6 Commits

Author SHA1 Message Date
sparknack
4d944aecf7
enhance: add disk file writer with Direct IO support (#43692)
issue: #43040
pr: #42665 

This patch introduces a disk file writer that supports Direct IO.

Currently, it is exclusively utilized during the QueryNode load process.

Below is its parameters:

1. `common.diskWriteMode` This parameter controls the write mode of the
local disk, which is used to write temporary data downloaded from remote
storage. Currently, only QueryNode uses 'common.diskWrite*' parameters.
Support for other components will be added in the future.
The options include 'direct' and 'buffered'. The default value is
'buffered'.

2. `common.diskWriteBufferSizeKb` Disk write buffer size in KB, only
used when disk write mode is 'direct', default is 64KB.
Current valid range is [4, 65536]. If the value is not aligned to 4KB,
it will be rounded up to the nearest multiple of 4KB.

3. `common.diskWriteNumThreads` This parameter controls the number of
writer threads used for disk write operations. The valid range is [0,
hardware_concurrency]. It is designed to limit the maximum concurrency
of disk write operations to reduce the impact on disk read performance.
For example, if you want to limit the maximum concurrency of disk write
operations to 1, you can set this parameter to 1.
The default value is 0, which means the caller will perform write
operations directly without using an additional writer thread pool. In
this case, the maximum concurrency of disk write operations is
determined by the caller's thread pool size.

Both parameters can be updated during runtime.

---------

Signed-off-by: Shawn Wang <shawn.wang@zilliz.com>
2025-08-08 12:13:41 +08:00
Chun Han
4fe8011a70
enhance: refine variable-length-type memory usage(#38736) (#43093)
related: #38736
pr: https://github.com/milvus-io/milvus/pull/39578

Signed-off-by: MrPresent-Han <chun.han@gmail.com>
Co-authored-by: MrPresent-Han <chun.han@gmail.com>
2025-07-04 18:26:45 +08:00
Chun Han
afc0ca77e4
enhance: Optimize index format for improved load performance (#41041)
related: #40838
pr: https://github.com/milvus-io/milvus/pull/40839

Signed-off-by: MrPresent-Han <chun.han@gmail.com>
Co-authored-by: MrPresent-Han <chun.han@gmail.com>
2025-04-15 07:07:38 +08:00
smellthemoon
6ef014d931
fix: get correct size when sealed segment chunked (#37062)
#37019

Signed-off-by: lixinguo <xinguo.li@zilliz.com>
Co-authored-by: lixinguo <xinguo.li@zilliz.com>
2024-10-25 12:01:31 +08:00
Bingyi Sun
a75bb85f3a
feat: support chunked column for sealed segment (#35764)
This PR splits sealed segment to chunked data to avoid unnecessary
memory copy and save memory usage when loading segments so that loading
can be accelerated.

To support rollback to previous version, we add an option
`multipleChunkedEnable` which is false by default.

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-10-12 15:04:52 +08:00
Bingyi Sun
f229f244d2
enhance: add chunk basic impl (#34634)
https://github.com/milvus-io/milvus/issues/35112
This pr would not affect milvus functionality by now.
It implments a Chunk memory layout that looks like 
```
VariableColumn
|offset|offset|offset|
|data|data|data|

```
We maybe move offsets to the beginning and add null bitmaps later but
not in this PR.
And mmap test will also be added in another PR.

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-08-01 10:29:51 +08:00