2018-08-23 12:12:55 +00:00
|
|
|
// The ipfs-cluster-service application.
|
2016-12-21 18:37:25 +00:00
|
|
|
package main
|
|
|
|
|
|
|
|
import (
|
2017-07-04 20:39:10 +00:00
|
|
|
"bufio"
|
2016-12-21 18:37:25 +00:00
|
|
|
"fmt"
|
2017-12-19 17:05:32 +00:00
|
|
|
"io"
|
2016-12-21 18:37:25 +00:00
|
|
|
"os"
|
|
|
|
"os/user"
|
|
|
|
"path/filepath"
|
|
|
|
|
2017-03-07 16:38:04 +00:00
|
|
|
// _ "net/http/pprof"
|
|
|
|
|
2016-12-21 18:37:25 +00:00
|
|
|
ipfscluster "github.com/ipfs/ipfs-cluster"
|
2017-02-09 15:29:17 +00:00
|
|
|
"github.com/ipfs/ipfs-cluster/state/mapstate"
|
2018-09-26 15:45:02 +00:00
|
|
|
|
|
|
|
semver "github.com/blang/semver"
|
|
|
|
logging "github.com/ipfs/go-log"
|
|
|
|
cli "github.com/urfave/cli"
|
2016-12-21 18:37:25 +00:00
|
|
|
)
|
|
|
|
|
2016-12-22 16:14:15 +00:00
|
|
|
// ProgramName of this application
|
2017-01-23 12:34:22 +00:00
|
|
|
const programName = `ipfs-cluster-service`
|
2016-12-21 18:37:25 +00:00
|
|
|
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
// flag defaults
|
|
|
|
const (
|
|
|
|
defaultAllocation = "disk-freespace"
|
2018-05-07 12:46:05 +00:00
|
|
|
defaultMonitor = "pubsub"
|
2018-08-14 17:57:14 +00:00
|
|
|
defaultPinTracker = "map"
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
defaultLogLevel = "info"
|
|
|
|
)
|
|
|
|
|
2018-10-18 13:21:11 +00:00
|
|
|
const (
|
|
|
|
stateCleanupPrompt = "The peer's state will be removed from the load path. Existing pins may be lost."
|
|
|
|
configurationOverwritePrompt = "Configuration(service.json) will be overwritten."
|
|
|
|
)
|
2018-10-18 04:23:47 +00:00
|
|
|
|
2017-01-24 15:55:37 +00:00
|
|
|
// We store a commit id here
|
|
|
|
var commit string
|
|
|
|
|
2016-12-21 18:37:25 +00:00
|
|
|
// Description provides a short summary of the functionality of this tool
|
|
|
|
var Description = fmt.Sprintf(`
|
2017-01-24 18:55:06 +00:00
|
|
|
%s runs an IPFS Cluster node.
|
2016-12-21 18:37:25 +00:00
|
|
|
|
2017-01-24 18:55:06 +00:00
|
|
|
A node participates in the cluster consensus, follows a distributed log
|
|
|
|
of pinning and unpinning requests and manages pinning operations to a
|
|
|
|
configured IPFS daemon.
|
2016-12-21 18:37:25 +00:00
|
|
|
|
2017-01-23 12:34:22 +00:00
|
|
|
This node also provides an API for cluster management, an IPFS Proxy API which
|
2016-12-21 18:37:25 +00:00
|
|
|
forwards requests to IPFS and a number of components for internal communication
|
2017-02-02 13:34:51 +00:00
|
|
|
using LibP2P. This is a simplified view of the components:
|
|
|
|
|
|
|
|
+------------------+
|
|
|
|
| ipfs-cluster-ctl |
|
|
|
|
+---------+--------+
|
|
|
|
|
|
2017-12-12 16:47:21 +00:00
|
|
|
| HTTP(s)
|
2017-02-02 13:34:51 +00:00
|
|
|
ipfs-cluster-service | HTTP
|
|
|
|
+----------+--------+--v--+----------------------+ +-------------+
|
|
|
|
| RPC/Raft | Peer 1 | API | IPFS Connector/Proxy +------> IPFS daemon |
|
|
|
|
+----^-----+--------+-----+----------------------+ +-------------+
|
|
|
|
| libp2p
|
|
|
|
|
|
|
|
|
+----v-----+--------+-----+----------------------+ +-------------+
|
|
|
|
| RPC/Raft | Peer 2 | API | IPFS Connector/Proxy +------> IPFS daemon |
|
|
|
|
+----^-----+--------+-----+----------------------+ +-------------+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
+----v-----+--------+-----+----------------------+ +-------------+
|
|
|
|
| RPC/Raft | Peer 3 | API | IPFS Connector/Proxy +------> IPFS daemon |
|
|
|
|
+----------+--------+-----+----------------------+ +-------------+
|
|
|
|
|
2016-12-21 18:37:25 +00:00
|
|
|
|
2017-01-23 13:21:26 +00:00
|
|
|
%s needs a valid configuration to run. This configuration is
|
|
|
|
independent from IPFS and includes its own LibP2P key-pair. It can be
|
2017-01-30 12:12:25 +00:00
|
|
|
initialized with "init" and its default location is
|
2016-12-21 18:37:25 +00:00
|
|
|
~/%s/%s.
|
|
|
|
|
2016-12-22 16:14:15 +00:00
|
|
|
For feedback, bug reports or any additional information, visit
|
|
|
|
https://github.com/ipfs/ipfs-cluster.
|
2017-02-02 22:52:06 +00:00
|
|
|
|
|
|
|
|
|
|
|
EXAMPLES
|
|
|
|
|
|
|
|
Initial configuration:
|
|
|
|
|
|
|
|
$ ipfs-cluster-service init
|
|
|
|
|
|
|
|
Launch a cluster:
|
|
|
|
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
$ ipfs-cluster-service daemon
|
2017-02-02 22:52:06 +00:00
|
|
|
|
|
|
|
Launch a peer and join existing cluster:
|
|
|
|
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
$ ipfs-cluster-service daemon --bootstrap /ip4/192.168.1.2/tcp/9096/ipfs/QmPSoSaPXpyunaBwHs1rZBKYSqRV4bLRk32VGYLuvdrypL
|
2016-12-21 18:37:25 +00:00
|
|
|
`,
|
2016-12-22 16:14:15 +00:00
|
|
|
programName,
|
|
|
|
programName,
|
2016-12-21 18:37:25 +00:00
|
|
|
DefaultPath,
|
|
|
|
DefaultConfigFile)
|
|
|
|
|
2017-01-30 12:12:25 +00:00
|
|
|
var logger = logging.Logger("service")
|
|
|
|
|
2016-12-21 18:37:25 +00:00
|
|
|
// Default location for the configurations and data
|
|
|
|
var (
|
2017-11-14 12:13:32 +00:00
|
|
|
// DefaultPath is initialized to $HOME/.ipfs-cluster
|
2016-12-21 18:37:25 +00:00
|
|
|
// and holds all the ipfs-cluster data
|
2017-11-14 12:13:32 +00:00
|
|
|
DefaultPath string
|
2016-12-21 18:37:25 +00:00
|
|
|
// The name of the configuration file inside DefaultPath
|
2017-01-23 12:34:22 +00:00
|
|
|
DefaultConfigFile = "service.json"
|
2016-12-21 18:37:25 +00:00
|
|
|
)
|
|
|
|
|
|
|
|
var (
|
|
|
|
configPath string
|
|
|
|
)
|
|
|
|
|
|
|
|
func init() {
|
2018-09-26 15:45:02 +00:00
|
|
|
// Set build information.
|
|
|
|
if build, err := semver.NewBuildVersion(commit); err == nil {
|
|
|
|
ipfscluster.Version.Build = []string{"git" + build}
|
|
|
|
}
|
2017-07-12 14:51:32 +00:00
|
|
|
|
2017-11-14 12:13:32 +00:00
|
|
|
// We try guessing user's home from the HOME variable. This
|
|
|
|
// allows HOME hacks for things like Snapcraft builds. HOME
|
|
|
|
// should be set in all UNIX by the OS. Alternatively, we fall back to
|
|
|
|
// usr.HomeDir (which should work on Windows etc.).
|
|
|
|
home := os.Getenv("HOME")
|
|
|
|
if home == "" {
|
|
|
|
usr, err := user.Current()
|
|
|
|
if err != nil {
|
2017-11-14 17:01:32 +00:00
|
|
|
panic(fmt.Sprintf("cannot get current user: %s", err))
|
2017-11-14 12:13:32 +00:00
|
|
|
}
|
|
|
|
home = usr.HomeDir
|
2016-12-22 16:14:15 +00:00
|
|
|
}
|
2017-11-14 12:13:32 +00:00
|
|
|
|
|
|
|
DefaultPath = filepath.Join(home, ".ipfs-cluster")
|
2016-12-21 18:37:25 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
func out(m string, a ...interface{}) {
|
|
|
|
fmt.Fprintf(os.Stderr, m, a...)
|
|
|
|
}
|
|
|
|
|
2018-03-23 01:08:00 +00:00
|
|
|
func checkErr(doing string, err error, args ...interface{}) {
|
2017-01-24 18:55:06 +00:00
|
|
|
if err != nil {
|
2018-03-23 01:08:00 +00:00
|
|
|
if len(args) > 0 {
|
|
|
|
doing = fmt.Sprintf(doing, args)
|
|
|
|
}
|
2017-01-24 18:55:06 +00:00
|
|
|
out("error %s: %s\n", doing, err)
|
2017-12-05 03:46:52 +00:00
|
|
|
err = locker.tryUnlock()
|
|
|
|
if err != nil {
|
|
|
|
out("error releasing execution lock: %s\n", err)
|
|
|
|
}
|
2017-01-24 18:55:06 +00:00
|
|
|
os.Exit(1)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-12-21 18:37:25 +00:00
|
|
|
func main() {
|
2017-03-07 16:38:04 +00:00
|
|
|
// go func() {
|
2017-07-24 15:26:46 +00:00
|
|
|
// log.Println(http.ListenAndServe("localhost:6060", nil))
|
2017-03-07 16:38:04 +00:00
|
|
|
// }()
|
|
|
|
|
2017-01-24 18:55:06 +00:00
|
|
|
app := cli.NewApp()
|
|
|
|
app.Name = programName
|
|
|
|
app.Usage = "IPFS Cluster node"
|
2017-02-02 22:52:06 +00:00
|
|
|
app.Description = Description
|
|
|
|
//app.Copyright = "© Protocol Labs, Inc."
|
2018-09-26 15:45:02 +00:00
|
|
|
app.Version = ipfscluster.Version.String()
|
2017-01-24 18:55:06 +00:00
|
|
|
app.Flags = []cli.Flag{
|
|
|
|
cli.StringFlag{
|
|
|
|
Name: "config, c",
|
|
|
|
Value: DefaultPath,
|
|
|
|
Usage: "path to the configuration and data `FOLDER`",
|
|
|
|
EnvVar: "IPFS_CLUSTER_PATH",
|
|
|
|
},
|
|
|
|
cli.BoolFlag{
|
|
|
|
Name: "force, f",
|
2017-02-02 22:52:06 +00:00
|
|
|
Usage: "forcefully proceed with some actions. i.e. overwriting configuration",
|
|
|
|
},
|
2017-01-24 18:55:06 +00:00
|
|
|
cli.BoolFlag{
|
|
|
|
Name: "debug, d",
|
2017-02-02 22:52:06 +00:00
|
|
|
Usage: "enable full debug logging (very verbose)",
|
2017-01-24 18:55:06 +00:00
|
|
|
},
|
|
|
|
cli.StringFlag{
|
|
|
|
Name: "loglevel, l",
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
Value: defaultLogLevel,
|
2018-01-11 17:09:10 +00:00
|
|
|
Usage: "set the loglevel for cluster components only [critical, error, warning, info, debug]",
|
2017-01-24 18:55:06 +00:00
|
|
|
},
|
|
|
|
}
|
2016-12-21 18:37:25 +00:00
|
|
|
|
2017-01-24 18:55:06 +00:00
|
|
|
app.Commands = []cli.Command{
|
|
|
|
{
|
|
|
|
Name: "init",
|
|
|
|
Usage: "create a default configuration and exit",
|
2017-07-24 15:26:46 +00:00
|
|
|
Description: fmt.Sprintf(`
|
|
|
|
This command will initialize a new service.json configuration file
|
|
|
|
for %s.
|
|
|
|
|
|
|
|
By default, %s requires a cluster secret. This secret will be
|
2017-07-24 22:21:20 +00:00
|
|
|
automatically generated, but can be manually provided with --custom-secret
|
2017-07-24 15:26:46 +00:00
|
|
|
(in which case it will be prompted), or by setting the CLUSTER_SECRET
|
|
|
|
environment variable.
|
|
|
|
|
|
|
|
The private key for the libp2p node is randomly generated in all cases.
|
|
|
|
|
2017-07-24 22:21:20 +00:00
|
|
|
Note that the --force first-level-flag allows to overwrite an existing
|
2017-07-24 15:26:46 +00:00
|
|
|
configuration.
|
|
|
|
`, programName, programName),
|
|
|
|
ArgsUsage: " ",
|
2017-07-04 20:39:10 +00:00
|
|
|
Flags: []cli.Flag{
|
|
|
|
cli.BoolFlag{
|
2017-07-24 15:26:46 +00:00
|
|
|
Name: "custom-secret, s",
|
|
|
|
Usage: "prompt for the cluster secret",
|
|
|
|
},
|
2017-07-04 20:39:10 +00:00
|
|
|
},
|
2017-01-24 18:55:06 +00:00
|
|
|
Action: func(c *cli.Context) error {
|
2017-07-28 19:10:52 +00:00
|
|
|
userSecret, userSecretDefined := userProvidedSecret(c.Bool("custom-secret"))
|
2018-02-16 12:45:16 +00:00
|
|
|
|
2018-03-23 01:08:00 +00:00
|
|
|
cfgMgr, cfgs := makeConfigs()
|
|
|
|
defer cfgMgr.Shutdown() // wait for saves
|
Issue #162: Rework configuration format
The following commit reimplements ipfs-cluster configuration under
the following premises:
* Each component is initialized with a configuration object
defined by its module
* Each component decides how the JSON representation of its
configuration looks like
* Each component parses and validates its own configuration
* Each component exposes its own defaults
* Component configurations are make the sections of a
central JSON configuration file (which replaces the current
JSON format)
* Component configurations implement a common interface
(config.ComponentConfig) with a set of common operations
* The central configuration file is managed by a
config.ConfigManager which:
* Registers ComponentConfigs
* Assigns the correspondent sections from the JSON file to each
component and delegates the parsing
* Delegates the JSON generation for each section
* Can be notified when the configuration is updated and must be
saved to disk
The new service.json would then look as follows:
```json
{
"cluster": {
"id": "QmTVW8NoRxC5wBhV7WtAYtRn7itipEESfozWN5KmXUQnk2",
"private_key": "<...>",
"secret": "00224102ae6aaf94f2606abf69a0e278251ecc1d64815b617ff19d6d2841f786",
"peers": [],
"bootstrap": [],
"leave_on_shutdown": false,
"listen_multiaddress": "/ip4/0.0.0.0/tcp/9096",
"state_sync_interval": "1m0s",
"ipfs_sync_interval": "2m10s",
"replication_factor": -1,
"monitor_ping_interval": "15s"
},
"consensus": {
"raft": {
"heartbeat_timeout": "1s",
"election_timeout": "1s",
"commit_timeout": "50ms",
"max_append_entries": 64,
"trailing_logs": 10240,
"snapshot_interval": "2m0s",
"snapshot_threshold": 8192,
"leader_lease_timeout": "500ms"
}
},
"api": {
"restapi": {
"listen_multiaddress": "/ip4/127.0.0.1/tcp/9094",
"read_timeout": "30s",
"read_header_timeout": "5s",
"write_timeout": "1m0s",
"idle_timeout": "2m0s"
}
},
"ipfs_connector": {
"ipfshttp": {
"proxy_listen_multiaddress": "/ip4/127.0.0.1/tcp/9095",
"node_multiaddress": "/ip4/127.0.0.1/tcp/5001",
"connect_swarms_delay": "7s",
"proxy_read_timeout": "10m0s",
"proxy_read_header_timeout": "5s",
"proxy_write_timeout": "10m0s",
"proxy_idle_timeout": "1m0s"
}
},
"monitor": {
"monbasic": {
"check_interval": "15s"
}
},
"informer": {
"disk": {
"metric_ttl": "30s",
"metric_type": "freespace"
},
"numpin": {
"metric_ttl": "10s"
}
}
}
```
This new format aims to be easily extensible per component. As such,
it already surfaces quite a few new options which were hardcoded
before.
Additionally, since Go API have changed, some redundant methods have been
removed and small refactoring has happened to take advantage of the new
way.
License: MIT
Signed-off-by: Hector Sanjuan <hector@protocol.ai>
2017-10-11 18:23:03 +00:00
|
|
|
|
2018-10-04 15:08:27 +00:00
|
|
|
var alreadyInitialized bool
|
|
|
|
if _, err := os.Stat(configPath); !os.IsNotExist(err) {
|
|
|
|
alreadyInitialized = true
|
|
|
|
}
|
|
|
|
|
|
|
|
if alreadyInitialized {
|
|
|
|
// acquire lock for config folder
|
|
|
|
err := locker.lock()
|
|
|
|
checkErr("acquiring execution lock", err)
|
|
|
|
defer locker.tryUnlock()
|
|
|
|
|
2018-10-18 13:21:11 +00:00
|
|
|
if !c.Bool("force") && !yesNoPrompt(fmt.Sprintf("%s\n%s Continue? [y/n]:", stateCleanupPrompt, configurationOverwritePrompt)) {
|
2018-10-18 04:23:47 +00:00
|
|
|
return nil
|
2018-10-04 15:08:27 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
err = cfgMgr.LoadJSONFromFile(configPath)
|
|
|
|
checkErr("reading configuration", err)
|
|
|
|
|
2018-10-18 13:21:11 +00:00
|
|
|
err = cleanupState(cfgs.consensusCfg)
|
2018-10-04 15:08:27 +00:00
|
|
|
checkErr("Cleaning up consensus data", err)
|
|
|
|
}
|
|
|
|
|
Issue #162: Rework configuration format
The following commit reimplements ipfs-cluster configuration under
the following premises:
* Each component is initialized with a configuration object
defined by its module
* Each component decides how the JSON representation of its
configuration looks like
* Each component parses and validates its own configuration
* Each component exposes its own defaults
* Component configurations are make the sections of a
central JSON configuration file (which replaces the current
JSON format)
* Component configurations implement a common interface
(config.ComponentConfig) with a set of common operations
* The central configuration file is managed by a
config.ConfigManager which:
* Registers ComponentConfigs
* Assigns the correspondent sections from the JSON file to each
component and delegates the parsing
* Delegates the JSON generation for each section
* Can be notified when the configuration is updated and must be
saved to disk
The new service.json would then look as follows:
```json
{
"cluster": {
"id": "QmTVW8NoRxC5wBhV7WtAYtRn7itipEESfozWN5KmXUQnk2",
"private_key": "<...>",
"secret": "00224102ae6aaf94f2606abf69a0e278251ecc1d64815b617ff19d6d2841f786",
"peers": [],
"bootstrap": [],
"leave_on_shutdown": false,
"listen_multiaddress": "/ip4/0.0.0.0/tcp/9096",
"state_sync_interval": "1m0s",
"ipfs_sync_interval": "2m10s",
"replication_factor": -1,
"monitor_ping_interval": "15s"
},
"consensus": {
"raft": {
"heartbeat_timeout": "1s",
"election_timeout": "1s",
"commit_timeout": "50ms",
"max_append_entries": 64,
"trailing_logs": 10240,
"snapshot_interval": "2m0s",
"snapshot_threshold": 8192,
"leader_lease_timeout": "500ms"
}
},
"api": {
"restapi": {
"listen_multiaddress": "/ip4/127.0.0.1/tcp/9094",
"read_timeout": "30s",
"read_header_timeout": "5s",
"write_timeout": "1m0s",
"idle_timeout": "2m0s"
}
},
"ipfs_connector": {
"ipfshttp": {
"proxy_listen_multiaddress": "/ip4/127.0.0.1/tcp/9095",
"node_multiaddress": "/ip4/127.0.0.1/tcp/5001",
"connect_swarms_delay": "7s",
"proxy_read_timeout": "10m0s",
"proxy_read_header_timeout": "5s",
"proxy_write_timeout": "10m0s",
"proxy_idle_timeout": "1m0s"
}
},
"monitor": {
"monbasic": {
"check_interval": "15s"
}
},
"informer": {
"disk": {
"metric_ttl": "30s",
"metric_type": "freespace"
},
"numpin": {
"metric_ttl": "10s"
}
}
}
```
This new format aims to be easily extensible per component. As such,
it already surfaces quite a few new options which were hardcoded
before.
Additionally, since Go API have changed, some redundant methods have been
removed and small refactoring has happened to take advantage of the new
way.
License: MIT
Signed-off-by: Hector Sanjuan <hector@protocol.ai>
2017-10-11 18:23:03 +00:00
|
|
|
// Generate defaults for all registered components
|
2018-03-23 01:08:00 +00:00
|
|
|
err := cfgMgr.Default()
|
Issue #162: Rework configuration format
The following commit reimplements ipfs-cluster configuration under
the following premises:
* Each component is initialized with a configuration object
defined by its module
* Each component decides how the JSON representation of its
configuration looks like
* Each component parses and validates its own configuration
* Each component exposes its own defaults
* Component configurations are make the sections of a
central JSON configuration file (which replaces the current
JSON format)
* Component configurations implement a common interface
(config.ComponentConfig) with a set of common operations
* The central configuration file is managed by a
config.ConfigManager which:
* Registers ComponentConfigs
* Assigns the correspondent sections from the JSON file to each
component and delegates the parsing
* Delegates the JSON generation for each section
* Can be notified when the configuration is updated and must be
saved to disk
The new service.json would then look as follows:
```json
{
"cluster": {
"id": "QmTVW8NoRxC5wBhV7WtAYtRn7itipEESfozWN5KmXUQnk2",
"private_key": "<...>",
"secret": "00224102ae6aaf94f2606abf69a0e278251ecc1d64815b617ff19d6d2841f786",
"peers": [],
"bootstrap": [],
"leave_on_shutdown": false,
"listen_multiaddress": "/ip4/0.0.0.0/tcp/9096",
"state_sync_interval": "1m0s",
"ipfs_sync_interval": "2m10s",
"replication_factor": -1,
"monitor_ping_interval": "15s"
},
"consensus": {
"raft": {
"heartbeat_timeout": "1s",
"election_timeout": "1s",
"commit_timeout": "50ms",
"max_append_entries": 64,
"trailing_logs": 10240,
"snapshot_interval": "2m0s",
"snapshot_threshold": 8192,
"leader_lease_timeout": "500ms"
}
},
"api": {
"restapi": {
"listen_multiaddress": "/ip4/127.0.0.1/tcp/9094",
"read_timeout": "30s",
"read_header_timeout": "5s",
"write_timeout": "1m0s",
"idle_timeout": "2m0s"
}
},
"ipfs_connector": {
"ipfshttp": {
"proxy_listen_multiaddress": "/ip4/127.0.0.1/tcp/9095",
"node_multiaddress": "/ip4/127.0.0.1/tcp/5001",
"connect_swarms_delay": "7s",
"proxy_read_timeout": "10m0s",
"proxy_read_header_timeout": "5s",
"proxy_write_timeout": "10m0s",
"proxy_idle_timeout": "1m0s"
}
},
"monitor": {
"monbasic": {
"check_interval": "15s"
}
},
"informer": {
"disk": {
"metric_ttl": "30s",
"metric_type": "freespace"
},
"numpin": {
"metric_ttl": "10s"
}
}
}
```
This new format aims to be easily extensible per component. As such,
it already surfaces quite a few new options which were hardcoded
before.
Additionally, since Go API have changed, some redundant methods have been
removed and small refactoring has happened to take advantage of the new
way.
License: MIT
Signed-off-by: Hector Sanjuan <hector@protocol.ai>
2017-10-11 18:23:03 +00:00
|
|
|
checkErr("generating default configuration", err)
|
|
|
|
|
|
|
|
// Set user secret
|
|
|
|
if userSecretDefined {
|
2018-03-23 01:08:00 +00:00
|
|
|
cfgs.clusterCfg.Secret = userSecret
|
Issue #162: Rework configuration format
The following commit reimplements ipfs-cluster configuration under
the following premises:
* Each component is initialized with a configuration object
defined by its module
* Each component decides how the JSON representation of its
configuration looks like
* Each component parses and validates its own configuration
* Each component exposes its own defaults
* Component configurations are make the sections of a
central JSON configuration file (which replaces the current
JSON format)
* Component configurations implement a common interface
(config.ComponentConfig) with a set of common operations
* The central configuration file is managed by a
config.ConfigManager which:
* Registers ComponentConfigs
* Assigns the correspondent sections from the JSON file to each
component and delegates the parsing
* Delegates the JSON generation for each section
* Can be notified when the configuration is updated and must be
saved to disk
The new service.json would then look as follows:
```json
{
"cluster": {
"id": "QmTVW8NoRxC5wBhV7WtAYtRn7itipEESfozWN5KmXUQnk2",
"private_key": "<...>",
"secret": "00224102ae6aaf94f2606abf69a0e278251ecc1d64815b617ff19d6d2841f786",
"peers": [],
"bootstrap": [],
"leave_on_shutdown": false,
"listen_multiaddress": "/ip4/0.0.0.0/tcp/9096",
"state_sync_interval": "1m0s",
"ipfs_sync_interval": "2m10s",
"replication_factor": -1,
"monitor_ping_interval": "15s"
},
"consensus": {
"raft": {
"heartbeat_timeout": "1s",
"election_timeout": "1s",
"commit_timeout": "50ms",
"max_append_entries": 64,
"trailing_logs": 10240,
"snapshot_interval": "2m0s",
"snapshot_threshold": 8192,
"leader_lease_timeout": "500ms"
}
},
"api": {
"restapi": {
"listen_multiaddress": "/ip4/127.0.0.1/tcp/9094",
"read_timeout": "30s",
"read_header_timeout": "5s",
"write_timeout": "1m0s",
"idle_timeout": "2m0s"
}
},
"ipfs_connector": {
"ipfshttp": {
"proxy_listen_multiaddress": "/ip4/127.0.0.1/tcp/9095",
"node_multiaddress": "/ip4/127.0.0.1/tcp/5001",
"connect_swarms_delay": "7s",
"proxy_read_timeout": "10m0s",
"proxy_read_header_timeout": "5s",
"proxy_write_timeout": "10m0s",
"proxy_idle_timeout": "1m0s"
}
},
"monitor": {
"monbasic": {
"check_interval": "15s"
}
},
"informer": {
"disk": {
"metric_ttl": "30s",
"metric_type": "freespace"
},
"numpin": {
"metric_ttl": "10s"
}
}
}
```
This new format aims to be easily extensible per component. As such,
it already surfaces quite a few new options which were hardcoded
before.
Additionally, since Go API have changed, some redundant methods have been
removed and small refactoring has happened to take advantage of the new
way.
License: MIT
Signed-off-by: Hector Sanjuan <hector@protocol.ai>
2017-10-11 18:23:03 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
// Save
|
2018-10-04 15:08:27 +00:00
|
|
|
saveConfig(cfgMgr)
|
2017-01-24 18:55:06 +00:00
|
|
|
return nil
|
|
|
|
},
|
|
|
|
},
|
2017-02-02 13:34:51 +00:00
|
|
|
{
|
2018-02-08 19:27:43 +00:00
|
|
|
Name: "daemon",
|
|
|
|
Usage: "run the IPFS Cluster peer (default)",
|
|
|
|
Flags: []cli.Flag{
|
|
|
|
cli.BoolFlag{
|
|
|
|
Name: "upgrade, u",
|
|
|
|
Usage: "run necessary state migrations before starting cluster service",
|
|
|
|
},
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
cli.StringSliceFlag{
|
|
|
|
Name: "bootstrap, j",
|
|
|
|
Usage: "join a cluster providing an existing peers multiaddress(es)",
|
|
|
|
},
|
|
|
|
cli.BoolFlag{
|
|
|
|
Name: "leave, x",
|
|
|
|
Usage: "remove peer from cluster on exit. Overrides \"leave_on_shutdown\"",
|
|
|
|
Hidden: true,
|
|
|
|
},
|
|
|
|
cli.StringFlag{
|
|
|
|
Name: "alloc, a",
|
|
|
|
Value: defaultAllocation,
|
|
|
|
Usage: "allocation strategy to use [disk-freespace,disk-reposize,numpin].",
|
|
|
|
},
|
2018-05-07 12:46:05 +00:00
|
|
|
cli.StringFlag{
|
|
|
|
Name: "monitor",
|
|
|
|
Value: defaultMonitor,
|
|
|
|
Hidden: true,
|
|
|
|
Usage: "peer monitor to use [basic,pubsub].",
|
|
|
|
},
|
2018-08-14 17:57:14 +00:00
|
|
|
cli.StringFlag{
|
|
|
|
Name: "pintracker",
|
|
|
|
Value: defaultPinTracker,
|
|
|
|
Hidden: true,
|
|
|
|
Usage: "pintracker to use [map,stateless].",
|
|
|
|
},
|
2018-02-08 19:27:43 +00:00
|
|
|
},
|
2017-10-20 10:45:42 +00:00
|
|
|
Action: daemon,
|
2017-02-02 13:34:51 +00:00
|
|
|
},
|
2017-11-28 22:45:10 +00:00
|
|
|
{
|
|
|
|
Name: "state",
|
|
|
|
Usage: "Manage ipfs-cluster-state",
|
|
|
|
Subcommands: []cli.Command{
|
2018-01-26 23:30:45 +00:00
|
|
|
{
|
|
|
|
Name: "version",
|
|
|
|
Usage: "display the shared state format version",
|
|
|
|
Action: func(c *cli.Context) error {
|
|
|
|
fmt.Printf("%d\n", mapstate.Version)
|
|
|
|
return nil
|
|
|
|
},
|
|
|
|
},
|
2017-11-28 22:45:10 +00:00
|
|
|
{
|
|
|
|
Name: "upgrade",
|
|
|
|
Usage: "upgrade the IPFS Cluster state to the current version",
|
|
|
|
Description: `
|
|
|
|
This command upgrades the internal state of the ipfs-cluster node
|
|
|
|
specified in the latest raft snapshot. The state format is migrated from the
|
|
|
|
version of the snapshot to the version supported by the current cluster version.
|
2017-12-06 14:00:01 +00:00
|
|
|
To successfully run an upgrade of an entire cluster, shut down each peer without
|
2017-11-28 22:45:10 +00:00
|
|
|
removal, upgrade state using this command, and restart every peer.
|
|
|
|
`,
|
|
|
|
Action: func(c *cli.Context) error {
|
2017-12-19 17:05:32 +00:00
|
|
|
err := locker.lock()
|
|
|
|
checkErr("acquiring execution lock", err)
|
|
|
|
defer locker.tryUnlock()
|
|
|
|
|
|
|
|
err = upgrade()
|
2017-11-28 22:45:10 +00:00
|
|
|
checkErr("upgrading state", err)
|
2017-12-19 17:05:32 +00:00
|
|
|
return nil
|
|
|
|
},
|
|
|
|
},
|
|
|
|
{
|
|
|
|
Name: "export",
|
|
|
|
Usage: "save the IPFS Cluster state to a json file",
|
|
|
|
Description: `
|
|
|
|
This command reads the current cluster state and saves it as json for
|
|
|
|
human readability and editing. Only state formats compatible with this
|
|
|
|
version of ipfs-cluster-service can be exported. By default this command
|
|
|
|
prints the state to stdout.
|
|
|
|
`,
|
|
|
|
Flags: []cli.Flag{
|
|
|
|
cli.StringFlag{
|
|
|
|
Name: "file, f",
|
|
|
|
Value: "",
|
|
|
|
Usage: "sets an output file for exported state",
|
|
|
|
},
|
|
|
|
},
|
|
|
|
Action: func(c *cli.Context) error {
|
|
|
|
err := locker.lock()
|
|
|
|
checkErr("acquiring execution lock", err)
|
|
|
|
defer locker.tryUnlock()
|
|
|
|
|
|
|
|
var w io.WriteCloser
|
|
|
|
outputPath := c.String("file")
|
|
|
|
if outputPath == "" {
|
|
|
|
// Output to stdout
|
|
|
|
w = os.Stdout
|
|
|
|
} else {
|
|
|
|
// Create the export file
|
|
|
|
w, err = os.Create(outputPath)
|
|
|
|
checkErr("creating output file", err)
|
|
|
|
}
|
|
|
|
defer w.Close()
|
|
|
|
|
|
|
|
err = export(w)
|
|
|
|
checkErr("exporting state", err)
|
|
|
|
return nil
|
|
|
|
},
|
|
|
|
},
|
|
|
|
{
|
|
|
|
Name: "import",
|
|
|
|
Usage: "load an IPFS Cluster state from an exported state file",
|
|
|
|
Description: `
|
|
|
|
This command reads in an exported state file storing the state as a persistent
|
|
|
|
snapshot to be loaded as the cluster state when the cluster peer is restarted.
|
|
|
|
If an argument is provided, cluster will treat it as the path of the file to
|
|
|
|
import. If no argument is provided cluster will read json from stdin
|
|
|
|
`,
|
2018-10-04 15:55:46 +00:00
|
|
|
Flags: []cli.Flag{
|
|
|
|
cli.BoolFlag{
|
|
|
|
Name: "force, f",
|
2018-10-18 04:23:47 +00:00
|
|
|
Usage: "forcefully proceed with replacing the current state with the given one, without prompting",
|
2018-10-04 15:55:46 +00:00
|
|
|
},
|
|
|
|
},
|
2017-12-19 17:05:32 +00:00
|
|
|
Action: func(c *cli.Context) error {
|
|
|
|
err := locker.lock()
|
|
|
|
checkErr("acquiring execution lock", err)
|
|
|
|
defer locker.tryUnlock()
|
|
|
|
|
2018-10-04 15:55:46 +00:00
|
|
|
if !c.Bool("force") {
|
2017-12-19 17:05:32 +00:00
|
|
|
if !yesNoPrompt("The peer's state will be replaced. Run with -h for details. Continue? [y/n]:") {
|
|
|
|
return nil
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Get the importing file path
|
|
|
|
importFile := c.Args().First()
|
|
|
|
var r io.ReadCloser
|
|
|
|
if importFile == "" {
|
|
|
|
r = os.Stdin
|
|
|
|
logger.Info("Reading from stdin, Ctrl-D to finish")
|
|
|
|
} else {
|
|
|
|
r, err = os.Open(importFile)
|
|
|
|
checkErr("reading import file", err)
|
|
|
|
}
|
|
|
|
defer r.Close()
|
|
|
|
err = stateImport(r)
|
|
|
|
checkErr("importing state", err)
|
|
|
|
logger.Info("the given state has been correctly imported to this peer. Make sure all peers have consistent states")
|
|
|
|
return nil
|
|
|
|
},
|
|
|
|
},
|
|
|
|
{
|
|
|
|
Name: "cleanup",
|
|
|
|
Usage: "cleanup persistent consensus state so cluster can start afresh",
|
|
|
|
Description: `
|
|
|
|
This command removes the persistent state that is loaded on startup to determine this peer's view of the
|
|
|
|
cluster state. While it removes the existing state from the load path, one invocation does not permanently remove
|
|
|
|
this state from disk. This command renames cluster's data folder to <data-folder-name>.old.0, and rotates other
|
|
|
|
deprecated data folders to <data-folder-name>.old.<n+1>, etc for some rotation factor before permanatly deleting
|
|
|
|
the mth data folder (m currently defaults to 5)
|
|
|
|
`,
|
2018-10-04 15:55:46 +00:00
|
|
|
Flags: []cli.Flag{
|
|
|
|
cli.BoolFlag{
|
|
|
|
Name: "force, f",
|
|
|
|
Usage: "forcefully proceed with rotating peer state without prompting",
|
|
|
|
},
|
|
|
|
},
|
2017-12-19 17:05:32 +00:00
|
|
|
Action: func(c *cli.Context) error {
|
|
|
|
err := locker.lock()
|
|
|
|
checkErr("acquiring execution lock", err)
|
|
|
|
defer locker.tryUnlock()
|
|
|
|
|
2018-10-04 15:55:46 +00:00
|
|
|
if !c.Bool("force") {
|
2018-10-18 13:21:11 +00:00
|
|
|
if !yesNoPrompt(fmt.Sprintf("%s Continue? [y/n]:", stateCleanupPrompt)) {
|
2017-12-19 17:05:32 +00:00
|
|
|
return nil
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-03-23 01:08:00 +00:00
|
|
|
cfgMgr, cfgs := makeConfigs()
|
|
|
|
err = cfgMgr.LoadJSONFromFile(configPath)
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
checkErr("reading configuration", err)
|
2017-12-19 17:05:32 +00:00
|
|
|
|
2018-10-18 13:21:11 +00:00
|
|
|
err = cleanupState(cfgs.consensusCfg)
|
2017-12-19 17:05:32 +00:00
|
|
|
checkErr("Cleaning up consensus data", err)
|
|
|
|
return nil
|
2017-11-28 22:45:10 +00:00
|
|
|
},
|
|
|
|
},
|
|
|
|
},
|
|
|
|
},
|
2017-12-12 16:47:21 +00:00
|
|
|
{
|
|
|
|
Name: "version",
|
|
|
|
Usage: "Print the ipfs-cluster version",
|
|
|
|
Action: func(c *cli.Context) error {
|
2018-02-20 16:55:18 +00:00
|
|
|
fmt.Printf("%s\n", ipfscluster.Version)
|
2017-12-12 16:47:21 +00:00
|
|
|
return nil
|
|
|
|
},
|
|
|
|
},
|
2017-01-24 18:55:06 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
app.Before = func(c *cli.Context) error {
|
|
|
|
absPath, err := filepath.Abs(c.String("config"))
|
|
|
|
if err != nil {
|
|
|
|
return err
|
|
|
|
}
|
|
|
|
|
|
|
|
configPath = filepath.Join(absPath, DefaultConfigFile)
|
|
|
|
|
2018-01-11 17:09:10 +00:00
|
|
|
setupLogLevel(c.String("loglevel"))
|
2017-01-24 18:55:06 +00:00
|
|
|
if c.Bool("debug") {
|
|
|
|
setupDebug()
|
|
|
|
}
|
2017-12-05 03:46:52 +00:00
|
|
|
|
2017-12-06 19:10:15 +00:00
|
|
|
locker = &lock{path: absPath}
|
2017-12-05 03:46:52 +00:00
|
|
|
|
2017-01-24 18:55:06 +00:00
|
|
|
return nil
|
2016-12-21 18:37:25 +00:00
|
|
|
}
|
2017-01-24 18:55:06 +00:00
|
|
|
|
2017-02-02 13:34:51 +00:00
|
|
|
app.Action = run
|
2017-01-24 18:55:06 +00:00
|
|
|
|
2017-02-02 13:34:51 +00:00
|
|
|
app.Run(os.Args)
|
|
|
|
}
|
|
|
|
|
2017-10-20 10:45:42 +00:00
|
|
|
// run daemon() by default, or error.
|
2017-02-02 13:34:51 +00:00
|
|
|
func run(c *cli.Context) error {
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
cli.ShowAppHelp(c)
|
|
|
|
os.Exit(1)
|
|
|
|
return nil
|
2016-12-21 18:37:25 +00:00
|
|
|
}
|
|
|
|
|
2018-01-11 17:09:10 +00:00
|
|
|
func setupLogLevel(lvl string) {
|
|
|
|
for f := range ipfscluster.LoggingFacilities {
|
2017-03-14 16:32:00 +00:00
|
|
|
ipfscluster.SetFacilityLogLevel(f, lvl)
|
|
|
|
}
|
Feat: emancipate Consensus from the Cluster component
This commit promotes the Consensus component (and Raft) to become a fully
independent thing like other components, passed to NewCluster during
initialization. Cluster (main component) no longer creates the consensus
layer internally. This has triggered a number of breaking changes
that I will explain below.
Motivation: Future work will require the possibility of running Cluster
with a consensus layer that is not Raft. The "consensus" layer is in charge
of maintaining two things:
* The current cluster peerset, as required by the implementation
* The current cluster pinset (shared state)
While the pinset maintenance has always been in the consensus layer, the
peerset maintenance was handled by the main component (starting by the "peers"
key in the configuration) AND the Raft component (internally)
and this generated lots of confusion: if the user edited the peers in the
configuration they would be greeted with an error.
The bootstrap process (adding a peer to an existing cluster) and configuration
key also complicated many things, since the main component did it, but only
when the consensus was initialized and in single peer mode.
In all this we also mixed the peerstore (list of peer addresses in the libp2p
host) with the peerset, when they need not to be linked.
By initializing the consensus layer before calling NewCluster, all the
difficulties in maintaining the current implementation in the same way
have come to light. Thus, the following changes have been introduced:
* Remove "peers" and "bootstrap" keys from the configuration: we no longer
edit or save the configuration files. This was a very bad practice, requiring
write permissions by the process to the file containing the private key and
additionally made things like Puppet deployments of cluster difficult as
configuration would mutate from its initial version. Needless to say all the
maintenance associated to making sure peers and bootstrap had correct values
when peers are bootstrapped or removed. A loud and detailed error message has
been added when staring cluster with an old config, along with instructions on
how to move forward.
* Introduce a PeerstoreFile ("peerstore") which stores peer addresses: in
ipfs, the peerstore is not persisted because it can be re-built from the
network bootstrappers and the DHT. Cluster should probably also allow
discoverability of peers addresses (when not bootstrapping, as in that case
we have it), but in the meantime, we will read and persist the peerstore
addresses for cluster peers in this file, different from the configuration.
Note that dns multiaddresses are now fully supported and no IPs are saved
when we have DNS multiaddresses for a peer.
* The former "peer_manager" code is now a pstoremgr module, providing utilities
to parse, add, list and generally maintain the libp2p host peerstore, including
operations on the PeerstoreFile. This "pstoremgr" can now also be extended to
perform address autodiscovery and other things indepedently from Cluster.
* Create and initialize Raft outside of the main Cluster component: since we
can now launch Raft independently from Cluster, we have more degrees of
freedom. A new "staging" option when creating the object allows a raft peer to
be launched in Staging mode, waiting to be added to a running consensus, and
thus, not electing itself as leader or doing anything like we were doing
before. This additionally allows us to track when the peer has become a
Voter, which only happens when it's caught up with the state, something that
was wonky previously.
* The raft configuration now includes an InitPeerset key, which allows to
provide a peerset for new peers and which is ignored when staging==true. The
whole Raft initialization code is way cleaner and stronger now.
* Cluster peer bootsrapping is now an ipfs-cluster-service feature. The
--bootstrap flag works as before (additionally allowing comma-separated-list
of entries). What bootstrap does, is to initialize Raft with staging == true,
and then call Join in the main cluster component. Only when the Raft peer
transitions to Voter, consensus becomes ready, and cluster becomes Ready.
This is cleaner, works better and is less complex than before (supporting
both flags and config values). We also backup and clean the state whenever
we are boostrapping, automatically
* ipfs-cluster-service no longer runs the daemon. Starting cluster needs
now "ipfs-cluster-service daemon". The daemon specific flags (bootstrap,
alloc) are now flags for the daemon subcommand. Here we mimic ipfs ("ipfs"
does not start the daemon but print help) and pave the path for merging both
service and ctl in the future.
While this brings some breaking changes, it significantly reduces the
complexity of the configuration, the code and most importantly, the
documentation. It should be easier now to explain the user what is the
right way to launch a cluster peer, and more difficult to make mistakes.
As a side effect, the PR also:
* Fixes #381 - peers with dynamic addresses
* Fixes #371 - peers should be Raft configuration option
* Fixes #378 - waitForUpdates may return before state fully synced
* Fixes #235 - config option shadowing (no cfg saves, no need to shadow)
License: MIT
Signed-off-by: Hector Sanjuan <code@hector.link>
2018-04-28 22:22:23 +00:00
|
|
|
ipfscluster.SetFacilityLogLevel("service", lvl)
|
2016-12-21 18:37:25 +00:00
|
|
|
}
|
|
|
|
|
2018-01-15 09:49:07 +00:00
|
|
|
func setupDebug() {
|
|
|
|
ipfscluster.SetFacilityLogLevel("*", "DEBUG")
|
|
|
|
}
|
|
|
|
|
2017-07-28 19:10:52 +00:00
|
|
|
func userProvidedSecret(enterSecret bool) ([]byte, bool) {
|
|
|
|
var secret string
|
|
|
|
if enterSecret {
|
|
|
|
secret = promptUser("Enter cluster secret (32-byte hex string): ")
|
|
|
|
} else if envSecret, envSecretDefined := os.LookupEnv("CLUSTER_SECRET"); envSecretDefined {
|
|
|
|
secret = envSecret
|
|
|
|
} else {
|
|
|
|
return nil, false
|
|
|
|
}
|
|
|
|
|
|
|
|
decodedSecret, err := ipfscluster.DecodeClusterSecret(secret)
|
|
|
|
checkErr("parsing user-provided secret", err)
|
|
|
|
return decodedSecret, true
|
|
|
|
}
|
|
|
|
|
2017-07-04 20:39:10 +00:00
|
|
|
func promptUser(msg string) string {
|
|
|
|
scanner := bufio.NewScanner(os.Stdin)
|
|
|
|
fmt.Print(msg)
|
|
|
|
scanner.Scan()
|
|
|
|
return scanner.Text()
|
|
|
|
}
|
2017-07-19 16:54:57 +00:00
|
|
|
|
2017-12-19 17:05:32 +00:00
|
|
|
// Lifted from go-ipfs/cmd/ipfs/daemon.go
|
|
|
|
func yesNoPrompt(prompt string) bool {
|
|
|
|
var s string
|
|
|
|
for i := 0; i < 3; i++ {
|
|
|
|
fmt.Printf("%s ", prompt)
|
|
|
|
fmt.Scanf("%s", &s)
|
|
|
|
switch s {
|
|
|
|
case "y", "Y":
|
|
|
|
return true
|
|
|
|
case "n", "N":
|
|
|
|
return false
|
|
|
|
case "":
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
fmt.Println("Please press either 'y' or 'n'")
|
|
|
|
}
|
|
|
|
return false
|
|
|
|
}
|