ReplicationMode -> ConsistencyMode+ReplicationFactor
All checks were successful
ci/woodpecker/pr/debug Pipeline was successful

This commit is contained in:
Yureka 2024-03-04 18:42:25 +01:00
parent 9f25721ad2
commit ce042e48d4
15 changed files with 169 additions and 112 deletions

View file

@ -38,7 +38,7 @@ data_dir = "/tmp/garage-data-$count"
rpc_bind_addr = "0.0.0.0:$((3900+$count))" # the port other Garage nodes will use to talk to this node rpc_bind_addr = "0.0.0.0:$((3900+$count))" # the port other Garage nodes will use to talk to this node
rpc_public_addr = "127.0.0.1:$((3900+$count))" rpc_public_addr = "127.0.0.1:$((3900+$count))"
bootstrap_peers = [] bootstrap_peers = []
replication_mode = "3" replication_factor = 3
rpc_secret = "$NETWORK_SECRET" rpc_secret = "$NETWORK_SECRET"
[s3_api] [s3_api]

View file

@ -18,9 +18,9 @@ garage:
sledCacheCapacity: "134217728" sledCacheCapacity: "134217728"
sledFlushEveryMs: "2000" sledFlushEveryMs: "2000"
# Default to 3 replicas, see the replication_mode section at # Default to 3 replicas, see the replication_factor section at
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#replication-mode # https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#replication-factor
replicationMode: "3" replicationFactor: 3
# zstd compression level of stored blocks # zstd compression level of stored blocks
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#compression-level # https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#compression-level
@ -55,7 +55,7 @@ garage:
sled_flush_every_ms = {{ .Values.garage.sledFlushEveryMs }} sled_flush_every_ms = {{ .Values.garage.sledFlushEveryMs }}
{{- end }} {{- end }}
replication_mode = "{{ .Values.garage.replicationMode }}" replication_factor = {{ .Values.garage.replicationFactor }}
compression_level = {{ .Values.garage.compressionLevel }} compression_level = {{ .Values.garage.compressionLevel }}

View file

@ -43,7 +43,7 @@
"rpc_bind_addr = \"0.0.0.0:3901\"\n" "rpc_bind_addr = \"0.0.0.0:3901\"\n"
"rpc_public_addr = \"" node ":3901\"\n" "rpc_public_addr = \"" node ":3901\"\n"
"db_engine = \"lmdb\"\n" "db_engine = \"lmdb\"\n"
"replication_mode = \"2\"\n" "replication_factor = 2\n"
"data_dir = \"" data-dir "\"\n" "data_dir = \"" data-dir "\"\n"
"metadata_dir = \"" meta-dir "\"\n" "metadata_dir = \"" meta-dir "\"\n"
"[s3_api]\n" "[s3_api]\n"

View file

@ -8,7 +8,7 @@ data:
metadata_dir = "/tmp/meta" metadata_dir = "/tmp/meta"
data_dir = "/tmp/data" data_dir = "/tmp/data"
replication_mode = "3" replication_factor = 3
rpc_bind_addr = "[::]:3901" rpc_bind_addr = "[::]:3901"
rpc_secret = "1799bccfd7411eddcf9ebd316bc1f5287ad12a68094e1c6ac6abde7e6feae1ec" rpc_secret = "1799bccfd7411eddcf9ebd316bc1f5287ad12a68094e1c6ac6abde7e6feae1ec"

View file

@ -163,7 +163,7 @@ mod tests {
r#" r#"
metadata_dir = "/tmp/garage/meta" metadata_dir = "/tmp/garage/meta"
data_dir = "/tmp/garage/data" data_dir = "/tmp/garage/data"
replication_mode = "3" replication_factor = 3
rpc_bind_addr = "[::]:3901" rpc_bind_addr = "[::]:3901"
rpc_secret_file = "{}" rpc_secret_file = "{}"
@ -185,7 +185,7 @@ mod tests {
r#" r#"
metadata_dir = "/tmp/garage/meta" metadata_dir = "/tmp/garage/meta"
data_dir = "/tmp/garage/data" data_dir = "/tmp/garage/data"
replication_mode = "3" replication_factor = 3
rpc_bind_addr = "[::]:3901" rpc_bind_addr = "[::]:3901"
rpc_secret_file = "{}" rpc_secret_file = "{}"
allow_world_readable_secrets = true allow_world_readable_secrets = true
@ -296,7 +296,7 @@ mod tests {
r#" r#"
metadata_dir = "/tmp/garage/meta" metadata_dir = "/tmp/garage/meta"
data_dir = "/tmp/garage/data" data_dir = "/tmp/garage/data"
replication_mode = "3" replication_factor = 3
rpc_bind_addr = "[::]:3901" rpc_bind_addr = "[::]:3901"
rpc_secret= "dummy" rpc_secret= "dummy"
rpc_secret_file = "dummy" rpc_secret_file = "dummy"

View file

@ -54,7 +54,7 @@ metadata_dir = "{path}/meta"
data_dir = "{path}/data" data_dir = "{path}/data"
db_engine = "lmdb" db_engine = "lmdb"
replication_mode = "1" replication_factor = 1
rpc_bind_addr = "127.0.0.1:{rpc_port}" rpc_bind_addr = "127.0.0.1:{rpc_port}"
rpc_public_addr = "127.0.0.1:{rpc_port}" rpc_public_addr = "127.0.0.1:{rpc_port}"

View file

@ -9,7 +9,7 @@ use garage_util::config::*;
use garage_util::error::*; use garage_util::error::*;
use garage_util::persister::PersisterShared; use garage_util::persister::PersisterShared;
use garage_rpc::replication_mode::ReplicationMode; use garage_rpc::replication_mode::*;
use garage_rpc::system::System; use garage_rpc::system::System;
use garage_block::manager::*; use garage_block::manager::*;
@ -39,8 +39,8 @@ pub struct Garage {
/// The set of background variables that can be viewed/modified at runtime /// The set of background variables that can be viewed/modified at runtime
pub bg_vars: vars::BgVars, pub bg_vars: vars::BgVars,
/// The replication mode of this cluster /// The replication factor of this cluster
pub replication_mode: ReplicationMode, pub replication_factor: ReplicationFactor,
/// The local database /// The local database
pub db: db::Db, pub db: db::Db,
@ -222,27 +222,26 @@ impl Garage {
.and_then(|x| NetworkKey::from_slice(&x)) .and_then(|x| NetworkKey::from_slice(&x))
.ok_or_message("Invalid RPC secret key")?; .ok_or_message("Invalid RPC secret key")?;
let replication_mode = ReplicationMode::parse(&config.replication_mode) let (replication_factor, consistency_mode) = parse_replication_mode(&config)?;
.ok_or_message("Invalid replication_mode in config file.")?;
info!("Initialize background variable system..."); info!("Initialize background variable system...");
let mut bg_vars = vars::BgVars::new(); let mut bg_vars = vars::BgVars::new();
info!("Initialize membership management system..."); info!("Initialize membership management system...");
let system = System::new(network_key, replication_mode, &config)?; let system = System::new(network_key, replication_factor, consistency_mode, &config)?;
let data_rep_param = TableShardedReplication { let data_rep_param = TableShardedReplication {
system: system.clone(), system: system.clone(),
replication_factor: replication_mode.replication_factor(), replication_factor: replication_factor.into(),
write_quorum: replication_mode.write_quorum(), write_quorum: replication_factor.write_quorum(consistency_mode),
read_quorum: 1, read_quorum: 1,
}; };
let meta_rep_param = TableShardedReplication { let meta_rep_param = TableShardedReplication {
system: system.clone(), system: system.clone(),
replication_factor: replication_mode.replication_factor(), replication_factor: replication_factor.into(),
write_quorum: replication_mode.write_quorum(), write_quorum: replication_factor.write_quorum(consistency_mode),
read_quorum: replication_mode.read_quorum(), read_quorum: replication_factor.read_quorum(consistency_mode),
}; };
let control_rep_param = TableFullReplication { let control_rep_param = TableFullReplication {
@ -338,7 +337,7 @@ impl Garage {
Ok(Arc::new(Self { Ok(Arc::new(Self {
config, config,
bg_vars, bg_vars,
replication_mode, replication_factor,
db, db,
system, system,
block_manager, block_manager,

View file

@ -7,7 +7,7 @@ use serde::{Deserialize, Serialize};
use garage_util::data::*; use garage_util::data::*;
use super::*; use super::*;
use crate::replication_mode::ReplicationMode; use crate::replication_mode::*;
#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq, Eq)] #[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq, Eq)]
pub struct RpcLayoutDigest { pub struct RpcLayoutDigest {
@ -29,7 +29,8 @@ pub struct SyncLayoutDigest {
} }
pub struct LayoutHelper { pub struct LayoutHelper {
replication_mode: ReplicationMode, replication_factor: ReplicationFactor,
consistency_mode: ConsistencyMode,
layout: Option<LayoutHistory>, layout: Option<LayoutHistory>,
// cached values // cached values
@ -57,7 +58,8 @@ impl Deref for LayoutHelper {
impl LayoutHelper { impl LayoutHelper {
pub fn new( pub fn new(
replication_mode: ReplicationMode, replication_factor: ReplicationFactor,
consistency_mode: ConsistencyMode,
mut layout: LayoutHistory, mut layout: LayoutHistory,
mut ack_lock: HashMap<u64, AtomicUsize>, mut ack_lock: HashMap<u64, AtomicUsize>,
) -> Self { ) -> Self {
@ -66,7 +68,7 @@ impl LayoutHelper {
// correct and we have rapid access to important values such as // correct and we have rapid access to important values such as
// the layout versions to use when reading to ensure consistency. // the layout versions to use when reading to ensure consistency.
if !replication_mode.is_read_after_write_consistent() { if consistency_mode != ConsistencyMode::Consistent {
// Fast path for when no consistency is required. // Fast path for when no consistency is required.
// In this case we only need to keep the last version of the layout, // In this case we only need to keep the last version of the layout,
// we don't care about coordinating stuff in the cluster. // we don't care about coordinating stuff in the cluster.
@ -103,7 +105,7 @@ impl LayoutHelper {
// This value is calculated using quorums to allow progress even // This value is calculated using quorums to allow progress even
// if not all nodes have successfully completed a sync. // if not all nodes have successfully completed a sync.
let sync_map_min = let sync_map_min =
layout.calculate_sync_map_min_with_quorum(replication_mode, &all_nongateway_nodes); layout.calculate_sync_map_min_with_quorum(replication_factor, &all_nongateway_nodes);
let trackers_hash = layout.calculate_trackers_hash(); let trackers_hash = layout.calculate_trackers_hash();
let staging_hash = layout.calculate_staging_hash(); let staging_hash = layout.calculate_staging_hash();
@ -114,7 +116,8 @@ impl LayoutHelper {
.or_insert(AtomicUsize::new(0)); .or_insert(AtomicUsize::new(0));
LayoutHelper { LayoutHelper {
replication_mode, replication_factor,
consistency_mode,
layout: Some(layout), layout: Some(layout),
ack_map_min, ack_map_min,
sync_map_min, sync_map_min,
@ -139,7 +142,8 @@ impl LayoutHelper {
let changed = f(self.layout.as_mut().unwrap()); let changed = f(self.layout.as_mut().unwrap());
if changed { if changed {
*self = Self::new( *self = Self::new(
self.replication_mode, self.replication_factor,
self.consistency_mode,
self.layout.take().unwrap(), self.layout.take().unwrap(),
std::mem::take(&mut self.ack_lock), std::mem::take(&mut self.ack_lock),
); );

View file

@ -6,11 +6,11 @@ use garage_util::encode::nonversioned_encode;
use garage_util::error::*; use garage_util::error::*;
use super::*; use super::*;
use crate::replication_mode::ReplicationMode; use crate::replication_mode::*;
impl LayoutHistory { impl LayoutHistory {
pub fn new(replication_factor: usize) -> Self { pub fn new(replication_factor: ReplicationFactor) -> Self {
let version = LayoutVersion::new(replication_factor); let version = LayoutVersion::new(replication_factor.into());
let staging = LayoutStaging { let staging = LayoutStaging {
parameters: Lww::<LayoutParameters>::new(version.parameters), parameters: Lww::<LayoutParameters>::new(version.parameters),
@ -119,7 +119,7 @@ impl LayoutHistory {
pub(crate) fn calculate_sync_map_min_with_quorum( pub(crate) fn calculate_sync_map_min_with_quorum(
&self, &self,
replication_mode: ReplicationMode, replication_factor: ReplicationFactor,
all_nongateway_nodes: &[Uuid], all_nongateway_nodes: &[Uuid],
) -> u64 { ) -> u64 {
// This function calculates the minimum layout version from which // This function calculates the minimum layout version from which
@ -133,7 +133,7 @@ impl LayoutHistory {
return self.current().version; return self.current().version;
} }
let quorum = replication_mode.write_quorum(); let quorum = replication_factor.write_quorum(ConsistencyMode::Consistent);
let min_version = self.min_stored(); let min_version = self.min_stored();
let global_min = self let global_min = self

View file

@ -14,13 +14,13 @@ use garage_util::error::*;
use garage_util::persister::Persister; use garage_util::persister::Persister;
use super::*; use super::*;
use crate::replication_mode::ReplicationMode; use crate::replication_mode::*;
use crate::rpc_helper::*; use crate::rpc_helper::*;
use crate::system::*; use crate::system::*;
pub struct LayoutManager { pub struct LayoutManager {
node_id: Uuid, node_id: Uuid,
replication_mode: ReplicationMode, replication_factor: ReplicationFactor,
persist_cluster_layout: Persister<LayoutHistory>, persist_cluster_layout: Persister<LayoutHistory>,
layout: Arc<RwLock<LayoutHelper>>, layout: Arc<RwLock<LayoutHelper>>,
@ -38,20 +38,19 @@ impl LayoutManager {
node_id: NodeID, node_id: NodeID,
system_endpoint: Arc<Endpoint<SystemRpc, System>>, system_endpoint: Arc<Endpoint<SystemRpc, System>>,
peering: Arc<PeeringManager>, peering: Arc<PeeringManager>,
replication_mode: ReplicationMode, replication_factor: ReplicationFactor,
consistency_mode: ConsistencyMode,
) -> Result<Arc<Self>, Error> { ) -> Result<Arc<Self>, Error> {
let replication_factor = replication_mode.replication_factor();
let persist_cluster_layout: Persister<LayoutHistory> = let persist_cluster_layout: Persister<LayoutHistory> =
Persister::new(&config.metadata_dir, "cluster_layout"); Persister::new(&config.metadata_dir, "cluster_layout");
let cluster_layout = match persist_cluster_layout.load() { let cluster_layout = match persist_cluster_layout.load() {
Ok(x) => { Ok(x) => {
if x.current().replication_factor != replication_mode.replication_factor() { if x.current().replication_factor != replication_factor.replication_factor() {
return Err(Error::Message(format!( return Err(Error::Message(format!(
"Prevous cluster layout has replication factor {}, which is different than the one specified in the config file ({}). The previous cluster layout can be purged, if you know what you are doing, simply by deleting the `cluster_layout` file in your metadata directory.", "Prevous cluster layout has replication factor {}, which is different than the one specified in the config file ({}). The previous cluster layout can be purged, if you know what you are doing, simply by deleting the `cluster_layout` file in your metadata directory.",
x.current().replication_factor, x.current().replication_factor,
replication_factor replication_factor.replication_factor()
))); )));
} }
x x
@ -65,8 +64,12 @@ impl LayoutManager {
} }
}; };
let mut cluster_layout = let mut cluster_layout = LayoutHelper::new(
LayoutHelper::new(replication_mode, cluster_layout, Default::default()); replication_factor,
consistency_mode,
cluster_layout,
Default::default(),
);
cluster_layout.update_trackers(node_id.into()); cluster_layout.update_trackers(node_id.into());
let layout = Arc::new(RwLock::new(cluster_layout)); let layout = Arc::new(RwLock::new(cluster_layout));
@ -81,7 +84,7 @@ impl LayoutManager {
Ok(Arc::new(Self { Ok(Arc::new(Self {
node_id: node_id.into(), node_id: node_id.into(),
replication_mode, replication_factor,
persist_cluster_layout, persist_cluster_layout,
layout, layout,
change_notify, change_notify,
@ -295,11 +298,11 @@ impl LayoutManager {
adv.update_trackers adv.update_trackers
); );
if adv.current().replication_factor != self.replication_mode.replication_factor() { if adv.current().replication_factor != self.replication_factor.replication_factor() {
let msg = format!( let msg = format!(
"Received a cluster layout from another node with replication factor {}, which is different from what we have in our configuration ({}). Discarding the cluster layout we received.", "Received a cluster layout from another node with replication factor {}, which is different from what we have in our configuration ({}). Discarding the cluster layout we received.",
adv.current().replication_factor, adv.current().replication_factor,
self.replication_mode.replication_factor() self.replication_factor.replication_factor()
); );
error!("{}", msg); error!("{}", msg);
return Err(Error::Message(msg)); return Err(Error::Message(msg));

View file

@ -5,6 +5,7 @@ use garage_util::crdt::Crdt;
use garage_util::error::*; use garage_util::error::*;
use crate::layout::*; use crate::layout::*;
use crate::replication_mode::ReplicationFactor;
// This function checks that the partition size S computed is at least better than the // This function checks that the partition size S computed is at least better than the
// one given by a very naive algorithm. To do so, we try to run the naive algorithm // one given by a very naive algorithm. To do so, we try to run the naive algorithm
@ -120,7 +121,7 @@ fn test_assignment() {
let mut node_capacity_vec = vec![4000, 1000, 2000]; let mut node_capacity_vec = vec![4000, 1000, 2000];
let mut node_zone_vec = vec!["A", "B", "C"]; let mut node_zone_vec = vec!["A", "B", "C"];
let mut cl = LayoutHistory::new(3); let mut cl = LayoutHistory::new(ReplicationFactor::new(3).unwrap());
update_layout(&mut cl, &node_capacity_vec, &node_zone_vec, 3); update_layout(&mut cl, &node_capacity_vec, &node_zone_vec, 3);
let v = cl.current().version; let v = cl.current().version;
let (mut cl, msg) = cl.apply_staged_changes(Some(v + 1)).unwrap(); let (mut cl, msg) = cl.apply_staged_changes(Some(v + 1)).unwrap();

View file

@ -1,57 +1,94 @@
#[derive(Clone, Copy)] use garage_util::config::Config;
pub enum ReplicationMode { use garage_util::crdt::AutoCrdt;
None, use garage_util::error::*;
TwoWay, use serde::{Deserialize, Serialize};
TwoWayDangerous,
ThreeWay, #[derive(Debug, Clone, Copy, PartialEq, Serialize, Deserialize)]
ThreeWayDegraded, #[serde(transparent)]
ThreeWayDangerous, pub struct ReplicationFactor(usize);
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Default, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum ConsistencyMode {
/// Read- and Write-quorum are 1
Dangerous,
/// Read-quorum is 1
Degraded,
/// Read- and Write-quorum are determined for read-after-write-consistency
#[default]
Consistent,
} }
impl ReplicationMode { impl ConsistencyMode {
pub fn parse(v: &str) -> Option<Self> { pub fn parse(s: &str) -> Option<Self> {
match v { serde_json::from_value(serde_json::Value::String(s.to_string())).ok()
"none" | "1" => Some(Self::None), }
"2" => Some(Self::TwoWay), }
"2-dangerous" => Some(Self::TwoWayDangerous),
"3" => Some(Self::ThreeWay), impl AutoCrdt for ConsistencyMode {
"3-degraded" => Some(Self::ThreeWayDegraded), const WARN_IF_DIFFERENT: bool = true;
"3-dangerous" => Some(Self::ThreeWayDangerous), }
_ => None,
impl ReplicationFactor {
pub fn new(replication_factor: usize) -> Option<Self> {
if replication_factor < 1 {
None
} else {
Some(Self(replication_factor))
} }
} }
pub fn replication_factor(&self) -> usize { pub fn replication_factor(&self) -> usize {
match self { self.0
Self::None => 1, }
Self::TwoWay | Self::TwoWayDangerous => 2,
Self::ThreeWay | Self::ThreeWayDegraded | Self::ThreeWayDangerous => 3, pub fn read_quorum(&self, consistency_mode: ConsistencyMode) -> usize {
match consistency_mode {
ConsistencyMode::Dangerous | ConsistencyMode::Degraded => 1,
ConsistencyMode::Consistent => self.replication_factor().div_ceil(2),
} }
} }
pub fn read_quorum(&self) -> usize { pub fn write_quorum(&self, consistency_mode: ConsistencyMode) -> usize {
match self { match consistency_mode {
Self::None => 1, ConsistencyMode::Dangerous => 1,
Self::TwoWay | Self::TwoWayDangerous => 1, ConsistencyMode::Degraded | ConsistencyMode::Consistent => {
Self::ThreeWay => 2, (self.replication_factor() + 1) - self.read_quorum(ConsistencyMode::Consistent)
Self::ThreeWayDegraded | Self::ThreeWayDangerous => 1, }
}
}
pub fn write_quorum(&self) -> usize {
match self {
Self::None => 1,
Self::TwoWay => 2,
Self::TwoWayDangerous => 1,
Self::ThreeWay | Self::ThreeWayDegraded => 2,
Self::ThreeWayDangerous => 1,
}
}
pub fn is_read_after_write_consistent(&self) -> bool {
match self {
Self::None | Self::TwoWay | Self::ThreeWay => true,
_ => false,
} }
} }
} }
impl std::convert::From<ReplicationFactor> for usize {
fn from(replication_factor: ReplicationFactor) -> usize {
replication_factor.0
}
}
pub fn parse_replication_mode(
config: &Config,
) -> Result<(ReplicationFactor, ConsistencyMode), Error> {
match (&config.replication_mode, config.replication_factor, config.consistency_mode.as_str()) {
(Some(replication_mode), None, "consistent") => {
tracing::warn!("Legacy config option replication_mode in use. Please migrate to replication_factor and consistency_mode");
let parsed_replication_mode = match replication_mode.as_str() {
"1" | "none" => Some((ReplicationFactor(1), ConsistencyMode::Consistent)),
"2" => Some((ReplicationFactor(2), ConsistencyMode::Consistent)),
"2-dangerous" => Some((ReplicationFactor(2), ConsistencyMode::Dangerous)),
"3" => Some((ReplicationFactor(3), ConsistencyMode::Consistent)),
"3-degraded" => Some((ReplicationFactor(3), ConsistencyMode::Degraded)),
"3-dangerous" => Some((ReplicationFactor(3), ConsistencyMode::Dangerous)),
_ => None,
};
Some(parsed_replication_mode.ok_or_message("Invalid replication_mode in config file.")?)
},
(None, Some(replication_factor), consistency_mode) => {
let replication_factor = ReplicationFactor::new(replication_factor)
.ok_or_message("Invalid replication_factor in config file.")?;
let consistency_mode = ConsistencyMode::parse(consistency_mode)
.ok_or_message("Invalid consistency_mode in config file.")?;
Some((replication_factor, consistency_mode))
}
_ => None,
}.ok_or_message("Either the legacy replication_mode or replication_level and consistency_mode can be set, not both.")
}

View file

@ -112,8 +112,7 @@ pub struct System {
metrics: ArcSwapOption<SystemMetrics>, metrics: ArcSwapOption<SystemMetrics>,
replication_mode: ReplicationMode, pub(crate) replication_factor: ReplicationFactor,
pub(crate) replication_factor: usize,
/// Path to metadata directory /// Path to metadata directory
pub metadata_dir: PathBuf, pub metadata_dir: PathBuf,
@ -243,7 +242,8 @@ impl System {
/// Create this node's membership manager /// Create this node's membership manager
pub fn new( pub fn new(
network_key: NetworkKey, network_key: NetworkKey,
replication_mode: ReplicationMode, replication_factor: ReplicationFactor,
consistency_mode: ConsistencyMode,
config: &Config, config: &Config,
) -> Result<Arc<Self>, Error> { ) -> Result<Arc<Self>, Error> {
// ---- setup netapp RPC protocol ---- // ---- setup netapp RPC protocol ----
@ -274,14 +274,13 @@ impl System {
let persist_peer_list = Persister::new(&config.metadata_dir, "peer_list"); let persist_peer_list = Persister::new(&config.metadata_dir, "peer_list");
// ---- setup cluster layout and layout manager ---- // ---- setup cluster layout and layout manager ----
let replication_factor = replication_mode.replication_factor();
let layout_manager = LayoutManager::new( let layout_manager = LayoutManager::new(
config, config,
netapp.id, netapp.id,
system_endpoint.clone(), system_endpoint.clone(),
peering.clone(), peering.clone(),
replication_mode, replication_factor,
consistency_mode,
)?; )?;
let mut local_status = NodeStatus::initial(replication_factor, &layout_manager); let mut local_status = NodeStatus::initial(replication_factor, &layout_manager);
@ -315,7 +314,6 @@ impl System {
netapp: netapp.clone(), netapp: netapp.clone(),
peering: peering.clone(), peering: peering.clone(),
system_endpoint, system_endpoint,
replication_mode,
replication_factor, replication_factor,
rpc_listen_addr: config.rpc_bind_addr, rpc_listen_addr: config.rpc_bind_addr,
rpc_public_addr, rpc_public_addr,
@ -427,7 +425,9 @@ impl System {
} }
pub fn health(&self) -> ClusterHealth { pub fn health(&self) -> ClusterHealth {
let quorum = self.replication_mode.write_quorum(); let quorum = self
.replication_factor
.write_quorum(ConsistencyMode::Consistent);
// Gather information about running nodes. // Gather information about running nodes.
// Technically, `nodes` contains currently running nodes, as well // Technically, `nodes` contains currently running nodes, as well
@ -631,7 +631,7 @@ impl System {
.count(); .count();
let not_configured = self.cluster_layout().check().is_err(); let not_configured = self.cluster_layout().check().is_err();
let no_peers = n_connected < self.replication_factor; let no_peers = n_connected < self.replication_factor.into();
let expected_n_nodes = self.cluster_layout().all_nodes().len(); let expected_n_nodes = self.cluster_layout().all_nodes().len();
let bad_peers = n_connected != expected_n_nodes; let bad_peers = n_connected != expected_n_nodes;
@ -774,14 +774,14 @@ impl EndpointHandler<SystemRpc> for System {
} }
impl NodeStatus { impl NodeStatus {
fn initial(replication_factor: usize, layout_manager: &LayoutManager) -> Self { fn initial(replication_factor: ReplicationFactor, layout_manager: &LayoutManager) -> Self {
NodeStatus { NodeStatus {
hostname: Some( hostname: Some(
gethostname::gethostname() gethostname::gethostname()
.into_string() .into_string()
.unwrap_or_else(|_| "<invalid utf-8>".to_string()), .unwrap_or_else(|_| "<invalid utf-8>".to_string()),
), ),
replication_factor, replication_factor: replication_factor.into(),
layout_digest: layout_manager.layout().digest(), layout_digest: layout_manager.layout().digest(),
meta_disk_avail: None, meta_disk_avail: None,
data_disk_avail: None, data_disk_avail: None,

View file

@ -68,7 +68,7 @@ impl SystemMetrics {
let replication_factor = system.replication_factor; let replication_factor = system.replication_factor;
meter meter
.u64_value_observer("garage_replication_factor", move |observer| { .u64_value_observer("garage_replication_factor", move |observer| {
observer.observe(replication_factor as u64, &[]) observer.observe(replication_factor.replication_factor() as u64, &[])
}) })
.with_description("Garage replication factor setting") .with_description("Garage replication factor setting")
.init() .init()

View file

@ -30,12 +30,20 @@ pub struct Config {
)] )]
pub block_size: usize, pub block_size: usize,
/// Replication mode. Supported values: /// Number of replicas. Can be any positive integer, but uneven numbers are more favorable.
/// - none, 1 -> no replication /// - 1 for single-node clusters, or to disable replication
/// - 2 -> 2-way replication /// - 3 is the recommended and supported setting.
/// - 3 -> 3-way replication #[serde(default)]
// (we can add more aliases for this later) pub replication_factor: Option<usize>,
pub replication_mode: String,
/// Consistency mode for all for requests through this node
/// - Degraded -> Disable read quorum
/// - Dangerous -> Disable read and write quorum
#[serde(default = "default_consistency_mode")]
pub consistency_mode: String,
/// Legacy option
pub replication_mode: Option<String>,
/// Zstd compression level used on data blocks /// Zstd compression level used on data blocks
#[serde( #[serde(
@ -244,10 +252,15 @@ fn default_sled_cache_capacity() -> usize {
fn default_sled_flush_every_ms() -> u64 { fn default_sled_flush_every_ms() -> u64 {
2000 2000
} }
fn default_block_size() -> usize { fn default_block_size() -> usize {
1048576 1048576
} }
fn default_consistency_mode() -> String {
"consistent".into()
}
fn default_compression() -> Option<i32> { fn default_compression() -> Option<i32> {
Some(1) Some(1)
} }
@ -359,7 +372,7 @@ mod tests {
r#" r#"
metadata_dir = "/tmp/garage/meta" metadata_dir = "/tmp/garage/meta"
data_dir = "/tmp/garage/data" data_dir = "/tmp/garage/data"
replication_mode = "3" replication_factor = 3
rpc_bind_addr = "[::]:3901" rpc_bind_addr = "[::]:3901"
rpc_secret = "foo" rpc_secret = "foo"