System for load balancing by replicating portion of file while being read by first stream onto second device and reading portion with stream capable of accessing
First Claim
1. A method for improving load balancing in a file server comprising:
- determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon;
selecting a first retrieval stream reading a file;
replicating a portion of said file while being read by said first retrieval stream onto a second storage device; and
reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and system for improving load balancing in a file server is disclosed. The method includes determining the existence of an overload condition on a storage device, the storage device having a plurality of retrieval streams accessing at least one file thereon; selecting a first retrieval stream reading a file; replicating a portion of said file being read by said first retrieval stream onto a second storage device; and reading the replicated portion of said file on said second storage device with a retrieval stream capable of accessing the replicated portion of said file. The method and system enables the dynamic replication of data objects to respond to fluctuating user demand. The method and system is particularly useful in file servers such as multimedia servers delivering continuously in real time large multimedia files such as movies.
-
Citations
56 Claims
-
1. A method for improving load balancing in a file server comprising:
-
determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; selecting a first retrieval stream reading a file; replicating a portion of said file while being read by said first retrieval stream onto a second storage device; and reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A method for improving load balancing in a file server comprising:
-
determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; selecting a first retrieval stream reading a file; replicating a portion of said file being read by said first retrieval stream onto a second storage device; and reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file; wherein said replicating a portion of said file being read by said first retrieval stream onto a second storage device comprises; reading said file using said first retrieval stream from said first storage device; and writing said portion of said file using a retrieval stream capable of accessing said replicated portion of said file onto said second storage device. - View Dependent Claims (19)
-
-
16. A method for improving load balancing in a file server comprising:
-
determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; selecting a first retrieval stream reading a file; replicating a portion of said file being read by said first retrieval stream onto a second storage device; and reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file; wherein said file includes at least one permanent, primary segment; and wherein said replicated portion of said file comprises at least one secondary segment. - View Dependent Claims (17, 18, 20)
-
-
21. A method for improving load balancing in a file server comprising:
-
determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; selecting a first retrieval stream reading a file; replicating a portion of said file being read by said first retrieval stream onto a second storage device; and reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file; wherein said file comprises a plurality of blocks; and wherein replicating said portion of said file being read by said first retrieval stream onto said second storage device comprises; sequentially reading said plurality of blocks from said first retrieval stream; and writing one or more of said plurality of blocks onto said second storage device.
-
-
22. A method for improving load balancing in a file server comprising:
-
determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; selecting a first retrieval stream reading a file; replicating a portion of said file being read by said first retrieval stream onto a second storage device; and reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file; wherein said file comprises a plurality of segments, each of said plurality of segments comprising a plurality of blocks; and wherein replicating said portion of said file being read by said first retrieval stream onto said second storage device comprises; sequentially reading at least one of said segments from said first retrieval stream; and writing at least one of said segments on to said second storage device.
-
-
23. A method for improved load balancing in a file server comprising:
-
determining an excess number of permanently stored primary copies of a segment of a file; converting one of said permanently stored primary copies of said segment, not being accessed, to a temporary secondary copy of said segment, wherein said secondary copy of said segment is capable of being overwritten; and overwriting said secondary copy of said segment for improving the load balancing in said file server.
-
-
24. A method for improved load balancing in a file server comprising:
-
determining an excess number of permanently stored primary segments of a file; estimating a required number of primary segments based on load history; converting one of said permanently stored primary segments, not being accessed, to a temporary secondary segment wherein said secondary segment is capable of being overwritten; and overwriting said secondary for improving the load balancing in said file server. - View Dependent Claims (25)
-
-
26. A method for improved load balancing in a file server comprising:
-
determining a load on a temporarily stored secondary copy of a segment of a file; determining if said load on said secondary copy of said segment exceeds a threshold value, and converting said temporarily stored secondary copy of said segment to a permanently stored primary copy of said segment of said file, wherein said primary copy of said segment is prevented from being overwritten.
-
-
27. A method for improved load balancing in a file server comprising:
-
determining a load on a temporarily stored secondary segment of a file including determining a variable load history for said secondary segment; determining if said load on said secondary segment exceeds a threshold value; and converting said temporarily stored secondary segment to a permanently stored primary segment of said file, wherein said primary segment is prevented from being overwritten. - View Dependent Claims (28)
-
-
29. A system for improving load balancing in a file server comprising:
-
means for determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; means for selecting a first retrieval stream reading a file; means for replicating a portion of said file while being read by said first retrieval stream onto a second storage device; and means for reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file. - View Dependent Claims (30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42)
-
-
43. A system for improving load balancing in a file server comprising:
-
means for determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; means for selecting a first retrieval stream reading a file; means for replicating a portion of said file being read by said first retrieval stream onto a second storage device; and means for reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file; wherein said means for replicating a portion of said file being read by said first retrieval stream onto a second storage device comprises; means for reading said file using said first retrieval stream from said first storage device; and means for writing said portion of said file using a retrieval stream capable of accessing said replicated portion of said file onto said second storage device.
-
-
44. A system for improving load balancing in a file server comprising:
-
means for determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; means for selecting a first retrieval stream reading a file; means for replicating a portion of said file being read by said first retrieval stream onto a second storage device; and means for reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file; wherein said file includes at least one permanent, primary segment; and wherein said replicated portion of said file comprises at least one secondary segment. - View Dependent Claims (45, 46, 47, 48)
-
-
49. A system for improving load balancing in a file server comprising:
-
means for determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; means for selecting a first retrieval stream reading a file; means for replicating a portion of said file being read by said first retrieval stream onto a second storage device; and means for reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file; wherein said file comprises a plurality of blocks; and wherein said means for replicating said portion of said file being read by said first retrieval stream onto said second storage device comprises; means for sequentially reading said plurality of blocks from said first retrieval stream; and means for writing one or more of said plurality of blocks onto said second storage device.
-
-
50. A system for improving load balancing in a file server comprising:
-
means for determining the existence of an overload condition on a first storage device, said first storage device having a plurality of retrieval streams accessing at least one file thereon; means for selecting a first retrieval stream reading a file; means for replicating a portion of said file being read by said first retrieval stream onto a second storage device; and means for reading said replicated portion of said file on said second storage device with a retrieval stream capable of accessing said replicated portion of said file; wherein said file comprises a plurality of segments, each of said plurality of segments comprising a plurality of blocks; and wherein said means for replicating said portion of said file being read by said first retrieval stream onto said second storage device comprises; means for sequentially reading at least one of said segments from said first retrieval stream; and means for writing at least one of said segments on to said second storage device.
-
-
51. A system for improved load balancing in a file server comprising:
-
means for determining an excess number of permanently stored primary copies of a segment of a file; means for converting one of said permanently stored primary copies of said segment, not being accessed, to a temporary secondary copy of said segment, wherein said secondary copy of said segment is capable of being overwritten; and means for overwriting said secondary copy of said segment for improving the load balancing in said file server.
-
-
52. A system for improved load balancing in a file serve comprising:
-
means for determining an excess number of permanently store primary segment of a file; means for estimating a required number of primary segments based on load history; means for converting one of said permanently stored primary segments, not being accessed, to a temporary secondary segment, wherein said secondary segment is capable of being overwritten; and means for overwriting said secondary segment for improving the load balancing in said server. - View Dependent Claims (53)
-
-
54. A system for improved load balancing in a file server comprising:
-
means for determining a load on a temporarily stored secondary copy of a segment of a file; means for determining if said load on said secondary copy of said segment exceeds a threshold value; and means for converting said temporarily stored secondary copy of said segment to a permanently stored primary copy of said segment of said file, wherein said primary copy of said segment is prevented from being overwritten.
-
-
55. A system for improved load balancing in a file server comprising:
-
means for determining a load on a temporarily stored secondary segment of a file including means for determining a variable load history for said secondary segment; means for determining if said load on said secondary segment exceeds a threshold value; and means for converting said temporarily stored secondary segment to a permanently stored primary segment of said file, wherein said primary segment is prevented from being overwritten. - View Dependent Claims (56)
-
Specification