Re: [Gluster-users] DRBD like performance?
I'm having a similar problem, I'm looking into DRBD but the downside here will be, if the head server goes down the clients won't automatically switch over to the slave server... -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Jeffery Soo Sent: 29 November 2009 09:30 To: gluster-users@gluster.org Subject: [Gluster-users] DRBD like performance? I had the intention of using GlusterFS to replace DRBD to setup a clustered/redundant webserver but so far the performance is about 7-8x slower than native due to the live writing feature that GlusterFS uses. Is it possible to have a setup like DRBD to improve performance? Basically I want to know if I can get the same functionality and performance of DRBD? I have 2 servers and with DRBD each server would perform all reads locally (giving native performance) and does not write data until it is fully written locally (delayed write I guess you could say). This way you get the replication but still get native performance. Is there a current way to setup GlusterFS like this in order to get this 'DRBD-like' functionality? ___ 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] performance/stat-prefetch
Hi, I have a 2 server setup (6 bricks on each server replicated and then hashed). I'm trying to load performance/stat-prefetch at the end of the client vol but it doesn't seem to work. I mount it ok, then do a df -h, it just hangs with nothing in using up resources in top. Any thoughts? Josh. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Poor performance
I'm seeing ### Add quick-read for small files volume quickread type performance/quick-read option cache-timeout 1 # default 1 second option max-file-size 256KB# default 64Kb subvolumes iocache end-volume Should that not be: ### Add quick-read for small files volume quickread type performance/quick-read option cache-timeout 1 # default 1 second option max-file-size 256KB# default 64Kb subvolumes writeback end-volume Or is the writeback vol supposed to be dangling? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Andre Felipe Machado Sent: 27 November 2009 12:58 To: gluster-users@gluster.org Subject: Re: [Gluster-users] Poor performance Hello, You could study and adapt for your environment and apps behaviour: http://www.techforce.com.br/news/linux_blog/glusterfs_tuning_s mall_files Regards. Andre Felipe Machado ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] performance/stat-prefetch
Was this the correct link? The server hangs with or without quick-read. Can you send me a link to the bug, I'll put myself on the list. Thanks, Josh. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Andre Felipe Machado Sent: 27 November 2009 13:02 To: gluster-users@gluster.org Subject: Re: [Gluster-users] performance/stat-prefetch Hello, Before 2.0.8 and its bug 314 correction, stats-prefetch and quick-read caused hangs when used in a setup at same time. http://www.techforce.com.br/news/linux_blog/glusterfs_tuning_s mall_files Regards. Andre Felipe Machado ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] performance/stat-prefetch
That's good news, I'll avoid stat-prefetch until the next version Richard de Vries wrote: I've observed the same problem in version 2.0.8. If you strace for example a ls -l, it is waiting forever for the lstat64 to finish. The current version pulled from git doesn't show this behavior. Richard -Original Message- Thanks. I don't have io-cache loaded either. The server will hang even if stat-prefethch is the only performance translator loaded. ___ 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] Rsync
Another update, I thought I'd try it without direct-io-mode=write-only, no joy. Next I'm going to try to simplify my setup (thinking 6 hashes mirrored might be too much?). As always, if you shade any more light or offer up any more ideas, please let me know. Thanks, Josh. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 05 October 2009 11:01 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync Just a quick update: The rsync is *still* not finished. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 01 October 2009 16:50 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync Thanks! I'm keeping a close eye on the is glusterfs DHT really distributed? thread =) I tried nodelay on and unhashd no. I tarred about 400G to the share in about 17 hours (~6MB/s?) and am running an rsync now. Will post the results when it's done. -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 01 October 2009 09:00 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi, We're looking into the problem on similar setups and workng on it. Meanwhile can you let us know if performance increases if you use this option: option transport.socket.nodelay on' in each of your protocol/client and protocol/server volumes. Pavan On 28/09/09 11:25 +0100, Hiren Joshi wrote: Another update: It took 1240 minutes (over 20 hours) to complete on the simplified system (without mirroring). What else can I do to debug? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 24 September 2009 13:05 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 24 September 2009 12:42 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Can you let us know the following: * What is the exact directory structure? /abc/def/ghi/jkl/[1-4] now abc, def, ghi and jkl are one of a thousand dirs. * How many files are there in each individual directory and of what size? Each of the [1-4] dirs has about 100 files in, all under 1MB. * It looks like each server process has 6 export directories. Can you run one server process each for a single export directory and check if the rsync speeds up? I had no idea you could do that. How? Would I need to create 6 config files and start gluster: /usr/sbin/glusterfsd -f /etc/glusterfs/export1.vol or similar? I'll give this a go * Also, do you have any benchmarks with a similar setup on say, NFS? NFS will create the dir tree in about 20 minutes then start copying the files over, it takes about 2-3 hours. Pavan On 24/09/09 12:13 +0100, Hiren Joshi wrote: It's been running for over 24 hours now. Network traffic is nominal, top shows about 200-400% cpu (7 cores so it's not too bad). About 14G of memory used (the rest is being used as disk cache). Thoughts? snip An update, after running the rsync for a day, I killed it and remounted all the disks (the underlying filesystem, not the gluster) with noatime, the rsync completed in about 600 minutes. I'm now going to try one level up (about 1,000,000,000 dirs). -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 07:55 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi Hiren, What glusterfs version are you using? Can you send us the volfiles and the log files. Pavan On 22/09/09 16:01 +0100, Hiren Joshi wrote: I forgot to mention, the mount is mounted with direct-io, would this make a difference? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 22 September 2009 11:40 To: gluster-users
Re: [Gluster-users] Rsync
The initial copy has to happen via gluster as I'm also using distribution as well as replication -Original Message- From: Stephan von Krawczynski [mailto:sk...@ithnet.com] Sent: 06 October 2009 16:39 To: Hiren Joshi Cc: Pavan Vilas Sondur; gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync Remember, the gluster-team does not like my way of data-feeding. If your setup blows up, don't blame them (or me :-) I can only tell you what I am doing: simply move (or copy) the initial data to the primary server of the replication setup and then start glusterfsd for exporting. You will notice that the data gets replicated as soon as stat is going on (first ls or the like). If you already exported the data via nfs before you probably only need to setup up glusterfs on the very same box and use it as primary server. Then there is no data copying at all. After months of experiments I can say that glusterfs runs pretty stable on _low_ performance setups. But you have to do one thing: lengthen the ping-timeout (something like option ping-timeout 120). If you do not do that you will loose some of your server(s) at any time and that will turn your glusterfs setup in a mess. If your environment is ok, it works. If your environment fails it will fail, too, sooner or later. In other words: it exports data, but it does not fulfill the promise of keeping your setup alive during failures - at this stage. My advice for the team is to stop whatever they may work on and take for physical boxes (2 server, 2 client), run a lot of bonnies and unplug/re-plug the servers non-deterministic. You can find all kinds of weirdos this way. Regards, Stephan On Mon, 5 Oct 2009 16:49:53 +0100 Hiren Joshi j...@moonfruit.com wrote: My users are more pitch fork less shooting. I don't understand what you're saying, should I have locally copied all the files over not using gluster before attempting an rsync? -Original Message- From: Stephan von Krawczynski [mailto:sk...@ithnet.com] Sent: 05 October 2009 14:13 To: Hiren Joshi Cc: Pavan Vilas Sondur; gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync It would be nice to remember my thread about _not_ copying data initially to gluster via the mountpoint. And one major reason for _local_ feed was: speed. Obviously a lot of cases are merely impossible because of the pure waiting time. If you had a live setup people would have already shot you... This is why I talked about a feature and not an accepted bug behaviour. Regards, Stephan On Mon, 5 Oct 2009 11:00:36 +0100 Hiren Joshi j...@moonfruit.com wrote: Just a quick update: The rsync is *still* not finished. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 01 October 2009 16:50 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync Thanks! I'm keeping a close eye on the is glusterfs DHT really distributed? thread =) I tried nodelay on and unhashd no. I tarred about 400G to the share in about 17 hours (~6MB/s?) and am running an rsync now. Will post the results when it's done. -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 01 October 2009 09:00 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi, We're looking into the problem on similar setups and workng on it. Meanwhile can you let us know if performance increases if you use this option: option transport.socket.nodelay on' in each of your protocol/client and protocol/server volumes. Pavan On 28/09/09 11:25 +0100, Hiren Joshi wrote: Another update: It took 1240 minutes (over 20 hours) to complete on the simplified system (without mirroring). What else can I do to debug? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 24 September 2009 13:05 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 24 September 2009 12:42 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Can you let us know the following: * What is the exact directory structure? /abc/def/ghi/jkl/[1-4] now abc, def, ghi and jkl are one of a thousand dirs
Re: [Gluster-users] Rsync
Just a quick update: The rsync is *still* not finished. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 01 October 2009 16:50 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync Thanks! I'm keeping a close eye on the is glusterfs DHT really distributed? thread =) I tried nodelay on and unhashd no. I tarred about 400G to the share in about 17 hours (~6MB/s?) and am running an rsync now. Will post the results when it's done. -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 01 October 2009 09:00 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi, We're looking into the problem on similar setups and workng on it. Meanwhile can you let us know if performance increases if you use this option: option transport.socket.nodelay on' in each of your protocol/client and protocol/server volumes. Pavan On 28/09/09 11:25 +0100, Hiren Joshi wrote: Another update: It took 1240 minutes (over 20 hours) to complete on the simplified system (without mirroring). What else can I do to debug? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 24 September 2009 13:05 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 24 September 2009 12:42 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Can you let us know the following: * What is the exact directory structure? /abc/def/ghi/jkl/[1-4] now abc, def, ghi and jkl are one of a thousand dirs. * How many files are there in each individual directory and of what size? Each of the [1-4] dirs has about 100 files in, all under 1MB. * It looks like each server process has 6 export directories. Can you run one server process each for a single export directory and check if the rsync speeds up? I had no idea you could do that. How? Would I need to create 6 config files and start gluster: /usr/sbin/glusterfsd -f /etc/glusterfs/export1.vol or similar? I'll give this a go * Also, do you have any benchmarks with a similar setup on say, NFS? NFS will create the dir tree in about 20 minutes then start copying the files over, it takes about 2-3 hours. Pavan On 24/09/09 12:13 +0100, Hiren Joshi wrote: It's been running for over 24 hours now. Network traffic is nominal, top shows about 200-400% cpu (7 cores so it's not too bad). About 14G of memory used (the rest is being used as disk cache). Thoughts? snip An update, after running the rsync for a day, I killed it and remounted all the disks (the underlying filesystem, not the gluster) with noatime, the rsync completed in about 600 minutes. I'm now going to try one level up (about 1,000,000,000 dirs). -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 07:55 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi Hiren, What glusterfs version are you using? Can you send us the volfiles and the log files. Pavan On 22/09/09 16:01 +0100, Hiren Joshi wrote: I forgot to mention, the mount is mounted with direct-io, would this make a difference? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 22 September 2009 11:40 To: gluster-users@gluster.org Subject: [Gluster-users] Rsync Hello all, I'm getting what I think is bizarre behaviour I have about 400G to rsync (rsync -av) onto a gluster share, the data is in a directory structure which has about 1000 directories per parent and about 1000 directories in each of them. When I try to rsync an end leaf directory (this has about 4 dirs and 100 files in each) the operation takes about 10 seconds. When I go one level above
Re: [Gluster-users] Rsync
My users are more pitch fork less shooting. I don't understand what you're saying, should I have locally copied all the files over not using gluster before attempting an rsync? -Original Message- From: Stephan von Krawczynski [mailto:sk...@ithnet.com] Sent: 05 October 2009 14:13 To: Hiren Joshi Cc: Pavan Vilas Sondur; gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync It would be nice to remember my thread about _not_ copying data initially to gluster via the mountpoint. And one major reason for _local_ feed was: speed. Obviously a lot of cases are merely impossible because of the pure waiting time. If you had a live setup people would have already shot you... This is why I talked about a feature and not an accepted bug behaviour. Regards, Stephan On Mon, 5 Oct 2009 11:00:36 +0100 Hiren Joshi j...@moonfruit.com wrote: Just a quick update: The rsync is *still* not finished. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 01 October 2009 16:50 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync Thanks! I'm keeping a close eye on the is glusterfs DHT really distributed? thread =) I tried nodelay on and unhashd no. I tarred about 400G to the share in about 17 hours (~6MB/s?) and am running an rsync now. Will post the results when it's done. -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 01 October 2009 09:00 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi, We're looking into the problem on similar setups and workng on it. Meanwhile can you let us know if performance increases if you use this option: option transport.socket.nodelay on' in each of your protocol/client and protocol/server volumes. Pavan On 28/09/09 11:25 +0100, Hiren Joshi wrote: Another update: It took 1240 minutes (over 20 hours) to complete on the simplified system (without mirroring). What else can I do to debug? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 24 September 2009 13:05 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 24 September 2009 12:42 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Can you let us know the following: * What is the exact directory structure? /abc/def/ghi/jkl/[1-4] now abc, def, ghi and jkl are one of a thousand dirs. * How many files are there in each individual directory and of what size? Each of the [1-4] dirs has about 100 files in, all under 1MB. * It looks like each server process has 6 export directories. Can you run one server process each for a single export directory and check if the rsync speeds up? I had no idea you could do that. How? Would I need to create 6 config files and start gluster: /usr/sbin/glusterfsd -f /etc/glusterfs/export1.vol or similar? I'll give this a go * Also, do you have any benchmarks with a similar setup on say, NFS? NFS will create the dir tree in about 20 minutes then start copying the files over, it takes about 2-3 hours. Pavan On 24/09/09 12:13 +0100, Hiren Joshi wrote: It's been running for over 24 hours now. Network traffic is nominal, top shows about 200-400% cpu (7 cores so it's not too bad). About 14G of memory used (the rest is being used as disk cache). Thoughts? snip An update, after running the rsync for a day, I killed it and remounted all the disks (the underlying filesystem, not the gluster) with noatime, the rsync completed in about 600 minutes. I'm now going to try one level up (about 1,000,000,000 dirs). -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 07:55 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi Hiren, What glusterfs version are you using? Can you send us the volfiles and the log files
Re: [Gluster-users] unable to start client, new setup 2.0.6 centos5.3
How are you trying to mount the client? mount -t glusterfs -o direct-io-mode=write-only -f /path/to/client.vol /mnt/ Works for me. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Charles Sent: 02 October 2009 17:31 To: gluster-users@gluster.org Subject: [Gluster-users] unable to start client, new setup 2.0.6 centos5.3 Hi, when attempting to start the client I received: no valid translator loaded at the top, orno mount point given. exiting [2009-10-02 10:34:40] E [glusterfsd.c:570:glusterfs_graph_init] glusterfs: no valid translator loaded at the top or no mount point given. exiting [2009-10-02 10:34:40] E [glusterfsd.c:1217:main] glusterfs: translator initialization failed. exiting - running 2.0.6 on centos 5.3 - 3 servers, 1 client - I'm attempting to replicate across the 3 servers - pls help # client config # file: /etc/glusterfs/glusterfs.vol volume remote1 type protocol/client option transport-type tcp option remote-host rh1 option remote-subvolume brick end-volume volume remote2 type protocol/client option transport-type tcp option remote-host rh2 option remote-subvolume brick end-volume volume remote3 type protocol/client option transport-type tcp option remote-host rh3 option remote-subvolume brick end-volume volume replicate type cluster/replicate subvolumes remote1 remote2 remote3 end-volume volume writebehind type performance/write-behind option window-size 1MB subvolumes replicate end-volume volume cache type performance/io-cache option cache-size 512MB subvolumes writebehind end-volume # # server config # volume posix type storage/posix option directory /bigpartition end-volume volume locks type features/locks subvolumes posix end-volume volume brick type performance/io-threads option thread-count 8 subvolumes locks end-volume volume server type protocol/server option transport-type tcp option auth.addr.brick.allow * subvolumes brick end-volume =cm ___ 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] Rsync
Thanks! I'm keeping a close eye on the is glusterfs DHT really distributed? thread =) I tried nodelay on and unhashd no. I tarred about 400G to the share in about 17 hours (~6MB/s?) and am running an rsync now. Will post the results when it's done. -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 01 October 2009 09:00 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi, We're looking into the problem on similar setups and workng on it. Meanwhile can you let us know if performance increases if you use this option: option transport.socket.nodelay on' in each of your protocol/client and protocol/server volumes. Pavan On 28/09/09 11:25 +0100, Hiren Joshi wrote: Another update: It took 1240 minutes (over 20 hours) to complete on the simplified system (without mirroring). What else can I do to debug? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 24 September 2009 13:05 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 24 September 2009 12:42 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Can you let us know the following: * What is the exact directory structure? /abc/def/ghi/jkl/[1-4] now abc, def, ghi and jkl are one of a thousand dirs. * How many files are there in each individual directory and of what size? Each of the [1-4] dirs has about 100 files in, all under 1MB. * It looks like each server process has 6 export directories. Can you run one server process each for a single export directory and check if the rsync speeds up? I had no idea you could do that. How? Would I need to create 6 config files and start gluster: /usr/sbin/glusterfsd -f /etc/glusterfs/export1.vol or similar? I'll give this a go * Also, do you have any benchmarks with a similar setup on say, NFS? NFS will create the dir tree in about 20 minutes then start copying the files over, it takes about 2-3 hours. Pavan On 24/09/09 12:13 +0100, Hiren Joshi wrote: It's been running for over 24 hours now. Network traffic is nominal, top shows about 200-400% cpu (7 cores so it's not too bad). About 14G of memory used (the rest is being used as disk cache). Thoughts? snip An update, after running the rsync for a day, I killed it and remounted all the disks (the underlying filesystem, not the gluster) with noatime, the rsync completed in about 600 minutes. I'm now going to try one level up (about 1,000,000,000 dirs). -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 07:55 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi Hiren, What glusterfs version are you using? Can you send us the volfiles and the log files. Pavan On 22/09/09 16:01 +0100, Hiren Joshi wrote: I forgot to mention, the mount is mounted with direct-io, would this make a difference? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 22 September 2009 11:40 To: gluster-users@gluster.org Subject: [Gluster-users] Rsync Hello all, I'm getting what I think is bizarre behaviour I have about 400G to rsync (rsync -av) onto a gluster share, the data is in a directory structure which has about 1000 directories per parent and about 1000 directories in each of them. When I try to rsync an end leaf directory (this has about 4 dirs and 100 files in each) the operation takes about 10 seconds. When I go one level above (1000 dirs with about 4 dirs in each with about 100 files in each) the operation takes about 10 minutes. Now, if I then go one level above that (that's 1000 dirs with 1000 dirs in each with about 4 dirs in each with about 100 files in each) the operation takes days! Top shows glusterfsd takes 300-600% cpu usage (2X4core), I have
Re: [Gluster-users] Rsync
Another update: It took 1240 minutes (over 20 hours) to complete on the simplified system (without mirroring). What else can I do to debug? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 24 September 2009 13:05 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 24 September 2009 12:42 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Can you let us know the following: * What is the exact directory structure? /abc/def/ghi/jkl/[1-4] now abc, def, ghi and jkl are one of a thousand dirs. * How many files are there in each individual directory and of what size? Each of the [1-4] dirs has about 100 files in, all under 1MB. * It looks like each server process has 6 export directories. Can you run one server process each for a single export directory and check if the rsync speeds up? I had no idea you could do that. How? Would I need to create 6 config files and start gluster: /usr/sbin/glusterfsd -f /etc/glusterfs/export1.vol or similar? I'll give this a go * Also, do you have any benchmarks with a similar setup on say, NFS? NFS will create the dir tree in about 20 minutes then start copying the files over, it takes about 2-3 hours. Pavan On 24/09/09 12:13 +0100, Hiren Joshi wrote: It's been running for over 24 hours now. Network traffic is nominal, top shows about 200-400% cpu (7 cores so it's not too bad). About 14G of memory used (the rest is being used as disk cache). Thoughts? snip An update, after running the rsync for a day, I killed it and remounted all the disks (the underlying filesystem, not the gluster) with noatime, the rsync completed in about 600 minutes. I'm now going to try one level up (about 1,000,000,000 dirs). -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 07:55 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi Hiren, What glusterfs version are you using? Can you send us the volfiles and the log files. Pavan On 22/09/09 16:01 +0100, Hiren Joshi wrote: I forgot to mention, the mount is mounted with direct-io, would this make a difference? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 22 September 2009 11:40 To: gluster-users@gluster.org Subject: [Gluster-users] Rsync Hello all, I'm getting what I think is bizarre behaviour I have about 400G to rsync (rsync -av) onto a gluster share, the data is in a directory structure which has about 1000 directories per parent and about 1000 directories in each of them. When I try to rsync an end leaf directory (this has about 4 dirs and 100 files in each) the operation takes about 10 seconds. When I go one level above (1000 dirs with about 4 dirs in each with about 100 files in each) the operation takes about 10 minutes. Now, if I then go one level above that (that's 1000 dirs with 1000 dirs in each with about 4 dirs in each with about 100 files in each) the operation takes days! Top shows glusterfsd takes 300-600% cpu usage (2X4core), I have about 48G of memory (usage is 0% as expected). Has anyone seen anything like this? How can I speed it up? Thanks, Josh. ___ 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 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] Rsync
-Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 24 September 2009 12:42 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Can you let us know the following: * What is the exact directory structure? /abc/def/ghi/jkl/[1-4] now abc, def, ghi and jkl are one of a thousand dirs. * How many files are there in each individual directory and of what size? Each of the [1-4] dirs has about 100 files in, all under 1MB. * It looks like each server process has 6 export directories. Can you run one server process each for a single export directory and check if the rsync speeds up? I had no idea you could do that. How? Would I need to create 6 config files and start gluster: /usr/sbin/glusterfsd -f /etc/glusterfs/export1.vol or similar? I'll give this a go * Also, do you have any benchmarks with a similar setup on say, NFS? NFS will create the dir tree in about 20 minutes then start copying the files over, it takes about 2-3 hours. Pavan On 24/09/09 12:13 +0100, Hiren Joshi wrote: It's been running for over 24 hours now. Network traffic is nominal, top shows about 200-400% cpu (7 cores so it's not too bad). About 14G of memory used (the rest is being used as disk cache). Thoughts? snip An update, after running the rsync for a day, I killed it and remounted all the disks (the underlying filesystem, not the gluster) with noatime, the rsync completed in about 600 minutes. I'm now going to try one level up (about 1,000,000,000 dirs). -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 07:55 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi Hiren, What glusterfs version are you using? Can you send us the volfiles and the log files. Pavan On 22/09/09 16:01 +0100, Hiren Joshi wrote: I forgot to mention, the mount is mounted with direct-io, would this make a difference? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 22 September 2009 11:40 To: gluster-users@gluster.org Subject: [Gluster-users] Rsync Hello all, I'm getting what I think is bizarre behaviour I have about 400G to rsync (rsync -av) onto a gluster share, the data is in a directory structure which has about 1000 directories per parent and about 1000 directories in each of them. When I try to rsync an end leaf directory (this has about 4 dirs and 100 files in each) the operation takes about 10 seconds. When I go one level above (1000 dirs with about 4 dirs in each with about 100 files in each) the operation takes about 10 minutes. Now, if I then go one level above that (that's 1000 dirs with 1000 dirs in each with about 4 dirs in each with about 100 files in each) the operation takes days! Top shows glusterfsd takes 300-600% cpu usage (2X4core), I have about 48G of memory (usage is 0% as expected). Has anyone seen anything like this? How can I speed it up? Thanks, Josh. ___ 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 mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Rsync
2.0.6-1.el5, it's a 6 brick distributed system which is mirrored over 2 machines (each brick has a mirror on another machine, these mirrors are put in the hash). An update, after running the rsync for a day, I killed it and remounted all the disks (the underlying filesystem, not the gluster) with noatime, the rsync completed in about 600 minutes. I'm now going to try one level up (about 1,000,000,000 dirs). -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 07:55 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi Hiren, What glusterfs version are you using? Can you send us the volfiles and the log files. Pavan On 22/09/09 16:01 +0100, Hiren Joshi wrote: I forgot to mention, the mount is mounted with direct-io, would this make a difference? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 22 September 2009 11:40 To: gluster-users@gluster.org Subject: [Gluster-users] Rsync Hello all, I'm getting what I think is bizarre behaviour I have about 400G to rsync (rsync -av) onto a gluster share, the data is in a directory structure which has about 1000 directories per parent and about 1000 directories in each of them. When I try to rsync an end leaf directory (this has about 4 dirs and 100 files in each) the operation takes about 10 seconds. When I go one level above (1000 dirs with about 4 dirs in each with about 100 files in each) the operation takes about 10 minutes. Now, if I then go one level above that (that's 1000 dirs with 1000 dirs in each with about 4 dirs in each with about 100 files in each) the operation takes days! Top shows glusterfsd takes 300-600% cpu usage (2X4core), I have about 48G of memory (usage is 0% as expected). Has anyone seen anything like this? How can I speed it up? Thanks, Josh. ___ 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] Rsync
- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 13:38 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Can you send us the volfiles and logfiles as well? Pavan On 23/09/09 10:08 +0100, Hiren Joshi wrote: 2.0.6-1.el5, it's a 6 brick distributed system which is mirrored over 2 machines (each brick has a mirror on another machine, these mirrors are put in the hash). An update, after running the rsync for a day, I killed it and remounted all the disks (the underlying filesystem, not the gluster) with noatime, the rsync completed in about 600 minutes. I'm now going to try one level up (about 1,000,000,000 dirs). -Original Message- From: Pavan Vilas Sondur [mailto:pa...@gluster.com] Sent: 23 September 2009 07:55 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: Rsync Hi Hiren, What glusterfs version are you using? Can you send us the volfiles and the log files. Pavan On 22/09/09 16:01 +0100, Hiren Joshi wrote: I forgot to mention, the mount is mounted with direct-io, would this make a difference? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 22 September 2009 11:40 To: gluster-users@gluster.org Subject: [Gluster-users] Rsync Hello all, I'm getting what I think is bizarre behaviour I have about 400G to rsync (rsync -av) onto a gluster share, the data is in a directory structure which has about 1000 directories per parent and about 1000 directories in each of them. When I try to rsync an end leaf directory (this has about 4 dirs and 100 files in each) the operation takes about 10 seconds. When I go one level above (1000 dirs with about 4 dirs in each with about 100 files in each) the operation takes about 10 minutes. Now, if I then go one level above that (that's 1000 dirs with 1000 dirs in each with about 4 dirs in each with about 100 files in each) the operation takes days! Top shows glusterfsd takes 300-600% cpu usage (2X4core), I have about 48G of memory (usage is 0% as expected). Has anyone seen anything like this? How can I speed it up? Thanks, Josh. ___ 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] Rsync
Also, there's nothing happening in the log files beyond the initial mount so it looks like the filesystem aspect of it is fine. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 23 September 2009 14:02 To: Pavan Vilas Sondur Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Rsync Bellow. I've found that I get a performance hit if I add read cache or whitebehind. Server conf: ##Open vols volume posix1 type storage/posix option directory /gluster/export1 end-volume volume posix2 type storage/posix option directory /gluster/export2 end-volume volume posix3 type storage/posix option directory /gluster/export3 end-volume volume posix4 type storage/posix option directory /gluster/export4 end-volume volume posix5 type storage/posix option directory /gluster/export5 end-volume volume posix6 type storage/posix option directory /gluster/export6 end-volume ## Add the ability to lock files etc volume locks1 type features/locks subvolumes posix1 end-volume volume locks2 type features/locks subvolumes posix2 end-volume volume locks3 type features/locks subvolumes posix3 end-volume volume locks4 type features/locks subvolumes posix4 end-volume volume locks5 type features/locks subvolumes posix5 end-volume volume locks6 type features/locks subvolumes posix6 end-volume ## Preformance translators volume brick1 type performance/io-threads option thread-count 8 subvolumes locks1 end-volume volume brick2 type performance/io-threads option thread-count 8 subvolumes locks2 end-volume volume brick3 type performance/io-threads option thread-count 8 subvolumes locks3 end-volume volume brick4 type performance/io-threads option thread-count 8 subvolumes locks4 end-volume volume brick5 type performance/io-threads option thread-count 8 subvolumes locks5 end-volume volume brick6 type performance/io-threads option thread-count 8 subvolumes locks6 end-volume ##export the lot #volume brick6 # type debug/trace # subvolumes trace_brick6 #end-volume volume server type protocol/server option transport-type tcp/server option auth.addr.brick1.allow * option auth.addr.brick2.allow * option auth.addr.brick3.allow * option auth.addr.brick4.allow * option auth.addr.brick5.allow * option auth.addr.brick6.allow * subvolumes brick1 brick2 brick3 brick4 brick5 brick6 end-volume Vol file: ##Clent config ##import all the briks from all the mirrors and mirror them volume glust1a_1 type protocol/client option transport-type tcp/client option remote-host glust1a option ping-timeout 30 option remote-subvolume brick1 end-volume volume glust1b_1 type protocol/client option transport-type tcp/client option remote-host glust1b option ping-timeout 30 option remote-subvolume brick1 end-volume volume mirror1_1 type cluster/replicate subvolumes glust1a_1 glust1b_1 end-volume volume glust1a_2 type protocol/client option transport-type tcp/client option remote-host glust1a option ping-timeout 30 option remote-subvolume brick2 end-volume volume glust1b_2 type protocol/client option transport-type tcp/client option remote-host glust1b option ping-timeout 30 option remote-subvolume brick2 end-volume volume mirror1_2 type cluster/replicate subvolumes glust1a_2 glust1b_2 end-volume volume glust1a_3 type protocol/client option transport-type tcp/client option remote-host glust1a option ping-timeout 30 option remote-subvolume brick3 end-volume volume glust1b_3 type protocol/client option transport-type tcp/client option remote-host glust1b option ping-timeout 30 option remote-subvolume brick3 end-volume volume mirror1_3 type cluster/replicate subvolumes glust1a_3 glust1b_3 end-volume volume glust1a_4 type protocol/client option transport-type tcp/client option remote-host glust1a option ping-timeout 30 option remote-subvolume brick4 end-volume volume glust1b_4 type protocol/client option transport-type tcp/client option remote-host glust1b option ping-timeout 30 option remote-subvolume brick4 end-volume volume mirror1_4 type cluster/replicate subvolumes glust1a_4 glust1b_4 end-volume volume glust1a_5 type protocol/client option transport-type tcp/client option remote-host glust1a option ping-timeout 30 option remote-subvolume brick5 end-volume volume glust1b_5 type protocol/client option transport-type tcp/client option remote-host glust1b option ping-timeout 30 option remote-subvolume brick5 end-volume volume mirror1_5 type cluster/replicate subvolumes glust1a_5 glust1b_5
[Gluster-users] Rsync
Hello all, I'm getting what I think is bizarre behaviour I have about 400G to rsync (rsync -av) onto a gluster share, the data is in a directory structure which has about 1000 directories per parent and about 1000 directories in each of them. When I try to rsync an end leaf directory (this has about 4 dirs and 100 files in each) the operation takes about 10 seconds. When I go one level above (1000 dirs with about 4 dirs in each with about 100 files in each) the operation takes about 10 minutes. Now, if I then go one level above that (that's 1000 dirs with 1000 dirs in each with about 4 dirs in each with about 100 files in each) the operation takes days! Top shows glusterfsd takes 300-600% cpu usage (2X4core), I have about 48G of memory (usage is 0% as expected). Has anyone seen anything like this? How can I speed it up? Thanks, Josh. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Rsync
I forgot to mention, the mount is mounted with direct-io, would this make a difference? -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: 22 September 2009 11:40 To: gluster-users@gluster.org Subject: [Gluster-users] Rsync Hello all, I'm getting what I think is bizarre behaviour I have about 400G to rsync (rsync -av) onto a gluster share, the data is in a directory structure which has about 1000 directories per parent and about 1000 directories in each of them. When I try to rsync an end leaf directory (this has about 4 dirs and 100 files in each) the operation takes about 10 seconds. When I go one level above (1000 dirs with about 4 dirs in each with about 100 files in each) the operation takes about 10 minutes. Now, if I then go one level above that (that's 1000 dirs with 1000 dirs in each with about 4 dirs in each with about 100 files in each) the operation takes days! Top shows glusterfsd takes 300-600% cpu usage (2X4core), I have about 48G of memory (usage is 0% as expected). Has anyone seen anything like this? How can I speed it up? Thanks, Josh. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] Worrying
Hello all, I have a 2 servers each exporting 6 bricks. The client mirrors the 2 servers and AFRs the 6 mirrors it creates. Running bonnie, the servers kept dropping (according to gluster logs they stopped responding to pings in 10 seconds) so I set the ping timeout to 30 second, now although bonnie runs I still see dropouts in the log. The worrying thing is that one of the servers is localhost! What's happening here? I'm frustratingly close to putting this system on our live network. The log: [2009-09-03 02:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1a_1: Server 127.0.0.1:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1b_1: Server 192.168.4.51:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1a_1: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1a_2: Server 127.0.0.1:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1b_2: Server 192.168.4.51:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1a_3: Server 127.0.0.1:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1b_3: Server 192.168.4.51:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1a_5: Server 127.0.0.1:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1b_5: Server 192.168.4.51:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1a_6: Server 127.0.0.1:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] E [client-protocol.c:437:client_ping_timer_expired] glust1b_6: Server 192.168.4.51:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1a_1: disconnected [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1b_6: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1b_6: disconnected [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1a_6: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1a_6: disconnected [2009-09-03 01:10:01] E [afr.c:2228:notify] mirror1_6: All subvolumes are down. Going offline until atleast one of them comes back up. [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1b_5: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1b_5: disconnected [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1a_5: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1a_5: disconnected [2009-09-03 01:10:01] E [afr.c:2228:notify] mirror1_5: All subvolumes are down. Going offline until atleast one of them comes back up. [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1b_3: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1b_3: disconnected [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1a_3: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1a_3: disconnected [2009-09-03 01:10:01] E [afr.c:2228:notify] mirror1_3: All subvolumes are down. Going offline until atleast one of them comes back up. [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1b_2: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1b_2: disconnected [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1a_2: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:01] N [client-protocol.c:6246:notify] glust1a_2: disconnected [2009-09-03 01:10:01] E [afr.c:2228:notify] mirror1_2: All subvolumes are down. Going offline until atleast one of them comes back up. [2009-09-03 01:10:01] E [saved-frames.c:165:saved_frames_unwind] glust1b_1: forced unwinding frame type(2) op(PING) [2009-09-03 01:10:02] N [client-protocol.c:6246:notify] glust1b_1: disconnected [2009-09-03 01:10:02] E [afr.c:2228:notify] mirror1_1: All subvolumes are down. Going offline until atleast one of them comes back up. [2009-09-03 01:10:31] E [client-protocol.c:437:client_ping_timer_expired] glust1a_4: Server 127.0.0.1:6996 has not responded in the last 30 seconds, disconnecting. [2009-09-03 01:10:31] E
[Gluster-users] Bonnie crash
Hello all, I'm using gluster 2.0.4 and bonnie++ 1.96, I can't get the test to complete. bonnie++ -u 99:99 -d /home/webspace_glust/test/ Using uid:99, gid:99. Writing a byte at a time...done Writing intelligently...done Rewriting...done Reading a byte at a time...done Reading intelligently...done start 'em...done...done...done...done...done... Create files in sequential order...Can't make directory ./Bonnie.24759 Cleaning up test directory after error. Bonnie: drastic I/O error (rmdir): No such file or directory I can't see what's wrong a quick google yielded very little. Any pointers appreciated Josh. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Interesting experiment
-Original Message- From: Liam Slusser [mailto:lslus...@gmail.com] Sent: 18 August 2009 18:51 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Interesting experiment On Tue, Aug 18, 2009 at 3:05 AM, Hiren Joshij...@moonfruit.com wrote: Hi, Ok, the basic setup is 6 bricks per server, 2 servers. Mirror the six bricks and DHT them. I'm running three tests, dd 1G of zeros to the gluster mount, dd 1000 100k files and dd 1000 1M files. With 3M write-behind I get: 0m35.460s for 1G file 0m52.427s for 100k files 1m37.209s for 1M files Then I added a 400M external journal to all the bricks, the twist being the journals were made on a ram drive Running the same tests: 0m33.614s for 1G file 0m52.851s for 100k files 1m31.693s for 1M files So why is it that adding an external journal (in the ram!) seems to make no difference at all? I would imagine that most of your bottle neck is with the network and not the disks. Modern raid disk storage systems are much quicker than gigabit ethernet. You're right, the raid gives me great (SSD type) performance! This is interesting, I'm on a gigabit network and it looks like it's maxing out when I dd a 1Gig file: about 18 kbits/sec When I dd 1000 1M files: about 8 kbits/sec Is it worth bonding? This look like I'm maxing out the network connection. liam ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Performance
We've had large ext3 filesystems go readonly (underlying hardware problem) and recovery can take a days. For this I'm using ext3 as well and as it's a raid 6 disk (hardware raided) I can probably get away with 4X1TB. But I'm currently experiencing bad performance on a single brick that's not mirrored. From: Mark Mielke [mailto:m...@mark.mielke.cc] Sent: 12 August 2009 18:51 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Performance On 08/12/2009 01:24 PM, Hiren Joshi wrote: 36 partitions on each server - the word partition is ambiguous. Are they 36 separate drives? Or multiple partitions on the same drive. If multiple partitions on the same drive, this would be a bad idea, as it would require the disk head to move back and forth between the partitions, significantly increasing the latency, and therefore significantly reducing the performance. If each partition is on its own drive, you still won't see benefit unless you have many clients concurrently changing many different files. In your above case, it's touching a single file in sequence, and having a cluster is costing you rather than benefitting you. We went with 36 partitions (on a single raid 6 drive) incase we got file system corruption, it would take less time to fsck a 100G partition than a 3.6TB one. Would a 3.6TB single disk be better? Putting 3.6 TB on a single disk sounds like a lot of eggs in one basket. :-) If you are worried about fsck, I would definitely do as the other poster suggested and use a journalled file system. This nearly eliminates the fsck time for most situations. This would be whether using 100G partitions or using 3.6T partitions. In fact, there is very few reasons not to use a journalled file system these days. As for how to deal with data on this partition - the file system is going to have a better chance of placing files close to each other, than setting up 36 partitions and having Gluster scatter the files across all of them based on a hash. Personally, I would choose 4 x 1 Tbyte drives over 1 x 3.6 Tbyte drive, as this nearly quadruples my bandwidth and for highly concurrent loads, nearly divides by four the average latency to access files. But, if you already have the 3.6 Tbyte drive, I think the only performance-friendly use would be to partition it based upon access requirements, rather than a hash (random). That is, files that are accessed frequently should be clustered together at the front of a disk, files accessed less frequently could be in the middle, and files accessed infrequently could be at the end. This would be a three partition disk. Gluster does not have a file system that does this automatically (that I can tell), so it would probably require a software solution on your end. For example, I believe dovecot (IMAP server) allows an alternative storage location to be defined, so that infrequently read files can be moved to another disk, and it knows to check the primary storage first, and fall back to the alternative storage after. It you can't break up your storage by access patterns, then I think a 3.6 Tbyte file system might still be the next best option - it's still better than 36 partitions. But, make sure you have a good file system on it, that scales well to this size. Cheers, mark -- Mark Mielke m...@mielke.cc mailto:m...@mielke.cc ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Performance
What are the advantages of XFS over ext3 (which I'm currently using)? My fear with XFS when selecting a filesystem was that it's not as active or as well supported as ext3 and if things go wrong, how easy would it be to recover? I have 6 x 1TB disks in a hardware raid 6 with battery backup and UPS, it's now just the performance I need to get sorted... From: Liam Slusser [mailto:lslus...@gmail.com] Sent: 12 August 2009 20:35 To: Mark Mielke Cc: Hiren Joshi; gluster-users@gluster.org Subject: Re: [Gluster-users] Performance I had a similar situation. My larger gluster cluster has two nodes but each node has 72 1.5tb hard drives. I ended up creating three 30TB 24 drive raid6 arrays, formated with xfs and 64bit-inodes, and then exporting three bricks with gluster. I would recommend using a hardware raid controller with battery backup power, UPS power, and a journaled filesystem and i think you'll be fine. I'm exporting the three bricks on each of my two nodes, the clients are using replication to replicate each of the three bricks on each server and then using distribute to tie it all together. liam On Wed, Aug 12, 2009 at 10:51 AM, Mark Mielke m...@mark.mielke.cc wrote: On 08/12/2009 01:24 PM, Hiren Joshi wrote: 36 partitions on each server - the word partition is ambiguous. Are they 36 separate drives? Or multiple partitions on the same drive. If multiple partitions on the same drive, this would be a bad idea, as it would require the disk head to move back and forth between the partitions, significantly increasing the latency, and therefore significantly reducing the performance. If each partition is on its own drive, you still won't see benefit unless you have many clients concurrently changing many different files. In your above case, it's touching a single file in sequence, and having a cluster is costing you rather than benefitting you. We went with 36 partitions (on a single raid 6 drive) incase we got file system corruption, it would take less time to fsck a 100G partition than a 3.6TB one. Would a 3.6TB single disk be better? Putting 3.6 TB on a single disk sounds like a lot of eggs in one basket. :-) If you are worried about fsck, I would definitely do as the other poster suggested and use a journalled file system. This nearly eliminates the fsck time for most situations. This would be whether using 100G partitions or using 3.6T partitions. In fact, there is very few reasons not to use a journalled file system these days. As for how to deal with data on this partition - the file system is going to have a better chance of placing files close to each other, than setting up 36 partitions and having Gluster scatter the files across all of them based on a hash. Personally, I would choose 4 x 1 Tbyte drives over 1 x 3.6 Tbyte drive, as this nearly quadruples my bandwidth and for highly concurrent loads, nearly divides by four the average latency to access files. But, if you already have the 3.6 Tbyte drive, I think the only performance-friendly use would be to partition it based upon access requirements, rather than a hash (random). That is, files that are accessed frequently should be clustered together at the front of a disk, files accessed less frequently could be in the middle, and files accessed infrequently could be at the end. This would be a three partition disk. Gluster does not have a file system that does this automatically (that I can tell), so it would probably require a software solution on your end. For example, I believe dovecot (IMAP server) allows an alternative storage location to be defined, so that infrequently read files can be moved to another disk, and it knows to check the primary storage first, and fall back to the alternative storage after. It you can't break up your storage by access patterns, then I think a 3.6 Tbyte file system might still be the next best option - it's still better than 36 partitions. But, make sure you have a good file system on it, that scales well to this size. Cheers, mark
[Gluster-users] Performance
Hello all, I have 2 servers both exporting 36 partitions. The client mirrors the 36 partitions on each server and puts them all into a DHT. dd if=/dev/zero of=/home/webspace_glust/zeros bs=1024 count=1024000 Takes 8 minutes, compared to 30 seconds vi NFS, now granted I'm using mostly default settings but a transfer rate of 2.1Mb/s vs about 40Mb/s seems low. What am I doing wrong? Where should I start with the performance tuning? Josh. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Performance
-Original Message- From: Mark Mielke [mailto:m...@mark.mielke.cc] Sent: 12 August 2009 16:35 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Performance On 08/12/2009 11:24 AM, Hiren Joshi wrote: Hello all, I have 2 servers both exporting 36 partitions. The client mirrors the 36 partitions on each server and puts them all into a DHT. dd if=/dev/zero of=/home/webspace_glust/zeros bs=1024 count=1024000 Takes 8 minutes, compared to 30 seconds vi NFS, now granted I'm using mostly default settings but a transfer rate of 2.1Mb/s vs about 40Mb/s seems low. What am I doing wrong? Where should I start with the performance tuning? How about start with a 1:1 comparison? Unless is somehow doing mirroring, you should remove the mirroring from your solution before comparing. Fair point, I've put on a single brick (no distribution no mirror) and I get: time dd if=/dev/zero of=/home/webspace_glust/zeros bs=1024 count=1024000 1024000+0 records in 1024000+0 records out 1048576000 bytes (1.0 GB) copied, 109.289 seconds, 9.6 MB/s real1m49.291s user0m0.156s sys 0m2.701s Compared to: time dd if=/dev/zero of=/home/webspace_nfs/josh/zeros bs=1024 count=1024000 1024000+0 records in 1024000+0 records out 1048576000 bytes (1.0 GB) copied, 29.4801 seconds, 35.6 MB/s real0m29.526s user0m0.486s sys 0m1.927s For NFS. Are you using striping? If you are not using striping, then the file /home/webspace_glust is going to be assigned to a single partition, and you would only be using a mirror of one partition. No striping, thanks, I didn't consider this, so I tried: time for x in `seq 1 1 1000`; do dd if=/dev/zero of=/home/webspace_nfs/zeros$x bs=1024 count=1024; echo $x; done real0m45.292s user0m0.760s sys 0m3.209s (about 20-40MB/s) and time for x in `seq 1 1 1000`; do dd if=/dev/zero of=/home/webspace_glust/zeros$x bs=1024 count=1024; echo $x; done real1m58.931s user0m0.432s sys 0m6.412s (about 8-10MB/s) 36 partitions on each server - the word partition is ambiguous. Are they 36 separate drives? Or multiple partitions on the same drive. If multiple partitions on the same drive, this would be a bad idea, as it would require the disk head to move back and forth between the partitions, significantly increasing the latency, and therefore significantly reducing the performance. If each partition is on its own drive, you still won't see benefit unless you have many clients concurrently changing many different files. In your above case, it's touching a single file in sequence, and having a cluster is costing you rather than benefitting you. We went with 36 partitions (on a single raid 6 drive) incase we got file system corruption, it would take less time to fsck a 100G partition than a 3.6TB one. Would a 3.6TB single disk be better? As for the 2.1Mb/s vs 40Mb/s, I have no clue. I'm new to Gluster myself, and I have yet to install it on my node cluster (10 servers) and perform timing myself. Cheers, mark -- Mark Mielkem...@mielke.cc ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Fuse problem
-Original Message- From: Jason Williams [mailto:jas...@jhu.edu] Sent: 11 August 2009 15:42 To: Hiren Joshi Cc: Vikas Gorur; gluster-users@gluster.org Subject: Re: [Gluster-users] Fuse problem Hiren Joshi wrote: -Original Message- From: Vikas Gorur [mailto:vi...@gluster.com] Sent: 11 August 2009 15:34 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Fuse problem - Hiren Joshi j...@moonfruit.com wrote: Hello all, I'm running a 64bit Centos5 setup and am trying to mount a gluster filesystem (which is exported out of the same box). glusterfs --debug --volfile=/root/gluster/webspace2.vol /home/webspace_glust/ Gives me: snip [2009-08-11 16:26:37] D [client-protocol.c:5963:init] glust1b_36: defaulting ping-timeout to 10 [2009-08-11 16:26:37] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.4/transport/socket.so [2009-08-11 16:26:37] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.4/transport/socket.so fuse: device not found, try 'modprobe fuse' first Make sure you have the fuse module loaded (modprobe fuse). I have fuse.x86_64 2.7.4-1.el5.rf installed but: # modprobe fuse FATAL: Module fuse not found. Vikas -- Engineer - http://gluster.com/ That is the userland part of fuse. There is also a kernel module that you will need to get and install. I'm guessing you have yum since this appears to be a RHEL 5 machine so try a 'yum search fuse' to see if you can find the name of the kernel module. It escapes me at the moment, which is why I suggest the yum search. yum install dkms-fuse did the trick.. thanks! -- Jason ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Fuse problem
-Original Message- From: Vikas Gorur [mailto:vi...@gluster.com] Sent: 11 August 2009 15:34 To: Hiren Joshi Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] Fuse problem - Hiren Joshi j...@moonfruit.com wrote: Hello all, I'm running a 64bit Centos5 setup and am trying to mount a gluster filesystem (which is exported out of the same box). glusterfs --debug --volfile=/root/gluster/webspace2.vol /home/webspace_glust/ Gives me: snip [2009-08-11 16:26:37] D [client-protocol.c:5963:init] glust1b_36: defaulting ping-timeout to 10 [2009-08-11 16:26:37] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.4/transport/socket.so [2009-08-11 16:26:37] D [transport.c:141:transport_load] transport: attempt to load file /usr/lib64/glusterfs/2.0.4/transport/socket.so fuse: device not found, try 'modprobe fuse' first Make sure you have the fuse module loaded (modprobe fuse). I have fuse.x86_64 2.7.4-1.el5.rf installed but: # modprobe fuse FATAL: Module fuse not found. Vikas -- Engineer - http://gluster.com/ ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] DHT with AFR
-Original Message- From: Vikas Gorur [mailto:vi...@gluster.com] Sent: 15 July 2009 09:01 To: Hiren Joshi Cc: Kirby Zhou; gluster-users@gluster.org Subject: Re: [Gluster-users] DHT with AFR - Hiren Joshi j...@moonfruit.com wrote: My thinking is both on the client so: I AFR my nodes. I then DHT my AFR bricks. I then mount the DHT vols. Or would I get better performance the other way around? DHT over AFR'd pairs is the configuration you want. You can then add another AFR pair whenever you want to scale up. When I add another pair, is there a way of re-distributing the data evenly? Will this have a big performance hit? Vikas -- Engineer - Gluster ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] io-threads/io-cache
Hi All, http://www.gluster.org/docs/index.php/Translators/performance Can anyone tell me the difference between the 2? It has the same description Thanks, Josh. ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] DHT with AFR
If I do this on a client that's solely dedicated to copying out and in again, will there be a performance hit on all the other clients using it? I really like the simplicity of glusterfs, hats off to the dev guys! -Original Message- From: Kirby Zhou [mailto:kirbyz...@sohu-rd.com] Sent: 15 July 2009 16:45 To: Hiren Joshi; 'Vikas Gorur' Cc: gluster-users@gluster.org Subject: RE: [Gluster-users] DHT with AFR AFAIK, There is no method to redistribute your already stored files except copy out then copy in again. -Original Message- From: Hiren Joshi [mailto:j...@moonfruit.com] Sent: Wednesday, July 15, 2009 4:52 PM To: Vikas Gorur Cc: Kirby Zhou; gluster-users@gluster.org Subject: RE: [Gluster-users] DHT with AFR -Original Message- From: Vikas Gorur [mailto:vi...@gluster.com] Sent: 15 July 2009 09:01 To: Hiren Joshi Cc: Kirby Zhou; gluster-users@gluster.org Subject: Re: [Gluster-users] DHT with AFR - Hiren Joshi j...@moonfruit.com wrote: My thinking is both on the client so: I AFR my nodes. I then DHT my AFR bricks. I then mount the DHT vols. Or would I get better performance the other way around? DHT over AFR'd pairs is the configuration you want. You can then add another AFR pair whenever you want to scale up. When I add another pair, is there a way of re-distributing the data evenly? Will this have a big performance hit? Vikas -- Engineer - Gluster ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] DHT with AFR
Hi all, I'm looking to create a system where all nodes are mirrored with at least one other node (using afr) but I also want it to be fully scalable (that is to say I can add another mirrored pair at any point to the system). Will AFR with DHT do what I want? Are there any problems/caveats with this setup that I should know about? What have been your experiences? Thanks, Josh. ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] DHT with AFR
My thinking is both on the client so: I AFR my nodes. I then DHT my AFR bricks. I then mount the DHT vols. Or would I get better performance the other way around? From: Kirby Zhou [mailto:kirbyz...@sohu-rd.com] Sent: 14 July 2009 17:51 To: Hiren Joshi; gluster-users@gluster.org Subject: RE: [Gluster-users] DHT with AFR Which do you want to get? AFR based on DHT or DHT based on AFR? From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hiren Joshi Sent: Wednesday, July 15, 2009 12:31 AM To: gluster-users@gluster.org Subject: [Gluster-users] DHT with AFR Hi all, I'm looking to create a system where all nodes are mirrored with at least one other node (using afr) but I also want it to be fully scalable (that is to say I can add another mirrored pair at any point to the system). Will AFR with DHT do what I want? Are there any problems/caveats with this setup that I should know about? What have been your experiences? Thanks, Josh. ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] GlusterFS Preformance
-Original Message- From: Stephan von Krawczynski [mailto:sk...@ithnet.com] Sent: 09 July 2009 13:50 To: Hiren Joshi Cc: Liam Slusser; gluster-users@gluster.org Subject: Re: [Gluster-users] GlusterFS Preformance On Thu, 9 Jul 2009 09:33:59 +0100 Hiren Joshi j...@moonfruit.com wrote: -Original Message- From: Stephan von Krawczynski [mailto:sk...@ithnet.com] Sent: 09 July 2009 09:08 To: Liam Slusser Cc: Hiren Joshi; gluster-users@gluster.org Subject: Re: [Gluster-users] GlusterFS Preformance On Wed, 8 Jul 2009 10:05:58 -0700 Liam Slusser lslus...@gmail.com wrote: You have to remember that when you are writing with NFS you're writing to one node, where as your gluster setup below is copying the same data to two nodes; so you're doubling the bandwidth. Dont expect nfs like performance on writing with multiple storage bricks. However read performance should be quite good. liam Do you think this problem can be solved by using 2 storage bricks on two different network cards on the client? I'd be surprised if the bottleneck here was the network. I'm testing on a xen network but I've only been given one eth per slice. Do you mean your clients and servers are virtual XEN installations (on the same physical box) ? They are on different boxes and using different disks (don't ask), this seemed like a good way to evaluate as I setup an NFS server using the same equipment to get relative timings. The plan is to roll it out onto new physical boxes in a month or 2 Regards, Stephan ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users