[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Release Note: Remove the deprecated method get/setWriteBufferSize from
Table and remove writeBufferSize from TableBuilder. Remove the
BufferedMutatorImpl from HTable. (was: Remove the deprecated method
get/setWriteBufferSize from Table. And remove the BufferedMutatorImpl from
HTable.)
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Fix For: 2.0.0, 3.0.0
>
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch, HBASE-18500-v6.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
> Review: https://reviews.apache.org/r/61454/
> Copy the comments from [~chia7712]. Remove the BufferdMutator brings four
> benefits.
> 1. correct the metrics (see HBASE-18476)
> 2. make HTable thread-safe (see HBASE-17368)
> 3. reduce the latency
> 4. get rid of some deprecated methods in Table
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Release Note: Remove the deprecated method get/setWriteBufferSize from
Table. And remove the BufferedMutatorImpl from HTable.
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Fix For: 2.0.0, 3.0.0
>
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch, HBASE-18500-v6.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
> Review: https://reviews.apache.org/r/61454/
> Copy the comments from [~chia7712]. Remove the BufferdMutator brings four
> benefits.
> 1. correct the metrics (see HBASE-18476)
> 2. make HTable thread-safe (see HBASE-17368)
> 3. reduce the latency
> 4. get rid of some deprecated methods in Table
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Resolution: Fixed
Fix Version/s: 3.0.0
2.0.0
Status: Resolved (was: Patch Available)
Pushed to master and branch-2. Thanks all for review.
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Fix For: 2.0.0, 3.0.0
>
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch, HBASE-18500-v6.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
> Review: https://reviews.apache.org/r/61454/
> Copy the comments from [~chia7712]. Remove the BufferdMutator brings four
> benefits.
> 1. correct the metrics (see HBASE-18476)
> 2. make HTable thread-safe (see HBASE-17368)
> 3. reduce the latency
> 4. get rid of some deprecated methods in Table
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v6.patch
Add a TODO(Copied the comments from [~anoop.hbase]) in v6.
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch, HBASE-18500-v6.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
> Review: https://reviews.apache.org/r/61454/
> Copy the comments from [~chia7712]. Remove the BufferdMutator brings four
> benefits.
> 1. correct the metrics (see HBASE-18476)
> 2. make HTable thread-safe (see HBASE-17368)
> 3. reduce the latency
> 4. get rid of some deprecated methods in Table
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Description:
Copied the test result from HBASE-17994.
Run start-hbase.sh in my local computer and use the default config to test with
PE tool.
{code}
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True randomWrite 1
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True asyncRandomWrite 1
{code}
Mean latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
| asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
50th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
| asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
99th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
| asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
In our internal 0.98 branch, the PE test result shows the async write has the
almost same latency with the blocking write. But for master branch, the result
shows the async write has better latency than the blocking client. Take a look
about the code, I thought the difference is the BufferedMutator. For master
branch, HTable don't have a write buffer and all write request will be flushed
directly. And user can use BufferedMutator when user want to perform
client-side buffering of writes. For the performance issue (autoFlush=True), I
thought we can use rpc caller directly in HTable's put method. Thanks.
Review: https://reviews.apache.org/r/61454/
Copy the comments from [~chia7712]. Remove the BufferdMutator brings four
benefits.
1. correct the metrics (see HBASE-18476)
2. make HTable thread-safe (see HBASE-17368)
3. reduce the latency
4. get rid of some deprecated methods in Table
was:
Copied the test result from HBASE-17994.
Run start-hbase.sh in my local computer and use the default config to test with
PE tool.
{code}
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True randomWrite 1
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True asyncRandomWrite 1
{code}
Mean latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
| asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
50th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
| asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
99th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
| asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
In our internal 0.98 branch, the PE test result shows the async write has the
almost same latency with the blocking write. But for master branch, the result
shows the async write has better latency than the blocking client. Take a look
about the code, I thought the difference is the BufferedMutator. For master
branch, HTable don't have a write buffer and all write request will be flushed
directly. And user can use BufferedMutator when user want to perform
client-side buffering of writes. For the performance issue (autoFlush=True), I
thought we can use rpc caller directly in HTable's put method. Thanks.
Review: https://reviews.apache.org/r/61454/
Copy the comments from [~chia7712]. Remove the BufferdMutator brings some
1. correct the metrics (see HBASE-18476)
2. make HTable thread-safe (see HBASE-17368)
3. reduce the latency
4. get rid of some deprecated methods in Table
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Description:
Copied the test result from HBASE-17994.
Run start-hbase.sh in my local computer and use the default config to test with
PE tool.
{code}
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True randomWrite 1
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True asyncRandomWrite 1
{code}
Mean latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
| asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
50th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
| asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
99th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
| asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
In our internal 0.98 branch, the PE test result shows the async write has the
almost same latency with the blocking write. But for master branch, the result
shows the async write has better latency than the blocking client. Take a look
about the code, I thought the difference is the BufferedMutator. For master
branch, HTable don't have a write buffer and all write request will be flushed
directly. And user can use BufferedMutator when user want to perform
client-side buffering of writes. For the performance issue (autoFlush=True), I
thought we can use rpc caller directly in HTable's put method. Thanks.
Review: https://reviews.apache.org/r/61454/
Copy the comments from [~chia7712]. Remove the brings
1. correct the metrics (see HBASE-18476)
2. make HTable thread-safe (see HBASE-17368)
3. reduce the latency
4. get rid of some deprecated methods in Table
was:
Copied the test result from HBASE-17994.
Run start-hbase.sh in my local computer and use the default config to test with
PE tool.
{code}
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True randomWrite 1
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True asyncRandomWrite 1
{code}
Mean latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
| asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
50th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
| asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
99th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
| asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
In our internal 0.98 branch, the PE test result shows the async write has the
almost same latency with the blocking write. But for master branch, the result
shows the async write has better latency than the blocking client. Take a look
about the code, I thought the difference is the BufferedMutator. For master
branch, HTable don't have a write buffer and all write request will be flushed
directly. And user can use BufferedMutator when user want to perform
client-side buffering of writes. For the performance issue (autoFlush=True), I
thought we can use rpc caller directly in HTable's put method. Thanks.
Review: https://reviews.apache.org/r/61454/
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 ||
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Description:
Copied the test result from HBASE-17994.
Run start-hbase.sh in my local computer and use the default config to test with
PE tool.
{code}
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True randomWrite 1
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True asyncRandomWrite 1
{code}
Mean latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
| asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
50th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
| asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
99th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
| asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
In our internal 0.98 branch, the PE test result shows the async write has the
almost same latency with the blocking write. But for master branch, the result
shows the async write has better latency than the blocking client. Take a look
about the code, I thought the difference is the BufferedMutator. For master
branch, HTable don't have a write buffer and all write request will be flushed
directly. And user can use BufferedMutator when user want to perform
client-side buffering of writes. For the performance issue (autoFlush=True), I
thought we can use rpc caller directly in HTable's put method. Thanks.
Review: https://reviews.apache.org/r/61454/
Copy the comments from [~chia7712]. Remove the BufferdMutator brings some
1. correct the metrics (see HBASE-18476)
2. make HTable thread-safe (see HBASE-17368)
3. reduce the latency
4. get rid of some deprecated methods in Table
was:
Copied the test result from HBASE-17994.
Run start-hbase.sh in my local computer and use the default config to test with
PE tool.
{code}
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True randomWrite 1
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True asyncRandomWrite 1
{code}
Mean latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
| asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
50th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
| asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
99th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
| asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
In our internal 0.98 branch, the PE test result shows the async write has the
almost same latency with the blocking write. But for master branch, the result
shows the async write has better latency than the blocking client. Take a look
about the code, I thought the difference is the BufferedMutator. For master
branch, HTable don't have a write buffer and all write request will be flushed
directly. And user can use BufferedMutator when user want to perform
client-side buffering of writes. For the performance issue (autoFlush=True), I
thought we can use rpc caller directly in HTable's put method. Thanks.
Review: https://reviews.apache.org/r/61454/
Copy the comments from [~chia7712]. Remove the brings
1. correct the metrics (see HBASE-18476)
2. make HTable thread-safe (see HBASE-17368)
3. reduce the latency
4. get rid of some deprecated methods in Table
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 ||
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Hadoop Flags: Incompatible change
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
> Review: https://reviews.apache.org/r/61454/
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v5.patch
The failed ut is not related. Retry for Hadoop QA. [~chia7712] [~ram_krish]
[~stack] Any more concerns?
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch, HBASE-18500-v5.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
> Review: https://reviews.apache.org/r/61454/
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v5.patch
Retry for Hadoop QA.
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch,
> HBASE-18500-v5.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
> Review: https://reviews.apache.org/r/61454/
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v5.patch
Fix the javadoc issue. And findbugs problem was addressed by HBASE-18315.
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch, HBASE-18500-v5.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
> Review: https://reviews.apache.org/r/61454/
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Description:
Copied the test result from HBASE-17994.
Run start-hbase.sh in my local computer and use the default config to test with
PE tool.
{code}
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True randomWrite 1
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True asyncRandomWrite 1
{code}
Mean latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
| asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
50th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
| asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
99th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
| asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
In our internal 0.98 branch, the PE test result shows the async write has the
almost same latency with the blocking write. But for master branch, the result
shows the async write has better latency than the blocking client. Take a look
about the code, I thought the difference is the BufferedMutator. For master
branch, HTable don't have a write buffer and all write request will be flushed
directly. And user can use BufferedMutator when user want to perform
client-side buffering of writes. For the performance issue (autoFlush=True), I
thought we can use rpc caller directly in HTable's put method. Thanks.
Review: https://reviews.apache.org/r/61454/
was:
Copied the test result from HBASE-17994.
Run start-hbase.sh in my local computer and use the default config to test with
PE tool.
{code}
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True randomWrite 1
./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
--nomapred --autoFlush=True asyncRandomWrite 1
{code}
Mean latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
| asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
50th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
| asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
99th latency test result.
|| || Test1 || Test2 || Test3 || Test4 || Test5 ||
| randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
| asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
In our internal 0.98 branch, the PE test result shows the async write has the
almost same latency with the blocking write. But for master branch, the result
shows the async write has better latency than the blocking client. Take a look
about the code, I thought the difference is the BufferedMutator. For master
branch, HTable don't have a write buffer and all write request will be flushed
directly. And user can use BufferedMutator when user want to perform
client-side buffering of writes. For the performance issue (autoFlush=True), I
thought we can use rpc caller directly in HTable's put method. Thanks.
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v4.patch
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: (was: HBASE-18500-v4.patch)
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v4.patch
Fix ut and findbugs.
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch, HBASE-18500-v4.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v3.patch
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch,
> HBASE-18500-v3.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Issue Type: Improvement (was: Bug)
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Improvement
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v2.patch
Attach a initial patch.
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Bug
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch, HBASE-18500-v2.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Assignee: Guanghao Zhang
Status: Patch Available (was: Open)
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Bug
>Reporter: Guanghao Zhang
>Assignee: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
[jira] [Updated] (HBASE-18500) Performance issue: Don't use BufferedMutator for HTable's put method
[
https://issues.apache.org/jira/browse/HBASE-18500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Guanghao Zhang updated HBASE-18500:
---
Attachment: HBASE-18500-v1.patch
> Performance issue: Don't use BufferedMutator for HTable's put method
>
>
> Key: HBASE-18500
> URL: https://issues.apache.org/jira/browse/HBASE-18500
> Project: HBase
> Issue Type: Bug
>Reporter: Guanghao Zhang
> Attachments: HBASE-18500-v1.patch
>
>
> Copied the test result from HBASE-17994.
> Run start-hbase.sh in my local computer and use the default config to test
> with PE tool.
> {code}
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True randomWrite 1
> ./bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=10
> --nomapred --autoFlush=True asyncRandomWrite 1
> {code}
> Mean latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 164.39 | 161.22 | 164.78 | 140.61 | 151.69 |
> | asyncRandomWrite | 122.29 | 125.58 | 122.23 | 113.18 | 123.02 |
> 50th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 130.00 | 125.00 | 123.00 | 112.00 | 121.00 |
> | asyncRandomWrite | 95.00 | 97.00 | 95.00 | 88.00 | 95.00 |
> 99th latency test result.
> || || Test1 || Test2 || Test3 || Test4 || Test5 ||
> | randomWrite | 600.00 | 600.00 | 650.00 | 404.00 | 425.00 |
> | asyncRandomWrite | 339.00 | 327.00 | 297.00 | 311.00 | 318.00 |
> In our internal 0.98 branch, the PE test result shows the async write has the
> almost same latency with the blocking write. But for master branch, the
> result shows the async write has better latency than the blocking client.
> Take a look about the code, I thought the difference is the BufferedMutator.
> For master branch, HTable don't have a write buffer and all write request
> will be flushed directly. And user can use BufferedMutator when user want to
> perform client-side buffering of writes. For the performance issue
> (autoFlush=True), I thought we can use rpc caller directly in HTable's put
> method. Thanks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
