Avi Kivity 0591303b72 Merge "avoid excessive memory usage during resharding" from Rapahel ...

"Intended to reduce memory usage when resharding by sharing sstable
components among shards. File descriptors are also shared from now
on, meaning that a much smaller number of file descriptors will be
used during resharding.

Fixes #1951."

branch 'excessive_memory_usage_v4' of github.com:raphaelsc/scylla

* 'excessive_memory_usage_v4' of github.com:raphaelsc/scylla:
  db: avoid excessive memory usage during resharding
  checked_file_impl: add support to dup
  sstables: group sstable components that can be shared among shards
  sstables: rename sstable member

2017-01-09 20:43:50 +02:00

..

pager

Use gc_clock instead of db_clock where possible

2016-12-22 13:27:55 +02:00

client_state.cc

client_state: Add has_schema_access function

2016-07-17 17:38:23 +00:00

client_state.hh

tracing: introduce trace_state capabilities bit field

2016-08-23 18:34:36 +03:00

endpoint_lifecycle_subscriber.hh

Fix pre-ScyllaDB copyright statements

2016-04-08 08:12:47 +03:00

load_broadcaster.cc

load_broadcaster report negative size

2015-12-29 11:55:34 +02:00

load_broadcaster.hh

gossip: Pass const ref for versioned_value in on_change and before_change

2015-12-09 12:29:15 +08:00

migration_listener.hh

migration_listener: Listen for view schema changes

2016-12-20 13:06:11 +00:00

migration_manager.cc

migration_manager: Only drop table without views

2016-12-20 13:06:11 +00:00

migration_manager.hh

migration_manager: Announce view drop

2016-12-20 13:06:11 +00:00

migration_task.cc

Fix pre-ScyllaDB copyright statements

2016-04-08 08:12:47 +03:00

migration_task.hh

Fix pre-ScyllaDB copyright statements

2016-04-08 08:12:47 +03:00

priority_manager.cc

introduce a priority manager

2016-01-25 15:20:38 -05:00

priority_manager.hh

priority manager: separate streaming reads from writes

2016-03-23 09:12:59 -04:00

query_state.hh

service::query_state: get rid of begin_tracing()

2016-07-19 18:21:58 +03:00

storage_proxy.cc

storage_proxy: prevent short read due to buffer size limit from being swallowed during range scan

2017-01-09 09:21:43 +00:00

storage_proxy.hh

storage_proxy: pass maximum result size to replicas

2016-12-22 17:16:23 +01:00

storage_service.cc

db: avoid excessive memory usage during resharding

2017-01-09 15:24:36 -02:00

storage_service.hh

storage_service: make is_joined() an immediate function

2016-12-28 18:37:22 +02:00