Joe L. Posted October 14, 2009 Share Posted October 14, 2009 I started a parity check on the most recent release of unRAID. All my disks were spun down... this made the initial "parity check" speed pretty slow, at 0KB/s. The initial calc says it will finish in about 260,934.6 minutes (a bit over 6 months) ... and hopefully, when the disks spin up and are doing a bit faster than 0KB/s, even sooner than that. Quote Link to comment
RobJ Posted October 14, 2009 Share Posted October 14, 2009 As it is going to be very hard for anyone to *ever* beat this 'performance mark', I just had to add it to the bottom of the User Benchmarks page! Quote Link to comment
Joe L. Posted October 14, 2009 Author Share Posted October 14, 2009 As it is going to be very hard for anyone to *ever* beat this 'performance mark', I just had to add it to the bottom of the User Benchmarks page! It will really skew the "average" performance numbers... Quote Link to comment
Rajahal Posted October 15, 2009 Share Posted October 15, 2009 So what's the story with this? Is this a bug with 4.5-beta7? Quote Link to comment
Joe L. Posted October 15, 2009 Author Share Posted October 15, 2009 So what's the story with this? Is this a bug with 4.5-beta7? No, not a bug... just that unRAID averages the statistics for parity speed calculations and when I first pressed the button all the disks were spun down. Once the disks all spun up, the estimated duration looked a lot shorter. All versions of unRAID work this way. Until the disks spin up, the speed of the parity check is 0KB/s. It is basic math (almost) KB-per-minute = KB-per-second * 60 disk-size-in-KB / KB-per-minute = parity calc estimated length in minutes so, filling in the numbers... 976762552 / ( 0 * 60 ) = 260934.6 minutes Of course, the dividing by zero takes some special programming... otherwise it would take the parity check a lot longer. Joe L. Quote Link to comment
Rajahal Posted October 15, 2009 Share Posted October 15, 2009 Ah, I see. So if I manually spun down all my drives, then started a parity check, I should see something similar (though a different number based on the size of my array). Correct? Quote Link to comment
Kaygee Posted October 15, 2009 Share Posted October 15, 2009 Based on the size of your parity drive. I can see someone "beating" Joe, very soon with an even longer parity check estimate. ;-) Quote Link to comment
Kaygee Posted October 15, 2009 Share Posted October 15, 2009 You mean like this? Yes. Exactly like that. Quote Link to comment
jupilerman Posted October 17, 2009 Share Posted October 17, 2009 Can I join the club Quote Link to comment
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.