John Spray 34ebfbdd6f pageserver: fix handling getpage with multiple shards on one node ...

Previously, we would wait for the LSN to be visible on whichever
timeline we happened to load at the start of the connection, then
proceed to look up the correct timeline for the key and do the read.

If the timeline holding the key was behind the timeline we used
for the LSN wait, then we might serve an apparently-successful read result
that actually contains data from behind the requested lsn.

2024-01-03 14:22:40 +00:00

..

bin

Move failpoint support code to utils.

2024-01-02 10:50:20 +04:00

consumption_metrics

pageserver: further refactoring from TenantId to TenantShardId (#6059)

2023-12-11 15:52:33 +00:00

deletion_queue

tests: update for tenant generations (#5449)

2023-12-07 12:27:16 +00:00

http

Move failpoint support code to utils.

2024-01-02 10:50:20 +04:00

tenant

pageserver: fix active tenant lookup hitting secondaries with sharding

2024-01-03 14:22:40 +00:00

auth.rs

JWT logging improvements (#5823)

2023-11-08 16:56:53 +00:00

basebackup.rs

Add batch ingestion mechanism to avoid high contention (#5886)

2024-01-03 10:41:58 +00:00

config.rs

Add batch ingestion mechanism to avoid high contention (#5886)

2024-01-03 10:41:58 +00:00

consumption_metrics.rs

refactor: calculate_synthetic_size_worker, remove PRE::NeedsDownload (#6111)

2023-12-13 14:23:19 +00:00

context.rs

page cache: metrics: add page content kind dimension (#5373)

2023-09-26 10:01:09 +03:00

control_plane_client.rs

pageserver: refactor TenantId to TenantShardId in Tenant & Timeline (#5957)

2023-11-29 14:52:35 +00:00

deletion_queue.rs

pageserver: refactor TenantId to TenantShardId in Tenant & Timeline (#5957)

2023-11-29 14:52:35 +00:00

disk_usage_eviction_task.rs

feat: relative last activity based eviction (#6136)

2023-12-20 18:44:19 +00:00

import_datadir.rs

Add batch ingestion mechanism to avoid high contention (#5886)

2024-01-03 10:41:58 +00:00

lib.rs

Move failpoint support code to utils.

2024-01-02 10:50:20 +04:00

metrics.rs

fix metric pageserver_initial_logical_size_start_calculation (#6191)

2023-12-19 17:44:49 +01:00

page_cache.rs

pageserver: further refactoring from TenantId to TenantShardId (#6059)

2023-12-11 15:52:33 +00:00

page_service.rs

pageserver: fix handling getpage with multiple shards on one node

2024-01-03 14:22:40 +00:00

pgdatadir_mapping.rs

Add batch ingestion mechanism to avoid high contention (#5886)

2024-01-03 10:41:58 +00:00

repository.rs

pageserver: add method to dump keyspace in mgmt api client (#6145)

2023-12-16 10:52:48 +00:00

statvfs.rs

fix: replace all std::PathBufs with camino::Utf8PathBuf (#5352)

2023-10-04 17:52:23 +03:00

task_mgr.rs

fix: Timeline deletion during busy startup (#6133)

2023-12-15 11:59:24 +00:00

tenant.rs

Move failpoint support code to utils.

2024-01-02 10:50:20 +04:00

trace.rs

fix: replace all std::PathBufs with camino::Utf8PathBuf (#5352)

2023-10-04 17:52:23 +03:00

virtual_file.rs

virtual_file metrics: expose max size of the fd cache (#6078)

2023-12-08 17:23:50 +00:00

walingest.rs

Add batch ingestion mechanism to avoid high contention (#5886)

2024-01-03 10:41:58 +00:00

walrecord.rs

Logical replication (#5271)

2023-10-18 16:42:22 +03:00

walredo.rs

walredo: stderr cleanup & make explicitly cancel safe (#6031)

2023-12-04 16:06:41 +00:00