Perf doc #1996
Merged
Perf doc #1996
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
tomquisel
approved these changes
Mar 8, 2019
docs/software/performance.md
Outdated
| The performance of a `stellar-core` node varies in two main dimensions: | ||
|
|
||
| 1. _What it is configured to do_: | ||
| * As discussed in the [admin.md](./admin.md) file, nodes may be configured as watchers, archivers, basic validators or full validators. These roles have different performance costs. |
There was a problem hiding this comment.
These list items aren't rendering right (I think you just need a newline)
docs/software/performance.md
Outdated
| * Each such role may have a variety of options enabled or disabled at varying costs to the node. | ||
|
|
||
| 2. _How it is physically and logically configured to do its job_: | ||
| * The physical hardware -- disks, CPUs, memory and networking equipment -- supporting the node can substantially affect performance. |
docs/software/performance.md
Outdated
|
|
||
| 1. The `BUCKET_DIR_PATH` config option sets the location that `stellar-core` places its buckets while (re)writing the bucket list. This should be located on a relatively fast, low-latency local disk. Ideally SSD or NVMe or similar. The faster the better. It does not need to be _very_ large and should not grow in usage _very_ fast, though `stellar-core` will fail if it fills up, so keep an eye on its utilization and make sure there's plenty of room. | ||
| 2. The `DATABASE` config value controls not only which _kind_ of database the node is performing transactions against, but also _where_ the database is located. Unlike with many database-backed programs, the _content_ of the database in a `stellar-core` installation is somewhat ephemeral: every node has a complete copy of it, as does every history archive, and the database can always be restored / rebuilt from history archives (it is in fact being continuously backed up every 5 minutes). So the main thing to optimize for here is latency, especially on nodes doing consensus. We recommend either: | ||
| * SQLite on a fast, local disk. This is probably the fastest option and is perfectly adequate for many types of node. |
graydon
force-pushed
the
perf-doc
branch
3 times, most recently
from
35828fa
to
14996e3
Compare
|
r+ 8683e14 |
latobarita
added a commit
that referenced
this pull request
Mar 16, 2019
Perf doc Reviewed-by: graydon
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This just adds a new (preliminary!) performance.md doc as we've been discussing, that talks explicitly about sources of load on stellar-core nodes and ways to configure it to control for them.
Additions welcome. I figured I'd get a sketch done and we could build it out with contributions from operators.
(There are 2 doc-maintenance commits in here too, the only one about performance.md is the third commit)