Re: Improve the process of removing bookies from a cluster

Glad to see this thread. This is one of the biggest limitations to autoscaling. On Tue, Sep 7, 2021 at 6:11 AM Jonathan Ellis wrote: > On Tue, Sep 7, 2021 at 8:05 AM Ivan Kelly wrote: > > > Hi Yang, > > > > > Autoscaling is exactly one motivation for me to bring this topic up. I > > >

Re: Running without journal

can completely avoid journal writes with ELPL + flush on close. Thanks, JV On Mon, May 3, 2021 at 8:34 AM Anup Ghatage wrote: > HI! > > I know we are interested in this for sure. (cc @Venkateswara Rao Jujjuri > ) > Is this similar to Matteo Merli's PR which I found was simple and still

Re: NPE in pendingAddOp

But post recycle should not result in this scenario as I mentioned in my comment. On Tue, Feb 16, 2021 at 2:49 PM Andrey Yegorov wrote: > Simple check for null won't prevent timing out wrong (post recycle/reuse) > handle. > > > On Tue, Feb 16, 2021 at 14:38 Venkateswara Rao J

Re: NPE in pendingAddOp

gt; > > Enrico > > > > Il giorno mar 16 feb 2021 alle ore 19:50 Venkateswara Rao Jujjuri < > > jujj...@gmail.com> ha scritto: > > > > > Ignore my comment about different thread, I see that > timeoutQuorumWait() > > is > > > run thr

Re: NPE in pendingAddOp

semble changes. On Tue, Feb 16, 2021 at 10:28 AM Venkateswara Rao Jujjuri wrote: > We have observed NPE in pendingAddOp in this line > <https://github.com/apache/bookkeeper/blob/master/bookkeeper-server/src/main/java/org/apache/bookkeeper/client/PendingAddOp.java#L173>. > > This l

NPE in pendingAddOp

We have observed NPE in pendingAddOp in this line . This looks like a race between execution of recyclePendAddOpObject() in OSE context and maybeTimeout() in

Re: Unbounded memory usage for WQ > AQ ?

On Mon, Jan 18, 2021 at 10:53 AM Sijie Guo wrote: > > One concern for me in this thread is case (3). I'd expect a client that > doesn't crash to not give up, and eventually replace the bookie if it is > unresponsive. > > The current implementation doesn't retry replacing a bookie if an entry is

Re: Unbounded memory usage for WQ > AQ ?

integrity check that Ivan worked on, when run periodically > will be able to repair that hole. > > Jack > > On Sat, Jan 9, 2021 at 1:06 AM Venkateswara Rao Jujjuri > > wrote: > > > [ External sender. Exercise caution. ] > > > > On Fri, Jan 8, 2021 at 2:29 PM

Re: Unbounded memory usage for WQ > AQ ?

On Fri, Jan 8, 2021 at 2:29 PM Matteo Merli wrote: > On Fri, Jan 8, 2021 at 2:15 PM Venkateswara Rao Jujjuri > wrote: > > > > > otherwise the write will timeout internally and it will get replayed > to a > > new bookie. > > If Qa is met and the writes of

Re: Unbounded memory usage for WQ > AQ ?

> otherwise the write will timeout internally and it will get replayed to a new bookie. If Qa is met and the writes of Qw-Qa fail after we send the success to the client, why would the write replayed on a new bookie? On Fri, Jan 8, 2021 at 1:47 PM Matteo Merli wrote: > On Fri, Jan 8, 2021 at

Re: [ANNOUNCE] New Committer: Anup Ghatage

Congratulations Anup!! On Wed, Oct 21, 2020 at 8:43 AM Anup Ghatage wrote: > Thank you! > I am excited to be a part of this passionate community and hope I can > contribute to making it even better. > > Regards, > Anup > > On Wed, Oct 21, 2020 at 2:05 AM Enrico Olivelli > wrote: > > > The

Re: Re-working the BookKeeper site

+1 I really like the layout. Great job Anup. On Mon, Aug 10, 2020 at 5:52 AM Enrico Olivelli wrote: > Anup, > do you have any news ? > I am working on a BP and actually building the website is really hard. > > It would be super to be able to setup your idea within a couple of months > > thanks

Re: Slack channel for HerdDB hosted on BK slack

+1 On Wed, Jul 8, 2020 at 8:53 PM Sijie Guo wrote: > +1 > > On Wed, Jul 8, 2020 at 1:34 AM Enrico Olivelli > wrote: > > > Hi, > > Can I create an #herddb channel on our BookKeeper slack space ? > > > > After my talk at PulsarSummit we started having a few new contacts on > > herddb-dev mailing

Question on disableEnsembleChange

I am looking at a feature to disableEnsembleChanges If the disableEnsembleChangeFeature

Re: BP-38 Publish Bookie Service Info on Metadata Service

>The client can derive bookieId from a BookieSocketAddress. Any reason to tie the bookieId to the hardware? I may be missing something, but the whole BP is to give flexibility of Bookie changing its end points. If we make it a UUID, then it is independent and more flexible right? On Wed, Mar 11,

Re: Bookkeeper stickers?

+1 On Thu, Nov 14, 2019 at 8:00 AM Anup Ghatage wrote: > That would be awesome! > What can we do for those of us who can't attend the events but would still > like the stickers? > > Regards, > Anup > > On Thu, Nov 14, 2019, 5:06 AM Enrico Olivelli wrote: > > > Hi, > > > > We do not have Apache

Re: Journal Corruption

s been > corrupted. > > We can't reliably detect which of the two cases happened, this is bad. > Even turning off preallocation won't help. > > We can fix the issue just by considering that we reached the end of the > journal but if the file was corrupted we may lose important bits,

Journal Corruption

We have observed Journal Corruption while replaying the journal log. I could be missing something but I don't see we have clear indication of where journal file ends. In the Journal.java:scanJournal() we have multiple breaks but mostly we assume either the journal file ends in the right place or

Re: Apache Bookkeeper Checksum Validation

On Fri, Oct 4, 2019 at 12:16 AM Enrico Olivelli wrote: > Karan, > > Il giorno gio 3 ott 2019 alle ore 23:41 Karan Mehta > ha scritto: > > > Thanks for the feedback. I will create a BP soon. > > > > > I won't shutdown the bookie, simply fail the write. It may happen in > case > > of a partial

Re: Bug in OnClusterChanged() ?

()) { this.readOnlyBookies = ImmutableSet.copyOf(readOnlyBookies); } On Fri, Jul 12, 2019 at 9:25 AM Venkateswara Rao Jujjuri wrote: > Not yet; may be the scope/window is extremely tiny. For this to be a > problem, only one node has to become RO->Offline. > If more than one node becomes RO then w

Re: Bug in OnClusterChanged() ?

anyone have a chance to take a look? > > Enrico > > Il mer 12 giu 2019, 19:26 Venkateswara Rao Jujjuri ha > scritto: > > > I am looking at onClusterChanged() in > > TopologyAwareEnsemblePlacementPolicy.java > > and I believe we don't handle the following ca

Bug in OnClusterChanged() ?

I am looking at onClusterChanged() in TopologyAwareEnsemblePlacementPolicy.java and I believe we don't handle the following case. 1. Bookie Became RO. We remove this from known bookies and add it to readOnlyBookies. 2. Same bookie went down; Now the arguments, writableBookies has no change, and

Re: Changing ledger metadata to binary format

> "Let's decide this when we need it" Right. This is the time as we are trying to add fault domain info to the cookie. > to make a flag in the metadata store that we flip to enable it. Right I do recall the same. But given your proposal in this thread, all readers try to read in binary format,

Re: Changing ledger metadata to binary format

ata part. > that's why I sort of pulling in the metadata piece only. however if filling > in a big picture would help discussing this problem, I can drive the whole > picture > for this roll-back story. > > - Sijie > > On Mon, Jul 30, 2018 at 7:55 AM Venkateswara Rao Jujjuri

Re: Cookie for FaultDomain Info?

; > > Il lun 20 mag 2019, 07:54 Venkateswara Rao Jujjuri ha > scritto: > > > > we should take care of designing a better API for the placement policy > > +1 Our placement policy is super complex and confusing. > > > > > We could also take into account the abi

Re: Cookie for FaultDomain Info?

gnatures quite often, adding parameters, changing return > type > > We could also take into account the ability of adding labels/tags to > bookies. > > Enrico > > > > > > - Sijie > > > > On Sun, May 19, 2019 at 9:48 AM Venkateswara Rao Jujjuri <

Cookie for FaultDomain Info?

In the current code, bookie to faultDomain mapping is supplied through different methods. Salesforce uses a script to read yaml file which contains racks/machines mapping. But I am wondering why can't we put this info in the Cookie? Assuming that these machines can never move across fault zones.

Re: Long poll LAC returning immediately on fenced

Does the LAC change on that bookie if ledger is fenced? On Fri, Mar 29, 2019 at 6:49 AM Ivan Kelly wrote: > Hi folks, > > I'm seeing a problem where a bookie is getting hammer by long poll > requests. ~8000rps. This seems to be happening because the long poll > logic doesn't wait if the ledger

Re: Cutting 4.9.1

+1 On Wed, Mar 13, 2019 at 6:36 PM Sijie Guo wrote: > +1 > > On Wed, Mar 13, 2019 at 5:16 PM Enrico Olivelli > wrote: > > > Hi guys, > > I need to cut 4.9.1 because we are seeing very often this issue > > > > >

Re: How to handle stale metadata?

On Mon, Feb 18, 2019 at 5:49 PM Sijie Guo wrote: > On Tue, Feb 19, 2019 at 4:22 AM Venkateswara Rao Jujjuri < > jujj...@gmail.com> > wrote: > > > Recently we ran into a situation where the LedgerMetadataListener never > > returned/detected metadata change. Due to

How to handle stale metadata?

Recently we ran into a situation where the LedgerMetadataListener never returned/detected metadata change. Due to this reader had stale metadata and tried to read from bookies that no longer have that ledger, hence NoSuchLedgerExistsException was returned to the caller. 1. I wonder if

Re: Community Meetings 2019

Having one standard time is good. But there needs to be participation too, otherwise it won't be successful. So lets find a good time that everyone can join. Other proposal is to setup two meetings in a month, one is convenient for US and other is convenient for Asia/Europe. Personally I am fine

Re: ExplicitLAC consolidation

Thanks for bringing this up. To start with, can we put all forms on LAC in a doc? i.e we have more than one way to read and write LAC. 1. What are the ways to send LAC to Bookies? 2. What are the ways bookies store the LAC? 3. What are the ways client can learn about LAC and the interfaces and

Fwd: [apache/bookkeeper] Your project apache/bookkeeper is using buggy third-party libraries [WARNING] (#1896)

-- Forwarded message - From: FDU-SE-LAB Date: Sun, Jan 6, 2019 at 8:33 PM Subject: [apache/bookkeeper] Your project apache/bookkeeper is using buggy third-party libraries [WARNING] (#1896) To: apache/bookkeeper Cc: Subscribed Hi, there! We are a research team working on

Re: Clusterwide vs Client configuration for metadata format version

If it is client level configuration, in theory it is possible to have latest client create v3 ledger while bookies are still running in the older version right? Who can stop that? if we let that happen what happens to the replication logic? How can it handle the new ledger format? If we go with

Re: Community meeting ?

I agree; lets do that. On Wed, Dec 12, 2018 at 8:58 AM Enrico Olivelli wrote: > Hi guys, > tomorrow we would have the Community Meeting. > > I wonder if we would better to suspend such activity during Winter > Holidays. > > Maybe it would be a change to revive this date after a period of >

Re: Bug with blockAddCompletions decrement

On Mon, Dec 3, 2018 at 1:40 AM Ivan Kelly wrote: > > This may not be an issue with the master as we moved to immutable > metadata, > > Not an issue with master as blockAddCompletions has been replaced with > a simple boolean and failure handling changed to only deal with one > failure at a time.

Bug with blockAddCompletions decrement

This may not be an issue with the master as we moved to immutable metadata, but older releases have an issue with not decrementing blockAddCompletions. Sijie/Ivan/Sam can you validate this? blockAddCompletions gets incremented while initiating the ensemble change in handleBookieFailure().

Re: BookKeeper Board report draft - due to today

+1 Thanks Enrico. JV On Wed, Nov 14, 2018 at 2:15 PM Jia Zhai wrote: > +1, Thanks for the help Enrico, Seems only PMC Chair could do it. > > On Thu, Nov 15, 2018 at 2:42 AM Enrico Olivelli > wrote: > > > Sijie, > > can I submit the report or only the PMC chair can ? > > The tool requires an

Re: Community meeting today

Yeah; will we have anyone joining to talk about etcd? On Thu, Oct 18, 2018 at 1:19 AM Enrico Olivelli wrote: > Hi guys, > today we will have the community meeting. > > link to the agenda > > https://cwiki.apache.org/confluence/display/BOOKKEEPER/2018-10-18+Meeting+Notes > > It would be great to

Re: BookKeeper Community Meeting

Mine is iffy. If I can, I will join around 8:15 On Thu, Oct 4, 2018 at 12:48 AM Enrico Olivelli wrote: > Hi > I have created the wiki page for the meeting > > > https://cwiki.apache.org/confluence/display/BOOKKEEPER/2018-10-04+Meeting+Notes > > Unfortunately I won't attend this time > > >

Re: [DISCUSS] BP-35: 128 bits support

on from 64 bit to 128 bit. > > > > > > > > > > Okay > > > > > > Last comment: > > > We are going to have a lot of special cases in layout of data/zk ledger > > > manager, to handle scopeid = 0. > > > > > > > I

Re: [DISCUSS] BP-35: 128 bits support

Thanks a lot, Sijie for the awesome doc. Let's pool some more thoughts into this and size the work. Thanks, JV On Fri, Aug 17, 2018 at 2:36 PM, Sijie Guo wrote: > Hi all, > > As promised in last community meeting, I put up all the thoughts and > discussion with JV I had into a BP for

Re: Usefulness of ensemble change during recovery

I don't think it a good idea to leave the tail to the replication. This could lead to the perception of data loss, and it's more evident in the case of larger WQ and disparity with AQ. If we determine LLAC based on having 'a copy', which is never acknowledged to the client, and if that bookie goes

Re: Changing ledger metadata to binary format

d all the pieces and if they fit together. Enrico, are you driving the roll-back story? or whoever, can you please come up with a comprehensive proposal? Thanks, JV On Mon, Jul 30, 2018 at 8:05 AM, Enrico Olivelli wrote: > Il giorno lun 30 lug 2018 alle ore 16:55 Venkateswara Rao Jujjuri < &

Re: Changing ledger metadata to binary format

We have introduced customMetadata in the past and that was not mandatory. How did we make that work with text format? Also, my preference is to wait until we have a need to introduce a new field for this conversion if needed. JV On Mon, Jul 30, 2018 at 12:42 AM, Enrico Olivelli wrote: > Il

Re: BookKeeper code coverage incredibly dropped in June from 72% to 54% !!

I don't see bookkeeper-server in the https://coveralls.io/builds/17501203 report. Rest looks almost identical. That must be causing the overall drop. On Tue, Jul 24, 2018 at 8:20 AM, Enrico Olivelli wrote: > Hi, > In June, the 14th, code coverage dropped > > here: 72% >

Re: [DISCUSS] ExplicitLAC on the reader's side

+1 On Tue, Jul 10, 2018 at 1:11 AM, Enrico Olivelli wrote: > Hi, > Now that Charan is working on making ExplicitLAC persistent I would like to > start the discussion about merging the reader side view of LAC (ExplicitLAC > + Pibbybacked/regular LAC) > > Major points: > - Now (4.8) ExplicitLAC

Re: Bookie disappears from ZK but continues to be up and running - shall we add a self check ?

@Enrico Let me understand the issue: Bookies are up and running but ZK doesn't show bookies on the list. Do you see if session expired or not? or bookies are hung in some way? We have seen multiple situations in this area: 1. Bookie process is around, but zk session lost. Alost all the time we

Re: Scanning the list of entries present on a bookie

all or discuss at next Thursday meeting? On Sat, Apr 21, 2018 at 12:37 AM, Enrico Olivelli <eolive...@gmail.com> wrote: > Il sab 21 apr 2018, 09:11 Venkateswara Rao Jujjuri <jujj...@gmail.com> ha > scritto: > > > Sorry, maxEntryId can't be used for LAC. Let me review the

Re: Scanning the list of entries present on a bookie

Sorry, maxEntryId can't be used for LAC. Let me review the patch and respond tomorrow. :) I was mostly thinking of sync-on-close which is my use case. Intermittent syncs will need a more robust way to define the LAC. On Sat, Apr 21, 2018 at 12:00 AM, Venkateswara Rao Jujjuri < jujj...@gmail.

Re: Scanning the list of entries present on a bookie

@Enrico I thought I had a pretty simple view on this. 1. No ensemble changes allowed on a ledger in this mode. 2. A sync is sent to all bookies on the ensemble and it is required that the sync must be successful to proceed forward. 3. Sync and Write are serialized. or sync can return maxEntryId.

Re: Replication Worker and targetBookie.

On Thu, Mar 8, 2018 at 11:33 AM, Sijie Guo <guosi...@gmail.com> wrote: > On Thu, Mar 8, 2018 at 8:07 AM, Venkateswara Rao Jujjuri < > jujj...@gmail.com> > wrote: > > > On Thu, Mar 8, 2018 at 2:38 AM, Ivan Kelly <iv...@apache.org> wrote: > > > >

Re: Replication Worker and targetBookie.

On Thu, Mar 8, 2018 at 2:38 AM, Ivan Kelly wrote: > > Given that RackAwareEnsemble policy defaults to finding a replacement > > bookie within > > the same rack, when a bookie is lost in a rack, the entire cluster will > be > > replicating > > to the same 'rack'. This puts a lot

Replication Worker and targetBookie.

With the fixes to ISSUE #596 ISSUE #583(6fcabfc80c5bd6cdfa9252cdfc4ed209cc0620a6) which allowed auto replication should honor ensemble placement policy, this patch also removed `targetBookie` from ReplicationWorker which means any node can replicate 'to' any other node in the cluster. This is

Re: BookKeeper Durability issues/proposals

eate the corresponding > > BPs/issues for individual problems, so that we can move this stuff > forward. > > > > - Sijie > > > > On Tue, Jan 16, 2018 at 12:33 PM, Venkateswara Rao Jujjuri < > > jujj...@gmail.com> wrote: > > > >> Here is the

Re: BP-30: table service as a contrib module in bookkeeper

A great step to move forward. BP-29 and BP-30 along with reorganizing ZK will help the BK to shape perfect MDS abstraction. While BP-30 is ambitious, it is a perfect way to start ambitious projects. :) JV On Wed, Feb 7, 2018 at 6:49 AM, Enrico Olivelli wrote: > It is very

MetadataVersionException handling in doAsyncCloseInternal()

We have bunch of code in doAsyncCloseInternal() to handle MetadataVersionException. I am wondering if there is a valid case where we need to handle this. Stay with me. :) When do we get this error? 1. When the client tried to write the metadata twice. Same metadata twice because of the client

Re: BP-28: Etcd as metadata store

Thanks for pushing this Sijie. I had a quick glance at it and looks like this is a stand-alone/place-holder code, and not connected yet to kick tires. I was under the impression you did have something we can hook up and play with. I could be wrong. :) Not that its a big deal to build that

Re: [DISCUSS] Deprecate FlatLedgerManager

+1 On Thu, Feb 1, 2018 at 12:20 PM, Ivan Kelly wrote: > +1 > > Flat is an vestigial. Prereq to removal is a tool for upgrading ledger > metadata. > > -Ivan > > On Thu, Feb 1, 2018 at 8:14 PM, Sijie Guo wrote: > > Hi all, > > > > `FlatLedgerManager` is not

Re: [ANNOUNCE] Apache BookKeeper 4.6.1 released

Awesome work Enrico! Thanks a lot!! On Wed, Jan 31, 2018 at 12:59 PM, Ivan Kelly wrote: > Thanks for all your work in getting this out Enrico! > > On Wed, Jan 31, 2018 at 9:38 AM, Sijie Guo wrote: > > Congrats Enrico! Thank you so much for driving 4.6.1

Re: [VOTE] Release 4.6.1, release candidate #0

+1 Release notes is good checksums are good source and binary pages are good. On Sun, Jan 28, 2018 at 2:50 PM, Yiming Zang wrote: > +1 > > - MD5 SHA signature looks good > - Source code looks good > - Binary looks good > > On Sun, Jan 28, 2018 at 6:59 AM, David Rusek

Re: [DISCUSS] Thoughts on enabling rerunFailedTests in surefire?

Great Idea. In addition, I would like to propose : Strictly tests (especially CI tests) must not be flaky. It really doesn't carry much use. As everyone tends to ignore them. Step-1: Separate them into a different pool, and you won't get a red mark for failing this pool/group. Step-2: Fix each

BookKeeper Durability issues/proposals

Here is the document I wrote on the durability. Please review/comment. We can crate issues based on this. https://docs.google.com/document/d/1LYZSiJ2x5mXMOjQqMWU7ZBRJD8YVDkB-hRPZ474O7Qw/edit?usp=sharing -- Jvrao --- First they ignore you, then they laugh at you, then they fight you, then you

Re: BP14 help wanted

Thanks for the update Enrico. Is there any estimation on how long your priorities are going to be different? couple of weeks? or more than that? On Fri, Jan 12, 2018 at 11:21 AM, Enrico Olivelli wrote: > Hi BookKeepers, > During this period I have changed my priorities, I

Dec 14 2018 - MoM

1. The release is delayed because of licensing issue. 2. Sam informed that salesforce is in the process of upstreaming local changes. Expect to see lots of pull requests from us. 3. Charan requested the team, especially Enrico Olivelli

Re: [ANNOUNCE] Apache BookKeeper 4.5.1 released

Congrats and Great work Enrico!! Awesome Job. On Wed, Nov 22, 2017 at 6:29 PM, Matteo Merli wrote: > Great work Enrico! > > On Wed, Nov 22, 2017 at 12:53 PM Enrico Olivelli > wrote: > > > The Apache BookKeeper team is proud to announce Apache

Re: Question regarding Checkpoint logic in SortedLedgerStorage

Charan this looks like an issue to me. Do we have a defect/issue opened? On Fri, Oct 13, 2017 at 4:18 PM, Sijie Guo wrote: > Charan, > > Didn't mean to say the logic is correct. I was just trying to point out > the points that I remembered for checkpoint. > > I am currently

Re: [VOTE] Move completely to github

+1 On Mon, Oct 9, 2017 at 2:17 AM, Ivan Kelly wrote: > My vote is a +1 > > On Mon, Oct 9, 2017 at 11:17 AM, Ivan Kelly wrote: > > I forgot the timeframe. The deadline to vote is midday UTC, on > > Thursday 12th October. > > > > > > On Mon, Oct 9, 2017 at

Re: Cookies and empty disks

Can we have a doc to put all these things? Thread has grown enough to cause confusion. Immediate things. 1. Don't assume new bookie if journal dir is empty. 2. Put cookies through bookie format, and bookie never boots on an empty cookie or mismatched cookie. 3. We can live with operations

Re: Cookies and empty disks

> 2. introduce UUID or epoch in the cookie. client connection should carry > namespace uuid and bookie uuid when establishing the connection. > 3. work on BP-4 to have a complete lifecycle management to take bookie out > and add bookie out. > > 1 is the immediate fix, so correct op

Re: Cookies and empty disks

On Fri, Oct 6, 2017 at 10:01 AM, Ivan Kelly <iv...@apache.org> wrote: > On Fri, Oct 6, 2017 at 6:35 PM, Venkateswara Rao Jujjuri > <jujj...@gmail.com> wrote: > >> However, imagine that the fenced message is only in the journal on b2, > >> b2 crashes, s

Re: Cookies and empty disks

> However, imagine that the fenced message is only in the journal on b2, > b2 crashes, something wipes the journal directory and then b2 comes > back up. In this case what happened? 1. We have WQ = 1 2. We had data loss (crash and comeup clean) But yeah, in addition to dataloss we have fencing

Re: [DISCUSS] BP-16: remove zookeeper dependency from bookkeeper client

If the real use of this work item is to use: - Only one bookie - Bookie is the metadata server too Maybe it is ok. But I am worried about the *magnitude* of the code refactor to accommodate this. I really like the idea of finding an alternate to ZK, but I think we need to have that direction

Re: Relax durability

Hi all, It has been a great and lively discussion. I can say this is one of the highly trended topics in the recent BK community discussion. Kudos to Enrico for starting this. Enrico, Sijie and I met and discussed this further and came up with the following consensus on how to move forward. *

Re: [DISCUSS] BP-14 Relax Durability

moment adding a per-entry 'durability option' seems to be very > flexible and simple to implement, it does not prevent us from doing further > improvements, like namely skipping the journal. > > Enrico > > > > 2017-08-26 19:55 GMT+02:00 Enrico Olivelli <eolive...@gmai

Re: [DISCUSS] BP-14 Relax Durability

Hi all, As promised during Thursday call, here is my proposal. *NOTE*: Major difference in this proposal compared to Enrico’s is making the durability a property of the ledger(type) as

Re: [DISCUSS] BP-14 Relax Durability

Hi all, As promised during Thursday call, here is my proposal. *NOTE*: Major difference in this proposal compared to Enrico’s is making the durability a property of the ledger(type) as

Re: Relax durability

As I mentioned in my email, a mixture of sync/relaxed entries of a ledger with the combination of ensemble changes makes LAC inaccurate. Let us have a document and iterate over that before writing code. Thanks, JV On Mon, Aug 21, 2017 at 5:35 AM, Enrico Olivelli wrote: >

Re: Relax durability

On Thu, Aug 17, 2017 at 4:42 AM, Enrico Olivelli wrote: > Hi, > I am working with my colleagues at an implementation to relax the > constraint that every acknowledged entry must have been successfully > written and fsynced to disk at journal level. > > The idea is to have a

Re: [DISCUSS] Release 4.6.0 and 4.5.1

On Fri, Aug 11, 2017 at 10:39 PM, Enrico Olivelli wrote: > Il sab 12 ago 2017, 04:35 Jia Zhai ha scritto: > > > Hi, > > I would like to have a a try on 4.6.0. > > > > On Sat, Aug 12, 2017 at 10:25 AM, Sijie Guo wrote: > > > > >

Re: [ANNOUNCE] Apache BookKeeper 4.5.0 released

Thanks a lot Sijie for patiently walking me through the process. Now I have real appreciation for the release mangers. ;) On Fri, Aug 11, 2017 at 10:59 AM, Sijie Guo wrote: > Awesome! Well done! This is a great milestone to the bookkeeper community! > > Thanks JV for doing

Re: [ANNOUNCE] Apache BookKeeper 4.5.0 released

Thanks a lot Sijie for patiently walking me through the process. Now I have real appreciation for the release mangers. ;) On Fri, Aug 11, 2017 at 10:59 AM, Sijie Guo wrote: > Awesome! Well done! This is a great milestone to the bookkeeper community! > > Thanks JV for doing

Re: [DISCUSS] move github notifications to other mailing list

Also if there is a way, I would like github to send email to the tagged person in addition to alias. Not sure if github can support that, that way tagged person can get quicker attention instead of processing every email on the issues@ or dev@ list. Not sure if github can support that feature. JV

[RESULT] [VOTE] Release 4.5.0, release candidate #0

me...@apache.org> > wrote: > > > > > > > +1 > > > > > > > > Checked src and bin package > > > > * Signatures ok > > > > * Build > > > > * Rat > > > > * Run local bookie > > > >(I

[VOTE] Release 4.5.0, release candidate #0

Hi everyone, Please review and vote on the release candidate #0 for version 4.5.0, as follows: [ ] +1, Approve the release [ ] -1, Do not approve the release (please provide specific comments) The complete staging area is available for your review, which includes: * Release Notes [1] * The

Re: [VOTE] Slack Channel for BookKeeper

+1 Just curious on why decided to transfer rather than create a new one. Fine either way. On Fri, Jul 28, 2017 at 12:22 AM, Francesco Caliumi - Diennea < francesco.cali...@diennea.com> wrote: > +1 non binding > > On Thu, 2017-07-27 at 21:45 +0200, Ivan Kelly wrote: > > +1 > > On Thu, Jul 27,

Re: ZooKeeper-less - single bookie setup

We have inMemoryMetaStore.java already to store metadata locally isn't it? there are some tests that make use of that too. So if you don't need ZK for consensus and you can use this inMemoryMetaStore for metadata store. On Thu, Jul 27, 2017 at 12:42 AM, Sijie Guo wrote: > it

Re: BP-11: New BookKeeper Website

Awesome !! lets make it dense. :) On Tue, Jul 25, 2017 at 12:15 PM, Yiming Zang wrote: > This looks awesome! > > On Tue, Jul 25, 2017 at 12:09 PM, Sijie Guo wrote: > > > Hi all, > > > > Luc Perkins is helping on a new bookkeeper documentation site

Re: BookKeeper 4.5.0 performance regression ?

On Mon, Jul 24, 2017 at 3:06 AM, Enrico Olivelli wrote: > 2017-07-21 20:37 GMT+02:00 Enrico Olivelli : > > > > > > > Il ven 21 lug 2017, 20:32 Sijie Guo ha scritto: > > > >> As the discussion in a separate thread, it might be making

Re: ByteBuf memory leak after Netty 4 switch on the client API

Can we also add some stats around this to track these. ? Discipline around memory release is new concept to Java world. On Fri, Jul 21, 2017 at 12:59 AM Enrico Olivelli wrote: > Hi, > I have just file this issue > https://github.com/apache/bookkeeper/issues/271 > > After

Re: Question regarding Synchronization in InterleavedLedgerStorage

On Fri, Jul 14, 2017 at 6:00 PM, Sijie Guo wrote: > > > On Sat, Jul 15, 2017 at 8:06 AM, Charan Reddy G > wrote: > >> Hey, >> >> In InterleavedLedgerStorage, since the initial version of it ( >>

Re: Bookie Http Endpoint

+ Dustin On Mon, Jul 17, 2017 at 12:30 PM, Sijie Guo wrote: > + Yiming > > I would suggest the people who already started the implementations (either > from Twitter or Salesforce) taking the lead. because they either already > had the implementation or are working on the

Re: BookKeeper and code-coverage - JaCoco

Adding Dustin to the thread. On Wed, Jul 5, 2017 at 12:57 AM, Enrico Olivelli wrote: > I am attaching a report (I am using Google Drive as most email clients will > block attachments with html inside) . > Just untar and play with your browser > > > 2017-07-04 18:18

Re: BeWeekly Community Meeting

Today is my duty to drop kids, and I can join only after 8:30. Please go ahead and I will catch the second half. Thanks, JV On Thu, Jul 13, 2017 at 3:58 AM, Enrico Olivelli wrote: > Hi, > this is just a reminder and invitation for all the new contributors (like > David) to

Re: [GitHub] sijie commented on issue #210: BOOKKEEPER-1100: Add Http Server for Bookkeeper

Please add this to the agenda tomorrow. Dustin please plan on attending. On Wed, Jul 12, 2017 at 7:18 PM wrote: > sijie commented on issue #210: BOOKKEEPER-1100: Add Http Server for > Bookkeeper > URL: https://github.com/apache/bookkeeper/pull/210#issuecomment-314950842 > >

Re: Git protected branches

Awesome. !! On Tue, Jul 11, 2017 at 6:06 AM, Enrico Olivelli wrote: > The ticket has been closed. > The protection is on > > -- Enrico > > 2017-07-07 11:22 GMT+02:00 Enrico Olivelli : > > > > > > > 2017-07-07 1:51 GMT+02:00 Sijie Guo

Re: BookKeeper 4.5.0 performance regression ?

With Netty changes, lack of native epoll() has huge perf impact as per Kishore. Are you sure you are using epoll()? On Mon, Jul 10, 2017 at 1:49 AM, Enrico Olivelli wrote: > 2017-07-10 10:40 GMT+02:00 Sijie Guo : > > > Also one other thing to check is

Re: [ANNOUNCE] JV Jujjuri joins the Apache BookKeeper PMC

Thank you all!! On Fri, Jul 7, 2017 at 5:22 AM, Edward Ribeiro wrote: > Congrats, JV! > > Ed > > On Fri, Jul 7, 2017 at 7:39 AM, Jia Zhai wrote: > > > Congrats, JV! > > > > On Fri, Jul 7, 2017 at 6:18 PM, Flavio Junqueira wrote:

Re: [DISCUSS] BookKeeper - A High Performance and Low Latency Storage Service

Everything said on this thread is important and accurate. The description on the website must be a story rather than a blurb. We should talk about BK's strengths as Enrico pointed out, and because of its versatility it became fundamental building block for various other technologies and usecases.

  1   2   >