[zfs-discuss] ZFS and Linux
Hi All ; What is the status of ZFS on linux and what are the kernel's supported? Regards Mertol http://www.sun.com/ http://www.sun.com/emrkt/sigs/6g_top.gif Mertol Ozyoney Storage Practice - Sales Manager Sun Microsystems, TR Istanbul TR Phone +902123352200 Mobile +905339310752 Fax +90212335 Email mailto:[EMAIL PROTECTED] [EMAIL PROTECTED] attachment: image001.gif___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Issue with simultaneous IO to lots of ZFS pools
Chris Siebenmann wrote: | Still, I'm curious -- why lots of pools? Administration would be | simpler with a single pool containing many filesystems. The short answer is that it is politically and administratively easier to use (at least) one pool per storage-buying group in our environment. I think the root cause of the issue is that multiple groups are buying physical rather than virtual storage yet it is all being attached to a single system. I will likely be a huge up hill battle but: if all the physical storage could be purchased by one group and a combination of ZFS reservations and quotas used on top level (eg one level down from the pool) datasets to allocate the virtual storage, and appropriate amounts charged to the groups, you could technical be able to use ZFS how it was intended with much fewer (hopefully 1 or 2) pools. -- Darren J Moffat ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] ZFS and Linux
What is the status of ZFS on linux and what are the kernel’s supported? There's sort of an experimental port to FUSE. Last I heard about it, it isn't exactly stable and the ARC's missing too, or at least gimped. There won't be in kernel ZFS due to license issues (CDDL vs. GPL). -mg ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] ZFS and Linux
Mario Goebbels wrote: What is the status of ZFS on linux and what are the kernel’s supported? There's sort of an experimental port to FUSE. Last I heard about it, it isn't exactly stable and the ARC's missing too, or at least gimped. There won't be in kernel ZFS due to license issues (CDDL vs. GPL). As I pointed out last time this discussion came up there are parts of the ZFS code base in GRUB already under the GPL. Also if ZFS can be implemented completely outside of the Linux kernel source tree as a plugin module then it falls into the same category of modules as proprietary binary device drivers. -- Darren J Moffat ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] ZFS and Linux
Also if ZFS can be implemented completely outside of the Linux kernel source tree as a plugin module then it falls into the same category of modules as proprietary binary device drivers. The Linux community has a strange attitude about proprietary drivers. Otherwise I wouldn't have to put up with the restricted driver manager and its antics on my laptop that runs Ubuntu (no Solaris until hard disk APM can be managed). Or read by proxy about Linus' (and his buddies) endless bickering about it. Also, they're still spreading FUD regarding these supposed layer violations. I wouldn't hold my hopes for now. -mg ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] ZFS and Linux
Mario Goebbels [EMAIL PROTECTED] wrote: What is the status of ZFS on linux and what are the kernel???s supported? There's sort of an experimental port to FUSE. Last I heard about it, it isn't exactly stable and the ARC's missing too, or at least gimped. There won't be in kernel ZFS due to license issues (CDDL vs. GPL). A license issue would would only exist if someone claimed that ZFS has been developed as a part of Linux. But then these people would create a Copyright problem ;-) Jörg -- EMail:[EMAIL PROTECTED] (home) Jörg Schilling D-13353 Berlin [EMAIL PROTECTED](uni) [EMAIL PROTECTED] (work) Blog: http://schily.blogspot.com/ URL: http://cdrecord.berlios.de/old/private/ ftp://ftp.berlios.de/pub/schily ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Issue with simultaneous IO to lots of ZFS pools
Darren J Moffat [EMAIL PROTECTED] wrote: Chris Siebenmann wrote: | Still, I'm curious -- why lots of pools? Administration would be | simpler with a single pool containing many filesystems. The short answer is that it is politically and administratively easier to use (at least) one pool per storage-buying group in our environment. I think the root cause of the issue is that multiple groups are buying physical rather than virtual storage yet it is all being attached to a single system. I will likely be a huge up hill battle but: if all the physical storage could be purchased by one group and a combination of ZFS reservations and quotas used on top level (eg one level down from the pool) datasets to allocate the virtual storage, and appropriate amounts charged to the groups, you could technical be able to use ZFS how it was intended with much fewer (hopefully 1 or 2) pools. The scenario Chris describes is one I see repeatedly at customers buying SAN storage (as late as last month!) and is considered a best practice on the business side. We may want to make this issue and it's management visible, as people moving from SAN to ZFS are likely to trip over it. In particular, I'd like to see a blueprint or at least a wiki discussion by someone from the SAN world on how to map those kinds of purchases to ZFS pools, how few one wants to have, what happens when it goes wrong, and how to mitigate it (;-)) --dave ps: as always, having asked for something, I'm also volunteering to help provide it: I'm not a storage or ZFS guy, but I am an author, and will happily help my Smarter Colleagues[tm] to write it up. -- David Collier-Brown| Always do right. This will gratify Sun Microsystems, Toronto | some people and astonish the rest [EMAIL PROTECTED] | -- Mark Twain (905) 943-1983, cell: (647) 833-9377, (800) 555-9786 x56583 bridge: (877) 385-4099 code: 506 9191# ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Issue with simultaneous IO to lots of ZFS pools
| I think the root cause of the issue is that multiple groups are buying | physical rather than virtual storage yet it is all being attached to a | single system. They're actually buying constant-sized chunks of virtual storage, which is provided through a pool of SAN-based disk space. This means that we're always going to have a certain number of logical pools of storage space to manage that are expanded in fixed-size chunks; the question is whether to manage them as separate ZFS pools or to aggregate them into fewer ZFS pools and then use quotas on sub-hierarchies. (With local storage you wouldn't have much choice; the physical disk size is not likely to map nicely into the constant-sized chunks you sell to people. With SAN storage you can pretty much make the 'disks' that Solaris sees map straight to the chunk size.) - cks ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] cp -r hanged copying a directory
Sorry for the delay. Here is the output for a couple of seconds: # iostat -xce 1 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 1.50.7 20.84.2 0.0 0.09.0 0 1 0 0 0 0 2 1 0 98 sd0 0.30.2 29.4 25.1 0.1 0.0 174.5 0 0 0 0 0 0 sd1 0.30.2 33.2 25.0 0.1 0.0 166.8 0 0 0 0 0 0 sd2 0.20.2 26.8 24.8 0.1 0.0 180.3 0 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 0 0 0 100 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 1 1 0 98 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 2 1 0 98 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 26 3 0 70 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 2 0 0 98 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.01.00.02.0 0.0 0.00.1 0 0 0 0 0 0 1 1 0 98 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 18 1 0 81 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 6 1 0 94 sd0 0.00.00.00.0 35.0 0.00.0 100
Re: [zfs-discuss] Issue with simultaneous IO to lots of ZFS pools
David Collier-Brown wrote: Darren J Moffat [EMAIL PROTECTED] wrote: Chris Siebenmann wrote: | Still, I'm curious -- why lots of pools? Administration would be | simpler with a single pool containing many filesystems. The short answer is that it is politically and administratively easier to use (at least) one pool per storage-buying group in our environment. I think the root cause of the issue is that multiple groups are buying physical rather than virtual storage yet it is all being attached to a single system. I will likely be a huge up hill battle but: if all the physical storage could be purchased by one group and a combination of ZFS reservations and quotas used on top level (eg one level down from the pool) datasets to allocate the virtual storage, and appropriate amounts charged to the groups, you could technical be able to use ZFS how it was intended with much fewer (hopefully 1 or 2) pools. The scenario Chris describes is one I see repeatedly at customers buying SAN storage (as late as last month!) and is considered a best practice on the business side. We may want to make this issue and it's management visible, as people moving from SAN to ZFS are likely to trip over it. In particular, I'd like to see a blueprint or at least a wiki discussion by someone from the SAN world on how to map those kinds of purchases to ZFS pools, how few one wants to have, what happens when it goes wrong, and how to mitigate it (;-)) There are two issues here. One is the number of pools, but the other is the small amount of RAM in the server. To be honest, most laptops today come with 2 GBytes, and most servers are in the 8-16 GByte range (hmmm... I suppose I could look up the average size we sell...) --dave ps: as always, having asked for something, I'm also volunteering to help provide it: I'm not a storage or ZFS guy, but I am an author, and will happily help my Smarter Colleagues[tm] to write it up. Should be relatively straightforward... we would need some help from someone in this situation to provide some sort of performance results (on a system with plenty of RAM). -- richard ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Issue with simultaneous IO to lots of ZFS pools
| There are two issues here. One is the number of pools, but the other | is the small amount of RAM in the server. To be honest, most laptops | today come with 2 GBytes, and most servers are in the 8-16 GByte range | (hmmm... I suppose I could look up the average size we sell...) Speaking as a sysadmin (and a Sun customer), why on earth would I have to provision 8 GB+ of RAM on my NFS fileservers? I would much rather have that memory in the NFS client machines, where it can actually be put to work by user programs. (If I have decently provisioned NFS client machines, I don't expect much from the NFS fileserver's cache. Given that the clients have caches too, I believe that the server's cache will mostly be hit for things that the clients cannot cache because of NFS semantics, like NFS GETATTR requests for revalidation and the like.) - cks ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] cp -r hanged copying a directory
Simon Breden wrote: Sorry for the delay. Here is the output for a couple of seconds: This is the smoking gun... # iostat -xce 1 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 1.50.7 20.84.2 0.0 0.09.0 0 1 0 0 0 0 2 1 0 98 sd0 0.30.2 29.4 25.1 0.1 0.0 174.5 0 0 0 0 0 0 sd1 0.30.2 33.2 25.0 0.1 0.0 166.8 0 0 0 0 0 0 sd2 0.20.2 26.8 24.8 0.1 0.0 180.3 0 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 I/O is moving, but not much activity... extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 0 0 0 100 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 I/O is stuck at the device. %w[ait] of 100 means that something is stuck on the device. This is probably not a ZFS issue, per se, but somehow the ZFS workload triggers it. -- richard ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Issue with simultaneous IO to lots of ZFS pools
Chris Siebenmann wrote: | There are two issues here. One is the number of pools, but the other | is the small amount of RAM in the server. To be honest, most laptops | today come with 2 GBytes, and most servers are in the 8-16 GByte range | (hmmm... I suppose I could look up the average size we sell...) Speaking as a sysadmin (and a Sun customer), why on earth would I have to provision 8 GB+ of RAM on my NFS fileservers? I would much rather have that memory in the NFS client machines, where it can actually be put to work by user programs. This depends entirely on the amount of disk CPU on the fileserver... A Thumper w/ 48 TB of disk and two dual-core CPUS is prob. somewhat under-provisioned w/ 8 GB of RAM. - Bart -- Bart Smaalders Solaris Kernel Performance [EMAIL PROTECTED] http://blogs.sun.com/barts You will contribute more with mercurial than with thunderbird. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Issue with simultaneous IO to lots of ZFS pools
Chris Siebenmann [EMAIL PROTECTED] wrote: | Speaking as a sysadmin (and a Sun customer), why on earth would I have | to provision 8 GB+ of RAM on my NFS fileservers? I would much rather | have that memory in the NFS client machines, where it can actually be | put to work by user programs. | | (If I have decently provisioned NFS client machines, I don't expect much | from the NFS fileserver's cache. Given that the clients have caches too, | I believe that the server's cache will mostly be hit for things that the | clients cannot cache because of NFS semantics, like NFS GETATTR requests | for revalidation and the like.) That's certainly true for the NFS part of the NFS fileserver, but to get the ZFS feature-set, you trade off cycles and memory. If we investigate this a bit, we should be able to figure out a rule of thumb for how little memory we need for an NFS-home-directories workload without cutting into performance. --dave -- David Collier-Brown| Always do right. This will gratify Sun Microsystems, Toronto | some people and astonish the rest [EMAIL PROTECTED] | -- Mark Twain (905) 943-1983, cell: (647) 833-9377, (800) 555-9786 x56583 bridge: (877) 385-4099 code: 506 9191# ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] cp -r hanged copying a directory
hmm, three drives with 35 io requests in the queue and none active? remind me not to buy a drive with that FW.. 1) upgrade the FW in the drives or 2) turn off NCQ with: echo set sata:sata_max_queue_depth = 0x1 /etc/system Rob ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Issue with simultaneous IO to lots of ZFS pools
Bart Smaalders wrote: Chris Siebenmann wrote: | There are two issues here. One is the number of pools, but the other | is the small amount of RAM in the server. To be honest, most laptops | today come with 2 GBytes, and most servers are in the 8-16 GByte range | (hmmm... I suppose I could look up the average size we sell...) Speaking as a sysadmin (and a Sun customer), why on earth would I have to provision 8 GB+ of RAM on my NFS fileservers? I would much rather have that memory in the NFS client machines, where it can actually be put to work by user programs. Chris, thanks for the comment. We will have to be very specific here. There is a minimum expected RAM per pool of 10 MBytes. So it is more of a function of the number of pools than the services rendered. I can see that crafting the message clearly will take some time. This depends entirely on the amount of disk CPU on the fileserver... A Thumper w/ 48 TB of disk and two dual-core CPUS is prob. somewhat under-provisioned w/ 8 GB of RAM. Except the smallest thumper we sell has 16 GBytes... :-) -- richard ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] ZFS boot (post build 88) questions
Are there any updated guides/blogs on how to configure ZFS boot on a build 88 or later system? If I already have an existing zpool, will I be able to just add a root/boot dataset or does the root/boot dataset have to have it's own pool? I have several working systems that have small UFS partitions for booting and LiveUpgrading and then the rest of the disk(s) are in a large zpool. I'm hoping I can migrate smoothly to a ZFS boot system and have all my disks in the same zpool without destroying everything and starting over. -Wyllys 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] cp -r hanged copying a directory
Thanks a lot Richard. To give a bit more info, I've copied my /var/adm/messages from booting up the machine: And @picker: I guess the 35 requests are stacked up waiting for the hanging request to be serviced? The question I have is where do I go from now, to get some more info on what is causing cp to have problems. I will now try another tack: use rsync to copy the directory to a disk outside the pool (i.e. my home directory on the boot drive), to see if it is happy doing that. May 1 17:04:15 zfsbox su: [ID 810491 auth.crit] 'su root' failed for simon on /dev/pts/5 May 1 17:48:15 zfsbox genunix: [ID 540533 kern.notice] ^MSunOS Release 5.11 Version snv_85 64-bit May 1 17:48:15 zfsbox genunix: [ID 172908 kern.notice] Copyright 1983-2008 Sun Microsystems, Inc. All rights reserved. May 1 17:48:15 zfsbox Use is subject to license terms. May 1 17:48:15 zfsbox unix: [ID 126719 kern.info] features: 13f6fffcpuid,tscp,cmp,cx16,sse3,nx,asysc,sse2,sse,pat,cx8,pae,mca,mmx,cmov,de,pge,mtrr,msr,tsc,lgpg May 1 17:48:15 zfsbox unix: [ID 168242 kern.info] mem = 4192764K (0xffe7f000) May 1 17:48:15 zfsbox rootnex: [ID 466748 kern.info] root nexus = i86pc May 1 17:48:15 zfsbox rootnex: [ID 349649 kern.info] pseudo0 at root May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] pseudo0 is /pseudo May 1 17:48:15 zfsbox rootnex: [ID 349649 kern.info] scsi_vhci0 at root May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] scsi_vhci0 is /scsi_vhci May 1 17:48:15 zfsbox rootnex: [ID 349649 kern.info] isa0 at root May 1 17:48:15 zfsbox pci_autoconfig: [ID 139057 kern.info] NOTICE: reprogram io-range on ppb[0/f/0]: 0x2000 ~ 0x2fff May 1 17:48:15 zfsbox pci_autoconfig: [ID 595143 kern.info] NOTICE: add io-range on subtractive ppb[0/6/0]: 0x3000 ~ 0x3fff May 1 17:48:15 zfsbox pcplusmp: [ID 658230 kern.info] NOTICE: apic: local nmi: 0 1 1 1 May 1 17:48:15 zfsbox pcplusmp: [ID 658230 kern.info] NOTICE: apic: local nmi: 1 1 1 1 May 1 17:48:15 zfsbox pcplusmp: [ID 658230 kern.info] NOTICE: apic: local nmi: 2 1 1 1 May 1 17:48:15 zfsbox pcplusmp: [ID 658230 kern.info] NOTICE: apic: local nmi: 3 1 1 1 May 1 17:48:15 zfsbox pcplusmp: [ID 177709 kern.info] pcplusmp: vector 0x9 ioapic 0x4 intin 0x9 is bound to cpu 1 May 1 17:48:15 zfsbox pseudo: [ID 129642 kern.info] pseudo-device: acpippm0 May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] acpippm0 is /pseudo/[EMAIL PROTECTED] May 1 17:48:15 zfsbox pseudo: [ID 129642 kern.info] pseudo-device: ppm0 May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] ppm0 is /pseudo/[EMAIL PROTECTED] May 1 17:48:15 zfsbox rootnex: [ID 349649 kern.info] npe0 at root: space 0 offset 0 May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] npe0 is /[EMAIL PROTECTED],0 May 1 17:48:15 zfsbox pcplusmp: [ID 803547 kern.info] pcplusmp: ide (ata) instance 0 vector 0xe ioapic 0x4 intin 0xe is bound to cpu 0 May 1 17:48:15 zfsbox genunix: [ID 640982 kern.info] IDE device at targ 0, lun 0 lastlun 0x0 May 1 17:48:15 zfsbox genunix: [ID 846691 kern.info] model HDS722516VLAT80 May 1 17:48:15 zfsbox genunix: [ID 479077 kern.info] ATA/ATAPI-6 supported, majver 0x7c minver 0x19 May 1 17:48:15 zfsbox genunix: [ID 640982 kern.info] ATAPI device at targ 1, lun 0 lastlun 0x0 May 1 17:48:15 zfsbox genunix: [ID 846691 kern.info] model TSSTcorpDVD-ROM SH-D162C May 1 17:48:15 zfsbox npe: [ID 236367 kern.info] PCI Express-device: [EMAIL PROTECTED], ata0 May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] ata0 is /[EMAIL PROTECTED],0/[EMAIL PROTECTED]/[EMAIL PROTECTED] May 1 17:48:15 zfsbox genunix: [ID 773945 kern.info] UltraDMA mode 2 selected May 1 17:48:15 zfsbox genunix: [ID 773945 kern.info] UltraDMA mode 5 selected May 1 17:48:15 zfsbox gda: [ID 243001 kern.info] Disk0:Vendor 'Gen-ATA ' Product 'HDS722516VLAT80 ' May 1 17:48:17 zfsbox ata: [ID 496167 kern.info] cmdk0 at ata0 target 0 lun 0 May 1 17:48:17 zfsbox genunix: [ID 936769 kern.info] cmdk0 is /[EMAIL PROTECTED],0/[EMAIL PROTECTED]/[EMAIL PROTECTED]/[EMAIL PROTECTED],0 May 1 17:48:20 zfsbox unix: [ID 190185 kern.info] SMBIOS v2.4 loaded (2169 bytes) May 1 17:48:20 zfsbox genunix: [ID 408114 kern.info] /cpus (cpunex0) online May 1 17:48:20 zfsbox pseudo: [ID 129642 kern.info] pseudo-device: dld0 May 1 17:48:20 zfsbox genunix: [ID 936769 kern.info] dld0 is /pseudo/[EMAIL PROTECTED] May 1 17:48:20 zfsbox pcplusmp: [ID 803547 kern.info] pcplusmp: pciexclass,060400 (pcie_pci) instance 1 vector 0x18 ioapic 0xff intin 0xff is bound to cpu 1 May 1 17:48:20 zfsbox npe: [ID 236367 kern.info] PCI Express-device: pci10de,[EMAIL PROTECTED], pcie_pci1 May 1 17:48:20 zfsbox genunix: [ID 936769 kern.info] pcie_pci1 is /[EMAIL PROTECTED],0/pci10de,[EMAIL PROTECTED] May 1 17:48:21 zfsbox pcplusmp: [ID 803547 kern.info] pcplusmp: pci10de,163 (nvidia) instance 0 vector 0x10 ioapic 0x4 intin 0x10 is bound to cpu 0 May 1 17:48:21 zfsbox pcie_pci: [ID 586369 kern.info] PCIE-device:
Re: [zfs-discuss] cp -r hanged copying a directory
Hi Simon, Simon Breden wrote: Thanks a lot Richard. To give a bit more info, I've copied my /var/adm/messages from booting up the machine: And @picker: I guess the 35 requests are stacked up waiting for the hanging request to be serviced? The question I have is where do I go from now, to get some more info on what is causing cp to have problems. I will now try another tack: use rsync to copy the directory to a disk outside the pool (i.e. my home directory on the boot drive), to see if it is happy doing that. What does truss show the cp doing? max ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] cp -r hanged copying a directory
This list seems out of sync (delayed) with email messages I receive. Why is that? Which are the best tools to use when reading / replying to these posts? Anyway from my email I can see that Max has sent me a question about truss -- here is my reply: Hi Max, I haven't used truss before, but give me the command line + switches and I'll be happy to run it. Simon 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] cp -r hanged copying a directory
Hi Simon, Simon Breden wrote: Hi Max, I haven't used truss before, but give me the command line + switches and I'll be happy to run it. Simon # truss -p pid_from_cp where pid_from_cp is... the pid of the cp process that is hung. The pid you can get from ps. I am curious if the cp is stuck on a specific file, or is just very slow, or is hung in the kernel. Also, can you kill the cp when it hangs? thanks, max 2008/5/1 [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] [EMAIL PROTECTED] mailto:[EMAIL PROTECTED]: Hi Simon, Simon Breden wrote: Thanks a lot Richard. To give a bit more info, I've copied my /var/adm/messages from booting up the machine: And @picker: I guess the 35 requests are stacked up waiting for the hanging request to be serviced? The question I have is where do I go from now, to get some more info on what is causing cp to have problems. I will now try another tack: use rsync to copy the directory to a disk outside the pool (i.e. my home directory on the boot drive), to see if it is happy doing that. What does truss show the cp doing? max ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Thumper / X4500 marvell driver issues
Doug wrote: When we installed the Marvell driver patch 125205-07 on our X4500 a few months ago and it started crashing, Sun support just told us to back out that patch. The system has been stable since then. We are still running Solaris 10 11/06 on that system. Is there an advantage to using 125205-07 and the IDR you mention compared to just not using NCQ? Better performance? If so, how much better? Everything depends on your I/O workload. We are updating thousands of RRD files, so it's _extremely_ random, relatively small I/Os. In our case, NCQ is a huge win (about a 25% improvement, as I recall). If you do mostly sequential I/O, It will probably make only a small difference. -- Carson ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] cp -r hanged copying a directory
This mailing list seems broken and out of sync -- your post is as 'Guest' and appears as a new post in the main zfs-discuss list -- and the main thread is out of sync with the replies, and I just got a java exception trying to post to the main thread -- what's going on here? 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] cp -r hanged copying a directory
Hi Max, I re-ran the cp command and when it hanged I ran 'ps -el' looked up the cp command, got it's PID and then ran: # truss -p PID_of_cp and it output nothing at all -- i.e. it hanged too -- just showing a flashing cursor. The system is still operational as I am typing into the browser. Before I ran the cp command I did a 'tail -f /var/adm/messages' and there is no output. I also did a 'tail -f /var/log/syslog' and there is also no output. If I try 'kill -15 PID_of_cp' and then 'ps -el' cp is still running. And if I try 'kill -9 PID_of_cp' and then 'ps -el' cp is still running. What next ? For what it's worth, here is further output from iostat, the first line looks interesting, but it appears to be buffered, as it's the same each time I run it -- possibly the last info from cp before it died??? (see below) So, any ideas what I can do next? Just going to reboot to kill the hanging cp -- wow, this is like Windows now :( (attempt to keep humor) bash-3.2$ iostat -xce 1 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk021.42.7 191.4 32.4 0.4 0.1 20.8 3 5 0 0 0 0 4 2 0 94 sd0 9.9 12.6 1193.8 1478.2 11.0 0.0 489.0 32 4 0 0 0 0 sd1 7.5 12.6 836.2 1479.1 10.9 0.0 543.7 32 4 0 0 0 0 sd2 7.7 12.6 877.1 1479.4 10.9 0.0 537.1 32 4 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 1 1 0 98 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 2 0 0 98 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 1 1 0 98 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 2 0 0 98 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 extended device statistics errors --- cpu devicer/sw/s kr/s kw/s wait actv svc_t %w %b s/w h/w trn tot us sy wt id cmdk0 0.00.00.00.0 0.0 0.00.0 0 0 0 0 0 0 4 1 0 96 sd0 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd1 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd2 0.00.00.00.0 35.0 0.00.0 100 0 0 0 0 0 sd3 0.00.00.00.0 0.0 0.00.0 0 0 0 5 0 5 ^C bash-3.2$ and I just saw this: (seems to be from yesterday -- I don't know if it's relevant to this though ??) # fmdump -e TIME CLASS Apr 30 01:12:14.9802 ereport.fs.zfs.checksum Apr 30 01:12:14.9896 ereport.fs.zfs.checksum Apr 30 01:12:14.9896 ereport.fs.zfs.checksum Apr 30 01:12:14.9896 ereport.fs.zfs.checksum Apr 30 01:12:14.9896 ereport.fs.zfs.checksum Apr 30 01:12:14.9896 ereport.fs.zfs.data Apr 30 01:12:14.9802 ereport.fs.zfs.checksum Apr 30
Re: [zfs-discuss] ZFS still crashing after patch
Today my production server crashed 4 times. THIS IS NIGHTMARE! Self-healing file system?! For me ZFS is SELF-KILLING filesystem. I cannot fsck it, there's no such tool. I cannot scrub it, it crashes 30-40 minutes after scrub starts. I cannot use it, it crashes a number of times every day! And with every crash number of checksum failures is growing: NAMESTATE READ WRITE CKSUM box5ONLINE 0 0 0 ...after a few hours... box5ONLINE 0 0 4 ...after a few hours... box5ONLINE 0 0 62 ...after another few hours... box5ONLINE 0 0 120 ...crash! and we start again... box5ONLINE 0 0 0 ...etc... actually 120 is record, sometimes it crashed as soon as it boots. and always there's a permanent error: errors: Permanent errors have been detected in the following files: box5:0x0 and very wise self-healing advice: http://www.sun.com/msg/ZFS-8000-8A Restore the file in question if possible. Otherwise restore the entire pool from backup. Thanks, but if I restore it from backup it won't be ZFS anymore, that's for sure. It's not I/O problem. AFAIK, default ZFS I/O error behavior is wait to repair (i've 10U4, non-configurable). Then why it panics? Recently there were discussions on failure of OpenSolaris community. Now it's been more than half a month since I reported such an error. Nobody even posted something like RTFM. Come on guys, I know you are there and busy with enterprise customers... but at least give me some troubleshooting ideas. i'm totally lost. just to remind, it's heavily loaded fs with 3-4 million files and folders. Link to original post: http://www.opensolaris.org/jive/thread.jspa?threadID=57425 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] ZFS still crashing after patch
On Thu, 1 May 2008, Rustam wrote: Today my production server crashed 4 times. THIS IS NIGHTMARE! Self-healing file system?! For me ZFS is SELF-KILLING filesystem. I cannot fsck it, there's no such tool. I cannot scrub it, it crashes 30-40 minutes after scrub starts. I cannot use it, it crashes a number of times every day! And with every crash number of checksum failures is growing: Is your ZFS pool configured with redundancy (e.g mirrors, raidz) or is it non-redundant? If non-redundant, then there is not much that ZFS can really do if a device begins to fail. Bob == Bob Friesenhahn [EMAIL PROTECTED], 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] cp -r hanged copying a directory
Hi Simon, Simon Breden wrote: Hi Max, I re-ran the cp command and when it hanged I ran 'ps -el' looked up the cp command, got it's PID and then ran: # truss -p PID_of_cp and it output nothing at all -- i.e. it hanged too -- just showing a flashing cursor. The system is still operational as I am typing into the browser. Before I ran the cp command I did a 'tail -f /var/adm/messages' and there is no output. I also did a 'tail -f /var/log/syslog' and there is also no output. If I try 'kill -15 PID_of_cp' and then 'ps -el' cp is still running. And if I try 'kill -9 PID_of_cp' and then 'ps -el' cp is still running. What next ? You can try the following: # mdb -k ::pgrep cp -- this should give you a line with the cp you are running. Next to cp is an address, use this address in the next line: address_from_pgrep::walk thread | ::threadlist -v This will give you a stack trace. Please post it. $q -- this gets you out of mdb max ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] cp -r hanged copying a directory
Keep getting Java exceptions posting to the proper thread for this -- just lost an hour --- WTF??? Had to reply to my own post as Max's reply (which I saw in my email inbox) has not appeared here. Again, what is wrong with this forum software -- it seems so buggy, or am I missing something here (I'm quite prepared to be wrong, but I'm getting really p*ssed off with this forum engine as I'm wasting time and getting Java errors about missing parent which I will post if I get more errors trying to post with this broken forum software -- if it allows me to) Thanks for your advice Max, and here is my reply to your suggestion: # mdb -k Loading modules: [ unix genunix specfs dtrace cpu.generic cpu_ms.AuthenticAMD.15 uppc pcplusmp scsi_vhci ufs ip hook neti sctp arp usba s1394 nca lofs zfs random md sppp smbsrv nfs ptm ipc crypto ] ::pgrep cp SPID PPID PGIDSIDUID FLAGS ADDR NAME R889868889868501 0x4a004000 ff01deca9048 cp ff01deca9048::walk thread | ::threadlist -v ADDR PROC LWP CLS PRIWCHAN ff01e0045840 ff01deca9048 ff01de9d9210 2 60 ff01d861ca80 PC: _resume_from_idle+0xf1CMD: cp -pr testdir z1 stack pointer for thread ff01e0045840: ff0007fcdf00 [ ff0007fcdf00 _resume_from_idle+0xf1() ] swtch+0x17f() cv_wait+0x61() zio_wait+0x5f() dbuf_read+0x1b5() dbuf_findbp+0xe8() dbuf_prefetch+0x9b() dmu_zfetch_fetch+0x43() dmu_zfetch_dofetch+0xc2() dmu_zfetch_find+0x3a1() dmu_zfetch+0xa5() dbuf_read+0xe3() dmu_buf_hold_array_by_dnode+0x1c4() dmu_read+0xd4() zfs_fillpage+0x15e() zfs_getpage+0x187() fop_getpage+0x9f() segvn_fault+0x9ef() as_fault+0x5ae() pagefault+0x95() trap+0x1286() 0xfb8001d9() fuword8+0x21() zfs_write+0x147() fop_write+0x69() write+0x2af() write32+0x1e() sys_syscall32+0x101() 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] cp -r hanged copying a directory
Just to reduce my stress levels and to give the webmaster some useful info to help fix this broken forum: I tried posting a reply to the main thread for 'cp -r hanged copying a directory' and got the following error -- seems like it can't find the parent thread/message's id in the database at a guess: Got this multiple times when trying to post, and as no information is given on how to contact teh system administrator in the message -- here is the message and exception stack trace: An error in the system has occurred. Please contact the system administrator if the problem persists. type: java.lang.IllegalArgumentException java.lang.IllegalArgumentException: Parent key 230968 not found when adding child 231029. at com.jivesoftware.util.LongTree.addChild(Unknown Source) at com.jivesoftware.forum.database.DbTreeWalker.addChild(Unknown Source) at com.jivesoftware.forum.database.DbForumThread.addMessage(Unknown Source) at com.jivesoftware.forum.proxy.ForumThreadProxy.addMessage(Unknown Source) at org.opensolaris.jive.action.ForumPostAction.createMessage(Unknown Source) at com.jivesoftware.forum.action.PostAction.execute(Unknown Source) at com.jivesoftware.forum.action.PostAction.doPost(Unknown Source) at sun.reflect.GeneratedMethodAccessor881.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25) at java.lang.reflect.Method.invoke(Method.java:585) at com.opensymphony.xwork.DefaultActionInvocation.invokeAction(DefaultActionInvocation.java:300) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:166) at com.opensymphony.xwork.interceptor.AroundInterceptor.intercept(AroundInterceptor.java:35) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.xwork.interceptor.AroundInterceptor.intercept(AroundInterceptor.java:35) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.xwork.interceptor.AroundInterceptor.intercept(AroundInterceptor.java:35) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.jivesoftware.forum.action.JiveExceptionInterceptor.intercept(Unknown Source) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.jivesoftware.base.action.JiveObjectLoaderInterceptor.intercept(Unknown Source) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.xwork.interceptor.AroundInterceptor.intercept(AroundInterceptor.java:35) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.xwork.interceptor.AroundInterceptor.intercept(AroundInterceptor.java:35) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.webwork.interceptor.FileUploadInterceptor.intercept(FileUploadInterceptor.java:71) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.xwork.interceptor.AroundInterceptor.intercept(AroundInterceptor.java:35) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.xwork.interceptor.AroundInterceptor.intercept(AroundInterceptor.java:35) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.xwork.interceptor.AroundInterceptor.intercept(AroundInterceptor.java:35) at com.opensymphony.xwork.DefaultActionInvocation.invoke(DefaultActionInvocation.java:164) at com.opensymphony.xwork.DefaultActionProxy.execute(DefaultActionProxy.java:116) at com.opensymphony.webwork.dispatcher.ServletDispatcher.serviceAction(ServletDispatcher.java:272) at com.jivesoftware.base.util.JiveWebWorkServlet.service(Unknown Source) at javax.servlet.http.HttpServlet.service(HttpServlet.java:802) at sun.reflect.GeneratedMethodAccessor156.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25) at java.lang.reflect.Method.invoke(Method.java:585) at org.apache.catalina.security.SecurityUtil$1.run(SecurityUtil.java:243) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAsPrivileged(Subject.java:517) at org.apache.catalina.security.SecurityUtil.execute(SecurityUtil.java:275) at org.apache.catalina.security.SecurityUtil.doAsPrivilege(SecurityUtil.java:161) at
Re: [zfs-discuss] ZFS still crashing after patch
Rustam wrote: Today my production server crashed 4 times. THIS IS NIGHTMARE! Self-healing file system?! For me ZFS is SELF-KILLING filesystem. I cannot fsck it, there's no such tool. I cannot scrub it, it crashes 30-40 minutes after scrub starts. I cannot use it, it crashes a number of times every day! And with every crash number of checksum failures is growing: NAMESTATE READ WRITE CKSUM box5ONLINE 0 0 0 ...after a few hours... box5ONLINE 0 0 4 ...after a few hours... box5ONLINE 0 0 62 ...after another few hours... box5ONLINE 0 0 120 ...crash! and we start again... box5ONLINE 0 0 0 ...etc... actually 120 is record, sometimes it crashed as soon as it boots. and always there's a permanent error: errors: Permanent errors have been detected in the following files: box5:0x0 and very wise self-healing advice: http://www.sun.com/msg/ZFS-8000-8A Restore the file in question if possible. Otherwise restore the entire pool from backup. Thanks, but if I restore it from backup it won't be ZFS anymore, that's for sure. That's a bit harsh. ZFS is telling you that you have corrupted data based on the checksums. Other types of filesystems would likely simply pass the corrupted data on silently. It's not I/O problem. AFAIK, default ZFS I/O error behavior is wait to repair (i've 10U4, non-configurable). Then why it panics? Do you have the panic messages? ZFS won't cause panics based on bad checksums. It will by default cause panic if it can't write data out to any device or if it completely loses access to non-redundant devices or loses both redundant devices at the same time. Recently there were discussions on failure of OpenSolaris community. Now it's been more than half a month since I reported such an error. Nobody even posted something like RTFM. Come on guys, I know you are there and busy with enterprise customers... but at least give me some troubleshooting ideas. i'm totally lost. just to remind, it's heavily loaded fs with 3-4 million files and folders. Link to original post: http://www.opensolaris.org/jive/thread.jspa?threadID=57425 Since this seems to show the same number of checksum errors across 2 different channels and 4 different drives. Given that, I'd assume that this is likely a dual-channel HBA of some sort. It would appear that you either have bad hardware or some sort of driver issue. Regards, Phil ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] cp -r hanged copying a directory
Hi Simon, Simon Breden wrote: Thanks for your advice Max, and here is my reply to your suggestion: # mdb -k Loading modules: [ unix genunix specfs dtrace cpu.generic cpu_ms.AuthenticAMD.15 uppc pcplusmp scsi_vhci ufs ip hook neti sctp arp usba s1394 nca lofs zfs random md sppp smbsrv nfs ptm ipc crypto ] ::pgrep cp SPID PPID PGIDSIDUID FLAGS ADDR NAME R889868889868501 0x4a004000 ff01deca9048 cp ff01deca9048::walk thread | ::threadlist -v ADDR PROC LWP CLS PRIWCHAN ff01e0045840 ff01deca9048 ff01de9d9210 2 60 ff01d861ca80 PC: _resume_from_idle+0xf1CMD: cp -pr testdir z1 stack pointer for thread ff01e0045840: ff0007fcdf00 [ ff0007fcdf00 _resume_from_idle+0xf1() ] swtch+0x17f() cv_wait+0x61() zio_wait+0x5f() dbuf_read+0x1b5() dbuf_findbp+0xe8() dbuf_prefetch+0x9b() dmu_zfetch_fetch+0x43() dmu_zfetch_dofetch+0xc2() dmu_zfetch_find+0x3a1() dmu_zfetch+0xa5() dbuf_read+0xe3() dmu_buf_hold_array_by_dnode+0x1c4() dmu_read+0xd4() zfs_fillpage+0x15e() zfs_getpage+0x187() fop_getpage+0x9f() segvn_fault+0x9ef() as_fault+0x5ae() pagefault+0x95() trap+0x1286() 0xfb8001d9() fuword8+0x21() zfs_write+0x147() fop_write+0x69() write+0x2af() write32+0x1e() sys_syscall32+0x101() So, a write has been issued, zfs is retrieving a page and is waiting for the pagein to complete. I'll take a further look tomorrow, but maybe someone else reading this has an idea. (It is midnight here). max This message posted from opensolaris.org ___ 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] cp -r hanged copying a directory
Simon Breden wrote: Thanks a lot Richard. To give a bit more info, I've copied my /var/adm/messages from booting up the machine: And @picker: I guess the 35 requests are stacked up waiting for the hanging request to be serviced? The question I have is where do I go from now, to get some more info on what is causing cp to have problems. I will now try another tack: use rsync to copy the directory to a disk outside the pool (i.e. my home directory on the boot drive), to see if it is happy doing that. May 1 17:04:15 zfsbox su: [ID 810491 auth.crit] 'su root' failed for simon on /dev/pts/5 May 1 17:48:15 zfsbox genunix: [ID 540533 kern.notice] ^MSunOS Release 5.11 Version snv_85 64-bit May 1 17:48:15 zfsbox genunix: [ID 172908 kern.notice] Copyright 1983-2008 Sun Microsystems, Inc. All rights reserved. May 1 17:48:15 zfsbox Use is subject to license terms. May 1 17:48:15 zfsbox unix: [ID 126719 kern.info] features: 13f6fffcpuid,tscp,cmp,cx16,sse3,nx,asysc,sse2,sse,pat,cx8,pae,mca,mmx,cmov,de,pge,mtrr,msr,tsc,lgpg May 1 17:48:15 zfsbox unix: [ID 168242 kern.info] mem = 4192764K (0xffe7f000) May 1 17:48:15 zfsbox rootnex: [ID 466748 kern.info] root nexus = i86pc May 1 17:48:15 zfsbox rootnex: [ID 349649 kern.info] pseudo0 at root May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] pseudo0 is /pseudo May 1 17:48:15 zfsbox rootnex: [ID 349649 kern.info] scsi_vhci0 at root May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] scsi_vhci0 is /scsi_vhci May 1 17:48:15 zfsbox rootnex: [ID 349649 kern.info] isa0 at root May 1 17:48:15 zfsbox pci_autoconfig: [ID 139057 kern.info] NOTICE: reprogram io-range on ppb[0/f/0]: 0x2000 ~ 0x2fff May 1 17:48:15 zfsbox pci_autoconfig: [ID 595143 kern.info] NOTICE: add io-range on subtractive ppb[0/6/0]: 0x3000 ~ 0x3fff May 1 17:48:15 zfsbox pcplusmp: [ID 658230 kern.info] NOTICE: apic: local nmi: 0 1 1 1 May 1 17:48:15 zfsbox pcplusmp: [ID 658230 kern.info] NOTICE: apic: local nmi: 1 1 1 1 May 1 17:48:15 zfsbox pcplusmp: [ID 658230 kern.info] NOTICE: apic: local nmi: 2 1 1 1 May 1 17:48:15 zfsbox pcplusmp: [ID 658230 kern.info] NOTICE: apic: local nmi: 3 1 1 1 May 1 17:48:15 zfsbox pcplusmp: [ID 177709 kern.info] pcplusmp: vector 0x9 ioapic 0x4 intin 0x9 is bound to cpu 1 May 1 17:48:15 zfsbox pseudo: [ID 129642 kern.info] pseudo-device: acpippm0 May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] acpippm0 is /pseudo/[EMAIL PROTECTED] May 1 17:48:15 zfsbox pseudo: [ID 129642 kern.info] pseudo-device: ppm0 May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] ppm0 is /pseudo/[EMAIL PROTECTED] May 1 17:48:15 zfsbox rootnex: [ID 349649 kern.info] npe0 at root: space 0 offset 0 May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] npe0 is /[EMAIL PROTECTED],0 May 1 17:48:15 zfsbox pcplusmp: [ID 803547 kern.info] pcplusmp: ide (ata) instance 0 vector 0xe ioapic 0x4 intin 0xe is bound to cpu 0 May 1 17:48:15 zfsbox genunix: [ID 640982 kern.info] IDE device at targ 0, lun 0 lastlun 0x0 May 1 17:48:15 zfsbox genunix: [ID 846691 kern.info] model HDS722516VLAT80 May 1 17:48:15 zfsbox genunix: [ID 479077 kern.info] ATA/ATAPI-6 supported, majver 0x7c minver 0x19 May 1 17:48:15 zfsbox genunix: [ID 640982 kern.info] ATAPI device at targ 1, lun 0 lastlun 0x0 May 1 17:48:15 zfsbox genunix: [ID 846691 kern.info] model TSSTcorpDVD-ROM SH-D162C May 1 17:48:15 zfsbox npe: [ID 236367 kern.info] PCI Express-device: [EMAIL PROTECTED], ata0 May 1 17:48:15 zfsbox genunix: [ID 936769 kern.info] ata0 is /[EMAIL PROTECTED],0/[EMAIL PROTECTED]/[EMAIL PROTECTED] May 1 17:48:15 zfsbox genunix: [ID 773945 kern.info] UltraDMA mode 2 selected May 1 17:48:15 zfsbox genunix: [ID 773945 kern.info] UltraDMA mode 5 selected May 1 17:48:15 zfsbox gda: [ID 243001 kern.info] Disk0: Vendor 'Gen-ATA ' Product 'HDS722516VLAT80 ' May 1 17:48:17 zfsbox ata: [ID 496167 kern.info] cmdk0 at ata0 target 0 lun 0 May 1 17:48:17 zfsbox genunix: [ID 936769 kern.info] cmdk0 is /[EMAIL PROTECTED],0/[EMAIL PROTECTED]/[EMAIL PROTECTED]/[EMAIL PROTECTED],0 May 1 17:48:20 zfsbox unix: [ID 190185 kern.info] SMBIOS v2.4 loaded (2169 bytes) May 1 17:48:20 zfsbox genunix: [ID 408114 kern.info] /cpus (cpunex0) online May 1 17:48:20 zfsbox pseudo: [ID 129642 kern.info] pseudo-device: dld0 May 1 17:48:20 zfsbox genunix: [ID 936769 kern.info] dld0 is /pseudo/[EMAIL PROTECTED] May 1 17:48:20 zfsbox pcplusmp: [ID 803547 kern.info] pcplusmp: pciexclass,060400 (pcie_pci) instance 1 vector 0x18 ioapic 0xff intin 0xff is bound to cpu 1 May 1 17:48:20 zfsbox npe: [ID 236367 kern.info] PCI Express-device: pci10de,[EMAIL PROTECTED], pcie_pci1 May 1 17:48:20 zfsbox genunix: [ID 936769 kern.info] pcie_pci1 is /[EMAIL PROTECTED],0/pci10de,[EMAIL PROTECTED] May 1 17:48:21 zfsbox pcplusmp: [ID 803547 kern.info] pcplusmp:
Re: [zfs-discuss] cp -r hanged copying a directory
[forget the BUI forum, e-mail works better, IMHO] Simon Breden wrote: Thanks a lot Richard. To give a bit more info, I've copied my /var/adm/messages from booting up the machine: I don't see any major issues related to this problem in the messages. And @picker: I guess the 35 requests are stacked up waiting for the hanging request to be serviced? The 35 iops are queued in the device driver waiting to be sent to the device (wait). The iops queued to the device is in the active queue (actv). The question I have is where do I go from now, to get some more info on what is causing cp to have problems. As your later mdb test confirmed, ZFS is patiently waiting on an I/O to complete. Solaris has sent that I/O to a device and hasn't heard a reply yet. By default, the sd driver will retry every 60 seconds, and eventually fail the I/O which will bounce back up to ZFS as an I/O error. Please double check your drive firmware. -- richard ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] ZFS still crashing after patch
Is your ZFS pool configured with redundancy (e.g mirrors, raidz) or is it non-redundant? If non-redundant, then there is not much that ZFS can really do if a device begins to fail. It's RAID 10 (more info here: http://www.opensolaris.org/jive/thread.jspa?threadID=57425): NAME STATE READ WRITE CKSUM box5 ONLINE 0 0 4 mirror ONLINE 0 0 2 c1d0 ONLINE 0 0 4 c2d0 ONLINE 0 0 4 mirror ONLINE 0 0 2 c2d1 ONLINE 0 0 4 c1d1 ONLINE 0 0 4 Actually, there's no damaged data so far. I don't get any unable to read/write kind of errors. It's just very strange checksum errors synchronized over all disks. That's a bit harsh. ZFS is telling you that you u have corrupted data based on the checksums. Other types of filesystems would likely simply pass the corrupted data on silently. Checksums are good, no complaints about that. Do you have the panic messages? ZFS won't cause panics based on bad checksums. It will by default cause panic if it can't write data out to any device or if it completely loses access to non-redundant devices or loses both redundant devices at the same time. A number of panic messages and crash dump stack trace are attached to the original post (http://www.opensolaris.org/jive/thread.jspa?threadID=57425). Here is the short snip: ::status debugging crash dump vmcore.5 (64-bit) from core operating system: 5.10 Generic_127112-07 (i86pc) panic message: BAD TRAP: type=e (#pf Page fault) rp=fe800017f8d0 addr=238 occurred in module unix due to a NULL pointer dereference dump content: kernel pages only ::stack mutex_enter+0xb() zio_buf_alloc+0x1a() zio_read+0xba() spa_scrub_io_start+0xf1() spa_scrub_cb+0x13d() traverse_callback+0x6a() traverse_segment+0x118() traverse_more+0x7b() spa_scrub_thread+0x147() thread_start+8() Since this seems to show the same number of checksum errors across 2 different channels and 4 different drives. Given that, I'd assume that this is likely a dual-channel HBA of some sort. It would appear that you either have bad hardware or some sort of driver issue. You right, this is the dual-channel Intel's ICH6 SATA controller. 10U4 has native support/drivers for this SATA controller (AHCI drivers afaik). The thing is that this hardware and ZFS were in production for almost 2 years (ok, not the best argument). However this problem occurred recently (20 days). It's even more strange because I didn't made any OS/diver upgrade or patch during last 2-3 months. However, this is good point. I've seen some new SATA/AHCI drivers available in 10U5. Maybe I should try to upgrade and see if it helps. Thanks Phil. -- Rustam 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] ZFS still crashing after patch
On Thu, 1 May 2008, Rustam wrote: operating system: 5.10 Generic_127112-07 (i86pc) Seems kind of old. I am using Generic_127112-11 here. Probably many hundreds of nasty bugs have been eliminated since the version you are using. Bob == Bob Friesenhahn [EMAIL PROTECTED], 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