Changes between Version 1 and Version 2 of VolunteerDataArchival

Timestamp:

Nov 23, 2011, 9:27:08 AM (12 years ago)

Author:

davea

Comment:

--

VolunteerDataArchival

@@ -31 +31 @@
    We don't consider direct client-to-client communication.
 
+Recovering from the failure of a host, using techniques like replication,
+involves uploading data from a 2nd host, then downloading it to a 3rd host.
+Each of these steps may take days.
+This, for volunteer storage the ratio
+
+ average time to failure / average time to recover
+
+may be fairly small (like 100).
+In other distributed storage systems (such as RAIDs) this ratio may
+be on the order of 100,000.
+Thus, these systems can modeled as a sequence of individual
+failures and recoveries.
+
+Volunteer storage, on the other hand, must be modeled as process
+in which multiple recoveries may be in progress at the same time,
+and new failures may occur during these recoveries.
 There are two basic techniques for achieving reliable storage using
 unreliable resources:
 
- * '''Replication''': a file 
+'''Replication''': a file is divided into N pieces,
+and each piece is stored on M hosts.
+If a replica is lost, and there another replica,
+that replica is uploaded to the server, then downloaded to another host.
 
- * '''Coding''': with Reed-Solomon coding, a file is divided into N 'packets',
-  and an additional K checksum packets are generated.
-  The original data can be reconstructed from any N of these N+K packets.
+
+
+'''Coding''': with Reed-Solomon coding, a file is divided into N 'packets',
+and an additional K checksum packets are generated.
+The original data can be reconstructed from any N of these N+K packets.
+
+In