[CASSANDRA-6746] Reads have a slow ramp up in speed - ASF JIRA

XML

Word

Printable

JSON

On a physical four node cluister I am doing a big write and then a big read. The read takes a long time to ramp up to respectable speeds.

2.1_vs_2.0_read.png
20/Feb/14 20:59
57 kB
Ryan McGuire
6746.blockdev_setra.full.png
17/Mar/14 19:03
82 kB
Ryan McGuire
6746.blockdev_setra.zoomed.png
17/Mar/14 19:03
105 kB
Ryan McGuire
6746.buffered_io_tweaks.logs.tar.gz
23/Mar/14 21:22
29 kB
Ryan McGuire
6746.buffered_io_tweaks.write-flush-compact-mixed.png
24/Mar/14 05:26
93 kB
Ryan McGuire
6746.buffered_io_tweaks.write-read-flush-compact.png
24/Mar/14 04:33
82 kB
Ryan McGuire
6746.txt
12/Mar/14 11:08
0.9 kB
Benedict Elliott Smith
6746-buffered-io-tweaks.png
23/Mar/14 19:36
77 kB
Ryan McGuire
6746-patched.png
13/Mar/14 03:14
65 kB
Ryan McGuire
buffered-io-tweaks.patch
23/Mar/14 09:26
7 kB
Pavel Yaskevich
cassandra-2.0-bdplab-trial-fincore.tar.bz2
28/Feb/14 16:43
354 kB
Ryan McGuire
cassandra-2.1-bdplab-trial-fincore.tar.bz2
28/Feb/14 16:43
202 kB
Ryan McGuire

is superceded by

CASSANDRA-6916 Preemptive opening of compaction result

relates to

CASSANDRA-6916 Preemptive opening of compaction result