DOC-5424 time series updates #1830
There are no files selected for viewing
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -12,7 +12,12 @@ categories: | |
| description: 'Out-of-order / backfilled ingestion performance considerations | ||
|
|
||
| ' | ||
| linkTitle: Out-of-order/backfill performance | ||
| aliases: | ||
| - /develop/data-types/timeseries/reference/out-of-order_performance_considerations | ||
| - /develop/data-types/timeseries/reference/out-of-order_performance_considerations/ | ||
| - /develop/data-types/timeseries/reference/ | ||
| - /develop/data-types/timeseries/reference | ||
| title: Out-of-order / backfilled ingestion performance considerations | ||
| weight: 5 | ||
| --- | ||
|
|
@@ -46,11 +51,11 @@ The graphs and tables below make these key points: | |
|
|
||
| - We've observed a maximum 95% drop in the achievable ops/sec even at 99% out-of-order ingestion. (Again, reducing the chunk size can cut the impact in half.) | ||
|
|
||
| {{< image filename="/images/timeseries/compressed-overall-ops-sec-vs-out-of-order-percentage.webp" alt="compressed-overall-ops-sec-vs-out-of-order-percentage" >}} | ||
|
There was a problem hiding this comment. Just because I'm curious... was there an edict to begin using WebP images rather than PNGs? The downside to WebP images is that they don't render in GitHub. In other PRs where graphics are swapped, you could see the change side by side in the PR diff viewer; can't do that with WebP. No axe to grind; just thought I'd ask. There was a problem hiding this comment. @dwdougherty It's just the file size (typically about half the size of the equivalent PNG, and no need to use pngcrush or other tools to optimise). "Speed is our superpower", etc, and we're guided to try to have the fastest everything (website, tools...) so I figured that gradually de-crufting and optimising what we've got in the docs was in order. |
||
|
|
||
| {{< image filename="/images/timeseries/compressed-overall-p50-lat-vs-out-of-order-percentage.webp" alt="compressed-overall-p50-lat-vs-out-of-order-percentage" >}} | ||
|
|
||
| {{< image filename="/images/timeseries/compressed-out-of-order-overhead-table.webp" alt="compressed-out-of-order-overhead-table" >}} | ||
|
|
||
| ## Uncompressed chunks out-of-order/backfilled impact analysis | ||
|
|
||
|
|
@@ -63,8 +68,8 @@ Apart from that, we can observe the following key take-aways: | |
|
|
||
| - We've observed a maximum 45% drop in the achievable ops/sec, even at 99% out-of-order ingestion. | ||
|
|
||
| {{< image filename="/images/timeseries/uncompressed-overall-ops-sec-vs-out-of-order-percentage.webp" alt="uncompressed-overall-ops-sec-vs-out-of-order-percentage" >}} | ||
|
|
||
| {{< image filename="/images/timeseries/uncompressed-overall-p50-lat-vs-out-of-order-percentage.webp" alt="uncompressed-overall-p50-lat-vs-out-of-order-percentage" >}} | ||
|
|
||
| {{< image filename="/images/timeseries/uncompressed-out-of-order-overhead-table.webp" alt="uncompressed-out-of-order-overhead-table" >}} | ||
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I've just started seeing aliases like this, with both no trailing slash and with. Are both necessary?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@dwdougherty TBH, I don't know, but my recent restructuring PR apparently had dodgy aliases (even though they looked right) and the PR to fix had both slash and no-slash aliases (and was reported to work OK). I don't know why it would make any difference, but I still find Hugo a bit enigmatic :-)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You and me both. 🫥