Boinc-client Version 6.x.x, Обсуждение работы шестой версии клиента Налаштування

[(_KoDAk_)]

ПОЛНАЯ история изменений версий BOINC с датами выхода релизов

Change Log для 6.11.хх

BOINC (6 - 6.10.58) Versions Change Log

BOINC 6.7/6.8/GR6.8 Change Log

Все версии боинка для закачки

ВСЕ ВЕРСИИ С 5-й по 6-ю <- РЕКОМЕНДУЕТСЯ КАЧАТЬ ОТСЮДА.

все версии, включая самые последние девелоперские!

официальный форум разработчиков (зарегистрироваться)

[(_KoDAk_)]

а как его сервисом повесить ?
+
BOINC 6.6.4 released for Windows, Windows x64, and Mac

Rom Walton wrote:

Howdy Folks,

This release has a bunch of new fixes for work-fetch and CPU scheduling.

Please report test results to http://boinc.berkeley.edu/alpha/

Thanks in advance.

----- Rom



Change Log:

- MGR: call UpdateSelection() from OnListRender() instead of from RestoreSelections(). Fixes #837.

- MGR: Suppress Skin Manager error messages by default; enable them only if the Manager is launched from the command line with an argument -c or --checkskins.

- client: if we're making an RPC to a project because of user request, clear the resource backoff times so that we potentially can ask the project for work.

- lib: comment out perror()s in connection code.

- client: remove the "deadlines_missed" and "overworked" clauses from RSC_WORK_FETCH::choose_project()

- client: restore notion of overworked; if a project is overworked for a resource R, don't fetch work for R unless there are idle instances

- GUI RPC: the "get all projects" RPC now also returns account managers

- GUI RPC: Fix compiler warning (missing return value).

- client: if user requests RPC, do it even if project is backed off

- manager: show backoff interval correctly

- client: update LTD correctly

- Work fetch / scheduler: There are two mechanisms to prevent the scheduler from sending jobs that won't finish by their deadline.

Simple mechanism:
The client sends the interval x for which CPUs are projected to be saturated.
Given a job with estimated duration y, the scheduler doesn't send it if x + y exceeds the delay bound. If it does send it, x is incremented by y.

Complex mechanism:
Client sends workload description.
Scheduler does EDF simulation, sees if deadlines are missed.
The only project using this AFAIK is BOINC alpha test.
Neither of these mechanisms takes coprocessors into account, and as a result jobs could be sent that are doomed to miss their deadline.

This checkin adds coprocessor awareness to the Simple mechanism.

Changes:
Client: compute estimated delay (i.e. time until non-saturation) for coprocessors as well as CPU. Send them in scheduler request as part of coproc descriptor.

- client: fixed bug that computed CPU estimated delay incorrectly

- client: the work request (req_secs) for a resource is the min of the project's share and the shortfall.

- client: computation of # idle CUDA instances was wrong

- client: tweak work fetch messages

- client: buffer 2000 messages instead of 1000

- client: work fetch fixes

- client: there was a problem with how the round simulator worked in the presence of coprocessors. The simulator maintained per-project queues of pending jobs. When a job finished (in the simulation) it would get one or more jobs from that project's pending queue.

The problem: this could cause "holes" in the scheduling of GPUs, and produce an erroneous nonzero shortfall for GPUs, leading to infinite work fetch.

The solution: maintain a separate (per-resource, not per--project) queue of pending coprocessor jobs. When a coprocessor job finishes, start pending jobs from the queue for that resource.

Another change: the simulator did strict reservation of coprocessors. If there are 2 instances of CUDA, and a 1-instance job is running in the simulation, it wouldn't start an additional 2-instance job. This also can cause erroneous nonzero shortfalls.

So instead, schedule coprocessors like CPUs, i.e. saturate them. This can cause distorted completion time estimates, but it's better than infinite work fetch.

- client: code cleanup