Commit Graph

4337 Commits

Author SHA1 Message Date
Anis Elleuch
908eb57795
Always get the actual object size (#14637)
In bulk ETag decryption, do not rely on the etag to check if it is
encrypted or not to decide if we should set the actual object size in
ObjectInfo. The reason is that multipart objects ETags are not
encrypted.

Always get the actual object size in that case.
2022-03-27 08:54:25 -07:00
Harshavardhana
5cfedcfe33
askDisks for strict quorum to be equal to read quorum (#14623) 2022-03-25 16:29:45 -07:00
Andreas Auernhammer
4d2fc530d0
add support for SSE-S3 bulk ETag decryption (#14627)
This commit adds support for bulk ETag
decryption for SSE-S3 encrypted objects.

If KES supports a bulk decryption API, then
MinIO will check whether its policy grants
access to this API. If so, MinIO will use
a bulk API call instead of sending encrypted
ETags serially to KES.

Note that MinIO will not use the KES bulk API
if its client certificate is an admin identity.

MinIO will process object listings in batches.
A batch has a configurable size that can be set
via `MINIO_KMS_KES_BULK_API_BATCH_SIZE=N`.
It defaults to `500`.

This env. variable is experimental and may be
renamed / removed in the future.

Signed-off-by: Andreas Auernhammer <hi@aead.dev>
2022-03-25 15:01:41 -07:00
Harshavardhana
f046f557fa
request only 1 best version for latest version resolution (#14625)
ListObjects, ListObjectsV2 calls are being heavily taxed when
there are many versions on objects left over from a previous
release or ILM was never setup to clean them up. Instead
of being absolutely correct at resolving the exact latest
version of an object, we simply rely on the top most 1
version and resolve the rest.

Once we have obtained the top most "1" version for
ListObject, ListObjectsV2 call we break out.
2022-03-25 08:50:07 -07:00
Harshavardhana
401958938d
add load balance properly restClientFromHash() bucket/prefix (#14621)
spread out resuming further to other nodes
2022-03-25 03:41:31 -07:00
Poorna
566cffe53d
save format.json by default for inspect API (#14620) 2022-03-25 02:02:17 -07:00
Minio Trusted
a42b576382 keep maximum concurrent operations to 512 (to sustain upto 1024 open fds) 2022-03-23 17:02:04 -07:00
Klaus Post
2ac54e5a7b
ListObjects: Filter lifecycle expired objects (#14606)
For ListObjects and ListObjectsV2 perform lifecycle checks on 
all objects before returning. This will filter out objects that are 
pending lifecycle expiration.

Bonus: Cheaper server pool conflict resolution by not converting to FileInfo.
2022-03-22 12:39:45 -07:00
Harshavardhana
8eecdc6d1f
odd stripe sizes should choose (odd+1)/2 to get correct quorum (#14610) 2022-03-22 12:21:14 -07:00
Klaus Post
50577e2bd2
Allow adjusting request pool both ways (#14609)
When reloading a dynamic config allow the request pool to scale both ways.

Existing requests hold on to the previous pool, so they will pop the elements from that.
2022-03-22 11:28:54 -07:00
Klaus Post
7bc1f986e8
Do not wait for results when canceled (#14607)
When canceled nobody may be listening for the results.

Prevents memory buildup from cancelled requests.
2022-03-22 09:37:01 -07:00
Harshavardhana
d796621ccc
choose smaller default deadline for diagnostics without --full (#14599) 2022-03-21 23:25:24 -07:00
Harshavardhana
f6113264f4 add detection for GOMAXPROCS < NumCPU 2022-03-21 19:05:10 -07:00
Harshavardhana
a3534a730b
fallback quorum should be "strict" globally if config is not loaded (#14589) 2022-03-20 17:39:06 -07:00
Harshavardhana
bd6f7b6d83
fix: make decommission restart non-blocking (#14591)
currently an on-going decommission, during a server
restart might block the startup sequence for relatively
longer periods, instead start the decommission in
background lazily.
2022-03-20 14:46:43 -07:00
Andreas Auernhammer
b0a4beb66a
PutObjectPart: set SSE-KMS headers and truncate ETags. (#14578)
This commit fixes two bugs in the `PutObjectPartHandler`.
First, `PutObjectPart` should return SSE-KMS headers
when the object is encrypted using SSE-KMS.
Before, this was not the case.

Second, the ETag should always be a 16 byte hex string,
perhaps followed by a `-X` (where `X` is the number of parts).
However, `PutObjectPart` used to return the encrypted ETag
in case of SSE-KMS. This leaks MinIO internal etag details
through the S3 API.

The combination of both bugs causes clients that use SSE-KMS
to fail when trying to validate the ETag. Since `PutObjectPart`
did not send the SSE-KMS response headers, the response looked
like a plaintext `PutObjectPart` response. Hence, the client
tries to verify that the ETag is the content-md5 of the part.
This could never be the case, since MinIO used to return the
encrypted ETag.

Therefore, clients behaving as specified by the S3 protocol
tried to verify the ETag in a situation they should not.

Signed-off-by: Andreas Auernhammer <hi@aead.dev>
2022-03-19 10:15:12 -07:00
Harshavardhana
01ee49045e
fix: handle race in server setup global CI/CD variable (#14579) 2022-03-18 18:21:09 -07:00
Harshavardhana
7bd9f821dd
return correct context errors for locking operations (#14569)
if a context is canceled do not need to return a timeout error
instead, return the appropriate error for context canceled.
2022-03-18 15:32:45 -07:00
Klaus Post
61eb9d4e29
Fix listing fallback re-using disks (#14576)
When more than 2 disks are unavailable for listing, the same disk will be used for fallback.

This makes quorum calculations incorrect since the same disk will have multiple entries.

This PR keeps track of which fallback disks have been handed out and only every returns a disk once.
2022-03-18 11:35:27 -07:00
Harshavardhana
43eb5a001c
re-use transport for AdminInfo() call (#14571)
avoids creating new transport for each `isServerResolvable`
request, instead re-use the available global transport and do
not try to forcibly close connections to avoid TIME_WAIT
build upon large clusters.

Never use httpClient.CloseIdleConnections() since that can have
a drastic effect on existing connections on the transport pool.

Remove it everywhere.
2022-03-17 16:20:10 -07:00
Klaus Post
c1760fb764
Move apiCalls to front for field alignment (#14568)
Fixes #14565
2022-03-17 10:57:52 -07:00
Minio Trusted
ffcadcd99e Revert "Use S3 client for uplooads/downloads during perf test (#14553)"
This reverts commit ff811f594b.

Speedtest is broken need to fix this more cleanly.
2022-03-16 23:34:49 -07:00
Krishnan Parthasarathi
7b81967a3c
Fix handling of object versions pending purge (#14555)
- GetObject() with vid should return 405
- GetObject() without vid should return 404
- ListObjects() should ignore this object if this is the "latest" version of the object
- ListObjectVersions() should list this object as "DELETE marker"
- Remove data parts before sync'ing the version pending purge
2022-03-16 16:59:43 -07:00
Krishna Srinivas
ff811f594b
Use S3 client for uplooads/downloads during perf test (#14553) 2022-03-16 16:58:46 -07:00
Harshavardhana
e3071157f0
allow MakeBucketLocation to work for metaBucket (#14548)
decommission would fail to start due to failure
in MakeBucketLocation() error on .minio.sys/ bucket
creation.

Allow these special buckets.
2022-03-14 11:25:24 -07:00
Klaus Post
c07af89e48
select: Add ScanRange to CSV&JSON (#14546)
Implements https://docs.aws.amazon.com/AmazonS3/latest/API/API_SelectObjectContent.html#AmazonS3-SelectObjectContent-request-ScanRange

Fixes #14539
2022-03-14 09:48:36 -07:00
Harshavardhana
9c846106fa
decouple service accounts from root credentials (#14534)
changing root credentials makes service accounts
in-operable, this PR changes the way sessionToken
is generated for service accounts.

It changes service account behavior to generate
sessionToken claims from its own secret instead
of using global root credential.

Existing credentials will be supported by
falling back to verify using root credential.

fixes #14530
2022-03-14 09:09:22 -07:00
Harshavardhana
cf94d1f1f1
do not crash readXLMetaNoData - if the xl.meta has incorrect content (#14538)
```
tmp = buf[want:]
```

Would potentially crash when `buf` is truncated for some reason
and does not have the expected bytes, this is of course considered
not normal and is an odd situation. But we do not need to crash
here instead allow for errors to be returned and let callers handle
the errors.
2022-03-14 09:07:46 -07:00
Poorna
f8d6eaaa96
fix: regression from range GET proxy on replicated buckets #14345 (#14532)
Fixes: #14531
2022-03-11 15:56:49 -08:00
Poorna
75b925c326
Deprecate root disk for disk caching (#14527)
This PR modifies #14513 to issue a deprecation
warning rather than reject settings on startup.
2022-03-10 18:42:44 -08:00
Harshavardhana
91d419ee6c
warn issues about large block I/O performance for Linux older than 4.0.0 (#14524)
This PR simply adds a warning message when it detects older kernel
versions and warn's them about potential performance issues on this
kernel.

The issue can be seen only with parallel I/O across all drives
on denser setups such as 90 drives or 45 drives per server configurations.
2022-03-10 17:36:13 -08:00
Harshavardhana
41079f1015
heal: remove blocking healDiskMeta upon startup (#14514)
This type of code is not necessary, read's of all
metadata content at `.minio.sys/config` automatically
triggers healing when necessary in the GetObjectNInfo()
call-path.

Having this code is not useful and this also adds to
the overall startup time of MinIO when there are lots
of users and policies.
2022-03-10 02:45:14 -08:00
Poorna
712dfa40cd
Add missing site replication hook for clearing sse config (#14512) 2022-03-10 00:04:34 -08:00
Klaus Post
b890bbfa63
Add local disk health checks (#14447)
The main goal of this PR is to solve the situation where disks stop 
responding to operations. This generally causes an FD build-up and 
eventually will crash the server.

This adds detection of hung disks, where calls on disk get stuck.

We add functionality to `xlStorageDiskIDCheck` where it keeps 
track of the number of concurrent requests on a given disk.

A total number of 100 operations are allowed. If this limit is reached 
we will block (but not reject) new requests, but we will monitor the 
state of the disk.

If no requests have been completed or updated within a 15-second 
window, we mark the disk as offline. Requests that are blocked will be 
unblocked and return an error as "faulty disk".

New requests will be rejected until the disk is marked OK again.

Once a disk has been marked faulty, a check will run every 5 seconds that 
will attempt to write and read back a file. As long as this fails the disk will 
remain faulty.

To prevent lots of long-running requests to mark the disk faulty we 
implement a callback feature that allows updating the status as parts 
of these operations are running.

We add a reader and writer wrapper that will update the status of each 
successful read/write operation. This should allow fine enough granularity 
that a slow, but still operational disk will not reach 15 seconds where 
50 operations have not progressed.

Note that errors themselves are not enough to mark a disk faulty. 
A nil (or io.EOF) error will mark a disk as "good".

* Make concurrent disk setting configurable via `_MINIO_DISK_MAX_CONCURRENT`.

* de-couple IsOnline() from disk health tracker

The purpose of IsOnline() is to ensure that we
reconnect the drive only when the "drive" was

- disconnected from network we need to validate
  if the drive is "correct" and is the same drive
  which belongs to this server.

- drive was replaced we have to format it - we
  support hot swapping of the drives.

IsOnline() is not meant for taking the drive offline
when it is hung, it is not useful we can let the
drive be online instead "return" errors for relevant
calls.

* return errFaultyDisk for DiskInfo() call

Co-authored-by: Harshavardhana <harsha@minio.io>

Possible future Improvements:

* Unify the REST server and local xlStorageDiskIDCheck. This would also improve stats significantly.
* Allow reads/writes to be aborted by the context.
* Add usage stats, concurrent count, blocked operations, etc.
2022-03-09 11:38:54 -08:00
Poorna
46ba15ab03
Return MethodNotAllowed if force del on replicated bucket (#14505) 2022-03-08 14:28:51 -08:00
Poorna
1e39ca39c3
fix: consistent replies for incorrect range requests on replicated buckets (#14345)
Propagate error from replication proxy target correctly to the client if range GET is unsatisfiable.
2022-03-08 13:58:55 -08:00
Krishnan Parthasarathi
80ef1ae51c
Simplify assembling of tierStats from data-usage (#14504) 2022-03-08 12:08:29 -08:00
Krishna Srinivas
4d0715d226
Implement netperf for "mc support perf net" (#14397)
Co-authored-by: Klaus Post <klauspost@gmail.com>
2022-03-08 09:54:38 -08:00
Klaus Post
8a274169da
heal: Fix first entry on dangling (#14495)
Instead of the first, the last entry was returned
pointerizing the range value.
2022-03-08 09:04:20 -08:00
Harshavardhana
5d6f6d8d5b
create missing .minio.sys/config, .minio.sys/buckets during decommission (#14497) 2022-03-07 16:18:57 -08:00
Anis Elleuch
bacf6156c1
metrics: Avoid crash when fetching tier metrics (#14493)
Data usage does not always contain tiering info even if the data usage
information is valid. Avoid a crash in that case.

(e.g. the scanner scanned the namespace, the user enables tiering,
prometheus scrapes the server before the scanner gets a chance to
update the data usage with new tiering information)
2022-03-07 10:59:32 -08:00
Klaus Post
1d1b213f1f
scanner: Consider preselection bias when selecting for Healing (#14492)
Healing decisions would align with skipped folder counters. This can lead to files 
never being selected for heal checks on "clean" paths.

Use different hashing methods and take objectHealProbDiv into account when 
calculating the cycle.

Found by @vadmeste
2022-03-07 09:25:53 -08:00
Harshavardhana
92a77cc78e
update pkg v1.1.20 to reload certs in k8s always (#14470) 2022-03-04 20:34:39 -08:00
Harshavardhana
b0c84e3de7
fix: deleteVersions causing xl.meta to have empty Versions[] slice (#14483)
This is a side-affect of the optimization done in PR #13544 which
causes a certain type of delete operations on given object versions
can cause lastVersion indication to be skipped, which leads to
an `xl.meta` where Versions[] slice is empty while the entire
file is intact by itself.

This PR tries to ensure that such files are visible and deletable
by regular means of listing as null 'delete-marker' and also
avoid the situation where this potential issue might arise.
2022-03-04 20:01:26 -08:00
Anis Elleuch
bbc914e174
heal: Do not override heal scan mode mode if it is set (#14476)
mc admin heal has --scan=deep flag which enforces bitrot checking 
when doing the healing.

Do not force override an existing heal scan option.
2022-03-04 18:25:06 -08:00
Anis Elleuch
3fca4055d2
heal: Re-heal an object when a corruption is found during normal scan (#14482)
When scanning using normal mode, HealObject() can report an 
error saying that it found a corrupted part. This doesn't have 
when HealObject() is called with bitrot scan flag. However, when 
this happens, we can still restart HealObject() with the bitrot scan.

This is also important because this means the scanner and the 
new disks healer will not be able to heal an object that doesn't 
exist in a specific disk and has corruption in another disk.

Also without this PR, mc admin heal command without bitrot will report
an error.
2022-03-04 18:24:34 -08:00
Harshavardhana
66afa16aed
canceled PUTs throw frivolous logs (#14475)
remote drives might throw frivolous logs,
if the caller canceled the PUT operation
in such scenarios there is no reason to log.
2022-03-04 10:31:33 -08:00
Harshavardhana
0e3bafcc54
improve logs, fix banner formatting (#14456) 2022-03-03 13:21:16 -08:00
Andreas Auernhammer
b48f719b8e
kes: remove unnecessary error conversion (#14459)
This commit removes some duplicate code that
converts KES API errors.

This code was added since KES `0.18.0` changed
some exported API errors. However, the KES SDK
handles this error conversion itself.
Therefore, it is not necessary to duplicate this
behavior in MinIO.

See: 21555fa624/error.go (L94)

Signed-off-by: Andreas Auernhammer <hi@aead.dev>
2022-03-03 09:42:37 -08:00
Lenin Alevski
289fcbd08c
KES dependency upgrade (#14454)
- Updating KES dependency to v.0.18.0
- Fixing incompatibility issue when checking for errors during KES key creation

Signed-off-by: Lenin Alevski <alevsk.8772@gmail.com>
2022-03-02 23:03:40 -08:00