This fixes the benchmark table present in the main page of remote store on opensearch documentation website.

Signed-off-by: Ashish <ashking94@gmail.com>
This commit is contained in:
Ashish 2023-10-04 18:53:12 +05:30 committed by GitHub
parent e74dc48481
commit b149493bea
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions

View File

@ -137,7 +137,7 @@ The following table lists the benchmarking results for the `so` workload with a
|--- |--- |--- |--- |--- | --- | --- | --- | --- | --- | --- |
| | | Document replication | Remote enabled | Percent difference | Document replication | Remote enabled | Percent difference | Document replication | Remote enabled | Percent difference |
|Indexing throughput |Mean |29582.5 | 40667.4 |37.47 |31154.9 |47862.3 |53.63 |31777.2 |51123.2 |60.88 |
|P50 |28915.4 |40343.4 |39.52 |30406.4 |47472.5 |56.13 |30852.1 |50547.2 |63.84 |
|Indexing throughput |P50 |28915.4 |40343.4 |39.52 |30406.4 |47472.5 |56.13 |30852.1 |50547.2 |63.84 |
|Indexing latency |P90 |1716.34 |1469.5 |-14.38 |3709.77 |2799.82 |-24.53 |5768.68 |3794.13 |-34.23 |
### HTTP logs
@ -148,7 +148,7 @@ The following table lists the benchmarking results for the `http_logs` workload
|--- |--- |--- |--- |--- | --- | --- | --- | --- | --- | --- |
| | | Document replication | Remote enabled |Percent difference | Document replication | Remote enabled | Percent difference |Document replication | Remote enabled | Percent difference |
|Indexing throughput |Mean |149062 |82198.7 |-44.86 |134696 |148749 |10.43 |133050 |197239 |48.24 |
|P50 |148123 |81656.1 |-44.87 |133591 |148859 |11.43 |132872 |197455 |48.61 |
|Indexing throughput |P50 |148123 |81656.1 |-44.87 |133591 |148859 |11.43 |132872 |197455 |48.61 |
|Indexing latency |P90 |327.011 |610.036 |86.55 |751.705 |669.073 |-10.99 |1145.19 |817.185 |-28.64 |
### NYC taxis
@ -159,7 +159,7 @@ The following table lists the benchmarking results for the `http_logs` workload
|--- |--- |--- |--- |--- | --- | --- | --- | --- | --- | --- |
| | | Document replication | Remote enabled |Percent difference | Document replication | Remote enabled | Percent difference |Document replication | Remote enabled | Percent difference |
|Indexing throughput |Mean |93383.9 |94186.1 |0.86 |91624.8 |125770 |37.27 |93627.7 |132006 |40.99 |
|P50 |91645.1 |93906.7 |2.47 |89659.8 |125443 |39.91 |91120.3 |132166 |45.05 |
|Indexing throughput |P50 |91645.1 |93906.7 |2.47 |89659.8 |125443 |39.91 |91120.3 |132166 |45.05 |
|Indexing latency |P90 |995.217 |1014.01 |1.89 |2236.33 |1750.06 |-21.74 |3353.45 |2472 |-26.28 |
As shown by the results, there are consistent gains in cases where the indexing latency is more than the average remote upload time. When you increase the number of bulk indexing clients, a remote-enabled configuration provides indexing throughput gains of up to 60--65%. For more detailed results, see [Issue #9790](https://github.com/opensearch-project/OpenSearch/issues/9790).