fluencelabs/gitbook-docs
1
0
Fork 0
mirror of https://github.com/fluencelabs/gitbook-docs synced 2025-06-12 06:21:33 +00:00
Code Issues Projects Releases Wiki Activity

GitBook: [main] 54 pages and 17 assets modified

Browse Source
This commit is contained in:
boneyard93501
2021-03-29 02:17:53 +00:00
committed by gitbook-bot
parent c6a1b1204a
commit 36ddf50532
71 changed files with 3814 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
development_development/development_reward_block_app/README.md Normal file
View File

@ -0,0 +1,19 @@
# Building The Reward Block Application
Our project aims to
* retrieve the latest block height from the Ethereum mainnet,
* use that result to retrieve the associated reward block data and
* store the result in a SQlite database
In order to simplify Ethereum data access, we will be using the [Etherscan API](https://etherscan.io/apis). Make sure you got yours ready as we are using two Etherscan endpoints:
* [eth\_blockNumber](https://api.etherscan.io/api?module=proxy&action=eth_blockNumber&apikey=YourApiKeyToken), which returns the most recent block height as a hex string and
* [getBlockReward](https://api.etherscan.io/api?module=block&action=getblockreward&blockno=2165403&apikey=YourApiKeyToken), which returns the block and uncle reward by block height
Both _eth\_blockNumber_ and _getBlockReward_ need access to remote endpoints and for our purposes, a cUrl service will do just fine. Hence, we ned to implement a curl adapter to access the curl binaries of the node. Moreover, as _eth\_blockNumber_ returns a hex string and _getBlockReward_ requires an integer, we need a hex to int conversion, which we are going to implement as a stand-alone service. Finally, a SQLite adapter is also required, although the sqlite3.wasm module is [readily available](https://github.com/fluencelabs/sqlite/releases) from the Fluence repo.
The high-level workflow of our application is depicted in Figure 1.
![Figure 1: Stylized Workflow](../../.gitbook/assets/image%20%282%29.png)

255
development_development/development_reward_block_app/development_additional_concepts.md Normal file
View File

@ -0,0 +1,255 @@
# Additional Concepts
In the previous sections we obtained block reward data by discovering the latest Ethereum block created. Of course, Ethereum produces a new block about every 13 seconds or so and it would be nice to automate the data acquisition process. One way, of course, would be to, say, cron or otherwise daemonize our frontend application. But where's the fun in that and we'd rather hand that task to the p2p network.
As we have seen in our AIR workflows, particles travel the path, trigger execution, and update their data. So far, we have only seen services consume previous outputs as \(complete\) inputs, which means that service at workflow sequence s needs to be fairly tightly coupled to service at sequence s-1, which is less than ideal. Luckily, Fluence provides a solution to access certain types of results as j_son paths_.
## Peer-Based Script Storage And Execution
As discussed previously, a peer-based ability to "poll" is a valuable feature to some applications. Fluence nodes come with a set of built-in services including the ability to store scripts on a peer with the intent of periodic execution.
This service, just as all distributed services, is managed by Aquamarine. The AIR script looks like:
```text
; add a script to
(call node ("script" "add") [script interval] id)
```
where:
* _node_ -- takes the peer id parameter
* _"script"_ -- is the \(hard-coded\) service id
* _script_ -- takes the AIR script as a **string**
* _interval_ -- the execution interval in seconds, optional, default is three \(3\) seconds; provide as **string**, e.g. five seconds are expressed as "5"
* _id_ -- is the return value
In addition to the service "add" method, there are also service "list" and service "remove" methods available:
```text
; list
(call node ("script" "list") [] list)
; remove
(call node ("script" "remove") [script_id] result)
```
where remove takes the id \(returned by "add"\) and returns a boolean.
Let's check on any stored services on our local node \(make sure you use your node id\) and as expected, no services have been uploaded for storage and execution.
```text
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/list_stored_services.clj -d '{"node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17"}'
client seed: 5ydZWdJAzMHAGQ2hCVJCa5ByYq7obp2yc9gRD43ajXrZ
client peerId: 12D3KooWBgzuiNn5mz1DwqDbqapBf3NSF8mRjSJV1KC3VphjAyWL
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: 17986fb7-36e7-4f10-b311-d2512f5fe2e5. Waiting for results... Press Ctrl+C to stop the script.
===================
[
[]
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'script',
function_name: 'list',
json_path: ''
}
]
]
===================
```
In order to upload the periodic "block to db poll", we can use parts of the _ethqlite\_roundtrip.clj_ script and hard-code the parameters since currently there is no option to separately upload the script and data. Make sure you replace the `node_*`, `service_*` and `api_key` placeholders with your actual values in the file!
```text
; air-scripts/ethqlite_block_committer.clj
(xor
(seq
(seq
(seq
(seq
(seq
(call relay ("op" "identity") [])
(call node_1 (service_1 "get_latest_block") [api_key] hex_block_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [hex_block_result])
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call node_2 (service_2 "hex_to_int") [hex_block_result] int_block_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [int_block_result])
)
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call node_1 (service_1 "get_block") [api_key int_block_result] block_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [block_result])
)
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call sqlite_node (sqlite_service "update_reward_blocks") [block_result] insert_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [insert_result])
)
)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") ["XOR FAILED" %last_error%])
)
)
)
```
```bash
# script file to string variable
AIR=`cat air-scripts/ethqlite_block_committer.clj`
# interval variable in seconds to string variable
INT="10"
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/add_stored_service.clj -d '{"node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17", "interval":"'"$INT"'", "script":"'"$AIR"'"}'
client seed: Cwhf8VuyqPCUPi8keyZAcRVBkaGNLWviHMRwDL2hG8D4
client peerId: 12D3KooWJgFCCeHpcEoVyxT5Fmg47ok43MPU7hfT9cNv5R3KeDEw
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: dd3ad854-b10d-4664-846d-42c59c59335f. Waiting for results... Press Ctrl+C to stop the script.
===================
[
"a1791c0f-084e-4b4d-a85c-a3eb65a18d57" # <= Take note of the storage id !
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'script',
function_name: 'add',
json_path: ''
}
]
]
===================
```
Checking once more for listed services hits pay dirt:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/list_stored_services.clj -d '{"node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17"}'
client seed: HpHQc1as9zGdiHaMQzyPDaPWrdMVEvAA8DwdJiAvczWS
client peerId: 12D3KooWFiiS7FMo18EbrtWZi38Nwe1SiYCRqcsJNEPtYh28zHNm
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: 5fb0af87-310f-4b12-8c73-e044cfd8ef6e. Waiting for results... Press Ctrl+C to stop the script.
===================
[
[
{
"failures": 0,
"id": "a1791c0f-084e-4b4d-a85c-a3eb65a18d57",
"interval": "10s",
"owner": "12D3KooWJgFCCeHpcEoVyxT5Fmg47ok43MPU7hfT9cNv5R3KeDEw",
"src": "$AIR"
}
]
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'script',
function_name: 'list',
json_path: ''
}
]
]
===================
```
And we are golden. Give it some time and start checking Ethqlite for latest block and reward info!!
TODO: this isn't working since we can't upload a key with the script.
For completeness sake, let's remove the stored service with the following AIR script:
```bash
; remove a script to
(call node ("script" "remove") [script_id] result)
```
TODO: finalize or delete for now.
## Advanced Service Output Access
As Aquamarine advances a particle's journey through the network, output from a service at workflow sequence s-1 method tends to be the input for a service at sequence s method. For example, the _hex\_to\_int_ method, as used earlier, takes the output from the _get\_latest\_block_ method. With single parameter outputs, this is a pretty straight forward and inherently decoupled dependency relation. However, when result parameters become more complex, such as structs, we still would like to keep services as decoupled as possible.
Fluence provides this capability by facilitating the conversion of \(Rust\) struct returns into [json values](https://github.com/fluencelabs/aquamarine/blob/master/interpreter-lib/src/execution/boxed_value/jvaluable.rs#L30). This allows json type key-value access to a desired subset of return values. If you got back to the _ethqlite.clj_ script, you may notice some fancy `$`, `!` operators tucked away in the deep recesses of parenthesis stacking. Below the pertinent snippet:
```text
; ethqlite_rountrip.clj
; <snip>
(seq
(seq
(seq
(call relay ("op" "identity") [])
(call sqlite_node (sqlite_service "get_reward_block") [int_block_result] select_result_2)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [select_result_2])
)
)
(seq
(seq
(call relay ("op" "identity") []) .; coming up next line !!
(call sqlite_node (sqlite_service "get_miner_rewards") [select_result_2.$.["block_miner"]!] select_result_3) ; <= Here it is !!
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [select_result_3])
)
)
)
; <snip>
```
Before we dive in, let's review the output from the _get\_reward\_block_ method which is part of the ethqlite service:
```rust
// https://github.com/fluencelabs/examples/blob/c508d096e712b7b22aa94641cd6bb7c2fdb67200/multi-service/ethqlite/src/crud.rs#L139
#[fce]
#[derive(Debug)]
// https://github.com/fluencelabs/examples/blob/c508d096e712b7b22aa94641cd6bb7c2fdb67200/multi-service/ethqlite/src/crud.rs#L89
pub struct RewardBlock {
pub block_number: i64,
pub timestamp: i64,
pub block_miner: String,
pub block_reward: String,
}
```
and the input expectations of _get\_miner\_rewards_, also an ethqlite service method, with the following [function](https://github.com/fluencelabs/examples/blob/c508d096e712b7b22aa94641cd6bb7c2fdb67200/multi-service/ethqlite/src/crud.rs#L177) signature: `pub fn get_miner_rewards(miner_address: String) -> MinerRewards`.
Basically, _get\_miner\_rewards_ wants an Ethereum address as a `String` and in the context of our AIR script we want to get the value from the _get\_reward\_block_ result. Rather than tightly coupling _get\_miner\_rewards_ to _get\_reward\_block_ in terms of, say, the _RewardBlock_ input parameter, we take advantage of the Fluence capability to turn structs into json strings and then supply the relevant key to extract the desired value. Specifically, we use the `$` operator to access the json representation at the desired index and the `!` operator to flatten the value, if desired.
For example,
```text
(call sqlite_node (sqlite_service "get_miner_rewards") [select_result_2.$.["block_miner"]!]
```
uses the _block\_miner_ key to retrieve the miner address for subsequent consumption. In order to take full advantage of this important feature, developers should return more complex results as FCE structs to prevent tight service coupling. This approach allows for significant reduction of service dependencies, re-writes and re-deployments due to even minor changes in upstream dependencies.

345
development_development/development_reward_block_app/development_eth_calls.md Normal file
View File

@ -0,0 +1,345 @@
# Ethereum Request Service
The source code for this section can be found [here](https://github.com/fluencelabs/examples/tree/main/multi-service) and is pretty straight forward with the two Etherscan api endpoints wrapped as public, FCE marked functions:
```rust
use crate::curl_request;
use fluence::fce;
use fluence::MountedBinaryResult;
fn result_to_string(result:MountedBinaryResult) -> String {
if result.is_success() {
return String::from_utf8(result.stdout).expect("Found invalid UTF-8");
}
String::from_utf8(result.stderr).expect("Found invalid UTF-8")
}
#[fce]
pub fn get_latest_block(api_key: String) -> String {
let url = f!("https://api.etherscan.io/api?module=proxy&action=eth_blockNumber&apikey={api_key}");
let header = "-d \"\"";
let curl_cmd:Vec<String> = vec![header.into(), url.into()];
let response = unsafe { curl_request(curl_cmd) };
let res = result_to_string(response);
let obj = serde_json::from_str::<serde_json::Value>(&res).unwrap();
serde_json::from_value(obj["result"].clone()).unwrap()
}
#[fce]
pub fn get_block(api_key: String, block_number: u32) -> String {
let url = f!("https://api.etherscan.io/api?module=block&action=getblockreward&blockno={block_number}&apikey={api_key}");
let header = "-d \"\"";
let curl_cmd:Vec<String> = vec![header.into(), url];
let response = unsafe { curl_request(curl_cmd) };
result_to_string(response)
}
```
Of course, both functions need to be able to make https calls, which is accomplished by calling \(unsafe\) `curl_request`:
```rust
// main.rs
#[macro_use]
extern crate fstrings;
use fluence::{fce, WasmLoggerBuilder};
use fluence::MountedBinaryResult as Result;
mod eth_block_getters;
fn main() {
WasmLoggerBuilder::new().build().ok();
}
#[fce]
#[link(wasm_import_module = "curl_adapter")]
extern "C" {
pub fn curl_request(curl_cmd: Vec<String>) -> Result;
}
```
Since we are dealing with Wasm modules, we don't have access to sockets at the module level but may be permissioned to call cUrl at the node level. In order to do that, we need to provide an adapter module. The code from the [cUrl adapter](https://github.com/fluencelabs/examples/tree/main/multi-service/curl_adapter) project illustrates how we're mounting the binary and expose the fce-marked interface for consumption, like above.
```bash
// main.rs
#![allow(improper_ctypes)]
use fluence::fce;
use fluence::MountedBinaryResult as Result;
fn main() {}
#[fce]
pub fn curl_request(curl_cmd: Vec<String>) -> Result {
let response = unsafe { curl(curl_cmd.clone()) };
log::info!("curl response for {:?} : {:?}", curl_cmd, response);
response
}
// mounted_binaries are available to import like this:
#[fce]
#[link(wasm_import_module = "host")]
extern "C" {
pub fn curl(cmd: Vec<String>) -> Result;
}
```
From both modules, we can now create a service configuration which specifies the name for each module and the permission specification for the mounted binaries:
```text
// Block-Getter-Config.toml
modules_dir = "artifacts/"
[[module]]
name = "curl_adapter"
[module.mounted_binaries]
curl = "/usr/bin/curl"
[[module]]
name = "block_getter"
```
If you haven't done so already, run `./scripts/build.sh` to compile the projects. Once we have _wasm_ files and the service configuration, we can check out our accomplishments with the REPL:
```bash
fce-repl Block-Getter-Config.toml
```
which gets us in the REPL to call the _interface_ command:
```bash
Welcome to the FCE REPL (version 0.5.2)
app service was created with service id = 15b9c3ee-ffbc-4464-bb7f-675a41acf81a
elapsed time 111.573048ms
1> interface
Loaded modules interface:
Result {
ret_code: S32
error: String
stdout: Array<U8>
stderr: Array<U8>
}
curl_adapter:
fn curl_request(curl_cmd: Array<String>) -> Result
block_getter:
fn get_block(api_key: String, block_number: U32) -> String
fn get_latest_block(api_key: String) -> String
2>
```
Checking the available interfaces, shows the **public** interfaces to our respective Wasm modules, which are ready for calling:
```bash
> call curl_adapter curl_request [["-sS", "https://google.com"]]
result: Object({"error": String(""), "ret_code": Number(0), "stderr": Array([]), "stdout": Array([Number(60), Number(72), Number(84), Number(77), Number(76), Number(62), Number(60), Number(72), Number(69), Number(65), N
<snip>
, Number(72), Number(84), Number(77), Number(76), Number(62), Number(13), Number(10)])})
elapsed time: 328.965523ms
```
As implemented, the raw cUrl call returns a [MountedBinaryResult](https://github.com/fluencelabs/rust-sdk/blob/c2fec5939fc17dcc227a78c7c8030549a6ff193f/crates/main/src/mounted_binary.rs) and we can see the corresponding _struct_ at the top of our `fce-repl` interfaces output. Looking through the return object, we see the standard pipe approach in place and find our query result in the stdout pipe. Of course, we are mostly interested in using cUrl from other modules as part of our service, such as getting the most recently produced block and its corresponding data:
```bash
3> call block_getter get_latest_block ["MC5H2NK6ZIPMR32U7D4W35AWNNVCQX1ENH"]
result: String("0xb7eeb3")
elapsed time: 559.991486ms
```
and with some cognitive gymnastics we convert 0xb7eeb3 to 12054195:
```bash
4> call block_getter get_block ["MC5H2NK6ZIPMR32U7D4W35AWNNVCQX1ENH", 12054195]
result: String("{\"status\":\"1\",\"message\":\"OK\",\"result\":{\"blockNumber\":\"12054195\",\"timeStamp\":\"1615957734\",\"blockMiner\":\"0x99c85bb64564d9ef9a99621301f22c9993cb89e3\",\"blockReward\":\"2000000000000000000\",\"uncles\":[],\"uncleInclusionReward\":\"0\"}}")
elapsed time: 578.485579ms
```
All good but please note that your latest block data is going to be significantly different from what's use here. Regardless, manual conversions are really not all that productive and that's why we implemented a [hex\_converter](https://github.com/fluencelabs/examples/tree/main/multi-service/hex_converter) module. Let's update our service config to:
```bash
// Block-Getter-With-Converter-Config.toml
modules_dir = "artifacts/"
[[module]]
name = "curl_adapter"
[module.mounted_binaries]
curl = "/usr/bin/curl"
[[module]]
name = "block_getter"
[[module]]
name = "hex_converter"
```
and running `fce-repl` with _Block-Getter-With-Converter-Config.toml_ lists the interface for the _hex\_converter_ module. So far, so good. Using the previously generated hex string, yields the expected conversion result:
```bash
Welcome to the FCE REPL (version 0.5.2)
app service was created with service id = 09bfcff0-67dd-44c2-a677-de5a7a0c6383
elapsed time 176.472631ms
1> interface
Loaded modules interface:
Result {
ret_code: S32
error: String
stdout: Array<U8>
stderr: Array<U8>
}
hex_converter:
fn hex_to_int(data: String) -> U64
block_getter:
fn get_latest_block(api_key: String) -> String
fn get_block(api_key: String, block_number: U32) -> String
curl_adapter:
fn curl_request(curl_cmd: Array<String>) -> Result
2> call hex_converter hex_to_int ["0xb7eeb3"]
result: Number(12054195)
elapsed time: 120.34µs
3>
```
Before we review the SQLite code, let's deploy our two services to the local node with the `fldist` tool. Make sure you got the node id and address for **your** local Fluence node:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 new_service --ms artifacts/curl_adapter.wasm:config/curl_cfg.json artifacts/block_getter.wasm:config/block_getter_cfg.json --name EthGetters
client seed: 4mp3sXX5FR9heeuqFtfRkq5GRqNJFQ8TvGCZ94PoSvQr
client peerId: 12D3KooWBdvur9HwahxMaGN2yrYDiofVD4GDBHivLtJwxwBuyzcr
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
uploading blueprint EthGetters to node 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 via client 12D3KooWBdvur9HwahxMaGN2yrYDiofVD4GDBHivLtJwxwBuyzcr
service id: ca0eceb3-871f-440e-aff1-0a186321437d
service created successfully
```
and for the hex conversion service:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 new_service --ms artifacts/hex_converter.wasm:config/hex_converter_cfg.json --name HexConverter
client seed: BGvUGBvYifJf8oHS6rA7UmBc7Cs8EeaJxie8eFyP7YmY
client peerId: 12D3KooWJLXYiXwmmWPEv7kdQ8nYb646L96XyyTgkrrMAXen3FQy
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
uploading blueprint HexConverter to node 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 via client 12D3KooWJLXYiXwmmWPEv7kdQ8nYb646L96XyyTgkrrMAXen3FQy
service id: 36043704-4d40-4c74-a1bd-3abbde28305d
service created successfully
```
Our first service, _EthGetters_, is comprised of two modules and the the second service, _HexConverter_, of one module. With those two services available, we have everything we need to get the block reward information for the most recently block. In order to get us there, we write a small AIR script to coordinate the services into an app:
```text
; latest_block_reward.clj
(xor
(seq
(seq
(seq
(seq
(call relay ("op" "identity") [])
(call node_1 (service_1 "get_latest_block") [api_key] hex_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [hex_result])
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call node_2 (service_2 "hex_to_int") [hex_result] int_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [int_result])
)
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call node_1 (service_1 "get_block") [api_key int_result] block_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [block_result])
)
)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") ["XOR FAILED" %last_error%])
)
)
```
As always, we use the `fldist` _run\_air_ command:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/latest_reward_block.clj -d '{"service_1": "ca0eceb3-871f-440e-aff1-0a186321437d", "service_2": "36043704-4d40-4c74-a1bd-3abbde28305d", "node_1":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17", "node_2": "12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17", "api_key":"your-api-key"}'
client seed: 9xfs3P1r5QmBxCohcA4xmpE448Q64c14jmYn4XNJZEiz
client peerId: 12D3KooWNfA3Za3bvfHutWhvtZxC5NWdbaujoFZkR8bh2WVTZzw3
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: 930ea13f-1474-4501-862a-ca5fad22ee42. Waiting for results... Press Ctrl+C to stop the script.
===================
[
"0xb7fe13"
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'ca0eceb3-871f-440e-aff1-0a186321437d',
function_name: 'get_latest_block',
json_path: ''
}
]
]
===================
===================
[
12058131
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: '36043704-4d40-4c74-a1bd-3abbde28305d',
function_name: 'hex_to_int',
json_path: ''
}
]
]
===================
===================
[
"{\"status\":\"1\",\"message\":\"OK\",\"result\":{\"blockNumber\":\"12058131\",\"timeStamp\":\"1616010177\",\"blockMiner\":\"0x829bd824b016326a401d083b33d092293333a830\",\"blockReward\":\"6159144598411626490\",\"uncles\":[{\"miner\":\"0xe72f79190bc8f92067c6a62008656c6a9077f6aa\",\"unclePosition\":\"0\",\"blockreward\":\"500000000000000000\"}],\"uncleInclusionReward\":\"62500000000000000\"}}"
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'ca0eceb3-871f-440e-aff1-0a186321437d',
function_name: 'get_block',
json_path: ''
}
]
]
===================
```
Right on! Our two services coordinate into the intended application returning the reward data for the latest block. Before we move on, locate the corresponding services on the Fluence testnet via the [ dashboard](https://dash.fluence.dev/), update your command-line with the appropriate service and node ids and run the same AIR script. Congratulations, you just run an app coordinated by distributed services!

10
development_development/development_reward_block_app/development_more_air.md Normal file
View File

@ -0,0 +1,10 @@
# A Little More AIR, Please
Before you go off becoming a prominent Fluence p2p application developer gazillionaire, there are a couple more AIR functions you should be aware off: par and fold.
## Disrtributed Workflow Parallelization
By now may have come to realize that building distributed "applications" is a tad different than
## Distributed List Processing with fold

251
development_development/development_reward_block_app/development_persisting_blocks.md Normal file
View File

@ -0,0 +1,251 @@
# Blocks To Database
It's been a long time coming but finally, we are ready to save data in SQLIte by simply coordinating the various services we already deployed into one big-ass AIR script:
```text
; ethqlite_rountrip.clj
(xor
(seq
(seq
(seq
(seq
(seq
(seq
(seq
(call relay ("op" "identity") [])
(call node_1 (service_1 "get_latest_block") [api_key] hex_block_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [hex_block_result])
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call node_2 (service_2 "hex_to_int") [hex_block_result] int_block_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [int_block_result])
)
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call node_1 (service_1 "get_block") [api_key int_block_result] block_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [block_result])
)
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call sqlite_node (sqlite_service "update_reward_blocks") [block_result] insert_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [insert_result])
)
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call sqlite_node (sqlite_service "get_latest_reward_block") [] select_result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [select_result])
)
)
)
(seq
(seq
(seq
(call relay ("op" "identity") [])
(call sqlite_node (sqlite_service "get_reward_block") [int_block_result] select_result_2)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [select_result_2])
)
)
(seq
(seq
(call relay ("op" "identity") [])
(call sqlite_node (sqlite_service "get_miner_rewards") [select_result_2.$.["block_miner"]!] select_result_3)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [select_result_3])
)
)
)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") ["XOR FAILED" %last_error%])
)
)
```
The script extends our previous incarnation by adding only one more method: `update_reward_blocks`, and a few testing calls, i.e., query the table. We need to gather our node and service ids \(which are different for you!\) to update our json data argument for the `fldist` call:
```bash
-d '{"service_1":"ca0eceb3-871f-440e-aff1-0a186321437d", \
"node_1":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17", \
"service_2":"36043704-4d40-4c74-a1bd-3abbde28305d", \
"node_2": "12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17", \
"sqlite_service":"470fcaba-6834-4ccf-ac0c-4f6494e9e77b", \
"sqlite_node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17", \
"api_key": "MC5H2NK6ZIPMR32U7D4W35AWNNVCQX1ENH"}'
```
and run the AIR script with the revised `fldist` command:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/ethqlite_roundtrip.clj -d '{"service_1":"ca0eceb3-871f-440e-aff1-0a186321437d", "node_1":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17","service_2":"36043704-4d40-4c74-a1bd-3abbde28305d", "node_2": "12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17", "sqlite_service":"470fcaba-6834-4ccf-ac0c-4f6494e9e77b", "sqlite_node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17", "api_key": "MC5H2NK6ZIPMR32U7D4W35AWNNVCQX1ENH"}' -s H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V
client seed: H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V
client peerId: 12D3KooWKphxxaXofYzC2TsN79RHZVubjmutKVdPUxVMHY3ZsVww
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: 5ce2dcf0-2d4d-40ec-8cef-d5a0cea4f0e7. Waiting for results... Press Ctrl+C to stop the script.
===================
[
"0xb807a1"
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'ca0eceb3-871f-440e-aff1-0a186321437d',
function_name: 'get_latest_block',
json_path: ''
}
]
]
===================
===================
[
12060577
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: '36043704-4d40-4c74-a1bd-3abbde28305d',
function_name: 'hex_to_int',
json_path: ''
}
]
]
===================
===================
[
"{\"status\":\"1\",\"message\":\"OK\",\"result\":{\"blockNumber\":\"12060577\",\"timeStamp\":\"1616042932\",\"blockMiner\":\"0x2f731c3e8cd264371ffdb635d07c14a6303df52a\",\"blockReward\":\"3622523288217263710\",\"uncles\":[],\"uncleInclusionReward\":\"0\"}}"
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'ca0eceb3-871f-440e-aff1-0a186321437d',
function_name: 'get_block',
json_path: ''
}
]
]
===================
===================
[
{
"err_str": "",
"success": 1
}
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: '470fcaba-6834-4ccf-ac0c-4f6494e9e77b',
function_name: 'update_reward_blocks',
json_path: ''
}
]
]
===================
===================
[
{
"block_miner": "\"0x2f731c3e8cd264371ffdb635d07c14a6303df52a\"",
"block_number": 12060577,
"block_reward": "3622523288217263710",
"timestamp": 1616042932
}
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: '470fcaba-6834-4ccf-ac0c-4f6494e9e77b',
function_name: 'get_latest_reward_block',
json_path: ''
}
]
]
===================
===================
[
{
"block_miner": "\"0x2f731c3e8cd264371ffdb635d07c14a6303df52a\"",
"block_number": 12060577,
"block_reward": "3622523288217263710",
"timestamp": 1616042932
}
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: '470fcaba-6834-4ccf-ac0c-4f6494e9e77b',
function_name: 'get_reward_block',
json_path: ''
}
]
]
===================
===================
[
{
"miner_address": "\"0x2f731c3e8cd264371ffdb635d07c14a6303df52a\"",
"rewards": [
"3622523288217263710"
]
}
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: '470fcaba-6834-4ccf-ac0c-4f6494e9e77b',
function_name: 'get_miner_rewards',
json_path: ''
}
]
]
===================
```
And that's a wrap!
In summary, we have developed and deployed multiple Fluence services to store Ethereum reward block data in a SQLite as a service database and used Aquamarine to coordinate those services into applications. See Figure 2 below.
Figure 2: Aquamarine Application Creation From Modules And Services
![](../../.gitbook/assets/image.png)
Working through this project hopefully made it quite clear that the combination of distributed network services and Aquamarine makes for the easy and expedient creation of powerful applications by composition and coordination. Moreover, it showcases the power of reusability and hints at the \(economic\) rent available to developers. Presumably not entirely unexpectedly, there is a bit more to discover, a little more power to be unleashed. In the next section we touch upon two additional concepts to extend our capabilities: How to incorporate peer-based script execution into our workflow and how to utilize advanced, in-flow \(or in-transit\) results processing.

397
development_development/development_reward_block_app/development_sqlite.md Normal file
View File

@ -0,0 +1,397 @@
# SQLite Service
All our work so far has been about gathering block reward information for the latest block:
```javascript
// Block reward info on Wednesday, March 17, at 2021 7:42:57 PM GMT
// for block 12058131:
"{\"status\":\"1\",\"message\":\"OK\",\"result\":{\"blockNumber\":\"12058131\",
\"timeStamp\":\"1616010177\",\"blockMiner\":\"0x829bd824b016326a401d083b33d092293333a830\",
\"blockReward\":\"6159144598411626490\",\"uncles\":[
{\"miner\":\"0xe72f79190bc8f92067c6a62008656c6a9077f6aa\",\"unclePosition\":\"0\",
\"blockreward\":\"500000000000000000\"}],
\"uncleInclusionReward\":\"62500000000000000\"}}"
```
which [happens about every 13 seconds or so on mainnet](https://etherscan.io/chart/blocktime) and every four seconds on Kovan. Rather than stashing the block reward results in a frontend-based storage solution, we deploy an SQLite service as our peer-to-peer hosted _Ethqlite_ service. Please see the [ethqlite repo](https://github.com/fluencelabs/examples/tree/main/multi-service/ethqlite) for the code.
To get SQLite as a service, we build our service from two modules: the [ethqlite repo](https://github.com/fluencelabs/examples/tree/main/multi-service/ethqlite) and the [Fluence sqlite](https://github.com/fluencelabs/sqlite) Wasm module, which we can build or pickup as a wasm files from the [releases](https://github.com/fluencelabs/sqlite/releases). This largely, but not entirely, mirrors what we did with the cUrl service: build the service by providing an adapter to the binary. Unlike the cUrl binary, we are bringing our own sqlite binary, i.e., _sqlite3.wasm_, with us.
This leaves us to code our _ethqlite_ module with respect to desired CRUD interfaces and security. As [previously](../../quick_start/quick_start_add_persistence/quick_start_persistence_setup.md) discussed, we want writes to the sqlite services to be privileged, which implies that we need to own the service and have the client seed to manage authentication and ambient authorization. Specifically, we can implement a rudimentary authorization system where authentication implies authorization \(to write\). The `is_owner` function in the _ethqlite_ repo does exactly that: if the caller can prove ownership by providing a valid client seed, than we have a true condition equating write-privileged ownership with the caller identity:
```rust
// auth.rs
use fluence::{fce, CallParameters};
use::fluence;
use crate::get_connection;
pub fn is_owner() -> bool {
let meta = fluence::get_call_parameters();
let caller = meta.init_peer_id;
let owner = meta.service_creator_peer_id;
caller == owner
}
#[fce]
pub fn am_i_owner() -> bool {
is_owner()
}
```
where the `fluence::get_call_parameters` is a FCE function returning the populated _CallParameter_ struct defined in the [Fluence Rust SDK](https://github.com/fluencelabs/rust-sdk/blob/71591f412cb65879d74e8c38838e827ab74d8802/crates/main/src/call_parameters.rs) provides us with the salient creator and caller parameters at runtime.
While the majority of the CRUD operations in _crud.rs_ are standard fare except, the auth & auth check appears in update\_reward\_blocks:
```rust
// crud.rs
#[fce]
pub fn update_reward_blocks(data_string: String) -> UpdateResult {
if !is_owner() { // <= auth & auth check !!
return UpdateResult { success:false, err_str: "You are not the owner".into()};
}
let obj:serde_json::Value = serde_json::from_str(&data_string).unwrap();
let obj = obj["result"].clone();
if obj["blockNumber"] == serde_json::Value::Null {
return UpdateResult { success:false, err_str: "Empty reward block string".into()};
}
let conn = get_connection();
let insert = "insert or ignore into reward_blocks values(?, ?, ?, ?)";
let mut ins_cur = conn.prepare(insert).unwrap().cursor();
<snip>
```
That is, any non-permissioned call is prevented from write operations and an error message is returned. Please note that in [main.rs](https://github.com/fluencelabs/examples/blob/main/multi-service/ethqlite/src/main.rs) we have a few admin convenience functions that are also protected by the `is_owner` guard.
## Building and Deploying Ethqlite
Our _build.sh_ script should look quite familiar with the possible exception of downloading the already built sqlite3.wasm file:
```bash
# build.sh
#!/bin/sh
fce build --release
rm artifacts/*
cp target/wasm32-wasi/release/ethqlite.wasm artifacts/
wget https://github.com/fluencelabs/sqlite/releases/download/v0.10.0_w/sqlite3.wasm
mv sqlite3.wasm artifacts/
```
Run `./build.sh` and check the artifacts for the expected wasm files
Like all Fluence services, Ethqlite needs a [service configuration](https://github.com/fluencelabs/examples/blob/main/multi-service/ethqlite/Config.toml) file, which looks a little more involved than what we have seen so far.
```text
modules_dir = "artifacts/"
[[module]]
name = "sqlite3"
mem_pages_count = 100
logger_enabled = false
[module.wasi]
preopened_files = ["/tmp"]
mapped_dirs = { "tmp" = "/tmp" }
[[module]]
name = "ethqlite"
mem_pages_count = 1
logger_enabled = false
[module.wasi]
preopened_files = ["/tmp"]
mapped_dirs = { "tmp" = "/tmp" }
```
Let's break it down:
* the first \[\[module\]\] section
* specifies the _sqlite3.wasm_ module we pulled from the repo,
* allocates memory, where each page is about 64KB, and
* permissions and maps node file access
* the second section is for our business logic \(CRUD\) adapter module where, again, we allocate the memory and permission and map file access.
We can now fire up `fce-repl`:
```bash
fce-repl Config.toml
Welcome to the FCE REPL (version 0.5.2)
app service was created with service id = 9b923db7-3747-41ab-b1fd-66bd0ccd9f68
elapsed time 916.210305ms
1> interface
Loaded modules interface:
UpdateResult {
success: I32
err_str: String
}
RewardBlock {
block_number: S64
timestamp: S64
block_miner: String
block_reward: String
}
InitResult {
success: I32
err_msg: String
}
MinerRewards {
miner_address: String
rewards: Array<String>
}
DBOpenDescriptor {
ret_code: S32
db_handle: U32
}
DBPrepareDescriptor {
ret_code: S32
stmt_handle: U32
tail: U32
}
DBExecDescriptor {
ret_code: S32
err_msg: String
}
ethqlite:
fn init_service() -> InitResult
fn get_miner_rewards(miner_address: String) -> MinerRewards
fn owner_nuclear_reset() -> I32
fn get_reward_block(block_number: U32) -> RewardBlock
fn update_reward_blocks(data_string: String) -> UpdateResult
fn get_latest_reward_block() -> RewardBlock
fn am_i_owner() -> I32
sqlite3:
fn sqlite3_reset(stmt_handle: U32) -> S32
<snip>
fn sqlite3_column_blob(stmt_handle: U32, icol: S32) -> Array<U8>
```
and see all the public Fluence interfaces including the ones from the _sqlite3.wasm_ module. Let's upload the service to the local network:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 new_service --ms ethqlite/artifacts/sqlite3.wasm:ethqlite/sqlite3_cfg.json ethqlite/artifacts/ethqlite.wasm:ethqlite/ethqlite_cfg.json --name EthQlite
client seed: 7VqRt2kXWZ15HABKh1hS4kvGfRcBA69cYuzV1Rwm3kHv
client peerId: 12D3KooWCzWm4xBv7nApuK8vNLSbKKYV36kvkz3ywqj5xcjscnz9
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
uploading blueprint EthQlite to node 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 via client 12D3KooWCzWm4xBv7nApuK8vNLSbKKYV36kvkz3ywqj5xcjscnz9
service id: fb9ba691-c0fc-4500-88cc-b74f3b281088
service created successfully
```
Now that we crated the service on our local node, let's make sure that we have the necessary owner privileges. First, we create a little AIR script that calls the _am\_i\_owner_ function from thee ethqlite service:
```text
; am_i_owner.clj
(xor
(seq
(seq
(call relay ("op" "identity") [])
(call node_1 (service "am_i_owner") [] result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [result])
)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") ["XOR FAILED" %last_error%])
)
)
```
and run it with the `fldist` tool:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/am_i_owner.clj -d '{"service":"fb9ba691-c0fc-4500-88cc-b74f3b281088", "node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17"}'
client seed: 3J8BqpGTQ1Ujbr8dvnpTxfr5EUneHf9ZwW84ru9sNmj7
client peerId: 12D3KooW9z5hBDY6cXnkEGraiPFn6hJ3VstqAkVaAM7oThTiWVjL
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: efa37779-e3aa-4353-b63d-12b444b6366b. Waiting for results... Press Ctrl+C to stop the script.
===================
[
0
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'fb9ba691-c0fc-4500-88cc-b74f3b281088',
function_name: 'am_i_owner',
json_path: ''
}
]
]
===================
```
As discussed earlier, the service needs some proof that we have owner privileges, which we can provide by adding the client seed, `-s`, to our call parameters:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/am_i_owner.clj -d '{"service":"fb9ba691-c0fc-4500-88cc-b74f3b281088", "node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17"}' -s 7VqRt2kXWZ15HABKh1hS4kvGfRcBA69cYuzV1Rwm3kHv
client seed: 7VqRt2kXWZ15HABKh1hS4kvGfRcBA69cYuzV1Rwm3kHv
client peerId: 12D3KooWCzWm4xBv7nApuK8vNLSbKKYV36kvkz3ywqj5xcjscnz9
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: f0371615-7d75-4971-84a9-3111b8263de7. Waiting for results... Press Ctrl+C to stop the script.
===================
[
1
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: 'fb9ba691-c0fc-4500-88cc-b74f3b281088',
function_name: 'am_i_owner',
json_path: ''
}
]
]
===================
```
and all is well. So where does that client seed _7VqRt2kXWZ15HABKh1hS4kvGfRcBA69cYuzV1Rwm3kHv_ come from ? The easy answer is that we copied it from the service creation return values -- line 2 above. But that doesn't really answer the question. The more involved answer is that every developer should have one or more cryptographic key pairs from which the client seed is derived. Moreover, creating a new service, the client seed should be specified but if not, the system creates one instead as above.
The easiest way to get a keypair and seed is from the `fldist` tool:
```bash
fldist create_keypair
client seed: 8LKYUmsWkMSiHBxo8deXyNJD3wXutq265TSTcmmtgQTJ
client peerId: 12D3KooWRtrFyYjis4qQpC4kHcJWbtpM4mZgLYBoDn93eXJEGtVH
relay peerId: 12D3KooWBUJifCTgaxAUrcM9JysqCcS4CS8tiYH5hExbdWCAoNwb
{
id: '12D3KooWKphxxaXofYzC2TsN79RHZVubjmutKVdPUxVMHY3ZsVww',
privKey: 'CAESQO/TcX2DkTukK6XxJUc/2U6gqOLVza5PRWM2FhXfJ1qilKtA6qsHx0Rdibwxsg4Vh7JjTfRfMXSlLJphGCOb7zI=',
pubKey: 'CAESIJSrQOqrB8dEXYm8MbIOFYeyY030XzF0pSyaYRgjm+8y',
seed: 'H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V'
}
```
So let's re-deploy the Ethqlite service and specify the client seed at creation time:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 new_service --ms ethqlite/artifacts/sqlite3.wasm:ethqlite/sqlite3_cfg.json ethqlite/artifacts/ethqlite.wasm:ethqlite/ethqlite_cfg.json --name EthQliteSecure -s H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V
client seed: H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V
client peerId: 12D3KooWKphxxaXofYzC2TsN79RHZVubjmutKVdPUxVMHY3ZsVww
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
uploading blueprint EthQliteSecure to node 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 via client 12D3KooWKphxxaXofYzC2TsN79RHZVubjmutKVdPUxVMHY3ZsVww
service id: 470fcaba-6834-4ccf-ac0c-4f6494e9e77b
service created successfully
```
Updating the call parameters to reflect the new service id and client seed confirms our ownership over the service:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/am_i_owner.clj -d '{"service":"470fcaba-6834-4ccf-ac0c-4f6494e9e77b", "node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17"}' -s H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V
client seed: H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V
client peerId: 12D3KooWKphxxaXofYzC2TsN79RHZVubjmutKVdPUxVMHY3ZsVww
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: 6d8c158b-d998-44ca-9d4c-255ce4b9cd21. Waiting for results... Press Ctrl+C to stop the script.
===================
[
1
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: '470fcaba-6834-4ccf-ac0c-4f6494e9e77b',
function_name: 'am_i_owner',
json_path: ''
}
]
]
===================
```
Back to our task at hand: persisting reward block data to our sqlite as a service. Looking over the source code, we know that in order to accomplish persistence, we need to:
* init the database: `pub fn init_service() -> InitResult`
* provide reward data : `pub fn update_reward_blocks(data_string: String) -> UpdateResult`
Initializing Ethqlite for the most part is a one time event, so we'll do it right now and outside of our recurring block discovery and commit workflow with another small AIR script:
```text
; ethqlite_init.clj
(xor
(seq
(seq
(call relay ("op" "identity") [])
(call node_1 (service "init_service") [] result)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") [result])
)
)
(seq
(call relay ("op" "identity") [])
(call %init_peer_id% (returnService "run") ["XOR FAILED" %last_error%])
)
)
```
which we deploy to the node with the `fldist` tool:
```bash
fldist --node-id 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 --node-addr /ip4/127.0.0.1/tcp/9999/ws/p2p/12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17 run_air -p air-scripts/ethqlite_init.clj -d '{"service":"470fcaba-6834-4ccf-ac0c-4f6494e9e77b", "node":"12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17"}' -s H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V
client seed: H9BSbZwKmFs93462xbAyfEdGdMXb5LZuXL7GSA4uPK4V
client peerId: 12D3KooWKphxxaXofYzC2TsN79RHZVubjmutKVdPUxVMHY3ZsVww
relay peerId: 12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17
Particle id: 2fb4a366-6f40-46c1-9329-d77c6d03dfad. Waiting for results... Press Ctrl+C to stop the script.
===================
[
{
"err_msg": "",
"success": 1
}
]
[
[
{
peer_pk: '12D3KooWQQYXh78acqBNuL5p1J5tmH4XCKLCHM21tMb8pcxqGL17',
service_id: '470fcaba-6834-4ccf-ac0c-4f6494e9e77b',
function_name: 'init_service',
json_path: ''
}
]
]
===================
```
If you run the init script again, you will receive an error _"Service already initiated"_, so we can be reasonably confident our code is working and it looks like our Ethqlite service is up and running on the local node.
Due to the security concerns for our database, it is not advisable, or even possible, to use an already deployed Sqlite service from the Fluence Dashboard. Instead, we deploy our own instance with our own \(secret\) client seed. To determine which network nodes are available, run:
```bash
fldist --env testnet env
client seed: Cj4Wpy5y955o2N3T8Hs5myRoFGhBaBhytCdsYeyFLQPw
client peerId: 12D3KooWQg8cyj4z8Bv4rGq1PeXL1XKEQd6Z2CCFguy9D4NnLaKm
relay peerId: 12D3KooWBUJifCTgaxAUrcM9JysqCcS4CS8tiYH5hExbdWCAoNwb
/dns4/net01.fluence.dev/tcp/19001/wss/p2p/12D3KooWEXNUbCXooUwHrHBbrmjsrpHXoEphPwbjQXEGyzbqKnE9
/dns4/net01.fluence.dev/tcp/19990/wss/p2p/12D3KooWMhVpgfQxBLkQkJed8VFNvgN4iE6MD7xCybb1ZYWW2Gtz
/dns4/net02.fluence.dev/tcp/19001/wss/p2p/12D3KooWHk9BjDQBUqnavciRPhAYFvqKBe4ZiPPvde7vDaqgn5er
/dns4/net03.fluence.dev/tcp/19001/wss/p2p/12D3KooWBUJifCTgaxAUrcM9JysqCcS4CS8tiYH5hExbdWCAoNwb
/dns4/net04.fluence.dev/tcp/19001/wss/p2p/12D3KooWJbJFaZ3k5sNd8DjQgg3aERoKtBAnirEvPV8yp76kEXHB
/dns4/net05.fluence.dev/tcp/19001/wss/p2p/12D3KooWCKCeqLPSgMnDjyFsJuWqREDtKNHx1JEBiwaMXhCLNTRb
/dns4/net06.fluence.dev/tcp/19001/wss/p2p/12D3KooWKnRcsTpYx9axkJ6d69LPfpPXrkVLe96skuPTAo76LLVH
/dns4/net07.fluence.dev/tcp/19001/wss/p2p/12D3KooWBSdm6TkqnEFrgBuSkpVE3dR1kr6952DsWQRNwJZjFZBv
/dns4/net08.fluence.dev/tcp/19001/wss/p2p/12D3KooWGzNvhSDsgFoHwpWHAyPf1kcTYCGeRBPfznL8J6qdyu2H
/dns4/net09.fluence.dev/tcp/19001/wss/p2p/12D3KooWF7gjXhQ4LaKj6j7ntxsPpGk34psdQicN2KNfBi9bFKXg
/dns4/net10.fluence.dev/tcp/19001/wss/p2p/12D3KooWB9P1xmV3c7ZPpBemovbwCiRRTKd3Kq2jsVPQN4ZukDfy
```
which lists the available testnet peers. Pick one, update the node-id parameter and drop the node-addr parameter in your deployment command-line, upload the new ethqlite service and initiate it. Congrat's, you are now the proud maker of a Fluence testnet Ehqlite service!
Now it is time to get block data into the database.

2
development_development/development_reward_block_app/recap.md Normal file
View File

@ -0,0 +1,2 @@
# Recap