This is an automated email from the ASF dual-hosted git repository.
yiguolei pushed a commit to branch branch-2.1
in repository https://gitbox.apache.org/repos/asf/doris.git
commit 46cadc9856cfca06a5f2b8885d32a2d06df9b43f
Author: AlexYue <yj976240...@gmail.com>
AuthorDate: Fri Jan 26 21:13:32 2024 +0800
[minor](Prefetch) log slow prefetch io operation #30415
---
be/src/common/config.cpp | 2 +-
be/src/io/fs/buffered_reader.cpp | 9 +++++++++
be/src/io/fs/buffered_reader.h | 3 ++-
3 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/be/src/common/config.cpp b/be/src/common/config.cpp
index 355a90ab7f9..58bb9156b5b 100644
--- a/be/src/common/config.cpp
+++ b/be/src/common/config.cpp
@@ -1148,7 +1148,7 @@ DEFINE_Int32(ingest_binlog_work_pool_size, "-1");
// Download binlog rate limit, unit is KB/s, 0 means no limit
DEFINE_Int32(download_binlog_rate_limit_kbs, "0");
-DEFINE_mInt32(buffered_reader_read_timeout_ms, "20000");
+DEFINE_mInt32(buffered_reader_read_timeout_ms, "600000");
DEFINE_Bool(enable_snapshot_action, "false");
diff --git a/be/src/io/fs/buffered_reader.cpp b/be/src/io/fs/buffered_reader.cpp
index 258749fc067..bdbfb04fa30 100644
--- a/be/src/io/fs/buffered_reader.cpp
+++ b/be/src/io/fs/buffered_reader.cpp
@@ -550,6 +550,10 @@ Status PrefetchBuffer::read_buffer(size_t off, const char*
out, size_t buf_len,
reset_offset((off / _size) * _size);
return read_buffer(off, out, buf_len, bytes_read);
}
+ auto start = std::chrono::steady_clock::now();
+ // The baseline time is calculated by dividing the size of each buffer by
MB/s.
+ // If it exceeds this value, it is considered a slow I/O operation.
+ constexpr auto read_time_baseline =
std::chrono::seconds(s_max_pre_buffer_size / 1024 / 1024);
{
std::unique_lock lck {_lock};
// buffer must be prefetched or it's closed
@@ -566,6 +570,11 @@ Status PrefetchBuffer::read_buffer(size_t off, const char*
out, size_t buf_len,
return Status::OK();
}
}
+ auto duration = std::chrono::duration_cast<std::chrono::seconds>(
+ std::chrono::steady_clock::now() - start);
+ if (duration > read_time_baseline) [[unlikely]] {
+ LOG_WARNING("The prefetch io is too slow");
+ }
RETURN_IF_ERROR(_prefetch_status);
// there is only parquet would do not sequence read
// it would read the end of the file first
diff --git a/be/src/io/fs/buffered_reader.h b/be/src/io/fs/buffered_reader.h
index 2f8eb465cdf..ca939dba94d 100644
--- a/be/src/io/fs/buffered_reader.h
+++ b/be/src/io/fs/buffered_reader.h
@@ -356,6 +356,8 @@ struct PrefetchBuffer :
std::enable_shared_from_this<PrefetchBuffer> {
size_t merge_small_ranges(size_t off, int range_index) const;
};
+constexpr int64_t s_max_pre_buffer_size = 4 * 1024 * 1024; // 4MB
+
/**
* A buffered reader that prefetch data in the daemon thread pool.
*
@@ -420,7 +422,6 @@ private:
PrefetchRange _file_range;
const std::vector<PrefetchRange>* _random_access_ranges = nullptr;
const IOContext* _io_ctx = nullptr;
- int64_t s_max_pre_buffer_size = 4 * 1024 * 1024; // 4MB
std::vector<std::shared_ptr<PrefetchBuffer>> _pre_buffers;
int64_t _whole_pre_buffer_size;
bool _initialized = false;
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org
