wbtiger
/
foundationdb
mirror of https://github.com/apple/foundationdb.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1916 from ajbeamon/merge-onto-new-servers 

Add knob to control whether merges request new servers or not.
This commit is contained in:
A.J. Beamon 2019-07-30 15:04:37 -07:00 committed by GitHub
parent 14648e20f9 4f3a8a2346
commit 41605735f5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
documentation/sphinx/source/release-notes.rst
View File

@ -27,6 +27,7 @@ Fixes
* During an upgrade, the multi-version client now persists database default options and transaction options that aren't reset on retry (e.g. transaction timeout). In order for these options to function correctly during an upgrade, a 6.2 or later client should be used as the primary client. `(PR #1767) <https://github.com/apple/foundationdb/pull/1767>`_.
* If a cluster is upgraded during an ``onError`` call, the cluster could return a ``cluster_version_changed`` error. `(PR #1734) <https://github.com/apple/foundationdb/pull/1734>`_.
* Do not set doBuildTeams in StorageServerTracker unless a storage server's interface changes, in order to avoid unnecessary work. `(PR #1779) <https://github.com/apple/foundationdb/pull/1779>`_.
* Data distribution will now pick a random destination when merging shards in the ``\xff`` keyspace. This avoids an issue with backup where the write-heavy mutation log shards could concentrate on a single process that has less data than everybody else. `(PR #1916) <https://github.com/apple/foundationdb/pull/1916>`_.
Status
------

9
fdbserver/DataDistributionQueue.actor.cpp
View File

@ -52,7 +52,14 @@ struct RelocateData {
rs.priority == PRIORITY_REBALANCE_OVERUTILIZED_TEAM ||
rs.priority == PRIORITY_REBALANCE_UNDERUTILIZED_TEAM ||
rs.priority == PRIORITY_SPLIT_SHARD ||
rs.priority == PRIORITY_TEAM_REDUNDANT ), interval("QueuedRelocation") {}
rs.priority == PRIORITY_TEAM_REDUNDANT ||
mergeWantsNewServers(rs.keys, rs.priority)), interval("QueuedRelocation") {}
static bool mergeWantsNewServers(KeyRangeRef keys, int priority) {
return priority == PRIORITY_MERGE_SHARD &&
(SERVER_KNOBS->MERGE_ONTO_NEW_TEAM == 2 ||
(SERVER_KNOBS->MERGE_ONTO_NEW_TEAM == 1 && keys.begin.startsWith(LiteralStringRef("\xff"))));
}
bool operator> (const RelocateData& rhs) const {
return priority != rhs.priority ? priority > rhs.priority : ( startTime != rhs.startTime ? startTime < rhs.startTime : randomId > rhs.randomId );

1
fdbserver/Knobs.cpp
View File

@ -101,6 +101,7 @@ ServerKnobs::ServerKnobs(bool randomize, ClientKnobs* clientKnobs) {
init( INFLIGHT_PENALTY_HEALTHY, 1.0 );
init( INFLIGHT_PENALTY_UNHEALTHY, 10.0 );
init( INFLIGHT_PENALTY_ONE_LEFT, 1000.0 );
init( MERGE_ONTO_NEW_TEAM, 1 ); if( randomize && BUGGIFY ) MERGE_ONTO_NEW_TEAM = deterministicRandom()->coinflip() ? 0 : 2;
// Data distribution
init( RETRY_RELOCATESHARD_DELAY, 0.1 );

1
fdbserver/Knobs.h
View File

@ -102,6 +102,7 @@ public:
double INFLIGHT_PENALTY_REDUNDANT;
double INFLIGHT_PENALTY_UNHEALTHY;
double INFLIGHT_PENALTY_ONE_LEFT;
int MERGE_ONTO_NEW_TEAM; // Merges will request new servers. 0 for off, 1 for \xff only, 2 for all shards.
// Data distribution
double RETRY_RELOCATESHARD_DELAY;