Re: [zfs-discuss] One dataset per user?
- Original Message - > On Jun 20, 2010, at 11:55, Roy Sigurd Karlsbakk wrote: > > > There will also be a few common areas for each department and > > perhaps a backup area. > > The back up area should be on a different set of disks. > > IMHO, a back up isn't a back up unless it is an /independent/ copy of > the data. The copy can be made via ZFS send/recv, tar, rsync, Legato/ > NetBackup, etc., but it needs to be on independent media. Otherwise, > if the original copy goes, so does the "backup". I think you misunderstand me here. The backup area will be a storage area for Ahsay (see http://www.ahsay.com/ ) for client and application (Oracle, Sybase, Exchange etc). All datasets will be copied to a secondary node either with ZFS Send/receive or (more probably) NexentaStore HA Cluster ( http://kurl.no/KzHU ). > > I have read people are having problems with lengthy boot times with > > lots of datasets. We're planning to do extensive snapshotting on > > this system, so there might be close to a hundred snapshots per > > dataset, perhaps more. With 200 users and perhaps 10-20 shared > > department datasets, the number of filesystems, snapshots included, > > will be around 20k or more. > > You may also want to consider breaking things up into different pools > as well. There seems to be an implicit assumption in this conversation > that everything will be in one pool, and that may not be the best > course of action. > > Perhaps one pool for users' homedirs, and another for the departmental > stuff? Or perhaps even two different pools for homedirs, with users > 'randomly' distributed between the two (though definitely don't do > something like alphabetical (it'll be non-even) or departmental > (people transfer) distribution). > > This could add a bit of overhead, but I don't think have 2 or 3 pools > would be much more of a big deal than one. So far the plan is to keep it in one pool for design and administration simplicity. Why would you want to split up (net) 40TB into more pools? Seems to me that'll mess up things a bit, having to split up SSDs for use on different pools, loosing the flexibility of a common pool etc. Why? Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
> Btw, what did you plan to use as L2ARC/slog? I was thinking of using four Crucial RealSSD 256MB SSDs with a small RAID1+0 for SLOG and the rest for L2ARC. The system will be mainly used for reads, so I don't think the SLOG needs will be too tough. If you have another suggestion, please tell :) Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. -- Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
On Jun 21, 2010, at 05:00, Roy Sigurd Karlsbakk wrote: So far the plan is to keep it in one pool for design and administration simplicity. Why would you want to split up (net) 40TB into more pools? Seems to me that'll mess up things a bit, having to split up SSDs for use on different pools, loosing the flexibility of a common pool etc. Why? If different groups or areas have different I/O characteristics for one. If in one case (users) you want responsiveness, you could go with striped-mirrors. However, if departments have lots of data, it may be worthwhile to put it on a RAID-Z pool for better storage efficiency. Just a thought. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
- Original Message - > On Jun 21, 2010, at 05:00, Roy Sigurd Karlsbakk wrote: > > > So far the plan is to keep it in one pool for design and > > administration simplicity. Why would you want to split up (net) 40TB > > into more pools? Seems to me that'll mess up things a bit, having to > > split up SSDs for use on different pools, loosing the flexibility of > > a common pool etc. Why? > > If different groups or areas have different I/O characteristics for > one. If in one case (users) you want responsiveness, you could go with > striped-mirrors. However, if departments have lots of data, it may be > worthwhile to put it on a RAID-Z pool for better storage efficiency. We have considered RAID-1+0 and concluded with no current needs for this, as of now. Close to 1TB SSD cache will also help to boost read speeds, so I think it will be sufficient, at least for now. About different I/O characteristics in different groups/areas, this is not something we have data on for now. Do you know a good way to check this? The data is located on two different zpools (sol10) today. Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
David Magda wrote: > On Jun 21, 2010, at 05:00, Roy Sigurd Karlsbakk wrote: > >> So far the plan is to keep it in one pool for design and >> administration simplicity. Why would you want to split up (net) 40TB >> into more pools? Seems to me that'll mess up things a bit, having to >> split up SSDs for use on different pools, loosing the flexibility of a >> common pool etc. Why? > > If different groups or areas have different I/O characteristics for one. > If in one case (users) you want responsiveness, you could go with > striped-mirrors. However, if departments have lots of data, it may be > worthwhile to put it on a RAID-Z pool for better storage efficiency. > Especially if the characteristics are different I find it a good idea to mix all on one set of spindles. This way you have lots of spindles for fast access and lots of space for the sake of space. If you devide the available spindles in two sets you will have much fewer spindles available for the responsiveness goal. I don't think taking them into a mirror can compensate that. --Arne ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
> From: James C. McPherson [mailto:j...@opensolaris.org] > > On the build systems that I maintain inside the firewall, > we mandate one filesystem per user, which is a very great > boon for system administration. What's the reasoning behind it? > My management scripts are > considerably faster running when I don't have to traverse > whole directory trees (ala ufs). That's a good reason. Why would you have to traverse whole directory structures if you had a single zfs filesystem in a single zpool, instead of many zfs filesystems in a single zpool? ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
> From: zfs-discuss-boun...@opensolaris.org [mailto:zfs-discuss- > boun...@opensolaris.org] On Behalf Of Roy Sigurd Karlsbakk > > Close to 1TB SSD cache will also help to boost read > speeds, Remember, this will not boost large sequential reads. (Could possibly maybe even hurt it.) This will only boost random reads. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
On 21/06/10 10:38 PM, Edward Ned Harvey wrote: From: James C. McPherson [mailto:j...@opensolaris.org] On the build systems that I maintain inside the firewall, we mandate one filesystem per user, which is a very great boon for system administration. What's the reasoning behind it? Politeness, basically. Every user on these machines is expected to make and use their own disk-space sandpit - having their own dataset makes that work nicely. My management scripts are considerably faster running when I don't have to traverse whole directory trees (ala ufs). That's a good reason. Why would you have to traverse whole > directory structures if you had a single zfs filesystem in > a single zpool, instead of many zfs filesystems in a single zpool? For instance, if I've got users a, b and c, who have their own datasets, and users z, y and x who do not: df -h /builds/[abczyx] will show me disk usage of /builds for z, y and x, but /builds/a /builds/b /builds/c for the ones who do have their own dataset. So when I'm trying to figure out who I need to yell at because they're using more than our acceptable limit (30Gb), I have to run "du -s /builds/[zyx]". And that takes time. Lots of time. Especially on these systems which are in huge demand from people all over Solaris-land. James C. McPherson -- Senior Software Engineer, Solaris Oracle http://www.jmcp.homeunix.com/blog ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
On 21/06/2010 13:59, James C. McPherson wrote: On 21/06/10 10:38 PM, Edward Ned Harvey wrote: From: James C. McPherson [mailto:j...@opensolaris.org] On the build systems that I maintain inside the firewall, we mandate one filesystem per user, which is a very great boon for system administration. What's the reasoning behind it? Politeness, basically. Every user on these machines is expected to make and use their own disk-space sandpit - having their own dataset makes that work nicely. Plus it allows delegation of snapshot/clone/send/recv to the users on certain systems. -- Darren J Moffat ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
On Mon, Jun 21, 2010 at 8:59 AM, James C. McPherson wrote: [...] > So when I'm > trying to figure out who I need to yell at because they're > using more than our acceptable limit (30Gb), I have to run > "du -s /builds/[zyx]". And that takes time. Lots of time. [...] Why not just use quotas? fpsm ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
On Mon, 21 Jun 2010, Edward Ned Harvey wrote: From: zfs-discuss-boun...@opensolaris.org [mailto:zfs-discuss- boun...@opensolaris.org] On Behalf Of Roy Sigurd Karlsbakk Close to 1TB SSD cache will also help to boost read speeds, Remember, this will not boost large sequential reads. (Could possibly maybe even hurt it.) This will only boost random reads. Or more accurately, it boosts repeated reads. It won't help much in the case where data is accessed only once. It is basically a poor-man's substitute for caching data in RAM. The RAM is at least 20X faster so the system should be stuffed with RAM first as long as the budget can afford it. Luckily, most servers experience mostly repeated reads. Bob -- Bob Friesenhahn bfrie...@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer,http://www.GraphicsMagick.org/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
On Mon, 21 Jun 2010, Arne Jansen wrote: Especially if the characteristics are different I find it a good idea to mix all on one set of spindles. This way you have lots of spindles for fast access and lots of space for the sake of space. If you devide the available spindles in two sets you will have much fewer spindles available for the responsiveness goal. I don't think taking them into a mirror can compensate that. This is something that I can agree with. Total vdevs in the pool is what primarily determines its responsiveness. while using the same number of devices, splitting the pool might not result in more vdevs in either pool. Mirrors do double the amount of readable devices but the side selected to read is random so the actual read performance improvement is perhaps on the order of 50% rather than 100%. Raidz does steal IOPS so smaller raidz vdevs will help and result in more vdevs in the pool. Bob -- Bob Friesenhahn bfrie...@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer,http://www.GraphicsMagick.org/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] Many checksum errors during resilver.
I've decided to upgrade my home server capacity by replacing the disks in one of my mirror vdevs. The procedure appeared to work out, but during resilver, a couple million checksum errors were logged on the new device. I've read through quite a bit of the archive and searched around a bit, but can not find anything definitive to ease my mind on whether to proceed. SunOS deepthought 5.10 Generic_142901-13 i86pc i386 i86pc pool: tank state: DEGRADED status: One or more devices is currently being resilvered. The pool will continue to function, possibly in a degraded state. action: Wait for the resilver to complete. scrub: resilver in progress for 0h0m, 0.00% done, 691h28m to go config: NAME STATE READ WRITE CKSUM tank DEGRADED 0 0 0 mirror DEGRADED 0 0 0 replacing DEGRADED 215 0 0 c1t6d0s0/o FAULTED 0 0 0 corrupted data c1t6d0 ONLINE 0 0 215 3.73M resilvered c1t2d0ONLINE 0 0 0 mirror ONLINE 0 0 0 c1t1d0ONLINE 0 0 0 c1t5d0ONLINE 0 0 0 mirror ONLINE 0 0 0 c1t0d0ONLINE 0 0 0 c1t4d0ONLINE 0 0 0 logs c8t1d0p1ONLINE 0 0 0 cache c2t1d0p2ONLINE 0 0 0 During the resilver, the cache device and the zil were both removed for errors (1-2k each). (Despite the c2/c8 discrepancy, they are partitions on the same OCZvertexII device.) # zpool status -xv tank pool: tank state: DEGRADED status: One or more devices has experienced an unrecoverable error. An attempt was made to correct the error. Applications are unaffected. action: Determine if the device needs to be replaced, and clear the errors using 'zpool clear' or replace the device with 'zpool replace'. see: http://www.sun.com/msg/ZFS-8000-9P scrub: resilver completed after 9h20m with 0 errors on Sat Jun 19 22:07:27 2010 config: NAMESTATE READ WRITE CKSUM tankDEGRADED 0 0 0 mirrorONLINE 0 0 0 c1t6d0 ONLINE 0 0 2.69M 539G resilvered c1t2d0 ONLINE 0 0 0 mirrorONLINE 0 0 0 c1t1d0 ONLINE 0 0 0 c1t5d0 ONLINE 0 0 0 mirrorONLINE 0 0 0 c1t0d0 ONLINE 0 0 0 c1t4d0 ONLINE 0 0 0 logs c8t1d0p1 REMOVED 0 0 0 cache c2t1d0p2 REMOVED 0 0 0 I cleared the errors (about 5000/GB resilvered!), removed the cache device, and replaced the zil partition with the whole device. After 3 pool scrubs with no errors, I want to check with someone else that it appears okay to replace the second drive in this mirror vdev. The one thing I have not tried is a large file transfer to the server, as I am also dealing with an NFS mount problem which popped up suspiciously close to my most recent patch update. # zpool status -v tank pool: tank state: ONLINE scrub: scrub completed after 3h26m with 0 errors on Mon Jun 21 01:45:00 2010 config: NAMESTATE READ WRITE CKSUM tankONLINE 0 0 0 mirrorONLINE 0 0 0 c1t6d0 ONLINE 0 0 0 c1t2d0 ONLINE 0 0 0 mirrorONLINE 0 0 0 c1t1d0 ONLINE 0 0 0 c1t5d0 ONLINE 0 0 0 mirrorONLINE 0 0 0 c1t0d0 ONLINE 0 0 0 c1t4d0 ONLINE 0 0 0 logs c0t0d0ONLINE 0 0 0 errors: No known data errors /var/adm/messages is positively over-run with these triplets/quadruplets, not all of which end which end up as "fatal" type. Jun 19 21:43:19 deepthought scsi: [ID 107833 kern.warning] WARNING: /p...@0,0/pci1043,8...@7/d...@1,0 (sd14): Jun 19 21:43:19 deepthought Error for Command: write(10) Error Level: Retryable Jun 19 21:43:19 deepthought scsi: [ID 107833 kern.notice] Requested Block: 26721062 Error Block: 26721062 Jun 19 21:43:19 deepthought scsi: [ID 107833 kern.notice] Vendor: ATA Serial Number: Jun 19 21:43:19 deepthought scsi: [ID 107833 kern.notice] Sense Key: Aborted Command Jun 19 21:43:19 deepthought scsi: [ID 107833 kern.notice] ASC: 0x8 (LUN communication failure), ASCQ: 0x0, FRU: 0x0 Jun 19 21:43:19 deepthought scsi: [ID 107833 kern.warning] WARNING: /p...@0,0/pci1043,8.
Re: [zfs-discuss] Many checksum errors during resilver.
Hi Justin, This looks like an older Solaris 10 release. If so, this looks like a zpool status display bug, where it looks like the checksum errors are occurring on the replacement device, but they are not. I would review the steps described in the hardware section of the ZFS troubleshooting wiki to confirm that the new disk is working as expected: http://www.solarisinternals.com/wiki/index.php/ZFS_Troubleshooting_Guide Then, follow steps in the Notify FMA That Device Replacement is Complete section to reset FMA. Then, start monitoring the replacement device with fmdump to see if any new activity occurs on this device. Thanks, Cindy On 06/21/10 10:21, Justin Daniel Meyer wrote: I've decided to upgrade my home server capacity by replacing the disks in one of my mirror vdevs. The procedure appeared to work out, but during resilver, a couple million checksum errors were logged on the new device. I've read through quite a bit of the archive and searched around a bit, but can not find anything definitive to ease my mind on whether to proceed. SunOS deepthought 5.10 Generic_142901-13 i86pc i386 i86pc pool: tank state: DEGRADED status: One or more devices is currently being resilvered. The pool will continue to function, possibly in a degraded state. action: Wait for the resilver to complete. scrub: resilver in progress for 0h0m, 0.00% done, 691h28m to go config: NAME STATE READ WRITE CKSUM tank DEGRADED 0 0 0 mirror DEGRADED 0 0 0 replacing DEGRADED 215 0 0 c1t6d0s0/o FAULTED 0 0 0 corrupted data c1t6d0 ONLINE 0 0 215 3.73M resilvered c1t2d0ONLINE 0 0 0 mirror ONLINE 0 0 0 c1t1d0ONLINE 0 0 0 c1t5d0ONLINE 0 0 0 mirror ONLINE 0 0 0 c1t0d0ONLINE 0 0 0 c1t4d0ONLINE 0 0 0 logs c8t1d0p1ONLINE 0 0 0 cache c2t1d0p2ONLINE 0 0 0 During the resilver, the cache device and the zil were both removed for errors (1-2k each). (Despite the c2/c8 discrepancy, they are partitions on the same OCZvertexII device.) # zpool status -xv tank pool: tank state: DEGRADED status: One or more devices has experienced an unrecoverable error. An attempt was made to correct the error. Applications are unaffected. action: Determine if the device needs to be replaced, and clear the errors using 'zpool clear' or replace the device with 'zpool replace'. see: http://www.sun.com/msg/ZFS-8000-9P scrub: resilver completed after 9h20m with 0 errors on Sat Jun 19 22:07:27 2010 config: NAMESTATE READ WRITE CKSUM tankDEGRADED 0 0 0 mirrorONLINE 0 0 0 c1t6d0 ONLINE 0 0 2.69M 539G resilvered c1t2d0 ONLINE 0 0 0 mirrorONLINE 0 0 0 c1t1d0 ONLINE 0 0 0 c1t5d0 ONLINE 0 0 0 mirrorONLINE 0 0 0 c1t0d0 ONLINE 0 0 0 c1t4d0 ONLINE 0 0 0 logs c8t1d0p1 REMOVED 0 0 0 cache c2t1d0p2 REMOVED 0 0 0 I cleared the errors (about 5000/GB resilvered!), removed the cache device, and replaced the zil partition with the whole device. After 3 pool scrubs with no errors, I want to check with someone else that it appears okay to replace the second drive in this mirror vdev. The one thing I have not tried is a large file transfer to the server, as I am also dealing with an NFS mount problem which popped up suspiciously close to my most recent patch update. # zpool status -v tank pool: tank state: ONLINE scrub: scrub completed after 3h26m with 0 errors on Mon Jun 21 01:45:00 2010 config: NAMESTATE READ WRITE CKSUM tankONLINE 0 0 0 mirrorONLINE 0 0 0 c1t6d0 ONLINE 0 0 0 c1t2d0 ONLINE 0 0 0 mirrorONLINE 0 0 0 c1t1d0 ONLINE 0 0 0 c1t5d0 ONLINE 0 0 0 mirrorONLINE 0 0 0 c1t0d0 ONLINE 0 0 0 c1t4d0 ONLINE 0 0 0 logs c0t0d0ONLINE 0 0 0 errors: No known data errors /var/adm/messages is positively over-run with these triplets/quadruplets, not all of which end which end up as "fatal" type. Jun 19 21:43:19 deepthought scsi: [ID 107833 kern.warning] WARNING: /p
Re: [zfs-discuss] One dataset per user?
- Original Message - > > From: zfs-discuss-boun...@opensolaris.org [mailto:zfs-discuss- > > boun...@opensolaris.org] On Behalf Of Roy Sigurd Karlsbakk > > > > Close to 1TB SSD cache will also help to boost read > > speeds, > > Remember, this will not boost large sequential reads. (Could possibly > maybe even hurt it.) This will only boost random reads. As far as I can see, we mostly have random reads, and not too much large sequential I/O, so this is what I'm looking for. Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] SLOG striping?
Hi all I plan to setup a new system with four Crucial RealSSD 256MB SSDs for both SLOG and L2ARC. The plan is to use four small slices for the SLOG, striping two mirrors. I have seen questions in here about the theoretical benefit of doing this, but I haven't seen any answers, just some doubt about the effect. Does anyone know if this will help gaining performance? Or will it be bad? Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] VXFS to ZFS Quota
- Original Message - > Hi > Currently I have 400+ users with quota set to 500MB limit. Currently > the file system is using veritas file system. > > I am planning to migrate all these home directory to a new server with > ZFS. How can i migrate the quotas. > > I can create 400+ file system for each users, > but will this affect my system performance during the system boot up? > Is this recommanded or any alternate is available for this issue. There's a lot of info in a thread I started quite recently "One dataset per user?". Take a look in there. Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] SLOG striping?
On Mon, 21 Jun 2010, Roy Sigurd Karlsbakk wrote: I plan to setup a new system with four Crucial RealSSD 256MB SSDs for both SLOG and L2ARC. The plan is to use four small slices for the SLOG, striping two mirrors. I have seen questions in here about the theoretical benefit of doing this, but I haven't seen any answers, just some doubt about the effect. Does anyone know if this will help gaining performance? Or will it be bad? I don't know anything about these SSDs but if they might lose the last record or two then striping would be bad since it would cause more writes to be lost. Data would only be recovered up to the first point of loss, even though some newer data is still available on a different SSD. Bob -- Bob Friesenhahn bfrie...@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer,http://www.GraphicsMagick.org/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] SLOG striping?
Roy Sigurd Karlsbakk wrote: Hi all I plan to setup a new system with four Crucial RealSSD 256MB SSDs for both SLOG and L2ARC. The plan is to use four small slices for the SLOG, striping two mirrors. I have seen questions in here about the theoretical benefit of doing this, but I haven't seen any answers, just some doubt about the effect. Does anyone know if this will help gaining performance? Or will it be bad? I'm planning to do something similar, though I only want to install 2 devices. Some thoughts I had so far: - mirroring l2arc won't gain anything, as it doesn't contain any information that cannot be rebuilt if a device is lost. Further, if a device is lost, the system just uses the remaining devices. So I wouldn't waste any space mirroring l2arc, I'll just stripe them. - the purpose of a zil device is to reduce latency. Throughput is probably not an issue, especially if you configure your pool so that large writes go to the main pool. As 2 devices don't have a lower latency than one, I see no real point in striping slog devices. - For slog you need SSD with supercap which are significantly more expensive than without. I'll try the OCZ Vertex 2 Pro in the next few days and can give a report how it performs. For L2ARC cheap MLC SSDs will do. So if I had the chance to buy 4 devices, I'd probably buy 2 different sets. 2 cheap large L2ARC devices, 2 fast supercapped small ones. The 2 slog devices would go into a mirror, the L2ARC devices in a stripe. I'd probably take the remaining space of the slog devices into the stripe, too, though this might affect write performance. Just me thoughts... -- Arne Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] SLOG striping?
> - mirroring l2arc won't gain anything, as it doesn't contain any > information that cannot be rebuilt if a device is lost. Further, if a > device is lost, > the system just uses the remaining devices. So I wouldn't waste any > space mirroring l2arc, I'll just stripe them. I don't plan to attempt to mirror L2ARC. Even the docs say it's unsupported, so no point of that. > - the purpose of a zil device is to reduce latency. Throughput is > probably not > an issue, especially if you configure your pool so that large writes > go to > the main pool. As 2 devices don't have a lower latency than one, I see > no real point in striping slog devices. My guess was a striped setup could give me 2xIOPS if SLOG is designed to do this. Any idea if it is? > - For slog you need SSD with supercap which are significantly more > expensive than without. I'll try the OCZ Vertex 2 Pro in the next few > days and can > give a report how it performs. For L2ARC cheap MLC SSDs will do. hm... Last I checked those OCZ Vertexes were on the both large and expensive side. What do you pay for a couple of small ones? We'll be installing 48 gigs of memory in this box, but I doubt we'll need more than 4GB SLOG in terms of traffic. > So if I had the chance to buy 4 devices, I'd probably buy 2 different > sets. 2 cheap large L2ARC devices, 2 fast supercapped small ones. The > 2 slog devices > would go into a mirror, the L2ARC devices in a stripe. I'd probably > take the > remaining space of the slog devices into the stripe, too, though this > might affect write performance. Any idea if something like a small, decently priced, supercapped SLC SSD exist? Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 97542685 r...@karlsbakk.net http://blogg.karlsbakk.net/ -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med fremmed opprinnelse. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] SLOG striping?
On Mon, Jun 21, 2010 at 11:24 AM, Roy Sigurd Karlsbakk wrote: > Any idea if something like a small, decently priced, supercapped SLC SSD > exist? The new OCZ Deneva drives (or others based on the SF-1500) should work well, but I don't know if there's pricing available yet. -B -- Brandon High : bh...@freaks.com ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] does sharing an SSD as slog and l2arc reduces its life span?
On 6/19/10 3:56 AM, Arne Jansen wrote: while thinking about using the OCZ Vertex 2 Pro SSD (which according to spec page has supercaps built in) as a shared slog and L2ARC device IMO it might be better to use the smallest (50GB, maybe overprovisioned down to ~20GB) Vertex 2 Pro as slog and a much cheaper SSD (X25-M) as L2ARC. But if 90% of the device are nearly statically allocated, the devices possibilities for wear-leveling are very restricted. If the ZIL is heavily used, the same 10% of the device get written over and over again, reducing the life span by 90%. As Bob Friesenhahn said, you're assuming dynamic wear leveling but modern SSDs also use static wear leveling, so this problem doesn't exist. (Note that in this context the terms "dynamic" and "static" may not mean what you think they mean.) Wes Felter ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] SLOG striping?
Roy Sigurd Karlsbakk wrote: - mirroring l2arc won't gain anything, as it doesn't contain any information that cannot be rebuilt if a device is lost. Further, if a device is lost, the system just uses the remaining devices. So I wouldn't waste any space mirroring l2arc, I'll just stripe them. I don't plan to attempt to mirror L2ARC. Even the docs say it's unsupported, so no point of that. Oops, makes sense ;) - For slog you need SSD with supercap which are significantly more expensive than without. I'll try the OCZ Vertex 2 Pro in the next few days and can give a report how it performs. For L2ARC cheap MLC SSDs will do. hm... Last I checked those OCZ Vertexes were on the both large and expensive side. What do you pay for a couple of small ones? We'll be installing 48 gigs of memory in this box, but I doubt we'll need more than 4GB SLOG in terms of traffic. 50GB for 400 Euro. They are MLC flash, but, as someone in a different thread pointed out, they have 3 years warranty ;) My hope is that they last long enough until cheaper options become available. My major concern is that if I buy two identical models they'll break the same day. This is not purely hypothetical. If they internally just count the write cycles and trigger a SMART fail if a certain threshold is reached, exactly this will happen. -- Arne ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] Seriously degraded SAS multipathing performance
I'm seeing seriously degraded performance with round-robin SAS multipathing. I'm hoping you guys can help me achieve full throughput across both paths. My System Config: OpenSolaris snv_134 2 x E5520 2.4 GHz Xeon Quad-Core Processors 48 GB RAM 2 x LSI SAS 9200-8e (eight-port external 6Gb/s SATA and SAS PCIe 2.0 HBA) 1 X Mellanox 40 Gb/s dual port card PCIe 2.0 1 x JBOD: Supermicro SC846E2-R900B (Dual LSI SASX36 3Gb/s Expander Backplane, 24 Hot Swap drives) 22 x Seagate Constellation ES SAS drives Performance I'm seeing with Multipathing Enabled (driver: mpt_sas): With only one of the two paths connected: 1 drive connected: 137 MB/s sustained write, asvc_t: 8 ms 22 drives connected: 1.1 GB/s sustained write, asvc_t: 12 ms With two paths connected, round-robin enabled: 1 drive connected: 13.7 MB/s sustained write, asvc_t: 25 ms 22 drives: 235 MB/s sustained write, asvc_t: 99 ms With two paths connected, round-robin disabled, pin half the drives to one path (path A), the other half of the drives to the other path (path B): 22 drives: 2.2 GB/s sustained write (1.1 GB/s per path), asvc_t: 12 ms Multipath support info: mpathadm show mpath-support libmpscsi_vhci.so mpath-support: libmpscsi_vhci.so Vendor: Sun Microsystems Driver Name: scsi_vhci Default Load Balance: round-robin Supported Load Balance Types: round-robin logical-block Allows To Activate Target Port Group Access: yes Allows Path Override: no Supported Auto Failback Config: 1 Auto Failback: on Failback Polling Rate (current/max): 0/0 Supported Auto Probing Config: 0 Auto Probing: NA Probing Polling Rate (current/max): NA/NA Supported Devices: Do I have to add an entry to this section of /kernel/drv/scsi_vhci.conf (if so, how do i find the information to add)?: # # For a device that has a GUID, discovered on a pHCI with mpxio enabled, vHCI access also depends on one of the scsi_vhci failover modules accepting the device. The default way this occurs is by a failover module's "probe" implementation (sfo_device_probe) indicating the device is supported under scsi_vhci. To override this default probe-oriented configuration in order to # #1) establish support for a device not currently accepted under scsi_vhci # # or 2) override the module selected by "probe" # # or 3) disable scsi_vhci support for a device # # you can add a 'scsi-vhci-failover-override' tuple, as documented in # scsi_get_device_type_string(9F). For each tuple, the first part provides basic device identity information (vid/pid) and the second part selects the failover module by "failover-module-name". If you want to disable scsi_vhci support for a device, use the special failover-module-name "NONE". # Currently, for each failover-module-name in 'scsi-vhci-failover-override' (except "NONE") there needs to be a # "misc/scsi_vhci/scsi_vhci_" in 'ddi-forceload' above. # # " 11" # "012345670123456789012345", "failover-module-name" or "NONE" # "|-VID--||-PID--|", # scsi-vhci-failover-override = # "STK FLEXLINE 400", "f_asym_lsi", # "SUN T4", "f_tpgs", # "CME XIRTEMMYS","NONE"; # #END: FAILOVER_MODULE_BLOCK (DO NOT MOVE OR DELETE). How can I get this working as expected (2.2 GB/s round-robin load-balanced across both paths)? Thanks in advance for your assistance! Josh Simon ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] does sharing an SSD as slog and l2arc reduces its life span?
Wes Felter wrote: On 6/19/10 3:56 AM, Arne Jansen wrote: while thinking about using the OCZ Vertex 2 Pro SSD (which according to spec page has supercaps built in) as a shared slog and L2ARC device IMO it might be better to use the smallest (50GB, maybe overprovisioned down to ~20GB) Vertex 2 Pro as slog and a much cheaper SSD (X25-M) as L2ARC. No budget for this. Lucky if I can get the budget for the Vertex 2 Pro. But if this sharing works (thanks to static wear leveling) it should be sufficient to leave 10-20% space. As Bob Friesenhahn said, you're assuming dynamic wear leveling but modern SSDs also use static wear leveling, so this problem doesn't exist. (Note that in this context the terms "dynamic" and "static" may not mean what you think they mean.) Thanks for the term. Yes, this makes sense. -- Arne ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] zfs periodic writes on idle system [Re: Getting desktop to auto sleep]
> Why does zfs produce a batch of writes every 30 seconds on opensolaris b134 > (5 seconds on a post b142 kernel), when the system is idle? It was caused by b134 gnome-terminal. I had an iostat running in a gnome-terminal window, and the periodic iostat output is written to a temporary file by gnome-terminal. This kept the hdd busy. Older gnome-terminals (b111) didn't write terminal output to a disk file. Workaround is to use xterm instead of b134 gnome-terminal. for a command that periodically produces output -- This message posted from opensolaris.org ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] One dataset per user?
On 22/06/10 01:05 AM, Fredrich Maney wrote: On Mon, Jun 21, 2010 at 8:59 AM, James C. McPherson wrote: [...] So when I'm trying to figure out who I need to yell at because they're using more than our acceptable limit (30Gb), I have to run "du -s /builds/[zyx]". And that takes time. Lots of time. [...] Why not just use quotas? Quotas are not always appropriate. Also, given our usage model, and wanting to provide a service that gatelings can use to work on multiple changesets concurrently, we figure that telling people your limit is XGb, and we will publicly shame you if you exceed it, then go and remove old stuff for you is sufficiently hands-off. We're adults here, not children or kiddies with no regard for our fellow engineers. James C. McPherson -- Senior Software Engineer, Solaris Oracle http://www.jmcp.homeunix.com/blog ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] SLOG striping?
> From: zfs-discuss-boun...@opensolaris.org [mailto:zfs-discuss- > boun...@opensolaris.org] On Behalf Of Roy Sigurd Karlsbakk > > I plan to setup a new system with four Crucial RealSSD 256MB SSDs for > both SLOG and L2ARC. The plan is to use four small slices for the SLOG, > striping two mirrors. I have seen questions in here about the > theoretical benefit of doing this, but I haven't seen any answers, just > some doubt about the effect. > > Does anyone know if this will help gaining performance? Or will it be > bad? log and cache devices don't stripe. You can add more than one, and the syntax is the same as if you were going to create a stripe in the main pool, but the end result is round-robin for log & cache devices. It's tough to say how much this will benefit performance, unless you try it. PS. I'm only repeating what I believe to have learned by older posts on this list. I didn't go read the code myself or anything like that, so I acknowledge some possibility that something I've said is wrong. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] SLOG striping?
On Jun 21, 2010, at 11:17 AM, Arne Jansen wrote: > Roy Sigurd Karlsbakk wrote: >> Hi all >> I plan to setup a new system with four Crucial RealSSD 256MB SSDs for both >> SLOG and L2ARC. The plan is to use four small slices for the SLOG, striping >> two mirrors. I have seen questions in here about the theoretical benefit of >> doing this, but I haven't seen any answers, just some doubt about the effect. >> Does anyone know if this will help gaining performance? Or will it be bad? > > I'm planning to do something similar, though I only want to install 2 devices. > Some thoughts I had so far: > > - mirroring l2arc won't gain anything, as it doesn't contain any information > that cannot be rebuilt if a device is lost. This is not properly stated. There is nothing in the L2ARC that is not also in the pool, so it is simply a cache. You are correct in that the L2ARC is not rebuilt, but you miss the reason why the rebuild is not necessary (or desired) > Further, if a device is lost, > the system just uses the remaining devices. So I wouldn't waste any space > mirroring l2arc, I'll just stripe them. Yes, this is the most economical solution. > - the purpose of a zil device is to reduce latency. The purpose of a separate device is to reduce latency for synchronous writes. > Throughput is probably not > an issue, especially if you configure your pool so that large writes go to > the main pool. As 2 devices don't have a lower latency than one, I see no > real point in striping slog devices. Striping separate log devices can help for high transaction rate environments or where the latency is constrained by bandwidth. > - For slog you need SSD with supercap which are significantly more expensive > than without. I'll try the OCZ Vertex 2 Pro in the next few days and can > give a report how it performs. For L2ARC cheap MLC SSDs will do. For a separate log, choose a device which honors cache flush commands. Nonvolatile caches are nice, but rare -- HDDs do act well as ZIL devices, but almost never have nonvolatile caches. -- richard -- Richard Elling rich...@nexenta.com +1-760-896-4422 ZFS and NexentaStor training, Rotterdam, July 13-15, 2010 http://nexenta-rotterdam.eventbrite.com/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] SLOG striping?
On Mon, 21 Jun 2010, Edward Ned Harvey wrote: log and cache devices don't stripe. You can add more than one, and The term 'stripe' has been so outrageously severely abused in this forum that it is impossible to know what someone is talking about when they use the term. Seemingly intelligent people continue to use wrong terminology because they think that protracting the confusion somehow helps new users. We are left with no useful definition of 'striping'. The slog does actually 'stripe' in some cases (depending on what 'stripe' means) if you study how it works in sufficient detail. At least that is what we have been told. The slog does not do micro-striping, nano-striping, pico-striping, or femto-striping (not even at the sub-bit level) but it does do mega-striping. Bob -- Bob Friesenhahn bfrie...@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer,http://www.GraphicsMagick.org/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss