Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
S
slash
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
uplex-varnish
slash
Commits
efc7cf58
Unverified
Commit
efc7cf58
authored
Feb 05, 2024
by
Nils Goroll
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
doc: Update CHANGES.rst
parent
21ebd388
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
27 additions
and
0 deletions
+27
-0
CHANGES.rst
CHANGES.rst
+27
-0
No files found.
CHANGES.rst
View file @
efc7cf58
...
...
@@ -21,6 +21,33 @@ fellow
.. https://gitlab.com/uplex/varnish/slash/-/commit/
* The ``ioerr_obj=purge`` and ``allocerr_obj=purge`` tunables are now
fully implemented. The statistics counter ``c_mem_obj_fail`` as been
added to track the number of times a failed object is hit.
* Reading cache objects has been made more asynchronous: Segment lists
for extended (non-embedded) segments are now read only on demand and
in a separate thread.
* Even more memory and disk space allocating functions have been
rewritten to use asynchronous allocations to lower latencies.
* Dramatically increased memory efficiency. This change may lead to
more memory being shown as free than before, and users of
SLASH/fellow may wonder why memory is kept unused: This is a
consequence of a deliberate decision in the buddy memory allocator
to allocate objects only at multiples of their (rounded up) size,
which helps to keep the allocator efficient.
.. _#41: https://gitlab.com/uplex/varnish/slash/-/issues/41
* Dramatically increased stability with minimal memory cache size
configurations as long as a correct *objsize_hint* parameter is
given (it needs to be *smaller* than the actual average object
size). A zero *memsz* argument can now be given to configure the
minimal memory cache size, which is NOT RECOMMENDED (the more memory
the better). Motivated by `#41`_
* Fixed many bugs
* Improved code coverage and added Coverity for additional linting.
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment