Tony Posted February 24, 2010 Report Posted February 24, 2010 We're using these: http://www.seagate.com/ww/v/index.jsp?locale=en-US&name=st3300657ss-chta-15k.7-sas-300gb-hd&vgnextoid=6664470bd8cc1210VgnVCM1000001a48090aRCRD&vgnextchannel=9ac2421baad8e110VgnVCM100000f5ee0a0aRCRD&reqPage=Model For pluto anyways but across all machines it could be a set of 15k.6 or 15k.5 as well. We're looking more reliability than speed so it makes no difference to us. As far as SAS drives I've seen them fail in production as well. I remember 2 in the last year both 15k RPM drives. Oh and Titan it's going to get swapped out as well it was on the to-do. It's a tough game to play people want the biggest and the best and SAS cost a lot more over SATA disks. Raptors were a great middle ground but it got to a point where for us there was no cost difference if we just switched the entire fleet. A lot of hosts though still use sata disks and some not any raid at all. They're using the enterprise sata disks typically which cost a lot more but not as much as sas disks still. They have close to the same annual failure rate advertised anyways. Quote
speedturtle Posted February 24, 2010 Report Posted February 24, 2010 Notice posted: http://forums.hawkhost.com/showthread.php?t=907 Basically 15K SAS over 10K SATA drives is the only change. Good call. I applaud the move. Well this is pretty amusing we deployed the replacement Pluto only to discover a failed drive! It died literally after deployment. So much for SAS being more reliable the name Pluto is what's cursed! And a good thing, too, that you have a sense of humor to carry you through Pluto's unbelievably bad luck. Quote
Brian Posted February 24, 2010 Report Posted February 24, 2010 It's not a sense of humor, really, he's just so delusional from the lack of sleep Quote
speedturtle Posted February 25, 2010 Report Posted February 25, 2010 It's not a sense of humor, really, he's just so delusional from the lack of sleep Hmm...if this is delusional, I wonder what happens when he is deranged? Quote
Cody R. Posted February 25, 2010 Report Posted February 25, 2010 Hmm...if this is delusional, I wonder what happens when he is deranged? Pretty sure he's close, migrations are time consuming, boring and tedious. Quote
Tony Posted February 28, 2010 Report Posted February 28, 2010 The drive gods are angry for us questioning them. Marlin two raptor drives failed and replaced without issue: http://forums.hawkhost.com/showthread.php?t=925 Saturn SAS drive failed and replaced: http://forums.hawkhost.com/showthread.php?t=926 Interesting error came from the saturn one: saturn Sense data: Hardware error (TRACK FOLLOWING ERROR). Controller 1, channel 0, SCSI device ID 1, LUN 0, cdb [28 00 0d 3d 44 00 00 02 00 00 00 00], data [70 00 04 00 00 00 00 00 00 00 00 00 09 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00] Physical drive removed: controller 1, connector 0, device 1, S/N (serial here). Logical device is degraded: controller 1, logical device 0 ("RAID10-A"). [/CODE] So yes it's true SAS drives do fail! Odd number of failures this week though that's 5 in a weeks span. Quote
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.