Re: Improve "direct" serialization

2016-10-14 Thread Valentin Kulichenko
Vova, You still can't write the first buffer to channel before the whole message is serialized. Are you going to have multiple write buffers? I'm confused :) -Val On Fri, Oct 14, 2016 at 1:49 PM, Vladimir Ozerov wrote: > Val, > > No need to copy on write. You simply

Re: Improve "direct" serialization

2016-10-14 Thread Valentin Kulichenko
Vova, I meant the copy on write. To know the length you need to fully marshal message first. This means that you will always copy the array before writing to channel. Unless I'm missing something, this eliminates the purpose of direct serialization. -Val On Thu, Oct 13, 2016 at 11:09 PM,

[GitHub] ignite pull request #1161: Ignite 1.6.10 opt direct write

2016-10-14 Thread devozerov
GitHub user devozerov opened a pull request: https://github.com/apache/ignite/pull/1161 Ignite 1.6.10 opt direct write You can merge this pull request into a Git repository by running: $ git pull https://github.com/gridgain/apache-ignite ignite-1.6.10-opt-direct-write

Re: Improve "direct" serialization

2016-10-14 Thread Yakov Zhdanov
I already tried smth like that when tried to make marshalling parallel. This is how I tried to reapproach it. 1. allocate set of direct buffers per each session (connection). that was 1 large buffer, but sliced with smaller ones over large offheap array. 2. each thread acquires chunk by chunk

[jira] [Created] (IGNITE-4086) Binary objets: Do not use BinaryField when comparing objects with the same schema.

2016-10-14 Thread Vladimir Ozerov (JIRA)
Vladimir Ozerov created IGNITE-4086: --- Summary: Binary objets: Do not use BinaryField when comparing objects with the same schema. Key: IGNITE-4086 URL: https://issues.apache.org/jira/browse/IGNITE-4086

[jira] [Created] (IGNITE-4085) Binary objets: Compare fields of well-known types without deserialization.

2016-10-14 Thread Vladimir Ozerov (JIRA)
Vladimir Ozerov created IGNITE-4085: --- Summary: Binary objets: Compare fields of well-known types without deserialization. Key: IGNITE-4085 URL: https://issues.apache.org/jira/browse/IGNITE-4085

[jira] [Created] (IGNITE-4084) Web Console: Register lodash in frontend tests globaly.

2016-10-14 Thread Alexey Kuznetsov (JIRA)
Alexey Kuznetsov created IGNITE-4084: Summary: Web Console: Register lodash in frontend tests globaly. Key: IGNITE-4084 URL: https://issues.apache.org/jira/browse/IGNITE-4084 Project: Ignite

[jira] [Created] (IGNITE-4083) Refactor services to classes

2016-10-14 Thread Alexey Kuznetsov (JIRA)
Alexey Kuznetsov created IGNITE-4083: Summary: Refactor services to classes Key: IGNITE-4083 URL: https://issues.apache.org/jira/browse/IGNITE-4083 Project: Ignite Issue Type: Sub-task

[jira] [Created] (IGNITE-4082) Refactor filters registration

2016-10-14 Thread Alexey Kuznetsov (JIRA)
Alexey Kuznetsov created IGNITE-4082: Summary: Refactor filters registration Key: IGNITE-4082 URL: https://issues.apache.org/jira/browse/IGNITE-4082 Project: Ignite Issue Type: Sub-task

[jira] [Created] (IGNITE-4080) Web console: Not work revert of node filter section on cache page

2016-10-14 Thread Vasiliy Sisko (JIRA)
Vasiliy Sisko created IGNITE-4080: - Summary: Web console: Not work revert of node filter section on cache page Key: IGNITE-4080 URL: https://issues.apache.org/jira/browse/IGNITE-4080 Project: Ignite

Re: Improve "direct" serialization

2016-10-14 Thread Vladimir Ozerov
Valya, Yes, in this design we will copy data into separate buffer on read. But what is important - it will happen only for message which is split between buffers. On Fri, Oct 14, 2016 at 2:33 AM, Valentin Kulichenko < valentin.kuliche...@gmail.com> wrote: > Vladimir, > > We don't write length