Re: [Gluster-users] intended use cases
- "Kent Tong" wrote: > Hi, > > What are the intended use cases for gluster? For example, is it > suitable for, > say, replacing a SAN? For example, is it good for the following? > [ ] Storing a huge volume of seldom accessed files (file archive) > [ ] Storing frequently read/write files (file server) > [ ] Storing frequently read files (web server) > [ ] Hosting databases > [ ] Hosting VM images All of the above. Vikas -- Engineer - http://gluster.com/ A: Because it messes up the way people read text. Q: Why is a top-posting such a bad thing? -- ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] Performance question
I'm using an unpatched fuse 2.7.4-1 and glusterfs 2.0.2-1 with the following configs and have this result which surprised me: # dd if=/dev/zero of=foo bs=512k count=1024 1024+0 records in 1024+0 records out 536870912 bytes (537 MB) copied, 14.1538 seconds, 37.9 MB/s # dd if=/dev/zero of=foo bs=512k count=1024 1024+0 records in 1024+0 records out 536870912 bytes (537 MB) copied, 24.4553 seconds, 22.0 MB/s Why is it slower if the file exists? Should it be? # Servers # volume posix0 type storage/posix option directory /cluster/0 end-volume volume locks0 type features/locks subvolumes posix0 end-volume volume brick0 type performance/io-threads option thread-count 8 subvolumes locks0 end-volume volume posix1 type storage/posix option directory /cluster/1 end-volume volume locks1 type features/locks subvolumes posix1 end-volume volume brick1 type performance/io-threads option thread-count 8 subvolumes locks1 end-volume volume posix2 type storage/posix option directory /cluster/2 end-volume volume locks2 type features/locks subvolumes posix2 end-volume volume brick2 type performance/io-threads option thread-count 8 subvolumes locks2 end-volume volume posix3 type storage/posix option directory /cluster/3 end-volume volume locks3 type features/locks subvolumes posix3 end-volume volume brick3 type performance/io-threads option thread-count 8 subvolumes locks3 end-volume volume server type protocol/server option transport-type tcp subvolumes brick0 brick1 brick2 brick3 option auth.addr.brick0.allow * option auth.addr.brick1.allow * option auth.addr.brick2.allow * option auth.addr.brick3.allow * end-volume Client volume ewcs2_cluster0 type protocol/client option transport-type tcp option remote-host ewcs2.ewcs.com option remote-subvolume brick0 end-volume volume ewcs2_cluster1 type protocol/client option transport-type tcp option remote-host ewcs2.ewcs.com option remote-subvolume brick1 end-volume volume ewcs2_cluster2 type protocol/client option transport-type tcp option remote-host ewcs2.ewcs.com option remote-subvolume brick2 end-volume volume ewcs2_cluster3 type protocol/client option transport-type tcp option remote-host ewcs2.ewcs.com option remote-subvolume brick3 end-volume volume ewcs4_cluster0 type protocol/client option transport-type tcp option remote-host ewcs4.ewcs.com option remote-subvolume brick0 end-volume volume ewcs4_cluster1 type protocol/client option transport-type tcp option remote-host ewcs4.ewcs.com option remote-subvolume brick1 end-volume volume ewcs4_cluster2 type protocol/client option transport-type tcp option remote-host ewcs4.ewcs.com option remote-subvolume brick2 end-volume volume ewcs4_cluster3 type protocol/client option transport-type tcp option remote-host ewcs4.ewcs.com option remote-subvolume brick3 end-volume volume ewcs7_cluster0 type protocol/client option transport-type tcp option remote-host ewcs7.ewcs.com option remote-subvolume brick0 end-volume volume ewcs7_cluster1 type protocol/client option transport-type tcp option remote-host ewcs7.ewcs.com option remote-subvolume brick1 end-volume volume ewcs7_cluster2 type protocol/client option transport-type tcp option remote-host ewcs7.ewcs.com option remote-subvolume brick2 end-volume volume ewcs7_cluster3 type protocol/client option transport-type tcp option remote-host ewcs7.ewcs.com option remote-subvolume brick3 end-volume volume repl1 type cluster/replicate subvolumes ewcs2_cluster0 ewcs4_cluster0 ewcs7_cluster0 end-volume volume repl2 type cluster/replicate subvolumes ewcs2_cluster1 ewcs4_cluster1 ewcs7_cluster1 end-volume volume repl3 type cluster/replicate subvolumes ewcs2_cluster2 ewcs4_cluster2 ewcs7_cluster2 end-volume volume repl4 type cluster/replicate subvolumes ewcs2_cluster3 ewcs4_cluster3 ewcs7_cluster3 end-volume volume distribute type cluster/distribute subvolumes repl1 repl2 repl3 repl4 end-volume volume writebehind type performance/write-behind option aggregate-size 128KB option cache-size 1MB subvolumes distribute end-volume volume ioc type performance/io-cache option cache-size 512MB subvolumes writebehind end-volume ### mount -t glusterfs /etc/glusterfs/glusterfs-client.vol /mnt/gluster ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] intended use cases
Hi, What are the intended use cases for gluster? For example, is it suitable for, say, replacing a SAN? For example, is it good for the following? [ ] Storing a huge volume of seldom accessed files (file archive) [ ] Storing frequently read/write files (file server) [ ] Storing frequently read files (web server) [ ] Hosting databases [ ] Hosting VM images ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] Client detect when server comes back up
Hi, I have a basic 2 server (serverA and serverB) replication with 1 client. Sometimes serverB will go offline, so client is writing directly to serverA. However when serverB comes back online, the client does not detect this and ignore serverB until I restart the client. Is this meant to happen? Regards, Simon ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Use of mod_glusterfs
Hi, Thanks for your return . I didn't know how to use it after install mod_glusterfs into apache ,Could you tell me for detail ? Should i mount the gluster for a directory ? or didn't mount directory ? How to write or read data from gluster through mod_glusterfs ? We only used gluster for reading purposes through apache. There is a little description in the wiki available. I would suggest you try that: http://www.gluster.org/docs/index.php/ Getting_modglusterfs_to_work. The module doesn't need a locally mounted gluster-share. It connects directly with libgluster to the storageservers. Regards Jasper___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] HadoopFS-like gluster setup
Peng Zhao wrote: [2009-07-01 18:36:25] E [socket.c:206:__socket_server_bind] server: binding to failed: Address already in use [2009-07-01 18:36:25] E [socket.c:209:__socket_server_bind] server: Port is already in use [2009-07-01 18:36:25] E [server-protocol.c:7631:init] server: failed to bind/listen on socket [2009-07-01 18:36:25] E [xlator.c:736:xlator_init_rec] xlator: Initialization of volume 'server' failed, review your volfile again [2009-07-01 18:36:25] E [glusterfsd.c:498:_xlator_graph_init] glusterfs: initializing translator failed [2009-07-01 18:36:25] E [glusterfsd.c:1191:main] glusterfs: translator initialization failed. exiting Looks like the server port is already in use. GlusterFS tries to bind to port 6996 by default if you do not specify one. Can you please check with a different port? Regards, Vijay ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] HadoopFS-like gluster setup
BTW, is there someone have configured gluster like HDFS (unify with automatic replication). Could someone share the volfile here? I think I'm not the only fan waiting here ;-) Gnep On Wed, Jul 1, 2009 at 6:39 PM, Peng Zhao wrote: > OK, my stupid. There was no fuse module. I built one and modprobe fuse. The > previous error is gone, with some new one: > Here are the DEBUG-level msg: > [2009-07-01 18:36:25] D [xlator.c:634:xlator_set_type] xlator: > dlsym(notify) on /usr/lib64/glusterfs/2.0.2/xlator/features/locks.so: > undefined symbol: notify -- neglecting > [2009-07-01 18:36:25] D [xlator.c:634:xlator_set_type] xlator: > dlsym(notify) on > /usr/lib64/glusterfs/2.0.2/xlator/performance/io-threads.so: undefined > symbol: notify -- neglecting > [2009-07-01 18:36:25] D [xlator.c:634:xlator_set_type] xlator: > dlsym(notify) on > /usr/lib64/glusterfs/2.0.2/xlator/performance/write-behind.so: undefined > symbol: notify -- neglecting > [2009-07-01 18:36:25] D [xlator.c:634:xlator_set_type] xlator: > dlsym(notify) on /usr/lib64/glusterfs/2.0.2/xlator/performance/io-cache.so: > undefined symbol: notify -- neglecting > [2009-07-01 18:36:25] D [glusterfsd.c:1179:main] glusterfs: running in pid > 6874 > [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-0: > defaulting frame-timeout to 30mins > [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-0: > defaulting ping-timeout to 10 > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-1: > defaulting frame-timeout to 30mins > [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-1: > defaulting ping-timeout to 10 > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-2: > defaulting frame-timeout to 30mins > [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-2: > defaulting ping-timeout to 10 > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-3: > defaulting frame-timeout to 30mins > [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-3: > defaulting ping-timeout to 10 > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [unify.c:4288:init] unified: namespace node > specified as compute-5-4 > [2009-07-01 18:36:25] D [scheduler.c:48:get_scheduler] scheduler: attempt > to load file rr.so > [2009-07-01 18:36:25] D [unify.c:4320:init] unified: Child node count is 2 > [2009-07-01 18:36:25] D [rr-options.c:188:rr_options_validate] rr: using > scheduler.limits.min-free-disk = 15 [default] > [2009-07-01 18:36:25] D [rr-options.c:216:rr_options_validate] rr: using > scheduler.refresh-interval = 10 [default] > [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-4: > defaulting frame-timeout to 30mins > [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-4: > defaulting ping-timeout to 10 > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt > to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so > [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-4: got > GF_EVENT_PARENT_UP, attempting connect on transport > [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-4: got > GF_EVENT_PARENT_UP, attempting connect on transport > [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-4: got > GF_EVENT_PARENT_UP, attempting connect on transport > [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-4: got > GF_EVENT_PARENT_UP, attempting connect on transport > [2009-07-01 18:36:25] D [write-behind.c:1859:init] writebehind: disabling > write-behind for first 1 bytes > [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-0: got > GF_EVENT_PARENT_UP, attempting connect on transport > [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-0: got > GF_EVENT_
Re: [Gluster-users] HadoopFS-like gluster setup
OK, my stupid. There was no fuse module. I built one and modprobe fuse. The previous error is gone, with some new one: Here are the DEBUG-level msg: [2009-07-01 18:36:25] D [xlator.c:634:xlator_set_type] xlator: dlsym(notify) on /usr/lib64/glusterfs/2.0.2/xlator/features/locks.so: undefined symbol: notify -- neglecting [2009-07-01 18:36:25] D [xlator.c:634:xlator_set_type] xlator: dlsym(notify) on /usr/lib64/glusterfs/2.0.2/xlator/performance/io-threads.so: undefined symbol: notify -- neglecting [2009-07-01 18:36:25] D [xlator.c:634:xlator_set_type] xlator: dlsym(notify) on /usr/lib64/glusterfs/2.0.2/xlator/performance/write-behind.so: undefined symbol: notify -- neglecting [2009-07-01 18:36:25] D [xlator.c:634:xlator_set_type] xlator: dlsym(notify) on /usr/lib64/glusterfs/2.0.2/xlator/performance/io-cache.so: undefined symbol: notify -- neglecting [2009-07-01 18:36:25] D [glusterfsd.c:1179:main] glusterfs: running in pid 6874 [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-0: defaulting frame-timeout to 30mins [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-0: defaulting ping-timeout to 10 [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-1: defaulting frame-timeout to 30mins [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-1: defaulting ping-timeout to 10 [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-2: defaulting frame-timeout to 30mins [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-2: defaulting ping-timeout to 10 [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-3: defaulting frame-timeout to 30mins [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-3: defaulting ping-timeout to 10 [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [unify.c:4288:init] unified: namespace node specified as compute-5-4 [2009-07-01 18:36:25] D [scheduler.c:48:get_scheduler] scheduler: attempt to load file rr.so [2009-07-01 18:36:25] D [unify.c:4320:init] unified: Child node count is 2 [2009-07-01 18:36:25] D [rr-options.c:188:rr_options_validate] rr: using scheduler.limits.min-free-disk = 15 [default] [2009-07-01 18:36:25] D [rr-options.c:216:rr_options_validate] rr: using scheduler.refresh-interval = 10 [default] [2009-07-01 18:36:25] D [client-protocol.c:5948:init] compute-5-4: defaulting frame-timeout to 30mins [2009-07-01 18:36:25] D [client-protocol.c:5959:init] compute-5-4: defaulting ping-timeout to 10 [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.2/transport/socket.so [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-4: got GF_EVENT_PARENT_UP, attempting connect on transport [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-4: got GF_EVENT_PARENT_UP, attempting connect on transport [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-4: got GF_EVENT_PARENT_UP, attempting connect on transport [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-4: got GF_EVENT_PARENT_UP, attempting connect on transport [2009-07-01 18:36:25] D [write-behind.c:1859:init] writebehind: disabling write-behind for first 1 bytes [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-0: got GF_EVENT_PARENT_UP, attempting connect on transport [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-0: got GF_EVENT_PARENT_UP, attempting connect on transport [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-1: got GF_EVENT_PARENT_UP, attempting connect on transport [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-1: got GF_EVENT_PARENT_UP, attempting connect on transport [2009-07-01 18:36:25] D [client-protocol.c:6276:notify] compute-5-2: got GF_EVENT_PARENT_UP, attempting
Re: [Gluster-users] HadoopFS-like gluster setup
On Wednesday 01 of July 2009 03:50, Peng Zhao wrote: > [2009-07-01 09:37:36] E [xlator.c:736:xlator_init_rec] xlator: > Initialization of volume 'fuse' failed, review your volfile again I got this error when the fuse module was not loaded, so check this first.. modprobe fuse ls -l /dev/fuse Pavel ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] DHT and adding bricks
hello there sorry for the newbie question, but I couldn't find an answer thru the old messages I am researching glusterfs for a personal project involving a constantly growing storage farm my config is simple: several bricks and a server doing DHT using cluster/distribute just like http://www.gluster.org/docs/index.php/Hash_Across_Four_Storage_Servers I learned that when you add a brick to an existing configuration, files copied to the folders that already existed, including the root folder are not distributed to the new bricks new files in new folders are what happens if I keep loading files on a folder that was already created after a new brick is added? will the new files eventually get distributed to the new bricks when the old bricks get full ? if not, is there a way around this ? after I added the bricks, I restarted the whole server, but nothing changed thanks in advance daniel ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] HELP: problem of stripe expansion !!!!!!!!!!!!!!!!!!!!!!!!
If i need height available with afr , did it use distribute + stripe + afr just like distribute(stripe( afr(2) 4)+stripe( afr(2) 4)+stripe( afr(2) 4)) ?? 2009-07-01 eagleeyes 发件人: Anand Babu Periasamy 发送时间: 2009-07-01 14:01:14 收件人: eagleeyes 抄送: gluster-users 主题: Re: [Gluster-users] HELP: problem of stripe expansion You cannot expand stripe directly. You have to use distribute + stripe, where you scale in stripe sets. For example, if you have 8 nodes, you create => distribute(stripe(4)+stripe(4)) Now if you want to scale your storage cluster, you should do so in stripe sets. Add 4 more nodes like this: => distribute(stripe(4)+stripe(4)+stripe(4)) Distributed-stripe not only makes stripe scalable, but better load balanced and reduced disk contention. -- Anand Babu Periasamy GPG Key ID: 0x62E15A31 Blog [http://unlocksmith.org] GlusterFS [http://www.gluster.org] GNU/Linux [http://www.gnu.org] eagleeyes wrote: > Hello: >Today i test stripe expansion : two volumes expand four volumes > , when i vi or cat a file ,the log was : > [2009-07-01 11:25:55] W [stripe.c:1920:stripe_open_getxattr_cbk] stripe: > client8 returned error No such file or directory > [2009-07-01 11:25:55] W [stripe.c:1920:stripe_open_getxattr_cbk] stripe: > client7 returned error No such file or directory > [2009-07-01 11:25:55] W [stripe.c:1871:stripe_open_cbk] stripe: client7 > returned error No such file or directory > [2009-07-01 11:25:55] W [stripe.c:1871:stripe_open_cbk] stripe: client8 > returned error No such file or directory > [2009-07-01 11:25:55] W [fuse-bridge.c:639:fuse_fd_cbk] glusterfs-fuse: 149: > OPEN() /file => -1 (No such file or directory) > > Did it a bug like dht expansion ? What should we do to deal with this > problem? > > my client configur changes is from subvolumes client5 client6 to > subvolumes client5 client6 client7 client8 > > > 2009-07-01 > > eagleeyes > > > > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users