterfs/3.0.4/xlator/protocol/server.so(protocol_server_interpret+0x1aa)[0x2b6622f25a0a] /usr/local/lib/glusterfs/3.0.4/xlator/protocol/server.so(protocol_server_pollin+0x8b)[0x2b6622f268cb] /usr/local/lib/glusterfs/3.0.4/xlator/protocol/server.so(notify+0x100)[0x2b6622f26aa0] /usr/local/lib/libglusterfs.so.0(xlator_notify+0x94)[0x2b661b24] /usr/local/lib/glusterfs/3.0.4/transport/ib-verbs.so[0x2aaaf048] /lib64/tls/libpthread.so.0[0x33c1906137] /lib64/tls/libc.so.6(__clone+0x73)[0x33c0ac7113] - -- ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Transport endpoint not connected
Joe, Do you have access to the core dump from the crash? If you do, please post the output of 'thread apply all bt full' within gdb on the core. Thanks, Avati On Wed, Apr 28, 2010 at 2:26 PM, Joe Warren-Meeks j...@encoretickets.co.uk wrote: Hey guys, Any clues or pointers with this problem? It's occurring every 6 hours or so.. Anything else I can do to help debug it? Kind regards -- joe. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users- boun...@gluster.org] On Behalf Of Joe Warren-Meeks Sent: 26 April 2010 12:31 To: Vijay Bellur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Transport endpoint not connected Here is the relevant crash section: patchset: v3.0.4 signal received: 11 time of crash: 2010-04-23 21:40:40 configuration details: argp 1 backtrace 1 dlfcn 1 fdatasync 1 libpthread 1 llistxattr 1 setfsid 1 spinlock 1 epoll.h 1 xattr.h 1 st_atim.tv_nsec 1 package-string: glusterfs 3.0.4 /lib/libc.so.6[0x7ffd0d809100] /usr/local/lib/glusterfs/3.0.4/xlator/performance/read- ahead.so(ra_fstat +0x82)[0 x7ffd0c968d22] /usr/local/lib/libglusterfs.so.0(default_fstat+0xcb)[0x7ffd0df7411b] /usr/local/lib/glusterfs/3.0.4/xlator/performance/quick- read.so(qr_fstat +0x113)[ 0x7ffd0c5570a3] /usr/local/lib/glusterfs/3.0.4/xlator/performance/write- behind.so(wb_fst at_helpe r+0xcb)[0x7ffd0c346adb] /usr/local/lib/libglusterfs.so.0(call_resume+0x390)[0x7ffd0df7cf60] /usr/local/lib/glusterfs/3.0.4/xlator/performance/write- behind.so(wb_res ume_othe r_requests+0x58)[0x7ffd0c349938] /usr/local/lib/glusterfs/3.0.4/xlator/performance/write- behind.so(wb_pro cess_que ue+0xe1)[0x7ffd0c348251] /usr/local/lib/glusterfs/3.0.4/xlator/performance/write- behind.so(wb_fst at+0x20a )[0x7ffd0c34a87a] /usr/local/lib/libglusterfs.so.0(default_fstat+0xcb)[0x7ffd0df7411b] /usr/local/lib/glusterfs/3.0.4/xlator/mount/fuse.so[0x7ffd0bf23a36] /usr/local/lib/glusterfs/3.0.4/xlator/mount/fuse.so[0x7ffd0bf246b6] /lib/libpthread.so.0[0x7ffd0db3f3f7] /lib/libc.so.6(clone+0x6d)[0x7ffd0d8aeb4d] And Startup section: - === = Version : glusterfs 3.0.4 built on Apr 19 2010 16:37:50 git: v3.0.4 Starting Time: 2010-04-26 10:00:59 Command line : /usr/local/sbin/glusterfs --log-level=NORMAL --volfile=/etc/glust erfs/repstore1-tcp.vol /data/import PID : 5910 System name : Linux Nodename : w2 Kernel Release : 2.6.24-27-server Hardware Identifier: x86_64 Given volfile: +-- - ---+ 1: ## file auto generated by /usr/local/bin/glusterfs-volgen (mount.vol) 2: # Cmd line: 3: # $ /usr/local/bin/glusterfs-volgen --name repstore1 --raid 1 10.10.130.11:/data/export 10.10.130.12:/data/export 4: 5: # RAID 1 6: # TRANSPORT-TYPE tcp 7: volume 10.10.130.12-1 8: type protocol/client 9: option transport-type tcp 10: option remote-host 10.10.130.12 11: option transport.socket.nodelay on 12: option transport.remote-port 6996 13: option remote-subvolume brick1 14: end-volume 15: 16: volume 10.10.130.11-1 17: type protocol/client 18: option transport-type tcp 19: option remote-host 10.10.130.11 20: option transport.socket.nodelay on 21: option transport.remote-port 6996 22: option remote-subvolume brick1 23: end-volume 24: 25: volume mirror-0 26: type cluster/replicate 27: subvolumes 10.10.130.11-1 10.10.130.12-1 28: end-volume 29: 30: volume readahead 31: type performance/read-ahead 32: option page-count 4 33: subvolumes mirror-0 34: end-volume 35: 36: volume iocache 37: type performance/io-cache 38: option cache-size `echo $(( $(grep 'MemTotal' /proc/meminfo | sed 's/[^0-9]//g') / 5120 ))`MB 39: option cache-timeout 1 40: subvolumes readahead 41: end-volume 42: 43: volume quickread 44: type performance/quick-read 45: option cache-timeout 1 46: option max-file-size 64kB 47: subvolumes iocache 48: end-volume 49: 50: volume writebehind 51: type performance/write-behind 52: option cache-size 4MB 53: subvolumes quickread 54: end-volume 55: 56: volume statprefetch 57: type performance/stat-prefetch 58: subvolumes writebehind 59: end-volume 60: -Original Message- From: Vijay Bellur [mailto:vi...@gluster.com] Sent: 22 April 2010 18:40 To: Joe Warren-Meeks Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Transport endpoint not connected Hi Joe, Can you please share the complete client log file? Thanks, Vijay Joe Warren-Meeks wrote: Hey guys, I've recently implemented gluster to share webcontent read-write between two servers. Version :
Re: [Gluster-users] Transport endpoint not connected
Here you go! Anything else I can do? Joe, can you please rerun the gdb command as: # gdb /usr/local/sbin/glusterfs -c /core.13560 Without giving the glusterfs binary in the parameter the backtrace is missing all the symbols and just the numerical addresses are not quite useful. Thanks, Avati ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Transport endpoint not connected
Oops, I'm an idiot, sorry about that.. here you go!
Thread 3 (process 13560):
#0 0x7ffd0db44402 in ?? () from /lib/libpthread.so.0
No symbol table info available.
#1 0x7ffd0c7600ff in ioc_open_cbk (frame=0x122c6a0,
cookie=0x122c7d0,
this=0x6104e0, op_ret=0, op_errno=117, fd=0x12af1f0) at
io-cache.c:474
tmp_ioc_inode = 0
local = (ioc_local_t *) 0x122c700
table = value optimized out
ioc_inode = value optimized out
inode = (inode_t *) 0x61d220
weight = value optimized out
path = 0x12af130 /docs/cbolds/PAGES/V1/THEATRENET
__FUNCTION__ = ioc_open_cbk
#2 0x7ffd0c96a395 in ra_open_cbk (frame=0x122c7d0,
cookie=value optimized out, this=value optimized out, op_ret=0,
op_errno=117, fd=0x12af1f0) at read-ahead.c:116
fn = (fop_open_cbk_t) 0x7ffd0c760090 ioc_open_cbk
_parent = (call_frame_t *) 0x122c6a0
old_THIS = (xlator_t *) 0x60fbe0
file = value optimized out
__FUNCTION__ = ra_open_cbk
#3 0x7ffd0cb8f4a2 in afr_open_cbk (frame=0x122c830, cookie=0x1,
this=value optimized out, op_ret=value optimized out,
op_errno=value optimized out, fd=0x12af1f0) at afr-open.c:140
fn = (fop_open_cbk_t) 0x7ffd0c96a1f0 ra_open_cbk
_parent = (call_frame_t *) 0x122c7d0
old_THIS = (xlator_t *) 0x60f390
__local = (afr_local_t *) 0x122c890
__this = (xlator_t *) 0x60f390
local = (afr_local_t *) 0x122c890
ctx = 140724576331344
fd_ctx = value optimized out
ret = value optimized out
call_count = value optimized out
__FUNCTION__ = afr_open_cbk
#4 0x7ffd0cdbe27b in client_open_cbk (frame=0x12af600,
hdr=value optimized out, hdrlen=value optimized out,
iobuf=value optimized out) at client-protocol.c:4090
fn = (ret_fn_t) 0x7ffd0cb8f280 afr_open_cbk
_parent = (call_frame_t *) 0x122c830
old_THIS = (xlator_t *) 0x60e110
op_ret = 0
op_errno = 0
fd = (fd_t *) 0x12af1f0
local = (client_local_t *) 0x12af840
fdctx = value optimized out
ino = 3793176
gen = 5462270833604952119
#5 0x7ffd0cdb8a2a in protocol_client_pollin (this=0x60e110,
trans=0x6151d0) at client-protocol.c:6827
conf = (client_conf_t *) 0x614bd0
ret = 0
iobuf = (struct iobuf *) 0x0
hdr = 0x7ffcfe6249a0
hdrlen = 116
#6 0x7ffd0cdbfc7a in notify (this=0x61d228, event=value optimized
out,
data=0x6151d0) at client-protocol.c:6946
ret = value optimized out
child_down = value optimized out
was_not_down = value optimized out
trans = (transport_t *) 0x122c7d0
conn = value optimized out
conf = (client_conf_t *) 0x614bd0
parent = value optimized out
__FUNCTION__ = notify
#7 0x7ffd0df6e033 in xlator_notify (xl=0x60e110, event=2,
data=0x6151d0)
at xlator.c:924
old_THIS = (xlator_t *) 0x7ffd0e19ec00
ret = value optimized out
#8 0x7ffd0bd1345b in socket_event_handler (fd=value optimized
out,
idx=3, data=0x6151d0, poll_in=1, poll_out=0, poll_err=0) at
socket.c:831
this = (transport_t *) 0x61d228
priv = (socket_private_t *) 0x615540
ret = 0
#9 0x7ffd0df8784a in event_dispatch_epoll (event_pool=0x609930)
at event.c:804
events = (struct epoll_event *) 0x6166e0
i = 1
ret = 2
__FUNCTION__ = event_dispatch_epoll
#10 0x00404533 in main (argc=4, argv=0x7fff5b5ccac8)
at glusterfsd.c:1425
ctx = (glusterfs_ctx_t *) 0x608010
cmd_args = value optimized out
stbuf = {st_dev = 0, st_ino = 140734726193120, st_nlink = 0,
st_mode = 236629549, st_uid = 32765, st_gid = 0, pad0 = 0, st_rdev =
0,
st_size = 0, st_blksize = 140724840091158, st_blocks =
140734726194672,
st_atim = {tv_sec = 140724840082928, tv_nsec = 140734726194735},
st_mtim = {
tv_sec = 140734726194720, tv_nsec = 140734726194712}, st_ctim = {
tv_sec = 140724842257208, tv_nsec = 4199943}, __unused = {0, 0,
140724829864661}}
tmp_logfile = '\0' repeats 1023 times
tmp_logfile_dyn = value optimized out
tmp_logfilebase = value optimized out
timestr = '\0' repeats 255 times
utime = 1271949306
tm = value optimized out
ret = 0
lim = {rlim_cur = 18446744073709551615,
rlim_max = 18446744073709551615}
specfp = value optimized out
graph = (xlator_t *) 0x609e70
trav = value optimized out
fuse_volume_found = 0
xl_count = value optimized out
pipe_fd = {6, 7}
gf_success = 0
gf_failure = -1
__FUNCTION__ = main
Thread 2 (process 13561):
#0 0x7ffd0d874b81 in nanosleep () from /lib/libc.so.6
No symbol table info available.
#1 0x7ffd0d8a8584 in usleep () from /lib/libc.so.6
No symbol table info available.
#2 0x7ffd0df79d63 in
Re: [Gluster-users] Transport endpoint not connected
On Wed, Apr 28, 2010 at 11:15 PM, Joe Warren-Meeks j...@encoretickets.co.uk wrote: Oops, I'm an idiot, sorry about that.. here you go! Thanks! We have a good understanding of the issue now. Please add yourself to the CC list at http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=868 to get fix updates. Avati ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] modprobe fuse; device or resource busy
I am getting the following error when trying to load fuse.ko built from fuse-2.7.4: FATAL: Error inserting fuse (/lib/modules/2.6.21.5-clustervision-181_cvos/kernel/fs/fuse/fuse.ko): Device or resource busy Upgrading the kernel would be difficult as the machine in question is a network booting cluster compute node. It has a customised kernel without fuse built in. Can anybody tell me what I am doing wrong? I have successfully used fuse-2.7.4 and earlier versions with older kernels in the past, but have never encountered this error. -Dan Bretherton. -- Mr. D.A. Bretherton Reading e-Science Centre Environmental Systems Science Centre Harry Pitt Building 3 Earley Gate University of Reading Reading, RG6 6AL UK Tel. +44 118 378 7722 Fax: +44 118 378 6413 ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] Gluster bandwidth usage -
Gluster-users - First I'd like to introduce myself, I'm Craig Carl, the new sales engineer here at Gluster Inc. I've been a Gluster user and a community/mailing list participant for a long time, and I'm very excited to be working with the incredible team here at Gluster Inc. and all of the members of the Gluster community. A strong community is vital to the success of any open source software project, I wanted to make sure you all know that your input and support is recognized and very much appreciated. Everyone here in the office is subscribed to this list and we are always glad to get feedback from you, good or otherwise. More on topic - Disk and processor speeds have increased by leaps and bounds in the last ten years while network connection speeds have stagnated, 1000Base-T is over ten years old(1). Because of those issues Gluster users usually hit some sort of bandwidth limit long before the storage node's CPU, memory, or disk I/O limits are reached. Bonding 1Gb interfaces can help, but the law of diminishing returns kicks in very quickly. We would like to know if bandwidth saturation is impacting your Gluster cluster. • Do you monitor and log the storage node's IP or IB interfaces for bandwidth used %? • Do the interfaces look saturated? How does a saturated link affect your access to the data? • Do you have MRTG, Cacti, or any other bandwidth monitoring tools installed and suspect network saturation is an issue at your site? • Have you had a bandwidth problem and solved it? • Would you be willing to share that data with us? Please let us know! Any information you have related to bandwidth and Gluster would be very helpful. If you want to send a responce directly to me please do, your data will be kept private. If you live or work in the San Francisco Bay Area I'd love to talk to you about how you are using Gluster, the beer(s) is on me, please get in touch! Thank you all very much for your continued support. Craig http://en.wikipedia.org/wiki/802.3ab#History -- Thanks, Craig Carl Gluster, Inc. Cell - (408) 829-9953 (California, USA) Office - (408) 770-1884 Gtalk - craig.c...@gmail.com Twitter - @gluster http://www.gluster.com/files/installation-demo/demo.html ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Data
Hi Brad, Glusterfs does not proactively migrate data on addition of a node, but there is a defrag script that allows an admin to do that. Please see the defrag and scale and defrag scripts here - http://ftp.gluster.com/pub/gluster/glusterfs/misc/defrag/ Regards, Tejas. - Original Message - From: Brad Alexander b...@servosity.com To: gluster-users@gluster.org Sent: Saturday, April 24, 2010 11:36:10 PM Subject: [Gluster-users] Data Good Afternoon, Does gluster proactively migrates data onto new devices in order to maintain a balanced distribution of data when new bricks are added? Thanks. Brad Alexander ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
