With this change, MinIO's ILM supports transitioning objects to a remote tier.
This change includes support for Azure Blob Storage, AWS S3 compatible object
storage incl. MinIO and Google Cloud Storage as remote tier storage backends.
Some new additions include:
- Admin APIs remote tier configuration management
- Simple journal to track remote objects to be 'collected'
This is used by object API handlers which 'mutate' object versions by
overwriting/replacing content (Put/CopyObject) or removing the version
itself (e.g DeleteObjectVersion).
- Rework of previous ILM transition to fit the new model
In the new model, a storage class (a.k.a remote tier) is defined by the
'remote' object storage type (one of s3, azure, GCS), bucket name and a
prefix.
* Fixed bugs, review comments, and more unit-tests
- Leverage inline small object feature
- Migrate legacy objects to the latest object format before transitioning
- Fix restore to particular version if specified
- Extend SharedDataDirCount to handle transitioned and restored objects
- Restore-object should accept version-id for version-suspended bucket (#12091)
- Check if remote tier creds have sufficient permissions
- Bonus minor fixes to existing error messages
Co-authored-by: Poorna Krishnamoorthy <poorna@minio.io>
Co-authored-by: Krishna Srinivas <krishna@minio.io>
Signed-off-by: Harshavardhana <harsha@minio.io>
Multiple disks from the same set would be writing concurrently.
```
WARNING: DATA RACE
Write at 0x00c002100ce0 by goroutine 166:
github.com/minio/minio/cmd.(*erasureSets).connectDisks.func1()
d:/minio/minio/cmd/erasure-sets.go:254 +0x82f
Previous write at 0x00c002100ce0 by goroutine 129:
github.com/minio/minio/cmd.(*erasureSets).connectDisks.func1()
d:/minio/minio/cmd/erasure-sets.go:254 +0x82f
Goroutine 166 (running) created at:
github.com/minio/minio/cmd.(*erasureSets).connectDisks()
d:/minio/minio/cmd/erasure-sets.go:210 +0x324
github.com/minio/minio/cmd.(*erasureSets).monitorAndConnectEndpoints()
d:/minio/minio/cmd/erasure-sets.go:288 +0x244
Goroutine 129 (finished) created at:
github.com/minio/minio/cmd.(*erasureSets).connectDisks()
d:/minio/minio/cmd/erasure-sets.go:210 +0x324
github.com/minio/minio/cmd.(*erasureSets).monitorAndConnectEndpoints()
d:/minio/minio/cmd/erasure-sets.go:288 +0x244
```
Current implementation heavily relies on readAllFileInfo
but with the advent of xl.meta inlined with data, we cannot
easily avoid reading data when we are only interested is
updating metadata, this leads to invariably write
amplification during metadata updates, repeatedly reading
data when we are only interested in updating metadata.
This PR ensures that we implement a metadata only update
API at storage layer, that handles updates to metadata alone
for any given version - given the version is valid and
present.
This helps reduce the chattiness for following calls..
- PutObjectTags
- DeleteObjectTags
- PutObjectLegalHold
- PutObjectRetention
- ReplicateObject (updates metadata on replication status)
The local node name is heavily used in tracing, create a new global
variable to store it. Multiple goroutines can access it since it won't be
changed later.
MRF was starting to heal when it receives a disk connection event, which
is not good when a node having multiple disks reconnects to the cluster.
Besides, MRF needs Remove healing option to remove stale files.
major performance improvements in range GETs to avoid large
read amplification when ranges are tiny and random
```
-------------------
Operation: GET
Operations: 142014 -> 339421
Duration: 4m50s -> 4m56s
* Average: +139.41% (+1177.3 MiB/s) throughput, +139.11% (+658.4) obj/s
* Fastest: +125.24% (+1207.4 MiB/s) throughput, +132.32% (+612.9) obj/s
* 50% Median: +139.06% (+1175.7 MiB/s) throughput, +133.46% (+660.9) obj/s
* Slowest: +203.40% (+1267.9 MiB/s) throughput, +198.59% (+753.5) obj/s
```
TTFB from 10MiB BlockSize
```
* First Access TTFB: Avg: 81ms, Median: 61ms, Best: 20ms, Worst: 2.056s
```
TTFB from 1MiB BlockSize
```
* First Access TTFB: Avg: 22ms, Median: 21ms, Best: 8ms, Worst: 91ms
```
Full object reads however do see a slight change which won't be
noticeable in real world, so not doing any comparisons
TTFB still had improvements with full object reads with 1MiB
```
* First Access TTFB: Avg: 68ms, Median: 35ms, Best: 11ms, Worst: 1.16s
```
v/s
TTFB with 10MiB
```
* First Access TTFB: Avg: 388ms, Median: 98ms, Best: 20ms, Worst: 4.156s
```
This change should affect all new uploads, previous uploads should
continue to work with business as usual. But dramatic improvements can
be seen with these changes.
* Provide information on *actively* healing, buckets healed/queued, objects healed/failed.
* Add concurrent healing of multiple sets (typically on startup).
* Add bucket level resume, so restarts will only heal non-healed buckets.
* Print summary after healing a disk is done.
also re-use storage disks for all `mc admin server info`
calls as well, implement a new LocalStorageInfo() API
call at ObjectLayer to lookup local disks storageInfo
also fixes bugs where there were double calls to StorageInfo()
most of the delete calls today spend time in
a blocking operation where multiple calls need
to be recursively sent to delete the objects,
instead we can use rename operation to atomically
move the objects from the namespace to `tmp/.trash`
we can schedule deletion of objects at this
location once in 15, 30mins and we can also add
wait times between each delete operation.
this allows us to make delete's faster as well
less chattier on the drives, each server runs locally
a groutine which would clean this up regularly.
This commit removes the `GetObject` method
from the `ObjectLayer` interface.
The `GetObject` method is not longer used by
the HTTP handlers implementing the high-level
S3 semantics. Instead, they use the `GetObjectNInfo`
method which returns both, an object handle as well
as the object metadata.
Therefore, it is no longer necessary that a concrete
`ObjectLayer` implements `GetObject`.
store the cache in-memory instead of disks to avoid large
write amplifications for list heavy workloads, store in
memory instead and let it auto expire.
server startup code expects the object layer to properly
convert error into a proper type, so that in situations when
servers are coming up and quorum is not available servers
wait on each other.
If the periodic `case <-t.C:` save gets held up for a long time it will end up
synchronize all disk writes for saving the caches.
We add jitter to per set writes so they don't sync up and don't hold a
lock for the write, since it isn't needed anyway.
If an outage prevents writes for a long while we also add individual
waits for each disk in case there was a queue.
Furthermore limit the number of buffers kept to 2GiB, since this could get
huge in large clusters. This will not act as a hard limit but should be enough
for normal operation.
This change moves away from a unified constructor for plaintext and encrypted
usage. NewPutObjReader is simplified for the plain-text reader use. For
encrypted reader use, WithEncryption should be called on an initialized PutObjReader.
Plaintext:
func NewPutObjReader(rawReader *hash.Reader) *PutObjReader
The hash.Reader is used to provide payload size and md5sum to the downstream
consumers. This is different from the previous version in that there is no need
to pass nil values for unused parameters.
Encrypted:
func WithEncryption(encReader *hash.Reader,
key *crypto.ObjectKey) (*PutObjReader, error)
This method sets up encrypted reader along with the key to seal the md5sum
produced by the plain-text reader (already setup when NewPutObjReader was
called).
Usage:
```
pReader := NewPutObjReader(rawReader)
// ... other object handler code goes here
// Prepare the encrypted hashed reader
pReader, err = pReader.WithEncryption(encReader, objEncKey)
```
- lock maintenance loop was incorrectly sleeping
as well as using ticker badly, leading to
extra expiration routines getting triggered
that could flood the network.
- multipart upload cleanup should be based on
timer instead of ticker, to ensure that long
running jobs don't get triggered twice.
- make sure to get right lockers for object name
currently we had a restriction where older setups would
need to follow previous style of "stripe" count being same
expansion, we can relax that instead newer pools can be
expanded for older setups with newer constraints of
common parity ratio.
For objects with `N` prefix depth, this PR reduces `N` such network
operations by converting `CheckFile` into a single bulk operation.
Reduction in chattiness here would allow disks to be utilized more
cleanly, while maintaining the same functionality along with one
extra volume check stat() call is removed.
Update tests to test multiple sets scenario
parentDirIsObject is not using set level understanding
to check for parent objects, without this it can lead to
objects that can actually reside on a separate set as
objects and would conflict.
Current implementation requires server pools to have
same erasure stripe sizes, to facilitate same SLA
and expectations.
This PR allows server pools to be variadic, i.e they
do not have to be same erasure stripe sizes - instead
they should have SLA for parity ratio.
If the parity ratio cannot be guaranteed by the new
server pool, the deployment is rejected i.e server
pool expansion is not allowed.
issue was introduced in #11106 the following
pattern
<-t.C // timer fired
if !t.Stop() {
<-t.C // timer hangs
}
Seems to hang at the last `t.C` line, this
issue happens because a fired timer cannot be
Stopped() anymore and t.Stop() returns `false`
leading to confusing state of usage.
Refactor the code such that use timers appropriately
with exact requirements in place.
crawler should only ListBuckets once not for each serverPool,
buckets are same across all pools, across sets and ListBuckets
always returns an unified view, once list buckets returns
sort it by create time to scan the latest buckets earlier
with the assumption that latest buckets would have lesser
content than older buckets allowing them to be scanned faster
and also to be able to provide more closer to latest view.
With new refactor of bucket healing, healing bucket happens
automatically including its metadata, there is no need to
redundant heal buckets also in ListBucketsHeal remove
it.
optimization mainly to avoid listing the entire
`.minio.sys/buckets/.minio.sys` directory, this
can get really huge and comes in the way of startup
routines, contents inside `.minio.sys/buckets/.minio.sys`
are rather transient and not necessary to be healed.
This refactor is done for few reasons below
- to avoid deadlocks in scenarios when number
of nodes are smaller < actual erasure stripe
count where in N participating local lockers
can lead to deadlocks across systems.
- avoids expiry routines to run 1000 of separate
network operations and routes per disk where
as each of them are still accessing one single
local entity.
- it is ideal to have since globalLockServer
per instance.
- In a 32node deployment however, each server
group is still concentrated towards the
same set of lockers that partipicate during
the write/read phase, unlike previous minio/dsync
implementation - this potentially avoids send
32 requests instead we will still send at max
requests of unique nodes participating in a
write/read phase.
- reduces overall chattiness on smaller setups.
Similar to #10775 for fewer memory allocations, since we use
getOnlineDisks() extensively for listing we should optimize it
further.
Additionally, remove all unused walkers from the storage layer
Harshavardhana
Krishnan Parthasarathi
Klaus Post
Anis Elleuch
Andreas Auernhammer
Poorna Krishnamoorthy