Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

users/evgenybud/vhost rdma server migration v2 #583

Closed

Conversation

budevg
Copy link
Collaborator

@budevg budevg commented Feb 28, 2024

SvartMetal and others added 30 commits January 16, 2024 18:22
* add more logs for s3

* add more logs for s3

* add more logs for s3

* add more logs for s3

* add more logs for s3

* fix issues

* rebase

* rebase

* rebase

* rebase

* fix style

* rebase

---------

Co-authored-by: BarkovBG <[email protected]>
)

* support diskSource.dontReadFromCheckpoint option

* enable dontReadFromCheckpoint for disks replication
…te agent disconnects by rack - problems in a single rack should not make RejectAgentTimeout reach max values (#159)

* NBSNEBIUS-76: RejectAgentTimeout dynamic calculation should deduplicate agent disconnects by rack - problems in a single rack should not make RejectAgentTimeout reach max values

* NBSNEBIUS-76: RejectAgentTimeout dynamic calculation should deduplicate agent disconnects by rack - problems in a single rack should not make RejectAgentTimeout reach max values - fixed lifecycle ut
* Add required resources for disk manager tests

* Replace sbr resources with FROM_SANDBOX macro

* Discover data through build_path instead of work_path

* Rename image directory to resources

* Make ya.make in alphabetic order
Pseudo terminal allocation was not previously supported in tests, the -t option caused significant divergence in test results with proprietary tests.
* [Disk Manager]: Snapshot: Check chunk contents for zeroes

Sometimes NBS can return chunks full of zeroes yet the zero field is set
to false. Check if chunk is actually a zero chunk.
* refactor sre tools

* resolve issues

* fix build

* fix issue
…HDD disks; slightly improved ShouldHandleCmsRequestsForHostsWithDependentHddDisks ut (#189)

* NBSNEBIUS-82: not counting broken placement group partitions for non-HDD disks; slightly improved ShouldHandleCmsRequestsForHostsWithDependentHddDisks ut

* NBSNEBIUS-82: not counting broken placement group partitions for non-HDD disks; slightly improved ShouldHandleCmsRequestsForHostsWithDependentHddDisks ut
…nActor and TVolumeActor (#151)

* NBS-4826 send message about long running blob operations to TPartitionActor and TVolumeActor

* NBS-4826 Fix review issues

* Remove unnecessary comments
* NBS-4748: migrate from solomon to monitoring

* NBS-4748: review fixes
qkrorlqr and others added 29 commits February 21, 2024 18:55
…, extracted CopyFileData implementation, rewritten it without GetContent/GetContentRef usage, added uts for it (preparation to implement a lazy-alloc block buffer to use it in HandleDescribeData) (#520)
…allback reason + fix ServiceActor not reporting `ReadData` counters (#521)

* [Filestore] NBSNEBIUS-121: TwoStageRead: add logging for `ReadData` fallback reason + fix ServiceActor not reporting `ReadData` counters
Write run_all.sh output to the logs_dir for
 the run instead of the logs root
* mute ServiceMigrate* nemesis tests

mute tests and specify split factor corresponding to it's chunk
size based on the number of skipped tests in nightly builds e.g.
https://github-actions-s3.website.nemax.nebius.cloud/ydb-platform/nbs/Nightly-build/7967342719/1/nebius-x86-64/summary/ya-test.html
track small number of recently completed requests; resolves #481
* issue-541: added DescribeSessions private api action

* issue-541: added DescribeSessions private api action

* issue-541: added DescribeSessions private api action

* issue-541: added DescribeSessions private api action - fixed includes, added forgotten file
* [CI]: Fix acceptance tests issues

Fix _cleaner_type for disk manager acceptance test.

* Use timezone aware time in cleanup process

* Improve error logging for DiskPolicy

* Fix incorrect types in BaseTestBinaryExecutor.run()

* Fix disk/snapshot naming in run_single_test
…-client, testing create+reset+describe sessions in client tests (#556)

* issue-541: added createsession and resetsession commands to filestore-client, testing create+reset+describe sessions in client tests

* issue-541: added createsession and resetsession commands to filestore-client, testing create+reset+describe sessions in client tests
When volume starts migration the endpoint will be switched to use regular data
path (NRD volume through actor system).

Additionally when "use-fastpath" added/removed to volume tags the endpoint will
switch to use fast/regular data path

Additionally resolves #312
@budevg budevg closed this Feb 28, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.