Menu
▾
▴
moosefs-users — Mailing list for MooseFS Users
You can subscribe to this list here.
| 2009 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
(4) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2010 |
Jan
(20) |
Feb
(11) |
Mar
(11) |
Apr
(9) |
May
(22) |
Jun
(85) |
Jul
(94) |
Aug
(80) |
Sep
(72) |
Oct
(64) |
Nov
(69) |
Dec
(89) |
| 2011 |
Jan
(72) |
Feb
(109) |
Mar
(116) |
Apr
(117) |
May
(117) |
Jun
(102) |
Jul
(91) |
Aug
(72) |
Sep
(51) |
Oct
(41) |
Nov
(55) |
Dec
(74) |
| 2012 |
Jan
(45) |
Feb
(77) |
Mar
(99) |
Apr
(113) |
May
(132) |
Jun
(75) |
Jul
(70) |
Aug
(58) |
Sep
(58) |
Oct
(37) |
Nov
(51) |
Dec
(15) |
| 2013 |
Jan
(28) |
Feb
(16) |
Mar
(25) |
Apr
(38) |
May
(23) |
Jun
(39) |
Jul
(42) |
Aug
(19) |
Sep
(41) |
Oct
(31) |
Nov
(18) |
Dec
(18) |
| 2014 |
Jan
(17) |
Feb
(19) |
Mar
(39) |
Apr
(16) |
May
(10) |
Jun
(13) |
Jul
(17) |
Aug
(13) |
Sep
(8) |
Oct
(53) |
Nov
(23) |
Dec
(7) |
| 2015 |
Jan
(35) |
Feb
(13) |
Mar
(14) |
Apr
(56) |
May
(8) |
Jun
(18) |
Jul
(26) |
Aug
(33) |
Sep
(40) |
Oct
(37) |
Nov
(24) |
Dec
(20) |
| 2016 |
Jan
(38) |
Feb
(20) |
Mar
(25) |
Apr
(14) |
May
(6) |
Jun
(36) |
Jul
(27) |
Aug
(19) |
Sep
(36) |
Oct
(24) |
Nov
(15) |
Dec
(16) |
| 2017 |
Jan
(8) |
Feb
(13) |
Mar
(17) |
Apr
(20) |
May
(28) |
Jun
(10) |
Jul
(20) |
Aug
(3) |
Sep
(18) |
Oct
(8) |
Nov
|
Dec
(5) |
| 2018 |
Jan
(15) |
Feb
(9) |
Mar
(12) |
Apr
(7) |
May
(123) |
Jun
(41) |
Jul
|
Aug
(14) |
Sep
|
Oct
(15) |
Nov
|
Dec
(7) |
| 2019 |
Jan
(2) |
Feb
(9) |
Mar
(2) |
Apr
(9) |
May
|
Jun
|
Jul
(2) |
Aug
|
Sep
(6) |
Oct
(1) |
Nov
(12) |
Dec
(2) |
| 2020 |
Jan
(2) |
Feb
|
Mar
|
Apr
(3) |
May
|
Jun
(4) |
Jul
(4) |
Aug
(1) |
Sep
(18) |
Oct
(2) |
Nov
|
Dec
|
| 2021 |
Jan
|
Feb
(3) |
Mar
|
Apr
|
May
|
Jun
|
Jul
(6) |
Aug
|
Sep
(5) |
Oct
(5) |
Nov
(3) |
Dec
|
| 2022 |
Jan
|
Feb
|
Mar
(3) |
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
|
From: leon h. <cod...@gm...> - 2010-10-15 15:34:52
|
but I deleted "/var/lib/mfs/" and I create "/var/lib/mfs", mfsmaster can not find this files(changelog.0.mfs metadata.mfs.back stats.mfs) in "/var/lib/mfs". How can I do? ? This is the online service, how do I get the "metadata.mfs.back" out from memory？ thanks again!!!!!thanks again!!!!! 2010/10/15 Michał Borychowski <mic...@ge...> > The "metadata.mfs.back" gets saved each hour so it should be back there > on the hour with 00 minutes. You should also have a new "changelog.0.mfs” > file > > > > > > Regards > > Michał > > > > *From:* leon hong [mailto:cod...@gm...] > *Sent:* Friday, October 15, 2010 4:46 PM > *To:* moo...@li... > *Subject:* Re: [Moosefs-users] help!!!!! I met a very serious problem > > > > As I removed the "/var/lib/mfs" directory, and later create > a "/var/lib/mfs",help!!!!!!!!~ > > > > > > the "/var/log/message": > > > ----------------------------------------------------------------------------------------------------------------------- > > Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533404: > 1287153740|UNLOCK(33003916) > > Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533405: > 1287153740|LENGTH(36510654,1024) > > Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533406: > 1287153740|UNLOCK(33003913) > > ............. > > > > thanks again! > > > > 2010/10/15 leon hong <cod...@gm...> > > hi~ > > > > I accidentally deleted the directory "/var/lib/mfs" > > How do I put the data in the lead out of memory?? > > > > help!!!!!!! > > > > > > thanks!!! > > > |
|
From: Michał B. <mic...@ge...> - 2010-10-15 15:21:58
|
The "metadata.mfs.back" gets saved each hour so it should be back there on the hour with 00 minutes. You should also have a new "changelog.0.mfs" file Regards Michał From: leon hong [mailto:cod...@gm...] Sent: Friday, October 15, 2010 4:46 PM To: moo...@li... Subject: Re: [Moosefs-users] help!!!!! I met a very serious problem As I removed the "/var/lib/mfs" directory, and later create a "/var/lib/mfs",help!!!!!!!!~ the "/var/log/message": ---------------------------------------------------------------------------- ------------------------------------------- Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533404: 1287153740|UNLOCK(33003916) Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533405: 1287153740|LENGTH(36510654,1024) Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533406: 1287153740|UNLOCK(33003913) ............. thanks again! 2010/10/15 leon hong <cod...@gm...> hi~ I accidentally deleted the directory "/var/lib/mfs" How do I put the data in the lead out of memory?? help!!!!!!! thanks!!! |
|
From: leon h. <cod...@gm...> - 2010-10-15 14:45:47
|
As I removed the "/var/lib/mfs" directory, and later create a "/var/lib/mfs",help!!!!!!!!~ the "/var/log/message": ----------------------------------------------------------------------------------------------------------------------- Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533404: 1287153740|UNLOCK(33003916) Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533405: 1287153740|LENGTH(36510654,1024) Oct 15 22:42:20 master1 mfsmaster[3024]: lost MFS change 322533406: 1287153740|UNLOCK(33003913) ............. thanks again! 2010/10/15 leon hong <cod...@gm...> > hi~ > > I accidentally deleted the directory "/var/lib/mfs" > How do I put the data in the lead out of memory?? > > help!!!!!!! > > > thanks!!! > |
|
From: leon h. <cod...@gm...> - 2010-10-15 14:23:45
|
hi~ I accidentally deleted the directory "/var/lib/mfs" How do I put the data in the lead out of memory?? help!!!!!!! thanks!!! |
|
From: Michał B. <mic...@ge...> - 2010-10-15 11:25:24
|
It would be even better if you issue "strace -o /tmp/strace.out mfsmetarestore -a" and send us the strace.out file Thank you Michał From: leon hong [mailto:cod...@gm...] Sent: Friday, October 15, 2010 10:23 AM To: moo...@li... Subject: [Moosefs-users] problem with mfsmetarestore.help~~ Hi~ I want to setup the metalogger server as the backup for the master, so I use mfsmetarestore to generate the metadata.mfs to start the master at the metalogger server. I copy the metadata_ml.mfs.back and changelog_ml.*.mfs in metalogger server to the "test machine", But it doesn't works. Here is "test machine",and do the following: [root@xx /var/lib/mfs]# pwd /var/lib/mfs [root@xx /var/lib/mfs]# ls changelog_ml.0.mfs changelog_ml.12.mfs changelog_ml.2.mfs changelog_ml.5.mfs changelog_ml.8.mfs sessions_ml.mfs changelog_ml.10.mfs changelog_ml.13.mfs changelog_ml.3.mfs changelog_ml.6.mfs changelog_ml.9.mfs changelog_ml.11.mfs changelog_ml.1.mfs changelog_ml.4.mfs changelog_ml.7.mfs metadata_ml.mfs.back [root@db2 /var/lib/mfs]# mfsmetarestore -a file 'metadata.mfs.back' not found - will try 'metadata_ml.mfs.back' instead loading objects (files,directories,etc.) ... loading node: read error: No such file or directory error can't read metadata from file: /var/lib/mfs/metadata_ml.mfs.back Here is some logs: ---------------------------------------------------------------------------- --------------------------------------- Oct 15 16:12:00 db2 mfsmaster[17645]: chunkservers status: Oct 15 16:12:00 db2 mfsmaster[17645]: server 1 (ip: 124.238.243.40, port: 9422): usedspace: 99948834816 (93.08 GiB), totalspace: 554869506048 (516.76 GiB), usage: 18.01% Oct 15 16:12:00 db2 mfsmaster[17645]: total: usedspace: 99948834816 (93.08 GiB), totalspace: 554869506048 (516.76 GiB), usage: 18.01% Oct 15 16:12:00 db2 mfsmaster[17645]: no meta loggers connected !!! I am sorry my English is not good. -leon hong |
|
From: Michał B. <mic...@ge...> - 2010-10-15 09:26:00
|
Please try to do "mfsmetarestore -a" on the metalogger machine (not the test machine) If you need any further assistance please let us know. Kind regards Michał Borychowski MooseFS Support Manager _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ Gemius S.A. ul. Wołoska 7, 02-672 Warszawa Budynek MARS, klatka D Tel.: +4822 874-41-00 Fax : +4822 874-41-01 From: leon hong [mailto:cod...@gm...] Sent: Friday, October 15, 2010 10:23 AM To: moo...@li... Subject: [Moosefs-users] problem with mfsmetarestore.help~~ Hi~ I want to setup the metalogger server as the backup for the master, so I use mfsmetarestore to generate the metadata.mfs to start the master at the metalogger server. I copy the metadata_ml.mfs.back and changelog_ml.*.mfs in metalogger server to the "test machine", But it doesn't works. Here is "test machine",and do the following: [root@xx /var/lib/mfs]# pwd /var/lib/mfs [root@xx /var/lib/mfs]# ls changelog_ml.0.mfs changelog_ml.12.mfs changelog_ml.2.mfs changelog_ml.5.mfs changelog_ml.8.mfs sessions_ml.mfs changelog_ml.10.mfs changelog_ml.13.mfs changelog_ml.3.mfs changelog_ml.6.mfs changelog_ml.9.mfs changelog_ml.11.mfs changelog_ml.1.mfs changelog_ml.4.mfs changelog_ml.7.mfs metadata_ml.mfs.back [root@db2 /var/lib/mfs]# mfsmetarestore -a file 'metadata.mfs.back' not found - will try 'metadata_ml.mfs.back' instead loading objects (files,directories,etc.) ... loading node: read error: No such file or directory error can't read metadata from file: /var/lib/mfs/metadata_ml.mfs.back Here is some logs: ---------------------------------------------------------------------------- --------------------------------------- Oct 15 16:12:00 db2 mfsmaster[17645]: chunkservers status: Oct 15 16:12:00 db2 mfsmaster[17645]: server 1 (ip: 124.238.243.40, port: 9422): usedspace: 99948834816 (93.08 GiB), totalspace: 554869506048 (516.76 GiB), usage: 18.01% Oct 15 16:12:00 db2 mfsmaster[17645]: total: usedspace: 99948834816 (93.08 GiB), totalspace: 554869506048 (516.76 GiB), usage: 18.01% Oct 15 16:12:00 db2 mfsmaster[17645]: no meta loggers connected !!! I am sorry my English is not good. -leon hong |
|
From: leon h. <cod...@gm...> - 2010-10-15 08:22:37
|
Hi~ I want to setup the metalogger server as the backup for the master, so I use mfsmetarestore to generate the metadata.mfs to start the master at the metalogger server. I copy the metadata_ml.mfs.back and changelog_ml.*.mfs in metalogger server to the "test machine", But it doesn't works. Here is "test machine",and do the following: [root@xx /var/lib/mfs]# pwd /var/lib/mfs [root@xx /var/lib/mfs]# ls changelog_ml.0.mfs changelog_ml.12.mfs changelog_ml.2.mfs changelog_ml.5.mfs changelog_ml.8.mfs sessions_ml.mfs changelog_ml.10.mfs changelog_ml.13.mfs changelog_ml.3.mfs changelog_ml.6.mfs changelog_ml.9.mfs changelog_ml.11.mfs changelog_ml.1.mfs changelog_ml.4.mfs changelog_ml.7.mfs metadata_ml.mfs.back [root@db2 /var/lib/mfs]# mfsmetarestore -a file 'metadata.mfs.back' not found - will try 'metadata_ml.mfs.back' instead loading objects (files,directories,etc.) ... loading node: read error: No such file or directory error can't read metadata from file: /var/lib/mfs/metadata_ml.mfs.back Here is some logs: ------------------------------------------------------------------------------------------------------------------- Oct 15 16:12:00 db2 mfsmaster[17645]: chunkservers status: Oct 15 16:12:00 db2 mfsmaster[17645]: server 1 (ip: 124.238.243.40, port: 9422): usedspace: 99948834816 (93.08 GiB), totalspace: 554869506048 (516.76 GiB), usage: 18.01% Oct 15 16:12:00 db2 mfsmaster[17645]: total: usedspace: 99948834816 (93.08 GiB), totalspace: 554869506048 (516.76 GiB), usage: 18.01% Oct 15 16:12:00 db2 mfsmaster[17645]: no meta loggers connected !!! I am sorry my English is not good. -leon hong |
|
From: leon h. <cod...@gm...> - 2010-10-15 03:06:41
|
hi~ How long will it take 'mfsrestorage -a'? |
|
From: Thomas S H. <tha...@gm...> - 2010-10-15 02:57:58
|
boy is my face red, mount.fuse was not installed, Thanks Jose! On Thu, Oct 14, 2010 at 3:49 PM, jose maria <let...@us...> wrote: > Thomas S Hatch escribió: > > So I think I might be able to use the fstab, but it doesn't seem to > > work, I have this line in my fstab: > > > > mfsmount /mnt/test fuse mfsmaster=mfsmaster,mfsport=9421,_netdev 0 0 > > > > and when I run mount -a -t fuse I get this: > > mount: wrong fs type, bad option, bad superblock on mfsmount, > > missing codepage or helper program, or other error > > (for several filesystems (e.g. nfs, cifs) you might > > need a /sbin/mount.<type> helper program) > > In some cases useful info is found in syslog - try > > dmesg | tail or so > > > > I am on Ubuntu Linux 10.04 > > moosefs 1.6.17 > > > > /sbin/mount.fuse --help > > > ------------------------------------------------------------------------------ > Download new Adobe(R) Flash(R) Builder(TM) 4 > The new Adobe(R) Flex(R) 4 and Flash(R) Builder(TM) 4 (formerly > Flex(R) Builder(TM)) enable the development of rich applications that run > across multiple browsers and platforms. Download your free trials today! > http://p.sf.net/sfu/adobe-dev2dev > _______________________________________________ > moosefs-users mailing list > moo...@li... > https://lists.sourceforge.net/lists/listinfo/moosefs-users > |
|
From: jose m. <let...@us...> - 2010-10-14 21:49:40
|
Thomas S Hatch escribió: > So I think I might be able to use the fstab, but it doesn't seem to > work, I have this line in my fstab: > > mfsmount /mnt/test fuse mfsmaster=mfsmaster,mfsport=9421,_netdev 0 0 > > and when I run mount -a -t fuse I get this: > mount: wrong fs type, bad option, bad superblock on mfsmount, > missing codepage or helper program, or other error > (for several filesystems (e.g. nfs, cifs) you might > need a /sbin/mount.<type> helper program) > In some cases useful info is found in syslog - try > dmesg | tail or so > > I am on Ubuntu Linux 10.04 > moosefs 1.6.17 > /sbin/mount.fuse --help |
|
From: Thomas S H. <tha...@gm...> - 2010-10-14 16:36:09
|
So I think I might be able to use the fstab, but it doesn't seem to work, I
have this line in my fstab:
mfsmount /mnt/test fuse mfsmaster=mfsmaster,mfsport=9421,_netdev 0 0
and when I run mount -a -t fuse I get this:
mount: wrong fs type, bad option, bad superblock on mfsmount,
missing codepage or helper program, or other error
(for several filesystems (e.g. nfs, cifs) you might
need a /sbin/mount.<type> helper program)
In some cases useful info is found in syslog - try
dmesg | tail or so
I am on Ubuntu Linux 10.04
moosefs 1.6.17
-Tom Hatch
|
|
From: Thomas S H. <tha...@gm...> - 2010-10-14 16:03:14
|
I am looking into mounting moosefs automatically, but due to some limitations in my environment using the fstab is not an option. I was curious if anyone had tried to use autofs to mount moosefs, I assume it would work but I have been unable to get the right configuration. Also, since an attempt to mount a filesystem that is not present will result in the mfsmount process hanging, is it possible to verify that the server is up before attempting a mount? This would make scripting the mount a viable option. -Thanks -Thomas S Hatch |
|
From: Thomas S H. <tha...@gm...> - 2010-10-09 18:30:25
|
Wow, how did I miss that? Thanks! On Oct 9, 2010 11:56 AM, "jose maria" <let...@us...> wrote: > >> >> I am having trouble accessing the trash on my mfs, I can mount the meta >> and I see the trash directory and the restricted directory, but when I >> ls the trash directory the ls command hangs and I need to kill -9 the ls >> process. >> >> I can mount the normal mfs filesystem without any problems and >> read/write, I just can't dig around in the trash. Am I missing something? >> > > * many files in trash, execute: > ls -1Q -I undel /mountpoint/trash/ > trashfiles.txt > > * read trashfiles.txt > > ------------------------------------------------------------------------------ > Beautiful is writing same markup. Internet Explorer 9 supports > standards for HTML5, CSS3, SVG 1.1, ECMAScript5, and DOM L2 & L3. > Spend less time writing and rewriting code and more time creating great > experiences on the web. Be a part of the beta today. > http://p.sf.net/sfu/beautyoftheweb > _______________________________________________ > moosefs-users mailing list > moo...@li... > https://lists.sourceforge.net/lists/listinfo/moosefs-users |
|
From: jose m. <let...@us...> - 2010-10-09 17:56:02
|
> > I am having trouble accessing the trash on my mfs, I can mount the meta > and I see the trash directory and the restricted directory, but when I > ls the trash directory the ls command hangs and I need to kill -9 the ls > process. > > I can mount the normal mfs filesystem without any problems and > read/write, I just can't dig around in the trash. Am I missing something? > * many files in trash, execute: ls -1Q -I undel /mountpoint/trash/ > trashfiles.txt * read trashfiles.txt |
|
From: Kristofer P. <kri...@cy...> - 2010-10-09 17:16:59
|
According to the web interface, how many items do you have in the trash? From: "Thomas S Hatch" <tha...@gm...> To: moo...@li... Sent: Friday, October 8, 2010 11:14:42 PM Subject: [Moosefs-users] Taking out the trash I am having trouble accessing the trash on my mfs, I can mount the meta and I see the trash directory and the restricted directory, but when I ls the trash directory the ls command hangs and I need to kill -9 the ls process. I can mount the normal mfs filesystem without any problems and read/write, I just can't dig around in the trash. Am I missing something? moosefs 1.6.17 Ubuntu 10.04 ext4 -Thomas S Hatch ------------------------------------------------------------------------------ Beautiful is writing same markup. Internet Explorer 9 supports standards for HTML5, CSS3, SVG 1.1, ECMAScript5, and DOM L2 & L3. Spend less time writing and rewriting code and more time creating great experiences on the web. Be a part of the beta today. http://p.sf.net/sfu/beautyoftheweb _______________________________________________ moosefs-users mailing list moo...@li... https://lists.sourceforge.net/lists/listinfo/moosefs-users |
|
From: Thomas S H. <tha...@gm...> - 2010-10-09 04:14:51
|
I am having trouble accessing the trash on my mfs, I can mount the meta and I see the trash directory and the restricted directory, but when I ls the trash directory the ls command hangs and I need to kill -9 the ls process. I can mount the normal mfs filesystem without any problems and read/write, I just can't dig around in the trash. Am I missing something? moosefs 1.6.17 Ubuntu 10.04 ext4 -Thomas S Hatch |
|
From: Travis H. <tra...@tr...> - 2010-10-01 04:38:43
|
On 2010-09-20, at 10:11 AM, Cuong Hoang Bui wrote: > Hi, > > I'm wondering about the storage backend for chunk servers. I have 2 options > 1. Using RAID for underly storage backend for chunk servers. > 2. Not use RAID, Just separate disks attached directly to OS. > > With RAID (maybe RAID 6) option, the solution is very good, but take > money for RAID card. > > With no RAID, I wonder about tolerance (disk failure). If I have 8 disks > attached directly to OS, for example I mount as /mnt/sdb, /mnt/sdc,.., > .mnt/sdh. If one of them failed, what happens to data, also operations > that's performing on this disk. Please give me some advice. > I guess without a hardware RAID card, to ensure no data loss due to a single disk failure, you could run a separate chunk server process per disk on the given machine, and then set the goal for the number of copies of files in the MFS store to be something more than one. This is likely a messy and complex configuration, it would likely be better to have two machines with 4 disks in each, for example, or to use a logical volume manager, multiple device, or software raid, depending on what your OS supports. as that might have slightly better performance than the network chatter for multiple instances of chunk servers on the same box. Travis |
|
From: Laurent W. <lw...@hy...> - 2010-09-30 15:04:25
|
On Thu, 30 Sep 2010 14:25:55 +0000 Ólafur Ósvaldsson <osv...@ne...> wrote: > Hi, Hello, > We are setting up MFS with 10 chunkservers, each will have 6x1TB disks, we are thinking if the performance gain of multiple spindles when running in Raid0 would outweight the possible rebuild time of 6TB if one disk would die. > > Or would it be better to have each disk as a seperate filesystem on the chunk server so that if one would fail it would only take away 1TB of data instead of 6TB in the Raid0 setup? I have copied something like 6TB at goal 1. put goal to 2, it's running for 1 week and it'll take phew…something like 3 or 4 more to be finished. MFS effort to attain the asked goal is quite low, as it isn't meant to slow the whole fs down to a crawl. It does it, but slowly. 6 disks as raid0 is a bit too much risky to my eyes. I'd vote for JBOD. As load will be spread between disks, you'll get quite good performance, even if not as good as raid 0/10. So, if a disk crashes, getting back at goal x for every file will be shorter than if a complete raid 0 volume crashes. Thus minimizing the possibily of another crash while goal x isn't available for all files, and the likelyhood of loosing the whole FS. HTH, -- Laurent Wandrebeck HYGEOS, Earth Observation Department / Observation de la Terre Euratechnologies 165 Avenue de Bretagne 59000 Lille, France tel: +33 3 20 08 24 98 http://www.hygeos.com GPG fingerprint/Empreinte GPG: F5CA 37A4 6D03 A90C 7A1D 2A62 54E6 EF2C D17C F64C |
|
From: Laurent W. <lw...@hy...> - 2010-09-30 14:53:48
|
On Mon, 27 Sep 2010 10:21:04 +0200 Ioannis Aslanidis <ias...@fl...> wrote: > Hello, Hi, > > I have a question regarding performance on intesive writes. If I mount > the filesystem in several machines that run intensive write > applications, what performance do I have to expect? Normally the > writes are appends. These applications also tend to move large files > of up to 1GB. I have (for now) 3 chunkservers, and I get ~50MB/sec while copying files on the mfs volume. There is no load on it, only goal 2 on its way. See http://www.moosefs.org/moosefs-faq.html#average for « real » load behaviour at gemius. (20/30 MB/sec). HTH, -- Laurent Wandrebeck HYGEOS, Earth Observation Department / Observation de la Terre Euratechnologies 165 Avenue de Bretagne 59000 Lille, France tel: +33 3 20 08 24 98 http://www.hygeos.com GPG fingerprint/Empreinte GPG: F5CA 37A4 6D03 A90C 7A1D 2A62 54E6 EF2C D17C F64C |
|
From: Ólafur Ó. <osv...@ne...> - 2010-09-30 14:41:29
|
Hi, We are setting up MFS with 10 chunkservers, each will have 6x1TB disks, we are thinking if the performance gain of multiple spindles when running in Raid0 would outweight the possible rebuild time of 6TB if one disk would die. Or would it be better to have each disk as a seperate filesystem on the chunk server so that if one would fail it would only take away 1TB of data instead of 6TB in the Raid0 setup? Hopefully you understand what I'm thinking about with this, if not just ask and I'll try harder to make a better explanation. /Oli -- Ólafur Osvaldsson System Administrator Nethonnun ehf. e-mail: osv...@ne... phone: +354 517 3418 |
|
From: Michał B. <mic...@ge...> - 2010-09-27 10:32:54
|
Hi! Our tests show that really there are some problems with FreeBSD 6.x (independently of thread library used). It is very interesting case and we will investigate it further. On the other hand FreeBSD 6.2 is quite old (from 2007) and we would suggest an upgrade. Our recommendation is 7.3 (unfortunately on versions 8.x there are some problems with FUSE; though these are not bugs in MooseFS itself but resources mounted by FUSE (including MooseFS) can cause "kernel panic". Kind regards Michal From: kuer ku [mailto:ku...@gm...] Sent: Sunday, September 26, 2010 12:15 PM To: moo...@li... Subject: [Moosefs-users] mfschunkserver cannot start up on FreeBSD 6.2 (i386) Hi, all, I want to deploy MFS/1.6.17 chunkservers on FreeBSD 6.2/i386 boxes. But it always core dump, here are some gdb info : Loaded symbols for /libexec/ld-elf.so.1 #0 0x65cbf4ab in pthread_testcancel () from /usr/lib/libpthread.so.2 [New Thread 0x814f000 (sleeping)] [New Thread 0x813ae00 (sleeping)] [New Thread 0x813ac00 (sleeping)] [New Thread 0x813aa00 (sleeping)] [New Thread 0x813a800 (runnable)] [New Thread 0x813a600 (LWP 100673)] [New Thread 0x813a400 (sleeping)] [New Thread 0x813a200 (sleeping)] [New Thread 0x813a000 (sleeping)] [New Thread 0x80ede00 (sleeping)] [New Thread 0x80edc00 (sleeping)] [New Thread 0x80eda00 (sleeping)] [New Thread 0x80ed800 (sleeping)] [New Thread 0x80ed200 (LWP 101110)] [New Thread 0x80ed000 (runnable)] [New LWP 100324] (gdb) bt #0 0x65cbf4ab in pthread_testcancel () from /usr/lib/libpthread.so.2 #1 0x65cb7e3c in pthread_mutexattr_init () from /usr/lib/libpthread.so.2 #2 0x65c91450 in ?? () (gdb) seems that some pthread function cause the problem. Does someone know how to fix them ?? thanks. -- kuer |
|
From: Ioannis A. <ias...@fl...> - 2010-09-27 08:21:34
|
Hello, I have a question regarding performance on intesive writes. If I mount the filesystem in several machines that run intensive write applications, what performance do I have to expect? Normally the writes are appends. These applications also tend to move large files of up to 1GB. Thank you. -- Ioannis Aslanidis System and Network Administrator Flumotion Services, S.A. sys...@fl... Office Phone: +34 93 508 63 59 Mobile Phone: +34 672 20 45 75 |
|
From: kuer ku <ku...@gm...> - 2010-09-26 10:15:23
|
Hi, all, I want to deploy MFS/1.6.17 chunkservers on FreeBSD 6.2/i386 boxes. But it always core dump, here are some gdb info : Loaded symbols for /libexec/ld-elf.so.1 #0 0x65cbf4ab in pthread_testcancel () from /usr/lib/libpthread.so.2 [New Thread 0x814f000 (sleeping)] [New Thread 0x813ae00 (sleeping)] [New Thread 0x813ac00 (sleeping)] [New Thread 0x813aa00 (sleeping)] [New Thread 0x813a800 (runnable)] [New Thread 0x813a600 (LWP 100673)] [New Thread 0x813a400 (sleeping)] [New Thread 0x813a200 (sleeping)] [New Thread 0x813a000 (sleeping)] [New Thread 0x80ede00 (sleeping)] [New Thread 0x80edc00 (sleeping)] [New Thread 0x80eda00 (sleeping)] [New Thread 0x80ed800 (sleeping)] [New Thread 0x80ed200 (LWP 101110)] [New Thread 0x80ed000 (runnable)] [New LWP 100324] (gdb) bt #0 0x65cbf4ab in pthread_testcancel () from /usr/lib/libpthread.so.2 #1 0x65cb7e3c in pthread_mutexattr_init () from /usr/lib/libpthread.so.2 #2 0x65c91450 in ?? () (gdb) seems that some pthread function cause the problem. Does someone know how to fix them ?? thanks. -- kuer |
|
From: Steve <st...@bo...> - 2010-09-24 08:07:52
|
Compression as well ? -------Original Message------- From: Alexander Akhobadze Date: 24/09/2010 08:03:20 To: moo...@li... Subject: [Moosefs-users] Deduplication Hi all! I wonder if you have plans to implement data deduplication in MooseFS ? I mean searching for the equal chunks and make them to be stored just once. In my humble opinion it will be no so hard with a glance each chunk have checksum already. Thanks! wbr Alexander Akhobadze ----------------------------------------------------------------------------- Nokia and AT&T present the 2010 Calling All Innovators-North America contest Create new apps & games for the Nokia N8 for consumers in U.S. and Canada $10 million total in prizes - $4M cash, 500 devices, nearly $6M in marketing Develop with Nokia Qt SDK, Web Runtime, or Java and Publish to Ovi Store http://p.sf.net/sfu/nokia-dev2dev _______________________________________________ moosefs-users mailing list moo...@li... https://lists.sourceforge.net/lists/listinfo/moosefs-users |
|
From: Alexander A. <akh...@ri...> - 2010-09-24 07:27:19
|
Hi Laurent ! No. I do not mean goal=1 :--) I mean the condition when user do a lot of copyes of some files in their own folders. In this case free space on any drive quickly becomes low :--( So I mean searching for the equal chunks belonging to different files. On unux-level this can be done by hard links. Also you can take a look at http://en.wikipedia.org/wiki/Data_deduplication Sorry for my English. Is my answer understandable? ====================================================== On Fri, 24 Sep 2010 11:02:34 +0400 Alexander Akhobadze <akh...@ri...> wrote: > Hi all! > > I wonder if you have plans to implement data deduplication in MooseFS ? > I mean searching for the equal chunks and make them > to be stored just once. > In my humble opinion it will be no so hard > with a glance each chunk have checksum already. > > Thanks! > wbr > Alexander Akhobadze I'm really unsure I understand your point here. If my guess is ok, what you want is goal=1 ? Then the answer is easy, mfssetgoal :-) If I'm wrong, then please enlighten me. Regards, |
84 messages has been excluded from this view by a project administrator.
