|
Last change
on this file was
4723af6,
checked in by Brian Warner <warner@…>, at 2017-06-06T10:20:49Z
|
|
LAFS now stands for "Least-Authority File Store" rather than "Least-Authority File System". refs #2345
Signed-off-by: Daira Hopwood <daira@…>
|
-
Property mode set to
100644
|
|
File size:
1.1 KB
|
| Line | |
|---|
| 1 | The lossmodel.lyx file is the source document for an in-progress paper |
|---|
| 2 | that analyzes the probability of losing files stored in a Tahoe-LAFS |
|---|
| 3 | file store under various scenarios. It describes: |
|---|
| 4 | |
|---|
| 5 | 1. How to estimate peer reliabilities, based on peer MTBF failure |
|---|
| 6 | data. |
|---|
| 7 | |
|---|
| 8 | 2. How to compute file loss probabilities, based on a given set of |
|---|
| 9 | shares stored on peers with estimated reliabilities. The peer |
|---|
| 10 | reliabilities do not have to be uniform, and the model takes into |
|---|
| 11 | account the file repair process. |
|---|
| 12 | |
|---|
| 13 | 3. How to estimate Tahoe parameters for k (shares needed), n (shares |
|---|
| 14 | distributed) and A (repair interval) to achieve a file reliability |
|---|
| 15 | target. |
|---|
| 16 | |
|---|
| 17 | 4. How to compute the estimated repair cost over time, discounted at |
|---|
| 18 | a fixed rate, of maintaining a file for a time period T. |
|---|
| 19 | |
|---|
| 20 | Future work will also address the latter three issues in the context |
|---|
| 21 | of "non-aggressive" repair, where repair will only be performed if |
|---|
| 22 | too many shares are lost, and it will also extend the repair cost |
|---|
| 23 | estimation model to suggest cost functions appropriate for common |
|---|
| 24 | network architectures. |
|---|
| 25 | |
|---|
| 26 | A PDF of the current version of the file may be downloaded from: |
|---|
| 27 | |
|---|
| 28 | http://willden.org/~shawn/lossmodel.pdf |
|---|
Note: See
TracBrowser
for help on using the repository browser.
