Re: [BULK] RE: R910/Linux CPU Heat Problems?
Hi, On Wed, 8 Dec 2010, Erich Weiler wrote: Very useful: [r...@server ~]# ipmitool sdr type Fan FAN 1 RPM| 30h | ok | 7.1 | 1320 RPM FAN 2 RPM| 31h | ok | 7.1 | 1320 RPM FAN 3 RPM| 32h | ok | 7.1 | 1440 RPM FAN 4 RPM| 33h | ok | 7.1 | 1680 RPM FAN 5 RPM| 34h | ok | 7.1 | 1560 RPM FAN 6 RPM| 35h | ok | 7.1 | 1680 RPM Fan RPM | 36h | ok | 10.1 | 3480 RPM Fan RPM | 37h | ok | 10.2 | 10080 RPM Fan RPM | 38h | ok | 10.3 | 3120 RPM Fan RPM | 39h | ok | 10.4 | 2160 RPM Fan Redundancy | 75h | ok | 7.1 | Fully Redundant I wonder why one fan is so fast while the others are slower. I'm beginning to think the BIOS might be the next step, to check Fan speed options... I guess the fast fan is one inside the power supplies, with little effect on CPU temperatueres. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Oswald Haan und Dr. Paul Suren Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: [BULK] RE: R910/Linux CPU Heat Problems?
Hi, On Wed, 8 Dec 2010, Jefferson Ogata wrote: On 2010-12-08 23:31, Bond Masuda wrote: yeah, looks like the R910 has 4 PSUs definitely something off with one of them. I'd consider taking a physical look at it who knows? maybe one PSU is failing and generating a lot of heat? BTW: each PSU has two fans. Or perhaps the high fan speed in one PSU is part of a scaled response to the high CPU temp. Maybe at higher CPU temps the other PSU fans will spin up to high speed. If the (single!) PSU fan is triggered by big heat from a CPU in the way of his air, one of the three central fan pairs should have got triggered to high speed too, and the second fan of the same PSU too. So the heat source (if ever, may be a failing sensor only) seems for me to be a local defect in one of the two PSUs. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Oswald Haan und Dr. Paul Suren Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: Perc 5i PE 1950 limitations
Hi, On Mon, 18 Oct 2010, markw wrote: Wondering what the drive capacity limitations are on a PE 1950 with perc 5i controller? Can it handle the newer 2.5 600GB SAS drives, or am I going to be stuck with a 300GB limit? Firmware release is 5.2.2-0072. I don't see anything in the release notes for the firmware, and it appears that dell does a max of 4x300gb drives in these things. I have got 600 GB drives for 1950, but only after special help by Mr. Heinz (jens_he...@dell.com). It will be out of the system warranty by formal reasons, but it works with PERC5/i. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Oswald Haan und Dr. Paul Suren Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: 2.5 vs 3.5 drive performance?
Hi, On Tue, 12 Oct 2010, Adam Nielsen wrote: Not sure if it's still the case, but these drives used to have smaller platters to reduce the seek time, so they were pretty much 2.5 drives in a 3.5 shell. Impossible. Well a quick Google suggests otherwise: http://www.pcguide.com/ref/hdd/op/mediaSize-c.html (see table at end of page) And to quote from the end of http://www.datarecoverylink.com/understanding_platter_sizes.html: Decreasing the size of the platters decreases the distance in which the head actuator must move the heads side-to-side performing random seeks thus improving seek time and making random reads/writes more efficient...The movement to smaller platters began in earnest when some manufacturers trimmed the platters in their 10,000 RPM hard disk drives from 3.74 down to 3 while keeping them as standard 3.5 form factor drives on the outside for compatibility. Seagate's Cheetah X15 15,000 RPM drive goes even further, dropping the platter size down to 2.5, again trading performance for capacity So given equal RPM the 2.5 drive should have a faster full-stroke seek, but as has been pointed out, an SSD would be even better in this respect. How do you see an effort of 2.5 against 3.5? Well if the platters are smaller the heads have less distance to move, so seeking from the start of the disk to the end would be quicker... The opposite is fact. [1] http://www.latestpcnews.com/western-digital-launches-new-backplane-compatible-wdvelociraptor-hard-drive/ Only advertising, sorry. Not all advertising is wrong :-) All these aspects forget the capacity loss. I was talking about same capacity. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Oswald Haan und Dr. Paul Suren Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: 2.5 vs 3.5 drive performance?
Hi, On Tue, 12 Oct 2010, Adam Nielsen wrote: With all drives, the used surface starts at the outer corner and does not reach to the inner corner. So 3.5 drives have in any case the bits sliding faster under the heads at a given rpm. Unless they're 10kRPM or faster. No, at any given speed. Not sure if it's still the case, but these drives used to have smaller platters to reduce the seek time, so they were pretty much 2.5 drives in a 3.5 shell. Impossible. I believe the WD Raptor was (is?) almost a 2.5 drive with a heatsink large enough to bring it up to 3.5 [1] - this is going back a few years now though, I don't know if it is still true. So given equal RPM the 2.5 drive should have a faster full-stroke seek, but as has been pointed out, an SSD would be even better in this respect. How do you see an effort of 2.5 against 3.5? The opposite is fact. [1] http://www.latestpcnews.com/western-digital-launches-new-backplane-compatible-wdvelociraptor-hard-drive/ Only advertising, sorry. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Oswald Haan und Dr. Paul Suren Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: 2.5 vs 3.5 drive performance?
Hi, On Sat, 9 Oct 2010, Seth Mos wrote: With all drives, the used surface starts at the outer corner and does not reach to the inner corner. So 3.5 drives have in any case the bits sliding faster under the heads at a given rpm. The sequential throughput of the 3.5 inch disk is a lot higher over the 2.5 inch disks. The smaller platters of the 2.5 inch drives does mean that the end to end swipe of the head is smaller between the 2 formats. This has random seek performance benefits. The lesser mass of the 2.5 inch platters mean that it normally uses less power as well. And you can stack a lot more of them into a 2U box == more iops. Reflecting equal track and bit density, 3.5 needs less tracks due to longer circles. So random seek performance benefit too is on the 3.5 side. More iops per physical server volume is the only benefit of 2.5. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Oswald Haan und Dr. Paul Suren Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
linux.dell.com rsync targets
Hi, would it be possible to offer http://linux.dell.com/files/ via rsync? Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: linux.dell.com rsync targets
Hi, On Thu, 1 Apr 2010, David Pierce wrote: Probably not the right place to ask, but I really doubt they would. I'd just use curl and a bit of logic in a script: 1. Get a list of files. 2. If I don't have a file in that list, get it. 3. If I have it, does mine have the same size (and maybe timestamp) (poorman's checksum)? If not, get it. Good that (or if) you do it, but a crazy way I won't go. I will only mirror it if I get access via rsync. On 04/01/2010 02:58 PM, Eberhard Moenkeberg wrote: Hi, would it be possible to offer http://linux.dell.com/files/ via rsync? Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: Monitoring non-Dell drives with OMSA?
Hi, On Thu, 1 Apr 2010, Robin Bowes wrote: On 01/04/10 00:59, Eberhard Moenkeberg wrote: If you don't mention that the failed drive is a one-year item from Dell, it is covered by your 3-year warranty. Er, I wouldn't think so - all Dell items have unique serial numbers. They will know which items have 3-year support and which have only 1-year. Maybe too if you buy Seagate drives at second source. I doubt that very much too. Dell drives have Dell firmware. They're not going let me send in generic Seagate drives for replacement. Ok, but if a Dell drive will fail and you put instantly a second-source drive in for it, you will return the Dell drive. And in a second phase, you could put your remaining second-source drives into all the hotspare positions, so they would be very late in a chance to get directly returned to Dell. But my question is: why didn't you choose originally the 5-year warranty from Dell? You can get it, even if not choosable in the web interface. Our original systems have 3-year warranty. I have asked if the drives can be delivered with 3-year warranty too. You can relong the warranty to 5 years for the whole system, and that would cover all Dell-delivered drives. And/or try to get an advertise for drives without tray - I am currently struggling for an empty 3,5 tray for R710 which can accept a 2,5 SATA SSD - Dell can't deliver what I want (at least my sales representative is too much straightened to really understand act properly - I know it would be possible if I would know the part number), and the proper drive tray with 160 GB SATA disk (to throw away for me) shall cost me 160 Euros plus tax. So the trays are costly - ask to go without. I have been quoted the same price for the drive, with or without the drive tray. Crazy, Dell, really. You know you can buy drive trays here [1] don't you? Thanks, but my case is a special one: they don't offer 3,5 SAS-trays with an internal adapter for 2,5 SATA drives - which I would need to swap the SATA drive and put a SSD instead. [1] http://www.scsi4me.com/dell-0f238f-3-5-inch-sas-satau-drive-tray-caddy-carrier-for-poweredge-r410-r710-t610-etc.html Thanks again, also for all others frustrated by the Dell official sales persons. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: R710 w/ Mixed SSD + SAS Drives
Hi, On Tue, 23 Mar 2010, Peter Grandi wrote: As to buying separate drives, you can buy nice Corsair X256 SSDs from Dell, as an accessory, and they are known to be very good (Indilinx controller) performers (I am buyin eight, mostly to go into a T710). Can you please post an URL? Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
RE: External array showing as /dev/sda
Hi, On Sun, 21 Mar 2010, David Hubbard wrote: From: Behalf Of J. Epperson I'm somehow missing how getting the non-installable smaller GPT VD to be /dev/sda will change that scenario. The other responder echoed one of my initial thoughts when he suggested turning off the external array. That should do it. If I could get the internal raid controller to be /dev/sda, then the RHEL/centos installer will not care about the fact that the external array is too big and would require GPT to boot off of, then the installer would let me proceed. It was only an issue with it being /dev/sda since that made the installer think there was no way to writen an MBR and boot off of it. But, unplugging external did lead me the right direcation. What I've had to do is this: 1) Internal array I had desired to be single RAID 50 across 8 drives. Thanks to Dell's choice of LSI for their current raid controllers and LSI missing the feature that most others seem to have in being able to present parts of one array as multiple logical drives, I ended up having to waste the first two drives to make a RAID 1 mirror smaller than 2 TB and then only six remaining drives in the RAID 50. 2) Unplugged the external array and installed centos using normal non-GPT boot to the raid 1 virtual drive. It installed to /dev/sda. 3) After install, edit /boot/grub/device.map and changed it to show: (hd0) /dev/sdb Then: grub grub device (hd0) /dev/sda device (hd0) /dev/sda grub root (hd0,0) root (hd0,0) Filesystem type is ext2fs, partition type 0x83 grub setup (hd0) setup (hd0) Checking if /boot/grub/stage1 exists... no Checking if /grub/stage1 exists... yes Checking if /grub/stage2 exists... yes Checking if /grub/e2fs_stage1_5 exists... yes Running embed /grub/e2fs_stage1_5 (hd0)... 15 sectors are embedded. succeeded Running install /grub/stage1 (hd0) (hd0)1+15 p (hd0,0)/grub/stage2 /grub/grub.conf... succeeded Done. 4) Reboot, connect external array while server is rebooting, comes back up and boots off of internal array from bios, grub is happy because now it is set up for /dev/sdb. Only downside to this situation is if something were to fail and take the external array down the server won't boot since internal will go back to being /dev/sda. But if the external array is down then we've got issues anyway. :-) The real matter is the sequence of drivers within the initrd file. I can't tell about RH, but with SUSE you have /etc/sysconfig/kernel with a line like INITRD_MODULES=amd74xx megaraid_mbox processor thermal fan jbd ext3 \ edd aic7xxx qla2300 tg3 where you can change the sequence for your needs. After changing, the initrd file needs a rebuild. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: Dell git trees now available by git://
Hi, On Thu, 11 Feb 2010, Matt Domsch wrote: For those wanting to follow along and contribute to Dell's various open source projects which have published git trees at http://linux.dell.com/git, you can now use http, rsync, and git:// to pull from the projects. For example, the tree for DKMS is available via any of: git://linux.dell.com/dkms.git http://linux.dell.com/git/dkms.git rsync://linux.dell.com/git/dkms.git We've had both http and rsync available for some time, just not well advertised. We added git:// today. I hope you enjoy this new way to participate. ftp://ftp5.gwdg.de/pub/linux/dell/ http://ftp5.gwdg.de/pub/linux/dell/ rsync://ftp5.gwdg.de/pub/linux/dell/ will be a mirror of both repo/ and git/. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: RAID battery-backed cache - necessary? (was: Linux-PowerEdge Digest, Vol 68, Issue 35)
Hi, On Thu, 11 Feb 2010, Adam Nielsen wrote: This is perhaps off-topic too, but I have always wondered... You might also want to look at getting a hardware RAID card or daughterboard like the PERC-6i - these will allow you to set up a RAID-10/50/60 that will stripe all data between two drives, giving you another twofold speed increase. You probably want to make sure that your card has battery backup if you care about your database - otherwise a power cut can lose cached data rather painfully, even if you have a UPS. If you're moderately paranoid, or your data is important, you should disable on-drive write caching, as these never have battery backup - but this will cost you some speed. (This is a software issue, though, and won't affect your purchased configuration.) I am curious as to why this type of battery-backed cache is important. The OS would do a large amount of caching (Linux can have a disk cache of many gigabytes) which I am sure would be far more effective than the small caches on many RAID cards. Given that the OS, if configured properly, should provide the best type of caching possible, why is it still necessary to have RAID cache and on-drive cache? Surely these would provide no additional benefit? Anyway, just something I've often wondered about :-) Simple: because sudden total power loss could waste the buffer cache. The battery backuped controller cache would keep the data and write back after the next power-on (if it happens within the battery lifetime). Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: Third-party drives not permitted on Gen 11 servers
Hi, On Wed, 10 Feb 2010, Jason Edgecombe wrote: Please, email your Dell customer rep and complain about this! I did. I contacted my Dell customer rep and he forwarded my complain to the product support group. He said they may re-evaluate things if lots of people complain. (I can hope...) We don't have the Dell R710's, and I still complained. The mass of complaints here could easily get to knowledge to those relevant people at DELL by help of the participating DELL members. I guess at least Matt Domsch has already formed a proper signal against his marketing collegues, and I guess he has the power to place it right. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
RE: PE 2650 - which memory?
Hi, On Wed, 9 Dec 2009, Howard, Chris wrote: You guys are a lifesaver. This says I have two 512MB DIMMs in bank1_A and bank1_B and speed is 266 Mhz. As I remember it is DDR-1 reg ECC. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: Hidden DRAC commands
Hi, On Tue, 17 Nov 2009, Adam Nielsen wrote: While waiting for the DRAC firmware source to be released (stuff is happening, just very slowly) I thought I'd poke around a bit more in the DRAC5 firmware and see what I could find. For those who are interested, I discovered a hidden subcommand in racadm. The racadm util command allows you to perform certain debug-related tasks. racadm util help will list them, and you can get further information with racadm util help command. Note that the bfinfo command is misspelled in the help, it is really bdinfo. One interesting command is racadm util misc -opendir /etc which will give you a directory listing of the /etc folder. It sure beats my previous method of for I in /etc/*; do $I; done :-) I still haven't figured out how to get a proper console though... Many thanks for this, really many. Too much vendors do not see the efforts they can gain thru open-sourcing their software, by binding the brains of their users. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH Goettingen (GWDG) Am Fassberg 11, 37077 Goettingen URL:http://www.gwdg.de E-Mail: g...@gwdg.de Tel.: +49 (0)551 201-1510Fax:+49 (0)551 201-2150 Geschaeftsfuehrer: Prof. Dr. Bernhard Neumair Aufsichtsratsvorsitzender: Dipl.-Kfm. Markus Hoppe Sitz der Gesellschaft: Goettingen Registergericht: Goettingen Handelsregister-Nr. B 598 - ___ Linux-PowerEdge mailing list Linux-PowerEdge@dell.com https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
Re: How To: Replace PERC6 In The r710 With An Areca ARC-1680
Hi, On Wed, 28 Oct 2009, Brian A. Seklecki wrote: All: Here are a few quick notes photos on ripping the PERC6 out of an r710 and replacing it with an Areca ARC-1680IX-12 : Photos: http://digitalfreaks.org/~lavalamp/cp/thumbnails.php?album=52 1) The PERC6 performance is really poor. It's really slow to write on any RAID level. In RAID5, it averages writes ~30-50 MBps where as Areca cards average 300-400 MBps - It's even faster with ZFS on FreeBSD/amd64 RELENG_8 and some sysctl tweaks - The management interface is horrible, the documentation for the proprietary CLI is horrible, and after 10 years, its yet to be integrated into the IPMI BMC - It's probably not Dell's fault. LSI/QLogic makes the chip; blame them (But it's Dell that takes it in the hilt, repeatably, with every generation of server, when they renew the contract) I used to get faster disk I/O in my SBUS QLogic FAS408 in my SparcStation 20. Anyway, you get what you pay for with Dell;.. but you can get a lot more w/ Areca...for what you pay for with Dell!? 2) The latest r710 and PERC6 use the industry standard SAS SFF-8087 internal cable connector between the HBA and the backplane. That means you can just swap out the HBA, or if you're one of Dell's big embedded clients, order the unit w/o PERC6 or have Dell ship you whatever you want (3Ware?), probably. 3) Installation of the Areca ARC-1680IX-12 We used a PCIe x8 SAS RAID Card 2/512mb Cache. We purchased it off of NewEgg.com for appropriately the same price as a PERC6 adds to an r710. The LCD monitor and battery put it slightly over. The unit is PCIE-8x and there's 512 of DDR Cache onboard, 2GB DDR addon, with up to 4GB addon (PERC can't compete here). The card has it's own Intel IOP348 1200MHz CPU, an IPv4-enabled firmware (Web, SSH, Telnet, SNMP, SMTP), and very very decent mgmnt F/OSS support. You can see photos of the ARC-1680X-12 in Pictures 10, 13, 14. The external connectors on the card are: - RS232 over RJ11/RJ14 (The included cable terminates to DB9M) - Ethernet management - External SAS SFF-8088 3.1) Installation Notes In pictures 3 and 4, you can see the Dell SFF-8087 cables from the PERC6 terminating into the backplane. The cables run along a raceway on the right side of the case (oriented look at the faceplate) In pictures 1 and 2, if you remove the CPU/RAM cover and front fan bank, you can see the cables in the raceway. Trace them back to the PERC6 and disconnect them from the HBA (Dell used a proprietary ribbon connector on the PERC6 side; good thinking Dell! Look at how well proprietary worked for IBM, Sun, etc.). This connector can be seen in picture 6 and 12. . Pull the cables out of the raceway, then disconnect the SFF-8087 from the SAS backplane. As you can see in picture 6, the PERC6 is secured in place in a special PCIE port retainer that reminds me MCA or EISA cards in my PS/2 servers. The retainer is a T-16 hex nut head, as see in picture 8. Failing that, use an acetylene welder or plasma torch. Install your Areca card on the top PCI-E 8x/16x port (picture 15) Install the SFF-SFF cable, included with the Areca, as seen in picture into the r710 backplane raceway. See picture 16 and 20 You may need to run multiple SFF cables depending on your backplane configuration. Note: 90 degree angled cables would be best. Dell has the custom made apparently, I can't find them on the Interwebs, so I carefully bend the SFF connector. Restore the fan array and CPU/RAM cover. Note: Photo 21 the SAS/SFF cable goes above the cover, so tuck the cover under the cable (90deg cable mitigates this) Final cable routing seen in Picture 22. Restore case and experience an instantaneous I/O'gasm' as your $16k server screams to life. Did I mention that the Areca has volume management built into it? :} Walk directly to the local bar and buy everyone a few rounds with the money you saved by having a few fast severs instead a datacenter full of them trying to keep up with the Slony backlog. Good luck and let me know if you have any questions (or where to find some slick SFF-8087 cables with a 90deg angle connector) You can see a dmesg(8) for the r710 w/ areca for NetBSD/amd64 -current from last month at: http://www.nycbug.org/?NAV=dmesgd;f_dmesg=;f_bsd=;f_nick=;f_descr=;dmesgid=2016#2016 Splendid. Brian, you are one of the greatest. Really. Thanks for this highlight. Viele Gruesse Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org) -- Eberhard Moenkeberg Arbeitsgruppe IT-Infrastruktur E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551 - Gesellschaft fuer wissenschaftliche Datenverarbeitung mbH
