test/milvus
1
0
Fork 0
mirror of https://gitee.com/milvus-io/milvus.git synced 2024-12-04 04:49:08 +08:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity

merge confict

Browse Source 
Former-commit-id: 3e82d3abfab86d9f64b293a45d4f8f008bfda5ac
This commit is contained in:
zhenwu 2019-10-23 14:55:03 +08:00
commit 79baa075bc
22 changed files with 352 additions and 282 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
CHANGELOG.md
View File

@ -7,11 +7,12 @@ Please mark all change in change log and use the ticket from JIRA.
## Bug
## Improvement
- \#64 - Improvement dump function in scheduler
- \#82 - Move easyloggingpp into "external" directory
## Feature
## Task
# Milvus 0.5.0 (TODO)
# Milvus 0.5.0 (2019-10-21)
## Bug
- MS-568 - Fix gpuresource free error

49
README.md
View File

@ -1,7 +1,9 @@
![Milvuslogo](https://github.com/milvus-io/docs/blob/branch-0.5.0/assets/milvus_logo.png)
![Milvuslogo](https://github.com/milvus-io/docs/blob/master/assets/milvus_logo.png)
![LICENSE](https://img.shields.io/badge/license-Apache--2.0-brightgreen)
![Language](https://img.shields.io/badge/language-C%2B%2B-blue)
[![codebeat badge](https://codebeat.co/badges/e030a4f6-b126-4475-a938-4723d54ec3a7?style=plastic)](https://codebeat.co/projects/github-com-jinhai-cn-milvus-master)
- [Slack Community](https://join.slack.com/t/milvusio/shared_invite/enQtNzY1OTQ0NDI3NjMzLWNmYmM1NmNjOTQ5MGI5NDhhYmRhMGU5M2NhNzhhMDMzY2MzNDdlYjM5ODQ5MmE3ODFlYzU3YjJkNmVlNDQ2ZTk)
- [Twitter](https://twitter.com/milvusio)
@ -13,34 +15,49 @@
# Welcome to Milvus
Firstly, welcome, and thanks for your interest in [Milvus](https://milvus.io)! ​​No matter who you are, what you do, we greatly appreciate your contribution to help us reinvent data science with Milvus.​ :beers:
## What is Milvus
Milvus is an open source vector search engine which provides state-of-the-art similarity search and analysis for billion-scale feature vectors.
Milvus is an open source similarity search engine for massive feature vectors. Designed with heterogeneous computing architecture for the best cost efficiency. Searches over billion-scale vectors take only milliseconds with minimum computing resources.
Milvus provides stable Python, Java and C++ APIs.
Keep up-to-date with newest releases and latest updates by reading Milvus [release notes](https://milvus.io/docs/en/Releases/v0.4.0/).
Keep up-to-date with newest releases and latest updates by reading Milvus [release notes](https://milvus.io/docs/en/Releases/v0.5.0/).
- GPU-accelerated search engine
- Heterogeneous computing
Milvus uses CPU/GPU heterogeneous computing architecture to process feature vectors, and are orders of magnitudes faster than traditional databases.
Milvus is designed with heterogeneous computing architecture for the best performance and cost efficiency.
- Various indexes
- Multiple indexes
Milvus supports quantization indexing, tree-based indexing, and graph indexing algorithms.
Milvus supports a variety of indexing types that employs quantization, tree-based, and graph indexing techniques.
- Intelligent scheduling
- Intelligent resource management
Milvus optimizes the search computation and index building according to your data size and available resources.
Milvus automatically adapts search computation and index building processes based on your datasets and available resources.
- Horizontal scalability
Milvus expands computation and storage by adding nodes during runtime, which allows you to scale the data size without redesigning the system.
Milvus supports online / offline expansion to scale both storage and computation resources with simple commands.
- High availability
Milvus is integrated with Kubernetes framework so that all single point of failures could be avoided.
- High compatibility
Milvus is compatible with almost all deep learning models and major programming languages such as Python, Java and C++, etc.
- Ease of use
Milvus can be easily installed in a few steps and enables you to exclusively focus on feature vectors.
- Visualized monitor
You can track system performance on Prometheus-based GUI monitor dashboards.
## Architecture
![Milvus_arch](https://github.com/milvus-io/docs/blob/branch-0.5.0/assets/milvus_arch.jpg)
![Milvus_arch](https://github.com/milvus-io/docs/blob/master/assets/milvus_arch.png)
## Get started
@ -117,20 +134,20 @@ To edit Milvus settings in `conf/server_config.yaml` and `conf/log_config.conf`,
#### Run Python example code
Make sure [Python 3.4](https://www.python.org/downloads/) or higher is already installed and in use.
Make sure [Python 3.5](https://www.python.org/downloads/) or higher is already installed and in use.
Install Milvus Python SDK.
```shell
# Install Milvus Python SDK
$ pip install pymilvus==0.2.0
$ pip install pymilvus==0.2.3
```
Create a new file `example.py`, and add [Python example code](https://github.com/milvus-io/pymilvus/blob/master/examples/AdvancedExample.py) to it.
Run the example code.
```python
```shell
# Run Milvus Python example
$ python3 example.py
```

4
ci/jenkins/scripts/coverage.sh
View File

@ -132,8 +132,8 @@ ${LCOV_CMD} -r "${FILE_INFO_OUTPUT}" -o "${FILE_INFO_OUTPUT_NEW}" \
"*/src/server/Server.cpp" \
"*/src/server/DBWrapper.cpp" \
"*/src/server/grpc_impl/GrpcServer.cpp" \
"*/src/utils/easylogging++.h" \
"*/src/utils/easylogging++.cc"
"*/src/external/easyloggingpp/easylogging++.h" \
"*/src/external/easyloggingpp/easylogging++.cc"
if [ $? -ne 0 ]; then
echo "gen ${FILE_INFO_OUTPUT_NEW} failed"

14
codecov.yaml Normal file
View File

@ -0,0 +1,14 @@
#Configuration File for CodeCov
coverage:
precision: 2
round: down
range: "70...100"
status:
project: on
patch: yes
changes: no
comment:
layout: "header, diff, changes, tree"
behavior: default

1
core/build-support/lint_exclusions.txt
View File

@ -6,4 +6,5 @@
*easylogging++*
*SqliteMetaImpl.cpp
*src/grpc*
*src/external*
*milvus/include*

6
core/coverage.sh
View File

@ -122,8 +122,10 @@ ${LCOV_CMD} -r "${FILE_INFO_OUTPUT}" -o "${FILE_INFO_OUTPUT_NEW}" \
"*/src/server/Server.cpp" \
"*/src/server/DBWrapper.cpp" \
"*/src/server/grpc_impl/GrpcServer.cpp" \
"*/src/utils/easylogging++.h" \
"*/src/utils/easylogging++.cc"
"*/src/external/easyloggingpp/easylogging++.h" \
"*/src/external/easyloggingpp/easylogging++.cc" \
"*/src/external/*"
if [ $? -ne 0 ]; then
echo "generate ${FILE_INFO_OUTPUT_NEW} failed"
exit -2

8
core/src/CMakeLists.txt
View File

@ -64,6 +64,13 @@ set(scheduler_files
${scheduler_task_files}
)
aux_source_directory(${MILVUS_ENGINE_SRC}/external/easyloggingpp external_easyloggingpp_files)
aux_source_directory(${MILVUS_ENGINE_SRC}/external/nlohmann external_nlohmann_files)
set(external_files
${external_easyloggingpp_files}
${external_nlohmann_files}
)
aux_source_directory(${MILVUS_ENGINE_SRC}/server server_files)
aux_source_directory(${MILVUS_ENGINE_SRC}/server/grpc_impl grpc_server_files)
aux_source_directory(${MILVUS_ENGINE_SRC}/utils utils_files)
@ -77,6 +84,7 @@ set(engine_files
${db_insert_files}
${db_meta_files}
${metrics_files}
${external_files}
${utils_files}
${wrapper_files}
)

0
core/src/utils/easylogging++.cc → core/src/external/easyloggingpp/easylogging++.cc vendored
View File

0
core/src/utils/easylogging++.h → core/src/external/easyloggingpp/easylogging++.h vendored
View File

2
core/src/index/knowhere/knowhere/common/Log.h
View File

@ -17,7 +17,7 @@
#pragma once
#include "utils/easylogging++.h"
#include "external/easyloggingpp/easylogging++.h"
namespace knowhere {

2
core/src/index/unittest/CMakeLists.txt
View File

@ -20,7 +20,7 @@ set(basic_libs
)
set(util_srcs
${MILVUS_ENGINE_SRC}/utils/easylogging++.cc
${MILVUS_ENGINE_SRC}/external/easyloggingpp/easylogging++.cc
${INDEX_SOURCE_DIR}/knowhere/knowhere/index/vector_index/helpers/FaissGpuResourceMgr.cpp
${INDEX_SOURCE_DIR}/knowhere/knowhere/index/vector_index/helpers/FaissIO.cpp
${INDEX_SOURCE_DIR}/knowhere/knowhere/index/vector_index/helpers/IndexParameter.cpp

2
core/src/main.cpp
View File

@ -23,11 +23,11 @@
#include <string>
#include "../version.h"
#include "external/easyloggingpp/easylogging++.h"
#include "metrics/Metrics.h"
#include "server/Server.h"
#include "utils/CommonUtil.h"
#include "utils/SignalUtil.h"
#include "utils/easylogging++.h"
INITIALIZE_EASYLOGGINGPP

130
core/src/scheduler/task/SearchTask.cpp
View File

@ -307,71 +307,71 @@ XSearchTask::MergeTopkToResultSet(const std::vector<int64_t>& input_ids, const s
}
}
void
XSearchTask::MergeTopkArray(std::vector<int64_t>& tar_ids, std::vector<float>& tar_distance, uint64_t& tar_input_k,
const std::vector<int64_t>& src_ids, const std::vector<float>& src_distance,
uint64_t src_input_k, uint64_t nq, uint64_t topk, bool ascending) {
if (src_ids.empty() || src_distance.empty()) {
return;
}
uint64_t output_k = std::min(topk, tar_input_k + src_input_k);
std::vector<int64_t> id_buf(nq * output_k, -1);
std::vector<float> dist_buf(nq * output_k, 0.0);
uint64_t buf_k, src_k, tar_k;
uint64_t src_idx, tar_idx, buf_idx;
uint64_t src_input_k_multi_i, tar_input_k_multi_i, buf_k_multi_i;
for (uint64_t i = 0; i < nq; i++) {
src_input_k_multi_i = src_input_k * i;
tar_input_k_multi_i = tar_input_k * i;
buf_k_multi_i = output_k * i;
buf_k = src_k = tar_k = 0;
while (buf_k < output_k && src_k < src_input_k && tar_k < tar_input_k) {
src_idx = src_input_k_multi_i + src_k;
tar_idx = tar_input_k_multi_i + tar_k;
buf_idx = buf_k_multi_i + buf_k;
if ((ascending && src_distance[src_idx] < tar_distance[tar_idx]) ||
(!ascending && src_distance[src_idx] > tar_distance[tar_idx])) {
id_buf[buf_idx] = src_ids[src_idx];
dist_buf[buf_idx] = src_distance[src_idx];
src_k++;
} else {
id_buf[buf_idx] = tar_ids[tar_idx];
dist_buf[buf_idx] = tar_distance[tar_idx];
tar_k++;
}
buf_k++;
}
if (buf_k < output_k) {
if (src_k < src_input_k) {
while (buf_k < output_k && src_k < src_input_k) {
src_idx = src_input_k_multi_i + src_k;
buf_idx = buf_k_multi_i + buf_k;
id_buf[buf_idx] = src_ids[src_idx];
dist_buf[buf_idx] = src_distance[src_idx];
src_k++;
buf_k++;
}
} else {
while (buf_k < output_k && tar_k < tar_input_k) {
tar_idx = tar_input_k_multi_i + tar_k;
buf_idx = buf_k_multi_i + buf_k;
id_buf[buf_idx] = tar_ids[tar_idx];
dist_buf[buf_idx] = tar_distance[tar_idx];
tar_k++;
buf_k++;
}
}
}
}
tar_ids.swap(id_buf);
tar_distance.swap(dist_buf);
tar_input_k = output_k;
}
// void
// XSearchTask::MergeTopkArray(std::vector<int64_t>& tar_ids, std::vector<float>& tar_distance, uint64_t& tar_input_k,
// const std::vector<int64_t>& src_ids, const std::vector<float>& src_distance,
// uint64_t src_input_k, uint64_t nq, uint64_t topk, bool ascending) {
// if (src_ids.empty() || src_distance.empty()) {
// return;
// }
//
// uint64_t output_k = std::min(topk, tar_input_k + src_input_k);
// std::vector<int64_t> id_buf(nq * output_k, -1);
// std::vector<float> dist_buf(nq * output_k, 0.0);
//
// uint64_t buf_k, src_k, tar_k;
// uint64_t src_idx, tar_idx, buf_idx;
// uint64_t src_input_k_multi_i, tar_input_k_multi_i, buf_k_multi_i;
//
// for (uint64_t i = 0; i < nq; i++) {
// src_input_k_multi_i = src_input_k * i;
// tar_input_k_multi_i = tar_input_k * i;
// buf_k_multi_i = output_k * i;
// buf_k = src_k = tar_k = 0;
// while (buf_k < output_k && src_k < src_input_k && tar_k < tar_input_k) {
// src_idx = src_input_k_multi_i + src_k;
// tar_idx = tar_input_k_multi_i + tar_k;
// buf_idx = buf_k_multi_i + buf_k;
// if ((ascending && src_distance[src_idx] < tar_distance[tar_idx]) ||
// (!ascending && src_distance[src_idx] > tar_distance[tar_idx])) {
// id_buf[buf_idx] = src_ids[src_idx];
// dist_buf[buf_idx] = src_distance[src_idx];
// src_k++;
// } else {
// id_buf[buf_idx] = tar_ids[tar_idx];
// dist_buf[buf_idx] = tar_distance[tar_idx];
// tar_k++;
// }
// buf_k++;
// }
//
// if (buf_k < output_k) {
// if (src_k < src_input_k) {
// while (buf_k < output_k && src_k < src_input_k) {
// src_idx = src_input_k_multi_i + src_k;
// buf_idx = buf_k_multi_i + buf_k;
// id_buf[buf_idx] = src_ids[src_idx];
// dist_buf[buf_idx] = src_distance[src_idx];
// src_k++;
// buf_k++;
// }
// } else {
// while (buf_k < output_k && tar_k < tar_input_k) {
// tar_idx = tar_input_k_multi_i + tar_k;
// buf_idx = buf_k_multi_i + buf_k;
// id_buf[buf_idx] = tar_ids[tar_idx];
// dist_buf[buf_idx] = tar_distance[tar_idx];
// tar_k++;
// buf_k++;
// }
// }
// }
// }
//
// tar_ids.swap(id_buf);
// tar_distance.swap(dist_buf);
// tar_input_k = output_k;
//}
} // namespace scheduler
} // namespace milvus

8
core/src/scheduler/task/SearchTask.h
View File

@ -42,10 +42,10 @@ class XSearchTask : public Task {
MergeTopkToResultSet(const std::vector<int64_t>& input_ids, const std::vector<float>& input_distance,
uint64_t input_k, uint64_t nq, uint64_t topk, bool ascending, scheduler::ResultSet& result);
static void
MergeTopkArray(std::vector<int64_t>& tar_ids, std::vector<float>& tar_distance, uint64_t& tar_input_k,
const std::vector<int64_t>& src_ids, const std::vector<float>& src_distance, uint64_t src_input_k,
uint64_t nq, uint64_t topk, bool ascending);
// static void
// MergeTopkArray(std::vector<int64_t>& tar_ids, std::vector<float>& tar_distance, uint64_t& tar_input_k,
// const std::vector<int64_t>& src_ids, const std::vector<float>& src_distance, uint64_t
// src_input_k, uint64_t nq, uint64_t topk, bool ascending);
public:
TableFileSchemaPtr file_;

2
core/src/utils/Log.h
View File

@ -17,7 +17,7 @@
#pragma once
#include "utils/easylogging++.h"
#include "external/easyloggingpp/easylogging++.h"
namespace milvus {

2
core/src/utils/LogUtil.h
View File

@ -17,8 +17,8 @@
#pragma once
#include "external/easyloggingpp/easylogging++.h"
#include "utils/Status.h"
#include "utils/easylogging++.h"
#include <sstream>
#include <string>

10
core/unittest/CMakeLists.txt
View File

@ -60,6 +60,13 @@ set(scheduler_files
${scheduler_optimizer_files}
)
aux_source_directory(${MILVUS_ENGINE_SRC}/external/easyloggingpp external_easyloggingpp_files)
aux_source_directory(${MILVUS_ENGINE_SRC}/external/nlohmann external_nlohmann_files)
set(external_files
${external_easyloggingpp_files}
${external_nlohmann_files}
)
aux_source_directory(${MILVUS_ENGINE_SRC}/server server_files)
aux_source_directory(${MILVUS_ENGINE_SRC}/server/grpc_impl grpc_server_files)
aux_source_directory(${MILVUS_ENGINE_SRC}/utils utils_files)
@ -74,7 +81,7 @@ set(helper_files
${MILVUS_ENGINE_SRC}/utils/TimeRecorder.cpp
${MILVUS_ENGINE_SRC}/utils/Status.cpp
${MILVUS_ENGINE_SRC}/utils/ValidationUtil.cpp
${MILVUS_ENGINE_SRC}/utils/easylogging++.cc
${MILVUS_ENGINE_SRC}/external/easyloggingpp/easylogging++.cc
)
set(common_files
@ -85,6 +92,7 @@ set(common_files
${db_insert_files}
${db_meta_files}
${metrics_files}
${external_files}
${scheduler_files}
${wrapper_files}
${helper_files}

381
core/unittest/db/test_search.cpp
View File

@ -30,6 +30,7 @@ namespace ms = milvus::scheduler;
void
BuildResult(std::vector<int64_t>& output_ids,
std::vector<float>& output_distance,
uint64_t input_k,
uint64_t topk,
uint64_t nq,
bool ascending) {
@ -39,9 +40,15 @@ BuildResult(std::vector<int64_t>& output_ids,
output_distance.resize(nq * topk);
for (uint64_t i = 0; i < nq; i++) {
for (uint64_t j = 0; j < topk; j++) {
//insert valid items
for (uint64_t j = 0; j < input_k; j++) {
output_ids[i * topk + j] = (int64_t)(drand48() * 100000);
output_distance[i * topk + j] = ascending ? (j + drand48()) : ((topk - j) + drand48());
output_distance[i * topk + j] = ascending ? (j + drand48()) : ((input_k - j) + drand48());
}
//insert invalid items
for (uint64_t j = input_k; j < topk; j++) {
output_ids[i * topk + j] = -1;
output_distance[i * topk + j] = -1.0;
}
}
}
@ -83,23 +90,32 @@ CheckTopkResult(const std::vector<int64_t>& input_ids_1,
ASSERT_EQ(input_ids_1.size(), input_distance_1.size());
ASSERT_EQ(input_ids_2.size(), input_distance_2.size());
uint64_t input_k1 = input_ids_1.size() / nq;
uint64_t input_k2 = input_ids_2.size() / nq;
for (int64_t i = 0; i < nq; i++) {
std::vector<float>
src_vec(input_distance_1.begin() + i * input_k1, input_distance_1.begin() + (i + 1) * input_k1);
src_vec(input_distance_1.begin() + i * topk, input_distance_1.begin() + (i + 1) * topk);
src_vec.insert(src_vec.end(),
input_distance_2.begin() + i * input_k2,
input_distance_2.begin() + (i + 1) * input_k2);
input_distance_2.begin() + i * topk,
input_distance_2.begin() + (i + 1) * topk);
if (ascending) {
std::sort(src_vec.begin(), src_vec.end());
} else {
std::sort(src_vec.begin(), src_vec.end(), std::greater<float>());
}
uint64_t n = std::min(topk, input_k1 + input_k2);
//erase invalid items
std::vector<float>::iterator iter;
for (iter = src_vec.begin(); iter != src_vec.end();) {
if (*iter < 0.0)
iter = src_vec.erase(iter);
else
++iter;
}
uint64_t n = std::min(topk, result[i].size());
for (uint64_t j = 0; j < n; j++) {
if (result[i][j].first < 0) {
continue;
}
if (src_vec[j] != result[i][j].second) {
std::cout << src_vec[j] << " " << result[i][j].second << std::endl;
}
@ -110,12 +126,13 @@ CheckTopkResult(const std::vector<int64_t>& input_ids_1,
} // namespace
void MergeTopkToResultSetTest(uint64_t topk_1, uint64_t topk_2, uint64_t nq, uint64_t topk, bool ascending) {
void
MergeTopkToResultSetTest(uint64_t topk_1, uint64_t topk_2, uint64_t nq, uint64_t topk, bool ascending) {
std::vector<int64_t> ids1, ids2;
std::vector<float> dist1, dist2;
ms::ResultSet result;
BuildResult(ids1, dist1, topk_1, nq, ascending);
BuildResult(ids2, dist2, topk_2, nq, ascending);
BuildResult(ids1, dist1, topk_1, topk, nq, ascending);
BuildResult(ids2, dist2, topk_2, topk, nq, ascending);
ms::XSearchTask::MergeTopkToResultSet(ids1, dist1, topk_1, nq, topk, ascending, result);
ms::XSearchTask::MergeTopkToResultSet(ids2, dist2, topk_2, nq, topk, ascending, result);
CheckTopkResult(ids1, dist1, ids2, dist2, topk, nq, ascending, result);
@ -134,70 +151,72 @@ TEST(DBSearchTest, MERGE_RESULT_SET_TEST) {
MergeTopkToResultSetTest(TOP_K, TOP_K, NQ, TOP_K, false);
/* test3, id1/dist1 small topk */
MergeTopkToResultSetTest(TOP_K/2, TOP_K, NQ, TOP_K, true);
MergeTopkToResultSetTest(TOP_K/2, TOP_K, NQ, TOP_K, false);
MergeTopkToResultSetTest(TOP_K / 2, TOP_K, NQ, TOP_K, true);
MergeTopkToResultSetTest(TOP_K / 2, TOP_K, NQ, TOP_K, false);
/* test4, id1/dist1 small topk, id2/dist2 small topk */
MergeTopkToResultSetTest(TOP_K/2, TOP_K/3, NQ, TOP_K, true);
MergeTopkToResultSetTest(TOP_K/2, TOP_K/3, NQ, TOP_K, false);
MergeTopkToResultSetTest(TOP_K / 2, TOP_K / 3, NQ, TOP_K, true);
MergeTopkToResultSetTest(TOP_K / 2, TOP_K / 3, NQ, TOP_K, false);
}
void MergeTopkArrayTest(uint64_t topk_1, uint64_t topk_2, uint64_t nq, uint64_t topk, bool ascending) {
std::vector<int64_t> ids1, ids2;
std::vector<float> dist1, dist2;
ms::ResultSet result;
BuildResult(ids1, dist1, topk_1, nq, ascending);
BuildResult(ids2, dist2, topk_2, nq, ascending);
uint64_t result_topk = std::min(topk, topk_1 + topk_2);
ms::XSearchTask::MergeTopkArray(ids1, dist1, topk_1, ids2, dist2, topk_2, nq, topk, ascending);
if (ids1.size() != result_topk * nq) {
std::cout << ids1.size() << " " << result_topk * nq << std::endl;
}
ASSERT_TRUE(ids1.size() == result_topk * nq);
ASSERT_TRUE(dist1.size() == result_topk * nq);
for (uint64_t i = 0; i < nq; i++) {
for (uint64_t k = 1; k < result_topk; k++) {
if (ascending) {
if (dist1[i * result_topk + k] < dist1[i * result_topk + k - 1]) {
std::cout << dist1[i * result_topk + k - 1] << " " << dist1[i * result_topk + k] << std::endl;
}
ASSERT_TRUE(dist1[i * result_topk + k] >= dist1[i * result_topk + k - 1]);
} else {
if (dist1[i * result_topk + k] > dist1[i * result_topk + k - 1]) {
std::cout << dist1[i * result_topk + k - 1] << " " << dist1[i * result_topk + k] << std::endl;
}
ASSERT_TRUE(dist1[i * result_topk + k] <= dist1[i * result_topk + k - 1]);
}
}
}
}
//void MergeTopkArrayTest(uint64_t topk_1, uint64_t topk_2, uint64_t nq, uint64_t topk, bool ascending) {
// std::vector<int64_t> ids1, ids2;
// std::vector<float> dist1, dist2;
// ms::ResultSet result;
// BuildResult(ids1, dist1, topk_1, topk, nq, ascending);
// BuildResult(ids2, dist2, topk_2, topk, nq, ascending);
// uint64_t result_topk = std::min(topk, topk_1 + topk_2);
// ms::XSearchTask::MergeTopkArray(ids1, dist1, topk_1, ids2, dist2, topk_2, nq, topk, ascending);
// if (ids1.size() != result_topk * nq) {
// std::cout << ids1.size() << " " << result_topk * nq << std::endl;
// }
// ASSERT_TRUE(ids1.size() == result_topk * nq);
// ASSERT_TRUE(dist1.size() == result_topk * nq);
// for (uint64_t i = 0; i < nq; i++) {
// for (uint64_t k = 1; k < result_topk; k++) {
// float f0 = dist1[i * topk + k - 1];
// float f1 = dist1[i * topk + k];
// if (ascending) {
// if (f1 < f0) {
// std::cout << f0 << " " << f1 << std::endl;
// }
// ASSERT_TRUE(f1 >= f0);
// } else {
// if (f1 > f0) {
// std::cout << f0 << " " << f1 << std::endl;
// }
// ASSERT_TRUE(f1 <= f0);
// }
// }
// }
//}
TEST(DBSearchTest, MERGE_ARRAY_TEST) {
uint64_t NQ = 15;
uint64_t TOP_K = 64;
//TEST(DBSearchTest, MERGE_ARRAY_TEST) {
// uint64_t NQ = 15;
// uint64_t TOP_K = 64;
//
// /* test1, id1/dist1 valid, id2/dist2 empty */
// MergeTopkArrayTest(TOP_K, 0, NQ, TOP_K, true);
// MergeTopkArrayTest(TOP_K, 0, NQ, TOP_K, false);
// MergeTopkArrayTest(0, TOP_K, NQ, TOP_K, true);
// MergeTopkArrayTest(0, TOP_K, NQ, TOP_K, false);
/* test1, id1/dist1 valid, id2/dist2 empty */
MergeTopkArrayTest(TOP_K, 0, NQ, TOP_K, true);
MergeTopkArrayTest(TOP_K, 0, NQ, TOP_K, false);
MergeTopkArrayTest(0, TOP_K, NQ, TOP_K, true);
MergeTopkArrayTest(0, TOP_K, NQ, TOP_K, false);
/* test2, id1/dist1 valid, id2/dist2 valid */
MergeTopkArrayTest(TOP_K, TOP_K, NQ, TOP_K, true);
MergeTopkArrayTest(TOP_K, TOP_K, NQ, TOP_K, false);
/* test3, id1/dist1 small topk */
MergeTopkArrayTest(TOP_K/2, TOP_K, NQ, TOP_K, true);
MergeTopkArrayTest(TOP_K/2, TOP_K, NQ, TOP_K, false);
MergeTopkArrayTest(TOP_K, TOP_K/2, NQ, TOP_K, true);
MergeTopkArrayTest(TOP_K, TOP_K/2, NQ, TOP_K, false);
/* test4, id1/dist1 small topk, id2/dist2 small topk */
MergeTopkArrayTest(TOP_K/2, TOP_K/3, NQ, TOP_K, true);
MergeTopkArrayTest(TOP_K/2, TOP_K/3, NQ, TOP_K, false);
MergeTopkArrayTest(TOP_K/3, TOP_K/2, NQ, TOP_K, true);
MergeTopkArrayTest(TOP_K/3, TOP_K/2, NQ, TOP_K, false);
}
// /* test2, id1/dist1 valid, id2/dist2 valid */
// MergeTopkArrayTest(TOP_K, TOP_K, NQ, TOP_K, true);
// MergeTopkArrayTest(TOP_K, TOP_K, NQ, TOP_K, false);
//
// /* test3, id1/dist1 small topk */
// MergeTopkArrayTest(TOP_K/2, TOP_K, NQ, TOP_K, true);
// MergeTopkArrayTest(TOP_K/2, TOP_K, NQ, TOP_K, false);
// MergeTopkArrayTest(TOP_K, TOP_K/2, NQ, TOP_K, true);
// MergeTopkArrayTest(TOP_K, TOP_K/2, NQ, TOP_K, false);
//
// /* test4, id1/dist1 small topk, id2/dist2 small topk */
// MergeTopkArrayTest(TOP_K/2, TOP_K/3, NQ, TOP_K, true);
// MergeTopkArrayTest(TOP_K/2, TOP_K/3, NQ, TOP_K, false);
// MergeTopkArrayTest(TOP_K/3, TOP_K/2, NQ, TOP_K, true);
// MergeTopkArrayTest(TOP_K/3, TOP_K/2, NQ, TOP_K, false);
//}
TEST(DBSearchTest, REDUCE_PERF_TEST) {
int32_t index_file_num = 478; /* sift1B dataset, index files num */
@ -206,8 +225,8 @@ TEST(DBSearchTest, REDUCE_PERF_TEST) {
std::vector<int32_t> thread_vec = {4, 8};
std::vector<int32_t> nq_vec = {1, 10, 100};
std::vector<int32_t> topk_vec = {1, 4, 16, 64};
int32_t NQ = nq_vec[nq_vec.size()-1];
int32_t TOPK = topk_vec[topk_vec.size()-1];
int32_t NQ = nq_vec[nq_vec.size() - 1];
int32_t TOPK = topk_vec[topk_vec.size() - 1];
std::vector<std::vector<int64_t>> id_vec;
std::vector<std::vector<float>> dist_vec;
@ -217,7 +236,7 @@ TEST(DBSearchTest, REDUCE_PERF_TEST) {
/* generate testing data */
for (i = 0; i < index_file_num; i++) {
BuildResult(input_ids, input_distance, TOPK, NQ, ascending);
BuildResult(input_ids, input_distance, TOPK, TOPK, NQ, ascending);
id_vec.push_back(input_ids);
dist_vec.push_back(input_distance);
}
@ -255,114 +274,114 @@ TEST(DBSearchTest, REDUCE_PERF_TEST) {
rc1.RecordSection("reduce done");
///////////////////////////////////////////////////////////////////////////////////////
/* method-2 */
std::vector<std::vector<int64_t>> id_vec_2(index_file_num);
std::vector<std::vector<float>> dist_vec_2(index_file_num);
std::vector<uint64_t> k_vec_2(index_file_num);
for (i = 0; i < index_file_num; i++) {
CopyResult(id_vec_2[i], dist_vec_2[i], top_k, id_vec[i], dist_vec[i], TOPK, nq);
k_vec_2[i] = top_k;
}
std::string str2 = "Method-2 " + std::to_string(max_thread_num) + " " +
std::to_string(nq) + " " + std::to_string(top_k);
milvus::TimeRecorder rc2(str2);
for (step = 1; step < index_file_num; step *= 2) {
for (i = 0; i + step < index_file_num; i += step * 2) {
ms::XSearchTask::MergeTopkArray(id_vec_2[i], dist_vec_2[i], k_vec_2[i],
id_vec_2[i + step], dist_vec_2[i + step], k_vec_2[i + step],
nq, top_k, ascending);
}
}
ms::XSearchTask::MergeTopkToResultSet(id_vec_2[0],
dist_vec_2[0],
k_vec_2[0],
nq,
top_k,
ascending,
final_result_2);
ASSERT_EQ(final_result_2.size(), nq);
rc2.RecordSection("reduce done");
for (i = 0; i < nq; i++) {
ASSERT_EQ(final_result[i].size(), final_result_2[i].size());
for (k = 0; k < final_result[i].size(); k++) {
if (final_result[i][k].first != final_result_2[i][k].first) {
std::cout << i << " " << k << std::endl;
}
ASSERT_EQ(final_result[i][k].first, final_result_2[i][k].first);
ASSERT_EQ(final_result[i][k].second, final_result_2[i][k].second);
}
}
///////////////////////////////////////////////////////////////////////////////////////
/* method-3 parallel */
std::vector<std::vector<int64_t>> id_vec_3(index_file_num);
std::vector<std::vector<float>> dist_vec_3(index_file_num);
std::vector<uint64_t> k_vec_3(index_file_num);
for (i = 0; i < index_file_num; i++) {
CopyResult(id_vec_3[i], dist_vec_3[i], top_k, id_vec[i], dist_vec[i], TOPK, nq);
k_vec_3[i] = top_k;
}
std::string str3 = "Method-3 " + std::to_string(max_thread_num) + " " +
std::to_string(nq) + " " + std::to_string(top_k);
milvus::TimeRecorder rc3(str3);
for (step = 1; step < index_file_num; step *= 2) {
for (i = 0; i + step < index_file_num; i += step * 2) {
threads_list.push_back(
threadPool.enqueue(ms::XSearchTask::MergeTopkArray,
std::ref(id_vec_3[i]),
std::ref(dist_vec_3[i]),
std::ref(k_vec_3[i]),
std::ref(id_vec_3[i + step]),
std::ref(dist_vec_3[i + step]),
std::ref(k_vec_3[i + step]),
nq,
top_k,
ascending));
}
while (threads_list.size() > 0) {
int nready = 0;
for (auto it = threads_list.begin(); it != threads_list.end(); it = it) {
auto &p = *it;
std::chrono::milliseconds span(0);
if (p.wait_for(span) == std::future_status::ready) {
threads_list.erase(it++);
++nready;
} else {
++it;
}
}
if (nready == 0) {
std::this_thread::yield();
}
}
}
ms::XSearchTask::MergeTopkToResultSet(id_vec_3[0],
dist_vec_3[0],
k_vec_3[0],
nq,
top_k,
ascending,
final_result_3);
ASSERT_EQ(final_result_3.size(), nq);
rc3.RecordSection("reduce done");
for (i = 0; i < nq; i++) {
ASSERT_EQ(final_result[i].size(), final_result_3[i].size());
for (k = 0; k < final_result[i].size(); k++) {
ASSERT_EQ(final_result[i][k].first, final_result_3[i][k].first);
ASSERT_EQ(final_result[i][k].second, final_result_3[i][k].second);
}
}
// ///////////////////////////////////////////////////////////////////////////////////////
// /* method-2 */
// std::vector<std::vector<int64_t>> id_vec_2(index_file_num);
// std::vector<std::vector<float>> dist_vec_2(index_file_num);
// std::vector<uint64_t> k_vec_2(index_file_num);
// for (i = 0; i < index_file_num; i++) {
// CopyResult(id_vec_2[i], dist_vec_2[i], top_k, id_vec[i], dist_vec[i], TOPK, nq);
// k_vec_2[i] = top_k;
// }
//
// std::string str2 = "Method-2 " + std::to_string(max_thread_num) + " " +
// std::to_string(nq) + " " + std::to_string(top_k);
// milvus::TimeRecorder rc2(str2);
//
// for (step = 1; step < index_file_num; step *= 2) {
// for (i = 0; i + step < index_file_num; i += step * 2) {
// ms::XSearchTask::MergeTopkArray(id_vec_2[i], dist_vec_2[i], k_vec_2[i],
// id_vec_2[i + step], dist_vec_2[i + step], k_vec_2[i + step],
// nq, top_k, ascending);
// }
// }
// ms::XSearchTask::MergeTopkToResultSet(id_vec_2[0],
// dist_vec_2[0],
// k_vec_2[0],
// nq,
// top_k,
// ascending,
// final_result_2);
// ASSERT_EQ(final_result_2.size(), nq);
//
// rc2.RecordSection("reduce done");
//
// for (i = 0; i < nq; i++) {
// ASSERT_EQ(final_result[i].size(), final_result_2[i].size());
// for (k = 0; k < final_result[i].size(); k++) {
// if (final_result[i][k].first != final_result_2[i][k].first) {
// std::cout << i << " " << k << std::endl;
// }
// ASSERT_EQ(final_result[i][k].first, final_result_2[i][k].first);
// ASSERT_EQ(final_result[i][k].second, final_result_2[i][k].second);
// }
// }
//
// ///////////////////////////////////////////////////////////////////////////////////////
// /* method-3 parallel */
// std::vector<std::vector<int64_t>> id_vec_3(index_file_num);
// std::vector<std::vector<float>> dist_vec_3(index_file_num);
// std::vector<uint64_t> k_vec_3(index_file_num);
// for (i = 0; i < index_file_num; i++) {
// CopyResult(id_vec_3[i], dist_vec_3[i], top_k, id_vec[i], dist_vec[i], TOPK, nq);
// k_vec_3[i] = top_k;
// }
//
// std::string str3 = "Method-3 " + std::to_string(max_thread_num) + " " +
// std::to_string(nq) + " " + std::to_string(top_k);
// milvus::TimeRecorder rc3(str3);
//
// for (step = 1; step < index_file_num; step *= 2) {
// for (i = 0; i + step < index_file_num; i += step * 2) {
// threads_list.push_back(
// threadPool.enqueue(ms::XSearchTask::MergeTopkArray,
// std::ref(id_vec_3[i]),
// std::ref(dist_vec_3[i]),
// std::ref(k_vec_3[i]),
// std::ref(id_vec_3[i + step]),
// std::ref(dist_vec_3[i + step]),
// std::ref(k_vec_3[i + step]),
// nq,
// top_k,
// ascending));
// }
//
// while (threads_list.size() > 0) {
// int nready = 0;
// for (auto it = threads_list.begin(); it != threads_list.end(); it = it) {
// auto &p = *it;
// std::chrono::milliseconds span(0);
// if (p.wait_for(span) == std::future_status::ready) {
// threads_list.erase(it++);
// ++nready;
// } else {
// ++it;
// }
// }
//
// if (nready == 0) {
// std::this_thread::yield();
// }
// }
// }
// ms::XSearchTask::MergeTopkToResultSet(id_vec_3[0],
// dist_vec_3[0],
// k_vec_3[0],
// nq,
// top_k,
// ascending,
// final_result_3);
// ASSERT_EQ(final_result_3.size(), nq);
//
// rc3.RecordSection("reduce done");
//
// for (i = 0; i < nq; i++) {
// ASSERT_EQ(final_result[i].size(), final_result_3[i].size());
// for (k = 0; k < final_result[i].size(); k++) {
// ASSERT_EQ(final_result[i][k].first, final_result_3[i][k].first);
// ASSERT_EQ(final_result[i][k].second, final_result_3[i][k].second);
// }
// }
}
}
}

2
core/unittest/main.cpp
View File

@ -18,7 +18,7 @@
#include <gtest/gtest.h>
#include <gmock/gmock.h>
#include "utils/easylogging++.h"
#include "external/easyloggingpp/easylogging++.h"
INITIALIZE_EASYLOGGINGPP

2
core/unittest/wrapper/CMakeLists.txt
View File

@ -26,7 +26,7 @@ set(wrapper_files
set(util_files
utils.cpp
${MILVUS_ENGINE_SRC}/utils/easylogging++.cc
${MILVUS_ENGINE_SRC}/external/easyloggingpp/easylogging++.cc
${MILVUS_ENGINE_SRC}/utils/Status.cpp
)

2
core/unittest/wrapper/test_wrapper.cpp
View File

@ -15,7 +15,7 @@
// specific language governing permissions and limitations
// under the License.
#include "utils/easylogging++.h"
#include "external/easyloggingpp/easylogging++.h"
#include "wrapper/VecIndex.h"
#include "knowhere/index/vector_index/helpers/FaissGpuResourceMgr.h"
#include "knowhere/index/vector_index/helpers/IndexParameter.h"

2
tests/milvus_benchmark/requirements.txt
View File

@ -1,6 +1,6 @@
numpy==1.16.3
pymilvus>=0.1.18
pyyaml==3.12
pyyaml==5.1
docker==4.0.2
tableprint==0.8.0
ansicolors==1.1.8