Initial version of Valkey 9.0 release blog #390
+85
−0
Conversation
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
Signed-off-by: Kyle J. Davis <[email protected]>
madolson
reviewed
Oct 13, 2025
| * **Zero copy responses**: Large requests avoid internal memory copying, yielding up to 20% higher throughput, | ||
| * **[Pipeline memory prefetch](https://github.com/valkey-io/valkey/pull/2092)**: Memory prefetching when pipelining, yielding up to 40% higher throughput, | ||
| * **[Multipath TCP](https://github.com/valkey-io/valkey/pull/1811)**: Adds Multipath TCP support which can reduce latency by 25%. | ||
| * **1000+ node cluster**: stability improvements for very large clusters, |
There was a problem hiding this comment.
I would cut this as there will be a dedicated blog. We didn't actually update much for this release.
| This approach works for most situations, but corner cases can lead to degraded performance, operational headaches, and, at worst, blocked node migrations and lost data. | ||
|
|
||
| Key-by-key migration uses a move-then-delete sequence. | ||
| Performance issues arise when Valkey tries to access a key during a partially migrated state: if the migration hasn’t completed, the client may not know if the key resides on a the original node or the new node and leading to a condition that has more network hops and additional processing. |
There was a problem hiding this comment.
Suggested change
| Performance issues arise when Valkey tries to access a key during a partially migrated state: if the migration hasn’t completed, the client may not know if the key resides on a the original node or the new node and leading to a condition that has more network hops and additional processing. | |
| Performance issues arise when a client tries to access a key during a partially migrated state: if the migration hasn’t completed, the client may not know if the key resides on a the original node or the new node and leading to a condition that has more network hops and additional processing. |
| Performance issues arise when Valkey tries to access a key during a partially migrated state: if the migration hasn’t completed, the client may not know if the key resides on a the original node or the new node and leading to a condition that has more network hops and additional processing. | ||
| Worse, in a multi-key operation, if one key resides in the original node and another in the new node, Valkey cannot properly execute the command, so it requires the client to retry the request until the data resides on a single node, leading to a mini-outage where Valkey still has the data but it is inaccessible until the migration is complete for the affected data. | ||
| Finally, in a situation where Valkey is attempting to migrate a very large key (such as collections in data types like sorted sets, sets, or lists) from one node to another, the entire key may be too large to be accepted by the target node’s input buffer leading to a blocked migration that needs manual intervention. | ||
| To unblock the migration you end up losing data either through forcing the slot assignment or deleting the key. |
There was a problem hiding this comment.
You can increase the buffer limit so this goes through, you don't need to lose data.
| Finally, in a situation where Valkey is attempting to migrate a very large key (such as collections in data types like sorted sets, sets, or lists) from one node to another, the entire key may be too large to be accepted by the target node’s input buffer leading to a blocked migration that needs manual intervention. | ||
| To unblock the migration you end up losing data either through forcing the slot assignment or deleting the key. | ||
|
|
||
| In Valkey, the keyspace is not really flat, but instead keys are bundled into one of 16,384 ‘slots’ and each node takes one or more slots. |
There was a problem hiding this comment.
Suggested change
| In Valkey, the keyspace is not really flat, but instead keys are bundled into one of 16,384 ‘slots’ and each node takes one or more slots. | |
| In Valkey, keys are bundled into one of 16,384 ‘slots’ and each node takes one or more slots. |
Is the flat comment needed, seems like it may be confusing since we do call the keyspace flat.
|
|
||
| In Valkey, the keyspace is not really flat, but instead keys are bundled into one of 16,384 ‘slots’ and each node takes one or more slots. | ||
| In Valkey 9.0 instead of being key-by-key, Valkey migrates entire slots at a time, atomically moving the slot from one node to another using the AOF format. | ||
| AOF does not work on a key-by-key basis, but instead AOF plays back all the operations that make up the data, so the input buffer only has to deal with individual items in collections and those will never exceed the size of the input buffer, avoiding large key migration issues. |
There was a problem hiding this comment.
the aof format is also key by key. The important information is we copy all the data from the source to the primary before we delete any data on the source.
The second half of this sentence is valid.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Description
Initial version of the blog for the 9.0 release.
I ran into a few issues that I could use some help with:
Issues Resolved
#312
Check List
--signoffBy submitting this pull request, I confirm that my contribution is made under the terms of the BSD-3-Clause License.