This is an automated email from the ASF dual-hosted git repository.
zhouky pushed a commit to branch branch-0.3
in repository https://gitbox.apache.org/repos/asf/incubator-celeborn.git
The following commit(s) were added to refs/heads/branch-0.3 by this push:
new fc34af568 [CELEBORN-803][FOLLOWUP] Make ```rpcAskTimeout``` default to
60s
fc34af568 is described below
commit fc34af5687294fa1e29eba316654356da9a4c345
Author: zky.zhoukeyong <[email protected]>
AuthorDate: Mon Jul 17 23:53:52 2023 +0800
[CELEBORN-803][FOLLOWUP] Make ```rpcAskTimeout``` default to 60s
### What changes were proposed in this pull request?
As title.
### Why are the changes needed?
Timeout of ```RpcEndpointRef.ask``` is controlled by
```celeborn.rpc.askTimeout```,
so we also need to increase ```celeborn.rpc.askTimeout``` to extend the
timeout of commit files.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Passes GA and manual test.
Closes #1725 from waitinfuture/803-fu.
Authored-by: zky.zhoukeyong <[email protected]>
Signed-off-by: zky.zhoukeyong <[email protected]>
(cherry picked from commit 1109e2c8f4468ab6d19632a6f3e7afba89e9b913)
Signed-off-by: zky.zhoukeyong <[email protected]>
---
common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala | 4 ++--
docs/configuration/client.md | 2 +-
docs/configuration/network.md | 2 +-
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git
a/common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala
b/common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala
index 42d85efe9..507ff22f3 100644
--- a/common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala
+++ b/common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala
@@ -1289,7 +1289,7 @@ object CelebornConf extends Logging {
.doc("Timeout for RPC ask operations. " +
"It's recommended to set at least `240s` when `HDFS` is enabled in
`celeborn.storage.activeTypes`")
.timeConf(TimeUnit.MILLISECONDS)
- .createWithDefaultString("30s")
+ .createWithDefaultString("60s")
val RPC_DISPATCHER_THREADS: OptionalConfigEntry[Int] =
buildConf("celeborn.rpc.dispatcher.threads")
@@ -3191,7 +3191,7 @@ object CelebornConf extends Logging {
.version("0.3.0")
.intConf
.checkValue(v => v > 0, "value must be positive")
- .createWithDefault(3)
+ .createWithDefault(4)
val CLIENT_COMMIT_IGNORE_EXCLUDED_WORKERS: ConfigEntry[Boolean] =
buildConf("celeborn.client.commitFiles.ignoreExcludedWorker")
diff --git a/docs/configuration/client.md b/docs/configuration/client.md
index e6f3d6ba9..a3d1cca42 100644
--- a/docs/configuration/client.md
+++ b/docs/configuration/client.md
@@ -62,7 +62,7 @@ license: |
| celeborn.client.push.timeout | 120s | Timeout for a task to push data rpc
message. This value should better be more than twice of
`celeborn.<module>.push.timeoutCheck.interval` | 0.3.0 |
| celeborn.client.registerShuffle.maxRetries | 3 | Max retry times for client
to register shuffle. | 0.3.0 |
| celeborn.client.registerShuffle.retryWait | 3s | Wait time before next retry
if register shuffle failed. | 0.3.0 |
-| celeborn.client.requestCommitFiles.maxRetries | 3 | Max retry times for
requestCommitFiles RPC. | 0.3.0 |
+| celeborn.client.requestCommitFiles.maxRetries | 4 | Max retry times for
requestCommitFiles RPC. | 0.3.0 |
| celeborn.client.reserveSlots.maxRetries | 3 | Max retry times for client to
reserve slots. | 0.3.0 |
| celeborn.client.reserveSlots.rackware.enabled | false | Whether need to
place different replicates on different racks when allocating slots. | 0.3.0 |
| celeborn.client.reserveSlots.retryWait | 3s | Wait time before next retry if
reserve slots failed. | 0.3.0 |
diff --git a/docs/configuration/network.md b/docs/configuration/network.md
index cc66b985b..52b39b483 100644
--- a/docs/configuration/network.md
+++ b/docs/configuration/network.md
@@ -44,7 +44,7 @@ license: |
| celeborn.network.memory.allocator.verbose.metric | false | Weather to enable
verbose metric for pooled allocator. | 0.3.0 |
| celeborn.network.timeout | 240s | Default timeout for network operations. |
0.2.0 |
| celeborn.port.maxRetries | 1 | When port is occupied, we will retry for max
retry times. | 0.2.0 |
-| celeborn.rpc.askTimeout | 30s | Timeout for RPC ask operations. It's
recommended to set at least `240s` when `HDFS` is enabled in
`celeborn.storage.activeTypes` | 0.2.0 |
+| celeborn.rpc.askTimeout | 60s | Timeout for RPC ask operations. It's
recommended to set at least `240s` when `HDFS` is enabled in
`celeborn.storage.activeTypes` | 0.2.0 |
| celeborn.rpc.connect.threads | 64 | | 0.2.0 |
| celeborn.rpc.dispatcher.threads | <undefined> | Threads number of
message dispatcher event loop | 0.3.0 |
| celeborn.rpc.io.threads | <undefined> | Netty IO thread number of
NettyRpcEnv to handle RPC request. The default threads number is the number of
runtime available processors. | 0.2.0 |
