History log of /3.0.3-GA/ep-engine/ (Results 176 - 200 of 4208)
Revision (<<< Hide revision tags) (Show revision tags >>>)Date Author Comments
(<<< Hide modified files)
(Show modified files >>>)
0f4424d321-Jul-2014 Mike Wiederhold <mike@couchbase.com>

Remove log messages that were used ot diagnose a warmup issue

These messages were added temporarily and are no longer neccessary
to keep in the code base.

Change-Id: I63ea88e375

Remove log messages that were used ot diagnose a warmup issue

These messages were added temporarily and are no longer neccessary
to keep in the code base.

Change-Id: I63ea88e3755ce2e63c35e629ccad1eff096cbe53
Reviewed-on: http://review.couchbase.org/39643
Reviewed-by: Sriram Ganesan <sriram@couchbase.com>
Tested-by: Michael Wiederhold <mike@couchbase.com>

show more ...

1e38cf4918-Jul-2014 Mike Wiederhold <mike@couchbase.com>

MB-11725: Add log message to help find cause of dataloss

There are two potential cases that might be the root cause of data
loss. One is that the parameters supplied to the backfill task

MB-11725: Add log message to help find cause of dataloss

There are two potential cases that might be the root cause of data
loss. One is that the parameters supplied to the backfill task are
incorrect and the other is that the backfill is actually done
improperly somewhere in couchstore. This log message will help us
narrow down where the issue is.

Change-Id: I31fd8c001ac220287fb2072b94aef95bede77da1
Reviewed-on: http://review.couchbase.org/39642
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: Michael Wiederhold <mike@couchbase.com>

show more ...

0c903de428-May-2014 Mike Wiederhold <mike@couchbase.com>

MB-11592: Create snapshots when getting items from the chk queues

This change introduces a new flag to indicate whether or not
ep-engine should create a new checkpoint for this snapshot.

MB-11592: Create snapshots when getting items from the chk queues

This change introduces a new flag to indicate whether or not
ep-engine should create a new checkpoint for this snapshot. This
flag is used internally by ep-engine and only ep-engine. We are
also changing the flags values for snapshot markers since they
weren't really flags previously. Below are the new values.

Disk 0x01
Memory 0x02
Checkpoint 0x04

Change-Id: I8a262eb7856c97e11e95570fbdaef82f3f79054a
Reviewed-on: http://review.couchbase.org/38779
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Michael Wiederhold <mike@couchbase.com>

show more ...

996b577810-Jul-2014 Mike Wiederhold <mike@couchbase.com>

MB-11592: Use a queue_item in a MutationResponse instead of and Item

This will allow us to pull queued_items out of the CheckpointManager
and into and ActiveStream without adding any mem

MB-11592: Use a queue_item in a MutationResponse instead of and Item

This will allow us to pull queued_items out of the CheckpointManager
and into and ActiveStream without adding any memory overhead. This
also simplified the cleanup of a MutationResponse because we no
longer need to seperately delete the item contained inside this
class.

Change-Id: I0fc67ac66da6bd0c0ad0cd0369ee0a377d2b3bd9
Reviewed-on: http://review.couchbase.org/39283
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: Michael Wiederhold <mike@couchbase.com>

show more ...

c29bbd9919-Jul-2014 Sundar Sridharan <sundar.sridharan@gmail.com>

MB-11405 MB-11434 limit max writers to 8 (configurable)

In systems having 40+ cores, spawning 20 threads causes many
issues like heavy CPU and memory use.
Limit number of writers to

MB-11405 MB-11434 limit max writers to 8 (configurable)

In systems having 40+ cores, spawning 20 threads causes many
issues like heavy CPU and memory use.
Limit number of writers to 8, readers to 16
This change adds dynamic configurability to the shared thread pool.
It is now possible to tune a running system dynamically by setting limits
on the number of readers, writers, auxio and nonio threads using cbepctl
For example,
cbepctl set flush_param max_num_writers 1 (1 writer thread across buckets)
cbepctl set flush_param max_num_auxio 4
cbepctl set flush_param max_num_nonio 1
cbepctl set flush_param max_num_readers 1
Change-Id: Ie1314c2658792d6bd80d5f95fa57c94feb35b32b
Reviewed-on: http://review.couchbase.org/39475
Tested-by: Sundararaman Sridharan <sundar@couchbase.com>
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

ef5b71fd18-Jul-2014 Mike Wiederhold <mike@couchbase.com>

Return want more when noop or flow control is successful

We want the memcached layer to call into our upr connection if there
is any sort of success on the previous call.

Change

Return want more when noop or flow control is successful

We want the memcached layer to call into our upr connection if there
is any sort of success on the previous call.

Change-Id: I092f92ef5a1de937b015a2f91e17c4306943d023
Reviewed-on: http://review.couchbase.org/39554
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: Michael Wiederhold <mike@couchbase.com>

show more ...

380f889118-Jul-2014 Sundar Sridharan <sundar.sridharan@gmail.com>

MB-11760 track max purge seqno on compactions' deletes

Also update cachedVBStates post compaction

Change-Id: I30dd24ee56ddd9ac3af0f6b2677ed595ec808f59
Reviewed-on: http://review

MB-11760 track max purge seqno on compactions' deletes

Also update cachedVBStates post compaction

Change-Id: I30dd24ee56ddd9ac3af0f6b2677ed595ec808f59
Reviewed-on: http://review.couchbase.org/39506
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: Sundararaman Sridharan <sundar@couchbase.com>

show more ...

e616ac0417-Jul-2014 Sundar Sridharan <sundar.sridharan@gmail.com>

MB-11731 remove shard level locking from ExecutorPool

we no longer need to block threads at shard level since
locks are acquired at the vbucket level

Change-Id: Iebc368d243499b7

MB-11731 remove shard level locking from ExecutorPool

we no longer need to block threads at shard level since
locks are acquired at the vbucket level

Change-Id: Iebc368d243499b76b5cf1f4f0d50c487866960dc
Reviewed-on: http://review.couchbase.org/39502
Reviewed-by: abhinav dangeti <abhinav@couchbase.com>
Tested-by: Sundararaman Sridharan <sundar@couchbase.com>

show more ...

dca5ef3218-Jul-2014 abhinavdangeti <abhinav@couchbase.com>

MB-11731: Vbucket-level locking as opposed to shard-level

For flusher tasks:
- flushVBucket
- compactVBucket
- snapshot task
- vbDelete

Change-Id: I0f17ed7dacdc23556

MB-11731: Vbucket-level locking as opposed to shard-level

For flusher tasks:
- flushVBucket
- compactVBucket
- snapshot task
- vbDelete

Change-Id: I0f17ed7dacdc23556f110e271048836ed6701685
Reviewed-on: http://review.couchbase.org/34501
Reviewed-by: Sundararaman Sridharan <sundar@couchbase.com>
Tested-by: abhinav dangeti <abhinav@couchbase.com>

show more ...

76d6ddec18-Jul-2014 abhinavdangeti <abhinav@couchbase.com>

MB-11698: Release reference to all connections in upr upon shutdown

Change-Id: I5759f89dcf1faaa5f7902fdb8fa08604a34f5814
Reviewed-on: http://review.couchbase.org/39514
Reviewed-by: C

MB-11698: Release reference to all connections in upr upon shutdown

Change-Id: I5759f89dcf1faaa5f7902fdb8fa08604a34f5814
Reviewed-on: http://review.couchbase.org/39514
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: abhinav dangeti <abhinav@couchbase.com>

show more ...

b6534b8a14-Jul-2014 Sundar Sridharan <sundar.sridharan@gmail.com>

MB-11434 distributed sleep on taskQ

Make shared thread pool workers sleep inside their respective
TaskQueue mutexes as opposed to a single global mutex to reduce
the CPU overhead of

MB-11434 distributed sleep on taskQ

Make shared thread pool workers sleep inside their respective
TaskQueue mutexes as opposed to a single global mutex to reduce
the CPU overhead of putting threads to sleep and waking them up.
We still try to wake only as many threads as ready tasks.
First try waking local threads, if still more tasks are ready,
then visit other TaskQueues to wake their sleeping threads

Results in 15% improvement in view operations local testing
Lowered scheduling overhead with larger number of threads

Change-Id: I8ca746a696b4b2166f327385125b8510c0567407
Reviewed-on: http://review.couchbase.org/39210
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: Sundararaman Sridharan <sundar@couchbase.com>

show more ...

299deafd04-Jul-2014 Sriram Ganesan <sriram@couchbase.com>

MB-9471: add atomic replace operation

Add an atomic replace operation

Change-Id: I3fa454301ac3745d960dbef0295996161ee1a8dd
Reviewed-on: http://review.couchbase.org/39109
Rev

MB-9471: add atomic replace operation

Add an atomic replace operation

Change-Id: I3fa454301ac3745d960dbef0295996161ee1a8dd
Reviewed-on: http://review.couchbase.org/39109
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Sriram Ganesan <sriram@couchbase.com>

show more ...

2ae8baaa16-Jul-2014 abhinavdangeti <abhinav@couchbase.com>

MB-11749: Prevent GetLocked response from masking NOT_MY_VB

Change-Id: Ibd1e8fa8a1635746c838a753b46d3e93096fd5b8
Reviewed-on: http://review.couchbase.org/39450
Reviewed-by: Sundarara

MB-11749: Prevent GetLocked response from masking NOT_MY_VB

Change-Id: Ibd1e8fa8a1635746c838a753b46d3e93096fd5b8
Reviewed-on: http://review.couchbase.org/39450
Reviewed-by: Sundararaman Sridharan <sundar@couchbase.com>
Tested-by: abhinav dangeti <abhinav@couchbase.com>

show more ...

3c9992a416-Jul-2014 abhinavdangeti <abhinav@couchbase.com>

MB-11726: QueueDirty when item expired on warmup

The return value for unlocked_softDelete is
NOT_FOUND even when an expired item is deleted.
Thus in the deleteItem scenario, we will

MB-11726: QueueDirty when item expired on warmup

The return value for unlocked_softDelete is
NOT_FOUND even when an expired item is deleted.
Thus in the deleteItem scenario, we will need to
queue a dirty item, if v is not NULL.

Change-Id: I78bfa5f082aebb0e2760d761f00fd0a37744e0c1
Reviewed-on: http://review.couchbase.org/39423
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: abhinav dangeti <abhinav@couchbase.com>

show more ...

f12b299d14-Jul-2014 abhinavdangeti <abhinav@couchbase.com>

Notify checkpoint creation events to paused UPR conns

- Notify these events to corresponding paused upr
connections along with tap connections.

Change-Id: I0c820c48953f63d590a75

Notify checkpoint creation events to paused UPR conns

- Notify these events to corresponding paused upr
connections along with tap connections.

Change-Id: I0c820c48953f63d590a7538041ae68b1b382a251
Reviewed-on: http://review.couchbase.org/39367
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: abhinav dangeti <abhinav@couchbase.com>

show more ...

3c8674b314-Jul-2014 Mike Wiederhold <mike@couchbase.com>

MB-11711: Don't log get errors for failed meta only gets

Failures for these are expected since we are checking to see if a
deleted item exists. As a result these should not be logged.

MB-11711: Don't log get errors for failed meta only gets

Failures for these are expected since we are checking to see if a
deleted item exists. As a result these should not be logged.

Change-Id: I40825d6a3cb780b647be258faeb9bc5e3ae99095
Reviewed-on: http://review.couchbase.org/39356
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: Michael Wiederhold <mike@couchbase.com>

show more ...

a68c6dcb14-Jul-2014 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-11661 Disable checkpoint merge support by default.

Merging closed checkpoints in a replica vbucket was mainly
supported to reduce the memory overhead in the replica vbucket,
which

MB-11661 Disable checkpoint merge support by default.

Merging closed checkpoints in a replica vbucket was mainly
supported to reduce the memory overhead in the replica vbucket,
which performs the replication to another replica vbucket.
For example, in the replication chain A->B->C, merging closed
checkpoints can be performed on the replica B if the replica C
is overloaded and constantly backs off the replication from the
replica B.

As of 3.0, we switch to the star replication, which doesn't
require supporting checkpoint merge operation. Thus, this change
disables the checkpoint merge operation by default, but still
allows us to enable / disable it dynamically at runtime.

Change-Id: I46b17030f35a5dad9575a6ecd2fde33f70b497bc
Reviewed-on: http://review.couchbase.org/39342
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

c1d594a312-Jul-2014 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-11661 Move cursor to the next checkpoint if reached to the end

If a cursor is already reached to the end of its current
checkpoint, then the cursor can be moved to the next checkpoint

MB-11661 Move cursor to the next checkpoint if reached to the end

If a cursor is already reached to the end of its current
checkpoint, then the cursor can be moved to the next checkpoint.
In this way, a checkpoint can be immediately freed from memory
if the checkpoint doesn't have any cursors.

Change-Id: I378d0e2527610d7ad7773ebd35e3814d31bb7777
Reviewed-on: http://review.couchbase.org/39339
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

45686f1512-Jul-2014 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-11661 Remove unreferenced closed checkpoints by item pager.

This change allows the item pager to remove unreferenced closed
checkpoints, so that it can free some memory before attempt

MB-11661 Remove unreferenced closed checkpoints by item pager.

This change allows the item pager to remove unreferenced closed
checkpoints, so that it can free some memory before attempting to
eject items from the vbucket hash table. In this way, we can
avoid ejecting innocent (frequently accessed) items from hashtable.

Change-Id: I1ec971ce6de348f4320679f18d844c3ac548345d
Reviewed-on: http://review.couchbase.org/39335
Reviewed-by: abhinav dangeti <abhinav@couchbase.com>
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

d621da3f12-Jul-2014 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-11661 Don't check the checkpoint manager upon ejecting an item

As a checkpoint has blob instances inside, we don't need to check
the checkpoint manager to see if we can eject an item

MB-11661 Don't check the checkpoint manager upon ejecting an item

As a checkpoint has blob instances inside, we don't need to check
the checkpoint manager to see if we can eject an item from the
hash table.

Change-Id: I57fc887dc80b88ba275bc50ef7b7f8a5ff45e8c7
Reviewed-on: http://review.couchbase.org/39334
Reviewed-by: abhinav dangeti <abhinav@couchbase.com>
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

180487be12-Jul-2014 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-11553 Adjust the checkpoint creation interval.

This change reduces the checkpoint creation interval to
mitigate the memory overhead caused by having blob instances
inside the open

MB-11553 Adjust the checkpoint creation interval.

This change reduces the checkpoint creation interval to
mitigate the memory overhead caused by having blob instances
inside the open checkpoint. If a checkpoint creation interval
is large, it can cause significant memory overhead due to blob
instances inside the current open checkpoint.

Note that we also limit the number of checkpoints in memory, so
this change won't allow us to keep creating a new checkpoint if
the limit is reached.

Change-Id: I33119ef8b539d5f0209b64bcfcfcbd82632ae7e1
Reviewed-on: http://review.couchbase.org/39333
Reviewed-by: Sundararaman Sridharan <sundar@couchbase.com>
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

47523d2e11-Jul-2014 Chiyoung Seo <chiyoung.seo@gmail.com>

Maintain a cursor's offset in a consistent way.

This change makes sure that a cursor's offset includes checkpoint
meta items (e.g., checkpoint_start, checkpoint_end).
However, when w

Maintain a cursor's offset in a consistent way.

This change makes sure that a cursor's offset includes checkpoint
meta items (e.g., checkpoint_start, checkpoint_end).
However, when we calculate the number of items remaining for
persistence or replication, we should not consider those meta
items.

Change-Id: I8a90c347c163674decdb7ed1b5eb824a5b9d4f86
Reviewed-on: http://review.couchbase.org/39298
Reviewed-by: abhinav dangeti <abhinav@couchbase.com>
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

eaad07a710-Jul-2014 Mike Wiederhold <mike@couchbase.com>

Add stats to indicate the snapshot a PassiveStream is receiving

These stats will help with debugging and will also be useful with
future commits that require information about the snapsh

Add stats to indicate the snapshot a PassiveStream is receiving

These stats will help with debugging and will also be useful with
future commits that require information about the snapshot that is
currently being processed.

Change-Id: I2ed88b0e064ee7744c02d80a66b545b24d5e11a0
Reviewed-on: http://review.couchbase.org/39281
Reviewed-by: Chiyoung Seo <chiyoung@couchbase.com>
Tested-by: Michael Wiederhold <mike@couchbase.com>

show more ...

d6defe6210-Jul-2014 Chiyoung Seo <chiyoung.seo@gmail.com>

Reduce the lock contention in notifying UPR connections of an event

This change uses partitioned spinlocks to reduce the lock
contention in notifying UPR connections of mutation events.

Reduce the lock contention in notifying UPR connections of an event

This change uses partitioned spinlocks to reduce the lock
contention in notifying UPR connections of mutation events.

Change-Id: I0e2898f8e10efcbf76ae200f7d9a0f42ebe4badd
Reviewed-on: http://review.couchbase.org/39254
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

d9f3922509-Jul-2014 Chiyoung Seo <chiyoung.seo@gmail.com>

Move ConnMap::notifyVBConnections to TapConnMap.

ConnMap::notifyVBConnections function is only used by TapConnMap.

Change-Id: If0eec43dc07253fa9c757910bb3ff110512220b3
Reviewed-

Move ConnMap::notifyVBConnections to TapConnMap.

ConnMap::notifyVBConnections function is only used by TapConnMap.

Change-Id: If0eec43dc07253fa9c757910bb3ff110512220b3
Reviewed-on: http://review.couchbase.org/39253
Reviewed-by: Michael Wiederhold <mike@couchbase.com>
Tested-by: Chiyoung Seo <chiyoung@couchbase.com>

show more ...

12345678910>>...169