Has anyone been using DRBD and Lustre in async mode? I was curious what type of speeds you were getting and also what network are you using? TIA
Hello, I ran some tests with DRBD and Lustre a few months ago (including in async mode). You can find my modest findings here on the Lustre wiki : http://wiki.lustre.org/index.php?title=Drbd_And_Lustre Cheers, Sebastien. Mag Gam a ?crit :> Has anyone been using DRBD and Lustre in async mode? I was curious > what type of speeds you were getting and also what network are you > using? > > TIA > _______________________________________________ > Lustre-discuss mailing list > Lustre-discuss at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-discuss > >
Ha yes..I seen this before Sebastein. :-) I wanted to see if other people have tried it and their thoughts were. thats all TIA On Mon, Aug 11, 2008 at 2:33 AM, S?bastien Buisson <sebastien.buisson at bull.net> wrote:> Hello, > > I ran some tests with DRBD and Lustre a few months ago (including in async > mode). You can find my modest findings here on the Lustre wiki : > http://wiki.lustre.org/index.php?title=Drbd_And_Lustre > > Cheers, > Sebastien. > > > Mag Gam a ?crit : >> >> Has anyone been using DRBD and Lustre in async mode? I was curious >> what type of speeds you were getting and also what network are you >> using? >> >> TIA >> _______________________________________________ >> Lustre-discuss mailing list >> Lustre-discuss at lists.lustre.org >> http://lists.lustre.org/mailman/listinfo/lustre-discuss >> >> >
I''m trying a Lustre + DRBD set-up, I would like to use DRBD with the following setup: on MDS: DRBD emulates an MDT on shared storage. From Lustre perspective one MDS is active, the other is passive on OSS: BRBD emulates two OST on shared storage for each OSS couple. From Lustre perspective each OSS is active for one OST and passive for the other. I''m planning to use DRBD in active/passive mode, so that the storage is mounted only on the active server, and luster is mounted on top. I''m not sure how to sync the mount/umount of the DRBD partition and the mount of MDT/OST upon failover. The target setup shall have 2 MDS (1 couple) and 8 OST (4 couples), dedicate LANs for heartbeat and drbd. Do you have any details of your setup you may share about this? TIA! On Aug 12, 4:50?am, "Mag Gam" <magaw... at gmail.com> wrote:> Ha yes..I seen this before Sebastein. :-) > > I wanted to see if other people have tried it and their thoughts were. > > thats all > TIA > > On Mon, Aug 11, 2008 at 2:33 AM, S?bastien Buisson > > <sebastien.buis... at bull.net> wrote: > > Hello, > > > I ran some tests with DRBD and Lustre a few months ago (including in async > > mode). You can find my modest findings here on the Lustre wiki : > >http://wiki.lustre.org/index.php?title=Drbd_And_Lustre > > > Cheers, > > Sebastien. > > > Mag Gam a ?crit : > > >> Has anyone been using DRBD and Lustre in async mode? I was curious > >> what type of speeds you were getting and also what network are you > >> using? > > >> TIA > >> _______________________________________________ > >> Lustre-discuss mailing list > >> Lustre-disc... at lists.lustre.org > >>http://lists.lustre.org/mailman/listinfo/lustre-discuss > > _______________________________________________ > Lustre-discuss mailing list > Lustre-disc... at lists.lustre.orghttp://lists.lustre.org/mailman/listinfo/lustre-discuss
Sorry Andrea, I would like to know this too. Hopefully someone here has done this before. Its worth a wiki On Thu, Aug 14, 2008 at 3:05 AM, Andrea Frittoli <andrea.frittoli at gmail.com> wrote:> I''m trying a Lustre + DRBD set-up, I would like to use DRBD with the > following setup: > > on MDS: DRBD emulates an MDT on shared storage. From Lustre > perspective one MDS is active, the other is passive > on OSS: BRBD emulates two OST on shared storage for each OSS couple. > >From Lustre perspective each OSS is active for one OST and passive for > the other. > > I''m planning to use DRBD in active/passive mode, so that the storage > is mounted only on the active server, and luster is mounted on top. > I''m not sure how to sync the mount/umount of the DRBD partition and > the mount of MDT/OST upon failover. > > The target setup shall have 2 MDS (1 couple) and 8 OST (4 couples), > dedicate LANs for heartbeat and drbd. > > Do you have any details of your setup you may share about this? > > TIA! > > > On Aug 12, 4:50 am, "Mag Gam" <magaw... at gmail.com> wrote: >> Ha yes..I seen this before Sebastein. :-) >> >> I wanted to see if other people have tried it and their thoughts were. >> >> thats all >> TIA >> >> On Mon, Aug 11, 2008 at 2:33 AM, S?bastien Buisson >> >> <sebastien.buis... at bull.net> wrote: >> > Hello, >> >> > I ran some tests with DRBD and Lustre a few months ago (including in async >> > mode). You can find my modest findings here on the Lustre wiki : >> >http://wiki.lustre.org/index.php?title=Drbd_And_Lustre >> >> > Cheers, >> > Sebastien. >> >> > Mag Gam a ?crit : >> >> >> Has anyone been using DRBD and Lustre in async mode? I was curious >> >> what type of speeds you were getting and also what network are you >> >> using? >> >> >> TIA >> >> _______________________________________________ >> >> Lustre-discuss mailing list >> >> Lustre-disc... at lists.lustre.org >> >>http://lists.lustre.org/mailman/listinfo/lustre-discuss >> >> _______________________________________________ >> Lustre-discuss mailing list >> Lustre-disc... at lists.lustre.orghttp://lists.lustre.org/mailman/listinfo/lustre-discuss > _______________________________________________ > Lustre-discuss mailing list > Lustre-discuss at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-discuss >
On Aug 30, 2008 16:35 -0400, Mag Gam wrote:> Sorry Andrea, I would like to know this too. Hopefully someone here > has done this before. Its worth a wikiCommon case is use of Linux-HA to manage primary/backup for each OST/MDT. Since Lustre 1.6+ uses "mount" and "unmount" to start/stop Lustre services this can be set up relatively easily with Linux-HA. There is likely even something in the Lustre manual.> On Thu, Aug 14, 2008 at 3:05 AM, Andrea Frittoli > <andrea.frittoli at gmail.com> wrote: > > I''m trying a Lustre + DRBD set-up, I would like to use DRBD with the > > following setup: > > > > on MDS: DRBD emulates an MDT on shared storage. From Lustre > > perspective one MDS is active, the other is passive > > on OSS: BRBD emulates two OST on shared storage for each OSS couple. > > >From Lustre perspective each OSS is active for one OST and passive for > > the other. > > > > I''m planning to use DRBD in active/passive mode, so that the storage > > is mounted only on the active server, and luster is mounted on top. > > I''m not sure how to sync the mount/umount of the DRBD partition and > > the mount of MDT/OST upon failover. > > > > The target setup shall have 2 MDS (1 couple) and 8 OST (4 couples), > > dedicate LANs for heartbeat and drbd. > > > > Do you have any details of your setup you may share about this? > > > > TIA! > > > > > > On Aug 12, 4:50 am, "Mag Gam" <magaw... at gmail.com> wrote: > >> Ha yes..I seen this before Sebastein. :-) > >> > >> I wanted to see if other people have tried it and their thoughts were. > >> > >> thats all > >> TIA > >> > >> On Mon, Aug 11, 2008 at 2:33 AM, S?bastien Buisson > >> > >> <sebastien.buis... at bull.net> wrote: > >> > Hello, > >> > >> > I ran some tests with DRBD and Lustre a few months ago (including in async > >> > mode). You can find my modest findings here on the Lustre wiki : > >> >http://wiki.lustre.org/index.php?title=Drbd_And_Lustre > >> > >> > Cheers, > >> > Sebastien. > >> > >> > Mag Gam a ?crit : > >> > >> >> Has anyone been using DRBD and Lustre in async mode? I was curious > >> >> what type of speeds you were getting and also what network are you > >> >> using? > >> > >> >> TIA > >> >> _______________________________________________ > >> >> Lustre-discuss mailing list > >> >> Lustre-disc... at lists.lustre.org > >> >>http://lists.lustre.org/mailman/listinfo/lustre-discuss > >> > >> _______________________________________________ > >> Lustre-discuss mailing list > >> Lustre-disc... at lists.lustre.orghttp://lists.lustre.org/mailman/listinfo/lustre-discuss > > _______________________________________________ > > Lustre-discuss mailing list > > Lustre-discuss at lists.lustre.org > > http://lists.lustre.org/mailman/listinfo/lustre-discuss > > > _______________________________________________ > Lustre-discuss mailing list > Lustre-discuss at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-discussCheers, Andreas -- Andreas Dilger Sr. Staff Engineer, Lustre Group Sun Microsystems of Canada, Inc.
Am Dienstag, 2. September 2008 22:24:58 schrieb Andreas Dilger: We are using a setup with the following spec: mds1 and mds2: 2 SATA Disks for MDS inside running raid0 with mdam tools. Above this drbd for network raid0 and Above that HA for failover. Besides that stonith is running inside HA for a real kill of the other node in case of trouble. Works good and reliable. We tested this real hard. If it is of general interest i could put down some notes how we did it but it will take some days. (I have do do it anyway for our docs ...) So please let me know if somebody is interested in this. Regards Heiko> On Aug 30, 2008 16:35 -0400, Mag Gam wrote: > > Sorry Andrea, I would like to know this too. Hopefully someone here > > has done this before. Its worth a wiki > > Common case is use of Linux-HA to manage primary/backup for each OST/MDT. > Since Lustre 1.6+ uses "mount" and "unmount" to start/stop Lustre services > this can be set up relatively easily with Linux-HA. There is likely even > something in the Lustre manual. > > > On Thu, Aug 14, 2008 at 3:05 AM, Andrea Frittoli > > > > <andrea.frittoli at gmail.com> wrote: > > > I''m trying a Lustre + DRBD set-up, I would like to use DRBD with the > > > following setup: > > > > > > on MDS: DRBD emulates an MDT on shared storage. From Lustre > > > perspective one MDS is active, the other is passive > > > on OSS: BRBD emulates two OST on shared storage for each OSS couple. > > > > > > >From Lustre perspective each OSS is active for one OST and passive for > > > > > > the other. > > > > > > I''m planning to use DRBD in active/passive mode, so that the storage > > > is mounted only on the active server, and luster is mounted on top. > > > I''m not sure how to sync the mount/umount of the DRBD partition and > > > the mount of MDT/OST upon failover. > > > > > > The target setup shall have 2 MDS (1 couple) and 8 OST (4 couples), > > > dedicate LANs for heartbeat and drbd. > > > > > > Do you have any details of your setup you may share about this? > > > > > > TIA! > > > > > > On Aug 12, 4:50 am, "Mag Gam" <magaw... at gmail.com> wrote: > > >> Ha yes..I seen this before Sebastein. :-) > > >> > > >> I wanted to see if other people have tried it and their thoughts were. > > >> > > >> thats all > > >> TIA > > >> > > >> On Mon, Aug 11, 2008 at 2:33 AM, S?bastien Buisson > > >> > > >> <sebastien.buis... at bull.net> wrote: > > >> > Hello, > > >> > > > >> > I ran some tests with DRBD and Lustre a few months ago (including in > > >> > async mode). You can find my modest findings here on the Lustre wiki > > >> > : http://wiki.lustre.org/index.php?title=Drbd_And_Lustre > > >> > > > >> > Cheers, > > >> > Sebastien. > > >> > > > >> > Mag Gam a ?crit : > > >> >> Has anyone been using DRBD and Lustre in async mode? I was curious > > >> >> what type of speeds you were getting and also what network are you > > >> >> using? > > >> >> > > >> >> TIA > > >> >> _______________________________________________ > > >> >> Lustre-discuss mailing list > > >> >> Lustre-disc... at lists.lustre.org > > >> >>http://lists.lustre.org/mailman/listinfo/lustre-discuss > > >> > > >> _______________________________________________ > > >> Lustre-discuss mailing list > > >> Lustre-disc... at lists.lustre.orghttp://lists.lustre.org/mailman/listinf > > >>o/lustre-discuss > > > > > > _______________________________________________ > > > Lustre-discuss mailing list > > > Lustre-discuss at lists.lustre.org > > > http://lists.lustre.org/mailman/listinfo/lustre-discuss > > > > _______________________________________________ > > Lustre-discuss mailing list > > Lustre-discuss at lists.lustre.org > > http://lists.lustre.org/mailman/listinfo/lustre-discuss > > Cheers, Andreas > -- > Andreas Dilger > Sr. Staff Engineer, Lustre Group > Sun Microsystems of Canada, Inc. > > _______________________________________________ > Lustre-discuss mailing list > Lustre-discuss at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-discuss-- ----------------------------------------------------------------------- Dipl.-Ing. Heiko Schr?ter Institute of Environmental Physics (IUP) ? ?phone: ++49-(0)421-218-4080 Institute of Remote Sensing (IFE) ? ? ? ? ? fax: ? ++49-(0)421-218-4555 University of Bremen (FB1) P.O. Box 330440 ? ? ? ? ? ? ? email: ?schroete at iup.physik.uni-bremen.de Otto-Hahn-Allee 1 ? ? ? ? ? 28359 Bremen ? ? ? ? ? ? ? ? Germany -----------------------------------------------------------------------
Id like a copy of that document. We''re running a similar setup which is not documented at all, more ad-hoc and in difference we''re not running stonith and we have a raid1+0 in each (mds)node, raid 1 over drbd and sync-mode B. Regards, Timh 2008/9/22 Heiko Schroeter <schroete at iup.physik.uni-bremen.de>:> Am Dienstag, 2. September 2008 22:24:58 schrieb Andreas Dilger: > > We are using a setup with the following spec: > > mds1 and mds2: > 2 SATA Disks for MDS inside running raid0 with mdam tools. > Above this drbd for network raid0 and > Above that HA for failover. > > Besides that stonith is running inside HA for a real kill of the other node in > case of trouble. > > Works good and reliable. We tested this real hard. > > If it is of general interest i could put down some notes how we did it but it > will take some days. > (I have do do it anyway for our docs ...) > So please let me know if somebody is interested in this. > > Regards > Heiko > > > >> On Aug 30, 2008 16:35 -0400, Mag Gam wrote: >> > Sorry Andrea, I would like to know this too. Hopefully someone here >> > has done this before. Its worth a wiki >> >> Common case is use of Linux-HA to manage primary/backup for each OST/MDT. >> Since Lustre 1.6+ uses "mount" and "unmount" to start/stop Lustre services >> this can be set up relatively easily with Linux-HA. There is likely even >> something in the Lustre manual. >> >> > On Thu, Aug 14, 2008 at 3:05 AM, Andrea Frittoli >> > >> > <andrea.frittoli at gmail.com> wrote: >> > > I''m trying a Lustre + DRBD set-up, I would like to use DRBD with the >> > > following setup: >> > > >> > > on MDS: DRBD emulates an MDT on shared storage. From Lustre >> > > perspective one MDS is active, the other is passive >> > > on OSS: BRBD emulates two OST on shared storage for each OSS couple. >> > > >> > > >From Lustre perspective each OSS is active for one OST and passive for >> > > >> > > the other. >> > > >> > > I''m planning to use DRBD in active/passive mode, so that the storage >> > > is mounted only on the active server, and luster is mounted on top. >> > > I''m not sure how to sync the mount/umount of the DRBD partition and >> > > the mount of MDT/OST upon failover. >> > > >> > > The target setup shall have 2 MDS (1 couple) and 8 OST (4 couples), >> > > dedicate LANs for heartbeat and drbd. >> > > >> > > Do you have any details of your setup you may share about this? >> > > >> > > TIA! >> > > >> > > On Aug 12, 4:50 am, "Mag Gam" <magaw... at gmail.com> wrote: >> > >> Ha yes..I seen this before Sebastein. :-) >> > >> >> > >> I wanted to see if other people have tried it and their thoughts were. >> > >> >> > >> thats all >> > >> TIA >> > >> >> > >> On Mon, Aug 11, 2008 at 2:33 AM, S?bastien Buisson >> > >> >> > >> <sebastien.buis... at bull.net> wrote: >> > >> > Hello, >> > >> > >> > >> > I ran some tests with DRBD and Lustre a few months ago (including in >> > >> > async mode). You can find my modest findings here on the Lustre wiki >> > >> > : http://wiki.lustre.org/index.php?title=Drbd_And_Lustre >> > >> > >> > >> > Cheers, >> > >> > Sebastien. >> > >> > >> > >> > Mag Gam a ?crit : >> > >> >> Has anyone been using DRBD and Lustre in async mode? I was curious >> > >> >> what type of speeds you were getting and also what network are you >> > >> >> using? >> > >> >> >> > >> >> TIA >> > >> >> _______________________________________________ >> > >> >> Lustre-discuss mailing list >> > >> >> Lustre-disc... at lists.lustre.org >> > >> >>http://lists.lustre.org/mailman/listinfo/lustre-discuss >> > >> >> > >> _______________________________________________ >> > >> Lustre-discuss mailing list >> > >> Lustre-disc... at lists.lustre.orghttp://lists.lustre.org/mailman/listinf >> > >>o/lustre-discuss >> > > >> > > _______________________________________________ >> > > Lustre-discuss mailing list >> > > Lustre-discuss at lists.lustre.org >> > > http://lists.lustre.org/mailman/listinfo/lustre-discuss >> > >> > _______________________________________________ >> > Lustre-discuss mailing list >> > Lustre-discuss at lists.lustre.org >> > http://lists.lustre.org/mailman/listinfo/lustre-discuss >> >> Cheers, Andreas >> -- >> Andreas Dilger >> Sr. Staff Engineer, Lustre Group >> Sun Microsystems of Canada, Inc. >> >> _______________________________________________ >> Lustre-discuss mailing list >> Lustre-discuss at lists.lustre.org >> http://lists.lustre.org/mailman/listinfo/lustre-discuss > > > > -- > ----------------------------------------------------------------------- > Dipl.-Ing. Heiko Schr?ter > Institute of Environmental Physics (IUP) phone: ++49-(0)421-218-4080 > Institute of Remote Sensing (IFE) fax: ++49-(0)421-218-4555 > University of Bremen (FB1) > P.O. Box 330440 email: schroete at iup.physik.uni-bremen.de > Otto-Hahn-Allee 1 > 28359 Bremen > Germany > ----------------------------------------------------------------------- > _______________________________________________ > Lustre-discuss mailing list > Lustre-discuss at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-discuss >-- Timh Bergstr?m System Administrator Diino AB - www.diino.com :wq
On Sep 22, 2008 11:19 +0200, Heiko Schroeter wrote:> We are using a setup with the following spec: > > mds1 and mds2: > 2 SATA Disks for MDS inside running raid0 with mdam tools. > Above this drbd for network raid0 and > Above that HA for failover. > > Besides that stonith is running inside HA for a real kill of the other > node in case of trouble. > > Works good and reliable. We tested this real hard. > > If it is of general interest i could put down some notes how we did it but it > will take some days. > (I have do do it anyway for our docs ...) > So please let me know if somebody is interested in this.It would definitely be useful to update (at least) the Lustre DRBD wiki page to indicate you are using this successfully, and any configuration DRBD options you are using. Similarly, if the Lustre manual is missing any information (or possibly a specific example) of how to use HA for Lustre that would also be useful.> > On Aug 30, 2008 16:35 -0400, Mag Gam wrote: > > > Sorry Andrea, I would like to know this too. Hopefully someone here > > > has done this before. Its worth a wiki > > > > Common case is use of Linux-HA to manage primary/backup for each OST/MDT. > > Since Lustre 1.6+ uses "mount" and "unmount" to start/stop Lustre services > > this can be set up relatively easily with Linux-HA. There is likely even > > something in the Lustre manual. > > > > > On Thu, Aug 14, 2008 at 3:05 AM, Andrea Frittoli > > > > > > <andrea.frittoli at gmail.com> wrote: > > > > I''m trying a Lustre + DRBD set-up, I would like to use DRBD with the > > > > following setup: > > > > > > > > on MDS: DRBD emulates an MDT on shared storage. From Lustre > > > > perspective one MDS is active, the other is passive > > > > on OSS: BRBD emulates two OST on shared storage for each OSS couple. > > > > > > > > >From Lustre perspective each OSS is active for one OST and passive for > > > > > > > > the other. > > > > > > > > I''m planning to use DRBD in active/passive mode, so that the storage > > > > is mounted only on the active server, and luster is mounted on top. > > > > I''m not sure how to sync the mount/umount of the DRBD partition and > > > > the mount of MDT/OST upon failover. > > > > > > > > The target setup shall have 2 MDS (1 couple) and 8 OST (4 couples), > > > > dedicate LANs for heartbeat and drbd. > > > > > > > > Do you have any details of your setup you may share about this? > > > > > > > > TIA! > > > > > > > > On Aug 12, 4:50 am, "Mag Gam" <magaw... at gmail.com> wrote: > > > >> Ha yes..I seen this before Sebastein. :-) > > > >> > > > >> I wanted to see if other people have tried it and their thoughts were. > > > >> > > > >> thats all > > > >> TIA > > > >> > > > >> On Mon, Aug 11, 2008 at 2:33 AM, S?bastien Buisson > > > >> > > > >> <sebastien.buis... at bull.net> wrote: > > > >> > Hello, > > > >> > > > > >> > I ran some tests with DRBD and Lustre a few months ago (including in > > > >> > async mode). You can find my modest findings here on the Lustre wiki > > > >> > : http://wiki.lustre.org/index.php?title=Drbd_And_Lustre > > > >> > > > > >> > Cheers, > > > >> > Sebastien. > > > >> > > > > >> > Mag Gam a ?crit : > > > >> >> Has anyone been using DRBD and Lustre in async mode? I was curious > > > >> >> what type of speeds you were getting and also what network are you > > > >> >> using? > > > >> >> > > > >> >> TIA > > > >> >> _______________________________________________ > > > >> >> Lustre-discuss mailing list > > > >> >> Lustre-disc... at lists.lustre.org > > > >> >>http://lists.lustre.org/mailman/listinfo/lustre-discuss > > > >> > > > >> _______________________________________________ > > > >> Lustre-discuss mailing list > > > >> Lustre-disc... at lists.lustre.orghttp://lists.lustre.org/mailman/listinf > > > >>o/lustre-discuss > > > > > > > > _______________________________________________ > > > > Lustre-discuss mailing list > > > > Lustre-discuss at lists.lustre.org > > > > http://lists.lustre.org/mailman/listinfo/lustre-discuss > > > > > > _______________________________________________ > > > Lustre-discuss mailing list > > > Lustre-discuss at lists.lustre.org > > > http://lists.lustre.org/mailman/listinfo/lustre-discuss > > > > Cheers, Andreas > > -- > > Andreas Dilger > > Sr. Staff Engineer, Lustre Group > > Sun Microsystems of Canada, Inc. > > > > _______________________________________________ > > Lustre-discuss mailing list > > Lustre-discuss at lists.lustre.org > > http://lists.lustre.org/mailman/listinfo/lustre-discuss > > > > -- > ----------------------------------------------------------------------- > Dipl.-Ing. Heiko Schr?ter > Institute of Environmental Physics (IUP) ? ?phone: ++49-(0)421-218-4080 > Institute of Remote Sensing (IFE) ? ? ? ? ? fax: ? ++49-(0)421-218-4555 > University of Bremen (FB1) > P.O. Box 330440 ? ? ? ? ? ? ? email: ?schroete at iup.physik.uni-bremen.de > Otto-Hahn-Allee 1 ? ? ? ? ? > 28359 Bremen ? ? ? ? ? ? ? ? > Germany > -----------------------------------------------------------------------Cheers, Andreas -- Andreas Dilger Sr. Staff Engineer, Lustre Group Sun Microsystems of Canada, Inc.
Heiko: I am interested in the doc too. Its worth while to update the Wiki On Tue, Sep 23, 2008 at 4:57 AM, Andreas Dilger <adilger at sun.com> wrote:> On Sep 22, 2008 11:19 +0200, Heiko Schroeter wrote: >> We are using a setup with the following spec: >> >> mds1 and mds2: >> 2 SATA Disks for MDS inside running raid0 with mdam tools. >> Above this drbd for network raid0 and >> Above that HA for failover. >> >> Besides that stonith is running inside HA for a real kill of the other >> node in case of trouble. >> >> Works good and reliable. We tested this real hard. >> >> If it is of general interest i could put down some notes how we did it but it >> will take some days. >> (I have do do it anyway for our docs ...) >> So please let me know if somebody is interested in this. > > It would definitely be useful to update (at least) the Lustre DRBD wiki > page to indicate you are using this successfully, and any configuration > DRBD options you are using. Similarly, if the Lustre manual is missing > any information (or possibly a specific example) of how to use HA for > Lustre that would also be useful. > >> > On Aug 30, 2008 16:35 -0400, Mag Gam wrote: >> > > Sorry Andrea, I would like to know this too. Hopefully someone here >> > > has done this before. Its worth a wiki >> > >> > Common case is use of Linux-HA to manage primary/backup for each OST/MDT. >> > Since Lustre 1.6+ uses "mount" and "unmount" to start/stop Lustre services >> > this can be set up relatively easily with Linux-HA. There is likely even >> > something in the Lustre manual. >> > >> > > On Thu, Aug 14, 2008 at 3:05 AM, Andrea Frittoli >> > > >> > > <andrea.frittoli at gmail.com> wrote: >> > > > I''m trying a Lustre + DRBD set-up, I would like to use DRBD with the >> > > > following setup: >> > > > >> > > > on MDS: DRBD emulates an MDT on shared storage. From Lustre >> > > > perspective one MDS is active, the other is passive >> > > > on OSS: BRBD emulates two OST on shared storage for each OSS couple. >> > > > >> > > > >From Lustre perspective each OSS is active for one OST and passive for >> > > > >> > > > the other. >> > > > >> > > > I''m planning to use DRBD in active/passive mode, so that the storage >> > > > is mounted only on the active server, and luster is mounted on top. >> > > > I''m not sure how to sync the mount/umount of the DRBD partition and >> > > > the mount of MDT/OST upon failover. >> > > > >> > > > The target setup shall have 2 MDS (1 couple) and 8 OST (4 couples), >> > > > dedicate LANs for heartbeat and drbd. >> > > > >> > > > Do you have any details of your setup you may share about this? >> > > > >> > > > TIA! >> > > > >> > > > On Aug 12, 4:50 am, "Mag Gam" <magaw... at gmail.com> wrote: >> > > >> Ha yes..I seen this before Sebastein. :-) >> > > >> >> > > >> I wanted to see if other people have tried it and their thoughts were. >> > > >> >> > > >> thats all >> > > >> TIA >> > > >> >> > > >> On Mon, Aug 11, 2008 at 2:33 AM, S?bastien Buisson >> > > >> >> > > >> <sebastien.buis... at bull.net> wrote: >> > > >> > Hello, >> > > >> > >> > > >> > I ran some tests with DRBD and Lustre a few months ago (including in >> > > >> > async mode). You can find my modest findings here on the Lustre wiki >> > > >> > : http://wiki.lustre.org/index.php?title=Drbd_And_Lustre >> > > >> > >> > > >> > Cheers, >> > > >> > Sebastien. >> > > >> > >> > > >> > Mag Gam a ?crit : >> > > >> >> Has anyone been using DRBD and Lustre in async mode? I was curious >> > > >> >> what type of speeds you were getting and also what network are you >> > > >> >> using? >> > > >> >> >> > > >> >> TIA >> > > >> >> _______________________________________________ >> > > >> >> Lustre-discuss mailing list >> > > >> >> Lustre-disc... at lists.lustre.org >> > > >> >>http://lists.lustre.org/mailman/listinfo/lustre-discuss >> > > >> >> > > >> _______________________________________________ >> > > >> Lustre-discuss mailing list >> > > >> Lustre-disc... at lists.lustre.orghttp://lists.lustre.org/mailman/listinf >> > > >>o/lustre-discuss >> > > > >> > > > _______________________________________________ >> > > > Lustre-discuss mailing list >> > > > Lustre-discuss at lists.lustre.org >> > > > http://lists.lustre.org/mailman/listinfo/lustre-discuss >> > > >> > > _______________________________________________ >> > > Lustre-discuss mailing list >> > > Lustre-discuss at lists.lustre.org >> > > http://lists.lustre.org/mailman/listinfo/lustre-discuss >> > >> > Cheers, Andreas >> > -- >> > Andreas Dilger >> > Sr. Staff Engineer, Lustre Group >> > Sun Microsystems of Canada, Inc. >> > >> > _______________________________________________ >> > Lustre-discuss mailing list >> > Lustre-discuss at lists.lustre.org >> > http://lists.lustre.org/mailman/listinfo/lustre-discuss >> >> >> >> -- >> ----------------------------------------------------------------------- >> Dipl.-Ing. Heiko Schr?ter >> Institute of Environmental Physics (IUP) phone: ++49-(0)421-218-4080 >> Institute of Remote Sensing (IFE) fax: ++49-(0)421-218-4555 >> University of Bremen (FB1) >> P.O. Box 330440 email: schroete at iup.physik.uni-bremen.de >> Otto-Hahn-Allee 1 >> 28359 Bremen >> Germany >> ----------------------------------------------------------------------- > > Cheers, Andreas > -- > Andreas Dilger > Sr. Staff Engineer, Lustre Group > Sun Microsystems of Canada, Inc. > >