Steve Ed 2011-10-21, 21:40
Rita 2011-11-07, 10:58
Ted Dunning 2011-11-07, 22:06
Rita 2011-11-08, 00:34
Ted Dunning 2011-11-08, 00:53
Rita 2011-11-08, 12:32
Ted Dunning 2011-11-08, 12:38
Matt Foley 2011-11-11, 09:57
Koji Noguchi 2011-11-11, 17:26
Thanks for pointing that out. I was talking about machine chassis failure
since it is the more serious case, but should have pointed out that losing
single disks is subject to the same logic with smaller amounts of data.
If, however, an installation uses RAID-0 for higher read speed then a disk
loss is the same as loss of an entire RAID-0 drive set. In contrast, using
RAID-5 or 6 makes loss of a single disk less problematic, but hurts
On Fri, Nov 11, 2011 at 9:57 AM, Matt Foley <[EMAIL PROTECTED]> wrote:
> I agree with Ted's argument that 3x replication is way better than 2x.
> But I do have to point out that, since 0.20.204, the loss of a disk no
> longer causes the loss of a whole node (thankfully!) unless it's the system
> disk. So in the example given, if you estimate a disk failure every 2
> hours, each node only has to re-replicate about 2GB of data, not 12GB. So
> about 1-in-72 such failures risks data loss, rather than 1-in-12. Which is
> still unacceptable, so use 3x replication! :-)
> On Mon, Nov 7, 2011 at 4:53 PM, Ted Dunning <[EMAIL PROTECTED]> wrote:
>> 3x replication has two effects. One is reliability. This is probably
>> more important in large clusters than small.
>> Another important effect is data locality during map-reduce. Having 3x
>> replication allows mappers to have almost all invocations read from local
>> disk. 2x replication compromises this. Even where you don't have local
>> data, the bandwidth available to read from 3x replicated data is 1.5x the
>> bandwidth available for 2x replication.
>> To get a rough feel for how reliable you should consider a cluster, you
>> can do a pretty simple computation. If you have 12 x 2T on a single
>> machine and you lose that machine, the remaining copies of that data must
>> be replicated before another disk fails. With HDFS and block-level
>> replication, the remaining copies will be spread across the entire cluster
>> to any disk failure is reasonably like to cause data loss. For a 1000 node
>> cluster with 12000 disks, it is conservative to estimate a disk failure on
>> average every 2 hours. Each node will have replicate about 12GB of data
>> which will take about 500 seconds or about 9 or 10 minutes if you only use
>> 25% of your network for re-replication. The probability of a disk failure
>> during a 10 minute period is 1-exp(-10/120) = 8%. This means that roughly
>> 1 in 12 full machine failures might cause data loss. You can pick
>> whatever you like for the rate at which nodes die, but I don't think that
>> this is acceptable.
>> My numbers for disk failures are purposely somewhat pessimistic. If you
>> change the MTBF for disks to 10 years instead of 3 years, then the
>> probability of data loss after a machine failure drops, but only to about
>> Now, I would be the first to say that these numbers feel too high, but I
>> also would rather not experience enough data loss events to have a reliable
>> gut feel for how often they should occur.
>> My feeling is that 2x is fine for data you can reconstruct and which you
>> don't need to read really fast, but not good enough for data whose loss
>> will get you fired.
>> On Mon, Nov 7, 2011 at 7:34 PM, Rita <[EMAIL PROTECTED]> wrote:
>>> I have been running with 2x replication on a 500tb cluster. No issues
>>> whatsoever. 3x is for super paranoid.
>>> On Mon, Nov 7, 2011 at 5:06 PM, Ted Dunning <[EMAIL PROTECTED]>wrote:
>>>> Depending on which distribution and what your data center power limits
>>>> are you may save a lot of money by going with machines that have 12 x 2 or
>>>> 3 tb drives. With suitable engineering margins and 3 x replication you can
>>>> have 5 tb net data per node and 20 nodes per rack. If you want to go all
>>>> cowboy with 2x replication and little space to spare then you can double
>>>> that density.
>>>> On Monday, November 7, 2011, Rita <[EMAIL PROTECTED]> wrote:
Steve Ed 2011-11-11, 17:59
Matt Foley 2011-11-11, 18:15
Todd Lipcon 2011-11-11, 18:37
Matt Foley 2011-11-15, 22:29