resident_memory_docs (#864)

* resident_memory_docs

* add glossary

* add glossary

* add glossary

* add glossary

* add glossary
This commit is contained in:
Alex Sharov 2020-08-04 15:03:59 +07:00 committed by GitHub
parent 91baa688bd
commit b5345a712a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 60 additions and 20 deletions

View File

@ -1,24 +1,34 @@
# Turbo-Geth
[GoDoc](https://godoc.org/github.com/ledgerwatch/turbo-geth)
Turbo-Geth is a fork of [Go-Ethereum](https://github.com/ethereum/go-ethereum) with focus on performance. [![CircleCI](https://circleci.com/gh/ledgerwatch/turbo-geth.svg?style=svg)](https://circleci.com/gh/ledgerwatch/turbo-geth)
[![CircleCI](https://circleci.com/gh/ledgerwatch/turbo-geth.svg?style=svg)](https://circleci.com/gh/ledgerwatch/turbo-geth)
Table of contents
=================
<!--ts-->
* [System Requirements](#system-requirements)
* [Usage](#usage)
* [Key features](#key-features)
* [Getting in touch](#getting-in-touch)
* [Team](#team)
* [Known issues](#known-issues)
* [GoDoc](https://godoc.org/github.com/ledgerwatch/turbo-geth)
<!--te-->
NB! <code>In-depth links are marked by the microscope sign (🔬) </code>
**Disclaimer: this software is currenly a tech preview. We will do our best to
keep it stable and make no breaking changes but we don't guarantee anything.
Things can and will break.**
---
NB! <code>In-depth links are marked by the microscope sign (🔬) </code>
---
Turbo-Geth is a fork of [Go-Ethereum](https://github.com/ethereum/go-ethereum) with focus on performance.
The current version is currently based on Go-Ethereum 1.9.15.
#### System Requirements
System Requirements
===================
About 830 GB of free disk storage (630 GB state storage, 200GB temp files)
@ -26,7 +36,8 @@ About 830 GB of free disk storage (630 GB state storage, 200GB temp files)
<code>🔬 more info on disk storage is here [here](https://ledgerwatch.github.io/turbo_geth_release.html#Disk-space)) </code>
#### Usage:
Usage
=====
```sh
> git clone --recurse-submodules -j8 https://github.com/ledgerwatch/turbo-geth.git && cd turbo-geth
@ -34,7 +45,8 @@ About 830 GB of free disk storage (630 GB state storage, 200GB temp files)
> ./build/bin/tg
```
## Key features
Key features
============
<code>🔬 See more detailed [overview of functionality and current limitations](https://ledgerwatch.github.io/turbo_geth_release.html). It is being updated on recurring basis.</code>
@ -111,9 +123,7 @@ Run RPC daemon
> ./build/bin/rpcdaemon --private.api.addr=localhost:9090
```
---
Currently supported JSON-RPC calls ([eth](./cmd/rpcdaemon/eth_api.go), [debug](./cmd/rpcdaemon/debug_api.go)):
Supported JSON-RPC calls ([eth](./cmd/rpcdaemon/eth_api.go), [debug](./cmd/rpcdaemon/debug_api.go)):
```
eth_call
@ -165,7 +175,8 @@ docker-compose build
XDG_DATA_HOME=/preferred/data/folder docker-compose up
```
## Getting in touch
Getting in touch
================
#### Turbo-Geth Discord Server
@ -177,7 +188,8 @@ a brief explanation of why you want to join the Discord, and how you heard about
Send an email to `security [at] torquem.ch`.
## Team
Team
=======
Core contributors:
@ -203,6 +215,32 @@ Thanks to:
* Our special respect and graditude is to the core team of [Go-Ethereum](https://github.com/ethereum/go-ethereum). Keep up the great job!
---
Happy testing! 🥤
Known issues
============
#### `htop` shows incorrect memory usage
TurboGeth's internal DB (LMDB) using `MemoryMap` - when OS does manage all `read, write, cache` operations instead of Application
([linux](https://linux-kernel-labs.github.io/refs/heads/master/labs/memory_mapping.html), [windows](https://docs.microsoft.com/en-us/windows/win32/memory/file-mapping))
`htop` on column `res` shows memory of "App + OS used to hold page cache for given App",
but it's not informative, because if `htop` says that app using 90% of memory you still
can run 3 more instances of app on the same machine - because most of that `90%` is "OS pages cache".
OS automatically free this cache any time it needs memory.
Smaller "page cache size" may not impact performance of TurboGeth at all.
Next tools show correct memory usage of TurboGeth:
- `vmmap -summary PID | grep -i "Physical footprint"`.
Without `grep` you can see details - `section MALLOC ZONE column Resident Size` shows App memory usage, `section REGION TYPE column Resident Size` shows OS pages cache size.
- `Prometheus` dashboard shows memory of Go app without OS pages cache (`make prometheus`, open in browser `localhost:3000`, credentials `admin/admin`)
- `cat /proc/<PID>/smaps`
TurboGeth uses ~4Gb of RAM during genesis sync and < 1Gb during normal work. OS pages cache can utilize unlimited amount of memory.
**Warning:** Multiple instances of TG on same machine will touch Disk concurrently,
it impacts performance - one of main TG optimisations: "reduce Disk random access".
"Blocks Execution stage" still does much random reads - this is reason why it's slowest stage.
We do not recommend run multiple genesis syncs on same Disk.
If genesis sync passed, then it's fine to run multiple TG on same Disk.

View File

@ -302,7 +302,9 @@ func StartPProf(enablePprof bool, enableMetrics bool, address string) {
mux.HandleFunc("/debug/pprof/profile", pprof.Profile)
mux.HandleFunc("/debug/pprof/symbol", pprof.Symbol)
mux.HandleFunc("/debug/pprof/trace", pprof.Trace)
log.Info("Starting pprof server", "addr", fmt.Sprintf("http://%s/debug/pprof", address))
cpuMsg := fmt.Sprintf("go tool pprof -lines -http=: http://%s/%s", address, "?seconds=20")
heapMsg := fmt.Sprintf("go tool pprof -lines -http=: http://%s/%s", address, "debug/pprof/heap")
log.Info("Starting pprof server", "cpu", cpuMsg, "heap", heapMsg)
}
if enableMetrics {
@ -312,7 +314,7 @@ func StartPProf(enablePprof bool, enableMetrics bool, address string) {
mux.Handle("/memsize/", http.StripPrefix("/memsize", &Memsize))
// Start system runtime metrics collection
go metrics.CollectProcessMetrics(3 * time.Second)
log.Info("Starting metrics server", "addr", fmt.Sprintf("http://%s/debug/pprof", address))
log.Info("Starting metrics server", "addr", address)
}
if enableMetrics || enablePprof {