storj/scripts/testdata/satellite-config.yaml.lock

885 lines
28 KiB
Plaintext
Raw Normal View History

# admin peer http listening address
# admin.address: ""
# an alternate directory path which contains the static assets to serve. When empty, it uses the embedded assets
# admin.static-dir: ""
# enable analytics reporting
# analytics.enabled: false
# hubspot api key
# analytics.hub-spot.api-key: ""
# the number of events that can be in the queue before dropping
# analytics.hub-spot.channel-size: 1000
# the number of concurrent api requests that can be made
# analytics.hub-spot.concurrent-sends: 4
# the default timeout for the hubspot http client
# analytics.hub-spot.default-timeout: 10s
# segment write key
# analytics.segment-write-key: ""
# how often to run the reservoir chore
# audit.chore-interval: 24h0m0s
# max number of times to attempt updating a statdb batch
# audit.max-retries-stat-db: 3
# limit above which we consider an audit is failed
# audit.max-reverify-count: 3
# the minimum acceptable bytes that storage nodes can transfer per second to the satellite
# audit.min-bytes-per-second: 128 B
# the minimum duration for downloading a share from storage nodes before timing out
# audit.min-download-timeout: 5m0s
# how often to recheck an empty audit queue
# audit.queue-interval: 1h0m0s
# number of reservoir slots allotted for nodes, currently capped at 3
# audit.slots: 3
# number of workers to run audits on segments
# audit.worker-concurrency: 2
2019-06-04 13:13:31 +01:00
# how frequently checker should check for bad segments
# checker.interval: 30s
# the probability of a single node going down within the next checker iteration
# checker.node-failure-rate: 5.435e-05
# how stale reliable node cache can be
# checker.reliability-cache-staleness: 5m0s
# comma-separated override values for repair threshold in the format k/o/n-override (min/optimal/total-override)
# checker.repair-overrides: 29/80/110-52,29/80/95-52,29/80/130-52
# Number of damaged segments to buffer in-memory before flushing to the repair queue
# checker.repair-queue-insert-batch-size: 100
# percent of held amount disposed to node after leaving withheld
compensation.dispose-percent: 50
# rate for data at rest per GB/hour
compensation.rates.at-rest-gb-hours: "0.00000205"
# rate for audit egress bandwidth per TB
compensation.rates.get-audit-tb: "10"
# rate for repair egress bandwidth per TB
compensation.rates.get-repair-tb: "10"
# rate for egress bandwidth per TB
compensation.rates.get-tb: "20"
# rate for repair ingress bandwidth per TB
compensation.rates.put-repair-tb: "0"
# rate for ingress bandwidth per TB
compensation.rates.put-tb: "0"
# comma separated monthly withheld percentage rates
compensation.withheld-percents: 75,75,75,50,50,50,25,25,25,0,0,0,0,0,0
# expiration time for auth tokens, account recovery tokens, and activation tokens
# console-auth.token-expiration-time: 24h0m0s
# url link for account activation redirect
# console.account-activation-redirect-url: ""
# server address of the graphql api gateway and frontend app
# console.address: :10100
# default duration for AS OF SYSTEM TIME
# console.as-of-system-time-duration: -5m0s
# auth token needed for access to registration token creation endpoint
# console.auth-token: ""
2019-05-28 15:32:51 +01:00
# secret used to sign auth tokens
# console.auth-token-secret: ""
# url link for for beta satellite feedback
# console.beta-satellite-feedback-url: ""
# url link for for beta satellite support
# console.beta-satellite-support-url: ""
# url link to contacts page
# console.contact-info-url: https://forum.storj.io
# indicates if user is allowed to add coupon codes to account from billing
# console.coupon-code-billing-ui-enabled: false
# indicates if user is allowed to add coupon codes to account from signup
# console.coupon-code-signup-ui-enabled: false
# indicates if Content Security Policy is enabled
# console.csp-enabled: true
# default project limits for users
# console.default-project-limit: 1
# url link to documentation
# console.documentation-url: https://docs.storj.io/
# external endpoint of the satellite if hosted
# console.external-address: ""
# incremental duration of penalty for failed login attempts in minutes
# console.failed-login-penalty: 2
# indicates if file browser flow is disabled
# console.file-browser-flow-disabled: false
# allow domains to embed the satellite in a frame, space separated
# console.frame-ancestors: tardigrade.io storj.io
# url link for gateway credentials requests
# console.gateway-credentials-request-url: https://auth.storjshare.io
# url link to general request page
# console.general-request-url: https://supportdcs.storj.io/hc/en-us/requests/new?ticket_form_id=360000379291
# indicates if generated console api should be used
# console.generated-api-enabled: false
# whether or not hCaptcha is enabled for user registration
# console.hcaptcha.enabled: false
# hCaptcha secret key
# console.hcaptcha.secret-key: ""
# hCaptcha site key
# console.hcaptcha.site-key: ""
# url link to storj.io homepage
# console.homepage-url: https://www.storj.io
# inactivity timer delay in seconds
# console.inactivity-timer-delay: 600
# indicates if session can be timed out due inactivity
# console.inactivity-timer-enabled: false
# indicates if satellite is in beta
# console.is-beta-satellite: false
# url link to let us know page
# console.let-us-know-url: https://storjlabs.atlassian.net/servicedesk/customer/portals
# url link for linksharing requests
# console.linksharing-url: https://link.storjshare.io
# number of times user can try to login without penalty
# console.login-attempts-without-penalty: 3
# indicates if new access grant flow should be used
# console.new-access-grant-flow: false
# indicates if new navigation structure should be rendered
# console.new-navigation: true
# indicates if new objects flow should be used
# console.new-objects-flow: true
# indicates if new project dashboard should be used
# console.new-project-dashboard: false
# how long oauth access tokens are issued for
# console.oauth-access-token-expiry: 24h0m0s
# how long oauth authorization codes are issued for
# console.oauth-code-expiry: 10m0s
# how long oauth refresh tokens are issued for
# console.oauth-refresh-token-expiry: 720h0m0s
# enable open registration
# console.open-registration-enabled: false
# optional url to external registration success page
# console.optional-signup-success-url: ""
# names and addresses of partnered satellites in JSON list format
# console.partnered-satellites: '[["US1","https://us1.storj.io"],["EU1","https://eu1.storj.io"],["AP1","https://ap1.storj.io"]]'
# password hashing cost (0=automatic)
# console.password-cost: 0
# indicates if the overview onboarding step should render with pathways
# console.pathway-overview-enabled: true
# url link to project limit increase request page
# console.project-limits-increase-request-url: https://supportdcs.storj.io/hc/en-us/requests/new?ticket_form_id=360000683212
# number of events before the limit kicks in
# console.rate-limit.burst: 5
# the rate at which request are allowed
# console.rate-limit.duration: 5m0s
# number of clients whose rate limits we store
# console.rate-limit.num-limits: 1000
# whether or not reCAPTCHA is enabled for user registration
# console.recaptcha.enabled: false
# reCAPTCHA secret key
# console.recaptcha.secret-key: ""
# reCAPTCHA site key
# console.recaptcha.site-key: ""
# used to display at web satellite console
# console.satellite-name: Storj
# name of organization which set up satellite
# console.satellite-operator: Storj Labs
# used to communicate with web crawlers and other web robots
# console.seo: "User-agent: *\nDisallow: \nDisallow: /cgi-bin/"
# path to static resources
# console.static-dir: ""
# url link to terms and conditions page
# console.terms-and-conditions-url: https://storj.io/storage-sla/
# the default free-tier bandwidth usage limit
# console.usage-limits.bandwidth.free: 150.00 GB
# the default paid-tier bandwidth usage limit
# console.usage-limits.bandwidth.paid: 100.00 TB
# the default free-tier project limit
# console.usage-limits.project.free: 1
# the default paid-tier project limit
# console.usage-limits.project.paid: 3
# the default free-tier segment usage limit
# console.usage-limits.segment.free: 150000
# the default paid-tier segment usage limit
# console.usage-limits.segment.paid: 100000000
# the default free-tier storage usage limit
# console.usage-limits.storage.free: 150.00 GB
# the default paid-tier storage usage limit
# console.usage-limits.storage.paid: 25.00 TB
# whether to load templates on each request
# console.watch: false
Remove Kademlia dependencies from Satellite and Storagenode (#2966) What: cmd/inspector/main.go: removes kad commands internal/testplanet/planet.go: Waits for contact chore to finish satellite/contact/nodesservice.go: creates an empty nodes service implementation satellite/contact/service.go: implements Local and FetchInfo methods & adds external address config value satellite/discovery/service.go: replaces kad.FetchInfo with contact.FetchInfo in Refresh() & removes Discover() satellite/peer.go: sets up contact service and endpoints storagenode/console/service.go: replaces nodeID with contact.Local() storagenode/contact/chore.go: replaces routing table with contact service storagenode/contact/nodesservice.go: creates empty implementation for ping and request info nodes service & implements RequestInfo method storagenode/contact/service.go: creates a service to return the local node and update its own capacity storagenode/monitor/monitor.go: uses contact service in place of routing table storagenode/operator.go: moves operatorconfig from kad into its own setup storagenode/peer.go: sets up contact service, chore, pingstats and endpoints satellite/overlay/config.go: changes NodeSelectionConfig.OnlineWindow default to 4hr to allow for accurate repair selection Removes kademlia setups in: cmd/storagenode/main.go cmd/storj-sim/network.go internal/testplane/planet.go internal/testplanet/satellite.go internal/testplanet/storagenode.go satellite/peer.go scripts/test-sim-backwards.sh scripts/testdata/satellite-config.yaml.lock storagenode/inspector/inspector.go storagenode/peer.go storagenode/storagenodedb/database.go Why: Replacing Kademlia Please describe the tests: • internal/testplanet/planet_test.go: TestBasic: assert that the storagenode can check in with the satellite without any errors TestContact: test that all nodes get inserted into both satellites' overlay cache during testplanet setup • satellite/contact/contact_test.go: TestFetchInfo: Tests that the FetchInfo method returns the correct info • storagenode/contact/contact_test.go: TestNodeInfoUpdated: tests that the contact chore updates the node information TestRequestInfoEndpoint: tests that the Request info endpoint returns the correct info Please describe the performance impact: Node discovery should be at least slightly more performant since each node connects directly to each satellite and no longer needs to wait for bootstrapping. It probably won't be faster in real time on start up since each node waits a random amount of time (less than 1 hr) to initialize its first connection (jitter).
2019-09-19 20:56:34 +01:00
# the public address of the node, useful for nodes behind NAT
contact.external-address: ""
# the maximum burst size for the contact rate limit token bucket
# contact.rate-limit-burst: 2
# the number of nodes or addresses to keep token buckets for
# contact.rate-limit-cache-size: 1000
# the amount of time that should happen between contact attempts usually
# contact.rate-limit-interval: 10m0s
# timeout for pinging storage nodes
# contact.timeout: 10m0s
# satellite database connection string
# database: postgres://
# satellite database api key lru capacity
# database-options.api-keys-cache.capacity: 1000
# satellite database api key expiration
# database-options.api-keys-cache.expiration: 1m0s
# macaroon revocation cache capacity
# database-options.revocations-cache.capacity: 10000
# macaroon revocation cache expiration
# database-options.revocations-cache.expiration: 5m0s
# Maximum Database Connection Lifetime, -1ns means the stdlib default
# db.conn_max_lifetime: 30m0s
# Maximum Amount of Idle Database connections, -1 means the stdlib default
# db.max_idle_conns: 1
# Maximum Amount of Open Database connections, -1 means the stdlib default
# db.max_open_conns: 5
# address to listen on for debug endpoints
# debug.addr: 127.0.0.1:0
# expose control panel
# debug.control: false
pkg/process: Now that we are trying to identify the root cause of the satellite load limitations (i.e. currently the satellite has a max ability of 400 rps for uploads and we need this to be higher), we are using the golang diagnostic tools to collect insight into what the bottlenecks are. We currently have a debug endpoint to gather some cpu and mem data, but it could be useful to have continuous profiling. GCP stackdriver has support for continuous profiling so lets set that up and see if it is helpful to gather more data. This PR adds support for [GCP continuous profiler](https://cloud.google.com/profiler) which allows enabling continuous cpu/mem profiling and the stats are sent to stackdriver in google cloud console. To enable the continuous profiling for a storj component, do the following: - prereq: the workload must be running in GKE and have Stackdriver Profiling IAM role permissions - provide the config flag `debug.profilename` in the config.yaml file for the workload (i.e. satellite api process, etc). The profilename should be the workload name, for example "satellite-api". - once the above config flag is provided, the profiler will be initialized and profiling stats will automatically be sent to GCP project where the workload is running and viewable in the Stackdriver Profile page in the console The current implementation assumes the workload is running in GKE, however if we find if useful we can add support to enable this from anywhere. But for simplicity, its configured this way assuming the main goal is to enable in production systems. Change-Id: Ibf8ebe2df7bf06fdd4951ee6a1e48854dd36ad47
2020-02-25 16:46:12 +00:00
# provide the name of the peer to enable continuous cpu/mem profiling for
# debug.profilername: ""
# If set, a path to write a process trace SVG to
# debug.trace-out: ""
# how often to send reminders to users who need to verify their email
# email-reminders.chore-interval: 24h0m0s
# enable sending emails reminding users to verify their email
# email-reminders.enable: false
# amount of time before sending first reminder to users who need to verify their email
# email-reminders.first-verification-reminder: 24h0m0s
# amount of time before sending second reminder to users who need to verify their email
# email-reminders.second-verification-reminder: 120h0m0s
# set if expired segment cleanup is enabled or not
# expired-deletion.enabled: true
# the time between each attempt to go through the db and clean up expired segments
# expired-deletion.interval: 24h0m0s
# how many expired objects to query in a batch
# expired-deletion.list-limit: 100
# the number of nodes to concurrently send garbage collection bloom filters to
# garbage-collection.concurrent-sends: 1
# set if garbage collection is enabled or not
# garbage-collection.enabled: true
# the false positive rate used for creating a garbage collection bloom filter
# garbage-collection.false-positive-rate: 0.1
# the initial number of pieces expected for a storage node to have, used for creating a filter
# garbage-collection.initial-pieces: 400000
# the time between each send of garbage collection filters to storage nodes
# garbage-collection.interval: 120h0m0s
# the amount of time to allow a node to handle a retain request
# garbage-collection.retain-send-timeout: 1m0s
# interval for AS OF SYSTEM TIME clause (crdb specific) to read from db at a specific time in the past
# graceful-exit.as-of-system-time-interval: -10s
# size of the buffer used to batch inserts into the transfer queue.
# graceful-exit.chore-batch-size: 500
# how often to run the transfer queue chore.
# graceful-exit.chore-interval: 30s
# whether or not graceful exit is enabled on the satellite side.
# graceful-exit.enabled: true
# size of the buffer used to batch transfer queue reads and sends to the storage node.
# graceful-exit.endpoint-batch-size: 300
# maximum number of transfer failures per piece.
# graceful-exit.max-failures-per-piece: 5
# maximum inactive time frame of transfer activities per node.
# graceful-exit.max-inactive-time-frame: 168h0m0s
# maximum number of order limits a satellite sends to a node before marking piece transfer failed
# graceful-exit.max-order-limit-send-count: 10
# minimum age for a node on the network in order to initiate graceful exit
# graceful-exit.node-min-age-in-months: 6
# maximum percentage of transfer failures per node.
# graceful-exit.overall-max-failures-percentage: 10
# the minimum duration for receiving a stream from a storage node before timing out
# graceful-exit.recv-timeout: 2h0m0s
# batch size (crdb specific) for deleting and adding items to the transfer queue
# graceful-exit.transfer-queue-batch-size: 1000
# path to the certificate chain for this identity
identity.cert-path: /root/.local/share/storj/identity/satellite/identity.cert
# path to the private key for this identity
identity.key-path: /root/.local/share/storj/identity/satellite/identity.key
# as of system interval
# live-accounting.as-of-system-interval: -10s
# bandwidth cache key time to live
# live-accounting.bandwidth-cache-ttl: 5m0s
# what to use for storing real-time accounting data
satellite/accounting: refactor live accounting to hold current estimated totals live accounting used to be a cache to store writes before they are picked up during the tally iteration, after which the cache is cleared. This created a window in which users could potentially exceed the storage limit. This PR refactors live accounting to hold current estimations of space used per project. This should also reduce DB load since we no longer need to query the satellite DB when checking space used for limiting. The mechanism by which the new live accounting system works is as follows: During the upload of any segment, the size of that segment is added to its respective project total in live accounting. At the beginning of the tally iteration we record the current values in live accounting as `initialLiveTotals`. At the end of the tally iteration we again record the current totals in live accounting as `latestLiveTotals`. The metainfo loop observer in tally allows us to get the project totals from what it observed in metainfo DB which are stored in `tallyProjectTotals`. However, for any particular segment uploaded during the metainfo loop, the observer may or may not have seen it. Thus, we take half of the difference between `latestLiveTotals` and `initialLiveTotals`, and add that to the total that was found during tally and set that as the new live accounting total. Initially, live accounting was storing the total stored amount across all nodes rather than the segment size, which is inconsistent with how we record amounts stored in the project accounting DB, so we have refactored live accounting to record segment size Change-Id: Ie48bfdef453428fcdc180b2d781a69d58fd927fb
2019-10-31 17:27:38 +00:00
# live-accounting.storage-backend: ""
# if true, log function filename and line number
# log.caller: false
# if true, set logging to development mode
# log.development: false
# configures log encoding. can either be 'console', 'json', or 'pretty'.
# log.encoding: ""
# the minimum log level to log
# log.level: info
# can be stdout, stderr, or a filename
# log.output: stderr
# if true, log stack traces
# log.stack: false
# smtp authentication type
# mail.auth-type: login
# oauth2 app's client id
# mail.client-id: ""
# oauth2 app's client secret
# mail.client-secret: ""
# sender email address
# mail.from: ""
# plain/login auth user login
# mail.login: ""
# plain/login auth user password
# mail.password: ""
# refresh token used to retrieve new access token
# mail.refresh-token: ""
# smtp server address
# mail.smtp-server-address: ""
# path to email templates source
# mail.template-path: ""
# uri which is used when retrieving new access token
# mail.token-uri: ""
# the database connection string to use
# metainfo.database-url: postgres://
# maximum time allowed to pass between creating and committing a segment
# metainfo.max-commit-interval: 48h0m0s
# maximum encrypted object key length
# metainfo.max-encrypted-object-key-length: 1280
# maximum inline segment size
# metainfo.max-inline-segment-size: 4.0 KiB
# maximum segment metadata size
# metainfo.max-metadata-size: 2.0 KiB
# maximum number of parts object can contain
# metainfo.max-number-of-parts: 10000
# maximum segment size
# metainfo.max-segment-size: 64.0 MiB
# minimum allowed part size (last part has no minimum size limit)
# metainfo.min-part-size: 5.0 MiB
# minimum remote segment size
# metainfo.min-remote-segment-size: 1.2 KiB
# toggle flag if overlay is enabled
# metainfo.overlay: true
# timeout for dialing nodes (0 means satellite default)
# metainfo.piece-deletion.dial-timeout: 3s
# threshold for retrying a failed node
# metainfo.piece-deletion.fail-threshold: 10m0s
# maximum number of concurrent requests to storage nodes
# metainfo.piece-deletion.max-concurrency: 100
# maximum number of concurrent pieces can be processed
# metainfo.piece-deletion.max-concurrent-pieces: 1000000
# maximum number of pieces per batch
# metainfo.piece-deletion.max-pieces-per-batch: 5000
# maximum number pieces per single request
# metainfo.piece-deletion.max-pieces-per-request: 1000
# timeout for a single delete request
# metainfo.piece-deletion.request-timeout: 15s
# max bucket count for a project.
# metainfo.project-limits.max-buckets: 100
# whether segment limit validation is enabled.
# metainfo.project-limits.validate-segment-limit: true
# number of projects to cache.
# metainfo.rate-limiter.cache-capacity: 10000
# how long to cache the projects limiter.
# metainfo.rate-limiter.cache-expiration: 10m0s
# whether rate limiting is enabled.
# metainfo.rate-limiter.enabled: true
# request rate per project per second.
# metainfo.rate-limiter.rate: 100
# redundancy scheme configuration in the format k/m/o/n-sharesize
# metainfo.rs: 29/35/80/110-256 B
# as of system interval
# metainfo.segment-loop.as-of-system-interval: -5m0s
# how long to wait for new observers before starting iteration
# metainfo.segment-loop.coalesce-duration: 5s
# how many items to query in a batch
# metainfo.segment-loop.list-limit: 2500
# rate limit (default is 0 which is unlimited segments per second)
# metainfo.segment-loop.rate-limit: 0
# ratio where to consider processed count as supicious
# metainfo.segment-loop.suspicious-processed-ratio: 0.03
# enable code for server-side copy
# metainfo.server-side-copy: true
# address(es) to send telemetry to (comma-separated)
# metrics.addr: collectora.storj.io:9000
# application name for telemetry identification. Ignored for certain applications.
# metrics.app: satellite
# application suffix. Ignored for certain applications.
# metrics.app-suffix: -release
# instance id prefix
# metrics.instance-prefix: ""
# how frequently to send up telemetry. Ignored for certain applications.
# metrics.interval: 1m0s
# path to log for oom notices
# monkit.hw.oomlog: /var/log/kern.log
# encryption keys to encrypt info in orders
# orders.encryption-keys: ""
# how long until an order expires
# orders.expiration: 48h0m0s
# how many items in the rollups write cache before they are flushed to the database
# orders.flush-batch-size: 1000
# how often to flush the rollups write cache to the database
# orders.flush-interval: 1m0s
# how many concurrent orders to process at once. zero is unlimited
# orders.orders-semaphore-size: 2
# the location of the maxmind database containing geoip country information
# overlay.geo-ip.db: ""
# a mock list of countries the satellite will attribute to nodes (useful for testing)
# overlay.geo-ip.mock-countries: []
# the amount of time to wait before accepting a redundant check-in from a node (unmodified info since last check-in)
# overlay.node-check-in-wait-period: 2h0m0s
# disable node cache
# overlay.node-selection-cache.disabled: false
# how stale the node selection cache can be
# overlay.node-selection-cache.staleness: 3m0s
# default duration for AS OF SYSTEM TIME
# overlay.node.as-of-system-time.default-interval: -10s
# enables the use of the AS OF SYSTEM TIME feature in CRDB
# overlay.node.as-of-system-time.enabled: true
# require distinct IPs when choosing nodes for upload
# overlay.node.distinct-ip: true
# how much disk space a node at minimum must have to be selected for upload
# overlay.node.minimum-disk-space: 500.00 MB
# the minimum node software version for node selection queries
# overlay.node.minimum-version: ""
# the fraction of new nodes allowed per request
# overlay.node.new-node-fraction: 0.05
# the amount of time without seeing a node before its considered offline
# overlay.node.online-window: 4h0m0s
# list of country codes to exclude from node selection for uploads
# overlay.node.upload-excluded-country-codes: []
# list of country codes to exclude nodes from target repair selection
# overlay.repair-excluded-country-codes: []
# number of update requests to process per transaction
# overlay.update-stats-batch-size: 100
# amount of percents that user will earn as bonus credits by depositing in STORJ tokens
# payments.bonus-rate: 10
# price user should pay for each TB of egress
# payments.egress-tb-price: "7"
# price node receive for storing TB of audit in cents
# payments.node-audit-bandwidth-price: 1000
# price node receive for storing disk space in cents/TB
# payments.node-disk-space-price: 150
# price node receive for storing TB of egress in cents
# payments.node-egress-bandwidth-price: 2000
# price node receive for storing TB of repair in cents
# payments.node-repair-bandwidth-price: 1000
# payments provider to use
# payments.provider: ""
# price user should pay for each segment stored in network per month
# payments.segment-price: "0.0000088"
# price user should pay for storing TB per month
# payments.storage-tb-price: "4"
# amount of time we wait before running next account balance update loop
# payments.stripe-coin-payments.account-balance-update-interval: 2m0s
# toogle autoadvance feature for invoice creation
# payments.stripe-coin-payments.auto-advance: false
# coinpayments API private key key
# payments.stripe-coin-payments.coinpayments-private-key: ""
# coinpayments API public key
# payments.stripe-coin-payments.coinpayments-public-key: ""
# amount of time we wait before running next conversion rates update loop
# payments.stripe-coin-payments.conversion-rates-cycle-interval: 10m0s
# stripe free tier coupon ID
# payments.stripe-coin-payments.stripe-free-tier-coupon-id: ""
# stripe API public key
# payments.stripe-coin-payments.stripe-public-key: ""
# stripe API secret key
# payments.stripe-coin-payments.stripe-secret-key: ""
# amount of time we wait before running next transaction update loop
# payments.stripe-coin-payments.transaction-update-interval: 2m0s
# how often to remove unused project bandwidth rollups
# project-bw-cleanup.interval: 168h0m0s
# number of months of project bandwidth rollups to retain, not including the current month
# project-bw-cleanup.retain-months: 2
satellite/accounting: add cache for getting project storage and bw limits This PR adds the following items: 1) an in-memory read-only cache thats stores project limit info for projectIDs This cache is stored in-memory since this is expected to be a small amount of data. In this implementation we are only storing in the cache projects that have been accessed. Currently for the largest Satellite (eu-west) there is about 4500 total projects. So storing the storage limit (int64) and the bandwidth limit (int64), this would end up being about 200kb (including the 32 byte project ID) if all 4500 projectIDs were in the cache. So this all fits in memory for the time being. At some point it may not as usage grows, but that seems years out. The cache is a read only cache. When requests come in to upload/download a file, we will read from the cache what the current limits are for that project. If the cache does not contain the projectID, it will get the info from the database (satellitedb project table), then add it to the cache. The only time the values in the cache are modified is when either a) the project ID is not in the cache, or b) the item in the cache has expired (default 10mins), then the data gets refreshed out of the database. This occurs by default every 10 mins. This means that if we update the usage limits in the database, that change might not show up in the cache for 10 mins which mean it will not be reflected to limit end users uploading/downloading files for that time period.. Change-Id: I3fd7056cf963676009834fcbcf9c4a0922ca4a8f
2020-09-09 20:20:44 +01:00
# number of projects to cache.
# project-limit.cache-capacity: 10000
# how long to cache the project limits.
# project-limit.cache-expiration: 10m0s
# time limit for downloading pieces from a node for repair
# repairer.download-timeout: 5m0s
# whether to download pieces for repair in memory (true) or download to disk (false)
# repairer.in-memory-repair: false
2019-06-04 13:13:31 +01:00
# how frequently repairer should try and repair more data
# repairer.interval: 5m0s
# maximum buffer memory (in bytes) to be allocated for read buffers
# repairer.max-buffer-mem: 4.0 MiB
[V3-1927] Repairer uploads to max threshold instead of success… (#2423) * pkg/datarepair: Add test to check num upload pieces Add a new test for ensuring the number of pieces that the repair process upload when a segment is injured. * satellite/orders: Don't create "put order limits" over total Repair must not create "put order limits" more than the total count. * pkg/datarepair: Update upload repair pieces test Update the test which checks the number of pieces which are uploaded during a repair for using the same excess over the success threshold value than the implementation. * satellites/orders: Limit repair put order for not being total Limit the number of put orders to be used by repair for only uploading pieces to a % excess over the successful threshold. * pkg/datarepair: Change DataRepair test to pass again Make some changes in the DataRepair test to make pass again after the repair upload repaired pieces only until a % excess over success threshold. Also update the steps description of the DataRepair test after it has been changed, to match on what's now, besides to leave it more generic for avoiding having to update it on minimal future refactorings. * satellite: Make repair excess optimal threshold configurable Add a new configuration parameter to the satellite for being able to configure the percentage excess over the optimal threshold, used for determining how many pieces should be repaired/uploaded, rather than having the value hard coded. * repairer: Add configurable param to segments/repairer Add a new parameters to the segment/repairer to calculate the maximum number of excess nodes, based on the optimal threshold, that repaired pieces can be uploaded. This new parameter has been added for not returning more nodes than the number of upload orders for data repair satellite service calculate for repairing pieces. * pkg/storage/ec: Update log message in clien.Repair * satellite: Update configuration lock file
2019-07-11 23:44:47 +01:00
# ratio applied to the optimal threshold to calculate the excess of the maximum number of repaired pieces to upload
# repairer.max-excess-rate-optimal-threshold: 0.05
# maximum segments that can be repaired concurrently
# repairer.max-repair: 5
# time limit for uploading repaired pieces to new storage nodes
# repairer.timeout: 5m0s
# time limit for an entire repair job, from queue pop to upload completion
# repairer.total-timeout: 45m0s
# the number of times a node has been audited to not be considered a New Node
# reputation.audit-count: 100
# the reputation cut-off for disqualifying SNs based on audit history
# reputation.audit-dq: 0.6
# The length of time to give suspended SNOs to diagnose and fix issues causing downtime. Afterwards, they will have one tracking period to reach the minimum online score before disqualification
# reputation.audit-history.grace-period: 168h0m0s
# whether nodes will be disqualified if they have low online score after a review period
# reputation.audit-history.offline-dq-enabled: false
# whether nodes will be suspended if they have low online score
# reputation.audit-history.offline-suspension-enabled: true
# The point below which a node is punished for offline audits. Determined by calculating the ratio of online/total audits within each window and finding the average across windows within the tracking period.
# reputation.audit-history.offline-threshold: 0.6
# The length of time to track audit windows for node suspension and disqualification
# reputation.audit-history.tracking-period: 720h0m0s
# The length of time spanning a single audit window
# reputation.audit-history.window-size: 12h0m0s
# the forgetting factor used to calculate the audit SNs reputation
# reputation.audit-lambda: 0.95
# weight to apply to audit reputation for total repair reputation calculation
# reputation.audit-repair-weight: 1
# weight to apply to audit reputation for total uplink reputation calculation
# reputation.audit-uplink-weight: 1
# the normalization weight used to calculate the audit SNs reputation
# reputation.audit-weight: 1
# whether nodes will be disqualified if they have been suspended for longer than the suspended grace period
# reputation.suspension-dq-enabled: false
# the time period that must pass before suspended nodes will be disqualified
# reputation.suspension-grace-period: 168h0m0s
# expiration to use if user does not specify an rest key expiration
# rest-keys.default-expiration: 720h0m0s
# age at which a rollup is archived
# rollup-archive.archive-age: 2160h0m0s
# number of records to delete per delete execution. Used only for crdb which is slow without limit.
# rollup-archive.batch-size: 500
# whether or not the rollup archive is enabled.
# rollup-archive.enabled: true
# how frequently rollup archiver should run
# rollup-archive.interval: 24h0m0s
# option for deleting tallies after they are rolled up
# rollup.delete-tallies: true
# how frequently rollup should run
# rollup.interval: 24h0m0s
# public address to listen on
server.address: :7777
# if true, client leaves may contain the most recent certificate revocation for the current certificate
# server.extensions.revocation: true
# if true, client leaves must contain a valid "signed certificate extension" (NB: verified against certs in the peer ca whitelist; i.e. if true, a whitelist must be provided)
# server.extensions.whitelist-signed-leaf: false
# path to the CA cert whitelist (peer identities must be signed by one these to be verified). this will override the default peer whitelist
# server.peer-ca-whitelist-path: ""
# identity version(s) the server will be allowed to talk to
# server.peer-id-versions: latest
# private address to listen on
server.private-address: 127.0.0.1:7778
# url for revocation database (e.g. bolt://some.db OR redis://127.0.0.1:6378?db=2&password=abc123)
# server.revocation-dburl: bolt://testdata/revocations.db
# if true, uses peer ca whitelist checking
# server.use-peer-ca-whitelist: true
# whether nodes will be disqualified if they have not been contacted in some time
# stray-nodes.enable-dq: true
# how often to check for and DQ stray nodes
# stray-nodes.interval: 168h0m0s
# Max number of nodes to return in a single query. Chore will iterate until rows returned is less than limit
# stray-nodes.limit: 1000
# length of time a node can go without contacting satellite before being disqualified
# stray-nodes.max-duration-without-contact: 720h0m0s
# as of system interval
# tally.as-of-system-interval: -5m0s
# how frequently the tally service should run
# tally.interval: 1h0m0s
# how many objects to query in a batch
# tally.list-limit: 2500
# how large of batches GetBandwidthSince should process at a time
# tally.read-rollup-batch-size: 10000
# how large of batches SaveRollup should process at a time
# tally.save-rollup-batch-size: 1000
# address for jaeger agent
# tracing.agent-addr: agent.tracing.datasci.storj.io:5775
# application name for tracing identification
# tracing.app: satellite
# application suffix
# tracing.app-suffix: -release
# buffer size for collector batch packet size
# tracing.buffer-size: 0
# whether tracing collector is enabled
# tracing.enabled: false
# how frequently to flush traces to tracing agent
# tracing.interval: 0s
# buffer size for collector queue size
# tracing.queue-size: 0
# how frequent to sample traces
# tracing.sample: 0
# Interval to check the version
# version.check-interval: 15m0s
# Request timeout for version checks
# version.request-timeout: 1m0s
# server address to check its version against
# version.server-address: https://version.storj.io
# set if zombie object cleanup is enabled or not
# zombie-deletion.enabled: true
# after what time object will be deleted if there where no new upload activity
# zombie-deletion.inactive-for: 24h0m0s
# the time between each attempt to go through the db and clean up zombie objects
# zombie-deletion.interval: 12h0m0s
# how many objects to query in a batch
# zombie-deletion.list-limit: 100