Gopal V created HDFS-4710:
-----------------------------
Summary: Turning off HDFS short-circuit checksums unexpectedly
slows down Hive
Key: HDFS-4710
URL: https://issues.apache.org/jira/browse/HDFS-4710
Project: Hadoop HDFS
Issue Type: Bug
Components: hdfs-client
Affects Versions: 2.0.4-alpha
Environment: Centos (EC2) + short-circuit reads on
Reporter: Gopal V
Priority: Minor
When short-circuit reads are on, HDFS client slows down when checksums are
turned off.
With checksums on, the query takes 45.341 seconds and with it turned off, it
takes 56.345 seconds. This is slower than the speeds observed when
short-circuiting is turned off.
The issue seems to be that FSDataInputStream.readByte() calls are directly
transferred to the disk fd when the checksums are turned off.
Even though all the columns are integers, the data being read will be read via
DataInputStream which does
{code}
public final int readInt() throws IOException {
int ch1 = in.read();
int ch2 = in.read();
int ch3 = in.read();
int ch4 = in.read();
{code}
To confirm, an strace of the Yarn container shows
{code}
26690 read(154, "B", 1) = 1
26690 read(154, "\250", 1) = 1
26690 read(154, ".", 1) = 1
26690 read(154, "\24", 1) = 1
{code}
To emulate this without the entirety of Hive code, I have written a simpler
test app
https://github.com/t3rmin4t0r/shortcircuit-reader
The jar will read a file in -bs <n> sized buffers. Running it with 1 byte
blocks gives similar results to the Hive test run.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
