Skip to content

Commit 74c12d3

Browse files
authored
Merge pull request #32643 from j9t/patch-1
docs: correct capitalization, add hyphenation, remove double spaces
2 parents 23cc4de + 67c726e commit 74c12d3

File tree

1 file changed

+11
-11
lines changed

1 file changed

+11
-11
lines changed
Lines changed: 11 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
---
2-
title: shuffle sharding
2+
title: Shuffle-sharding
33
id: shuffle-sharding
44
date: 2020-03-04
55
full_link:
@@ -18,28 +18,28 @@ We are often concerned with insulating different flows of requests
1818
from each other, so that a high-intensity flow does not crowd out low-intensity flows.
1919
A simple way to put requests into queues is to hash some
2020
characteristics of the request, modulo the number of queues, to get
21-
the index of the queue to use. The hash function uses as input
22-
characteristics of the request that align with flows. For example, in
21+
the index of the queue to use. The hash function uses as input
22+
characteristics of the request that align with flows. For example, in
2323
the Internet this is often the 5-tuple of source and destination
2424
address, protocol, and source and destination port.
2525

2626
That simple hash-based scheme has the property that any high-intensity flow
2727
will crowd out all the low-intensity flows that hash to the same queue.
2828
Providing good insulation for a large number of flows requires a large
29-
number of queues, which is problematic. Shuffle sharding is a more
29+
number of queues, which is problematic. Shuffle-sharding is a more
3030
nimble technique that can do a better job of insulating the low-intensity
31-
flows from the high-intensity flows. The terminology of shuffle sharding uses
31+
flows from the high-intensity flows. The terminology of shuffle-sharding uses
3232
the metaphor of dealing a hand from a deck of cards; each queue is a
33-
metaphorical card. The shuffle sharding technique starts with hashing
33+
metaphorical card. The shuffle-sharding technique starts with hashing
3434
the flow-identifying characteristics of the request, to produce a hash
35-
value with dozens or more of bits. Then the hash value is used as a
35+
value with dozens or more of bits. Then the hash value is used as a
3636
source of entropy to shuffle the deck and deal a hand of cards
37-
(queues). All the dealt queues are examined, and the request is put
38-
into one of the examined queues with the shortest length. With a
37+
(queues). All the dealt queues are examined, and the request is put
38+
into one of the examined queues with the shortest length. With a
3939
modest hand size, it does not cost much to examine all the dealt cards
4040
and a given low-intensity flow has a good chance to dodge the effects of a
41-
given high-intensity flow. With a large hand size it is expensive to examine
41+
given high-intensity flow. With a large hand size it is expensive to examine
4242
the dealt queues and more difficult for the low-intensity flows to dodge the
43-
collective effects of a set of high-intensity flows. Thus, the hand size
43+
collective effects of a set of high-intensity flows. Thus, the hand size
4444
should be chosen judiciously.
4545

0 commit comments

Comments
 (0)