|
w********i
发帖数: 244 | 2 I have 4 Servers, split between two Datacenters in different countries. How
do I make this thing Highly available locally in 1 datacenter with failover
to the other datacenter? Thank you!!! |
|
t**r
发帖数: 3428 | 3 NVIDIA GeForce driver deployment in datacenters is forbidden now (nvidia.com)
good or bad? |
|
|
a***y
发帖数: 19743 | 5 觉得下面这段很有意思。
But as we're fond of pointing out, Google is essentially a maker of very
capital-intensive, full-custom, warehouse-scale computers—a "hardware
company," if you will. It monetizes those datacenters by keeping as many
users as possible connected to them, and by serving ads to those users. To
make this strategy work, it has to hire lots of software people, who can
write the Internet-scale apps (search, mainly) that keep users connected and
viewing ads. Since the price of Google ads is s... 阅读全帖 |
|
I*D
发帖数: 40035 | 6 Role Title Description Start Date End Date Status Level From
Level To Standard Role Work Location Role Specialty 1 Level 1
Role Specialty 1 Level 2 Role Specialty 1 Level 3 Role Specialty 1
Level 4 Role Specialty 1 Level 5 Skill & Proficiency
PeopleSoft Administrator This person will be part of a team that supports
a PeopleSoft Financial system with several associated custom applications
and batches using ASP .NET, Hyperion, PL/SQL, SQL, and SQR. This ... 阅读全帖 |
|
c*****i
发帖数: 631 | 7 客户有2个datacenter，一个在东岸，一个在西岸。video server在datacenter里面，
需要mcast video到全国的remote office。
现在remote office到datacenter的link不support mcast。建议的方法是setup gre
tunnel btw remote office
and datacenter，然后在gre tunnel上run mcast。
1。RPF的问题，因为每个remote office有2个gre tunnel到2个datacenter，static
mroute不太适合，如果用MBGP有什么问题吗
2。RP的问题，打算做anycast RP，一个datacenter 放一个RP，然后跑MSDP。 |
|
发帖数: 1 | 8 今天收到HR的team match邮件，有人可以大概说一下哪个组比较有前途吗？大组是UFO
UFO Accelerated Cluster Turn-up (ACT)
When Google builds data centers there is a lot of manual work that goes into
the planning. The purpose of ACT is to implement a process using automation
and new workflow systems to decrease the total time from planning stage to
bringing up clusters down to one-quarter the current time, or less. Right
now it's a catch up game because when we are rolling out new technologies
the manual side is still working on the ... 阅读全帖 |
|
r*****e
发帖数: 7853 | 9 SUGAR LAND, Texas, Nov. 07, 2017 (GLOBE NEWSWIRE) -- Applied Optoelectronics
, Inc. (AAOI), a leading provider of fiber-optic access network products for
the internet datacenter, cable broadband, fiber-to-the-home (FTTH) and
telecom markets, today announced financial results for its third quarter
ended Sept. 30, 2017.
“While our third quarter results were negatively impacted by lower demand
from a large customer, we continued to experience solid demand from our
other large datacenter customers, ... 阅读全帖 |
|
n**********l
发帖数: 271 | 10 Is it possible for discontiguous networks (for example, multiple datacenters
across the world) to use the same ASN? A private backbone connecting them
is a must?
Route reflector does not solve the discontiguous problem, does it?
I was asked a bunch of questions for a CDN network and last night I realized
everything I said would make no sense if it has a noncontiguous backbone.
AS65000 East coast datacenter -- AS 100 (Upstream1) -- AS65000 West coast
datacenter
AS65000 East coast datacenter -- AS... 阅读全帖 |
|
d****o
发帖数: 1055 | 11 对于大家复习design problem有帮助
互联网已经发展多年，其中不乏脱颖而出者，这些网站多数都已存在了接近10年或10
年以上，在如此长时间的发展过程中，除了业务上面临的挑战，在技术上也面临了很多
的挑战。我挑选了一些Alexa排名较前的网站(排名截止到2012年4月21 日)，看看它们
在技术上是如何应对业务发展过程中的挑战的。
Google 目前Alexa排名第1。它诞生于1997年，当时是一个研究性项目，每个月
build一次索引，build出来的索引通过sharding(shard by doc)的方式分散到多台服务
器(Index Server)上，具体的网页数据同样通过sharding的方式分散到多台服务器(Doc
Server)上，当用户提交请求时，通过前端的一台服务器将请求提交给Index Server获
得打了分的倒排索引，然后从Doc Server提取具体的网页信息(例如网页标题、搜索关
键词匹配的片段信息等)，最终展现给用户。
随着索引的网页增加，这个结构可通过增加Index Server以及Doc Server来存储索
引以及网页的数据，但仍然会面临其他... 阅读全帖 |
|
w**k
发帖数: 1455 | 12 google不设计datacenters阿，datacenters有专门的公司设计，google就是把服务器放
里面，现在的趋势已经是各个公司想要把服务器放在同一个center里面，方便数据交换
。datacenter的技术和服务器有什么关系，datacenter现在就是一个做电力，空调，和
cross connection的管理和维护 |
|
p*********4
发帖数: 9 | 13 Title: Operations PM in Microsoft(vendor)
Duration: long term
Hourly rate:$37/hr with full benefits (family health insurance/ 2 weeks
vacation/ holidays)
Contacts: 425 999 8422 or p***[email protected]
Capacity Planning/Operations Program Manager
Main responsibilities
- Designed and implemented reporting and metrics structure for our team.
- Responsible for Capacity Planning and Deployments in production
datacenters in Washington, California, Amsterdam, Tokyo & Singapore.
- Responsible for datacent... 阅读全帖 |
|
w**k
发帖数: 1455 | 14 你不了解这些datacenters是怎么运作的而已，他们那种耗电量只能依靠generators，
电池在多也不可能够，只能提供缓冲。太多电池更不可能了。datacenter那里有地方啊
？而且电池发热量大空调费用怎么办啊，这些datacenters要常年保持恒温，恒湿度。
你大量电池放电好多都要消耗在空调上，根本不行 |
|
O**l
发帖数: 12923 | 15 1 电池装在室外 没有空间的约束
2 特斯拉提供datacenter的电池unlimited的容量 你愿意10gwh都能装
3 datacenter装电池主要目的是省钱
datacenters |
|
C*****5
发帖数: 8812 | 16 就是顺着yjhsjtu几天前转帖的好文
https://www.mitbbs.com/article_t/Stock/37054147.html
看了一些相关文章，快速总结一下：
AI 应用四大场景，DataCenter (Training & Inference), AutonomousVehicle(
inference)， Mobile (inference), Embedded/Edge(各种智能产品比如音响，
inference)
1）Nvidia AI应用的场景最要的市场还是在DataCenter 和 Autonomous Vehicle
2）在DataCenter这块，以后主流也是异构计算，通用GPU，专用芯片，FPGA百花齐放
3）Autonomous Vehicle要求安全，可靠性非常高，周期长。谁能先在汽车制造商和零
件制造商跑马圈上地谁的机会就大。
3) 手机端Nvidia机会不大。各大手机厂商都有自己的inference解决方案。比如华为，
苹果已经有产品。Android有Android NN定义了软件的接口。
4) Embedded/Edge Nvidia开源... 阅读全帖 |
|
Q*K
发帖数: 3464 | 17 http://slacy.com/blog/2011/03/what-larry-page-really-needs-to-d
What Larry Page really needs to do to return Google to its startup roots
Posted on March 24, 2011 by slacy
I worked at Google from 2005-2010, and saw the company go through many
changes, and a huge increase in staff. Most importantly, I saw the company
go from a place where engineers were seen as violent disruptors and
innovators, to a place where doing things “The Google Way” was king, and
where thinking outside the box was discou... 阅读全帖 |
|
s**********r
发帖数: 141 | 18 1.datacenter不是政府的，各公司应该有自己的datacenter。
2.不管谁家的，这些数据都是confidential的，一般的人是不知道的。
3.你几乎要知道了每家的datacenter，才能知道分布，难度很大。 |
|
s**********r
发帖数: 141 | 19 1.datacenter不是政府的，各公司应该有自己的datacenter。
2.不管谁家的，这些数据都是confidential的，一般的人是不知道的。
3.你几乎要知道了每家的datacenter，才能知道分布，难度很大。 |
|
c*****i
发帖数: 631 | 20 OTV现在support的site 数目和scale都有limitation，另外还有些feature limitaton
。不过我是半年多前作RFI的时候看的了，不知道现在具体怎么样.
我觉得中小型datacenter with DR requirement， OTV比较合适。
vpls比较适合大的datacenter，能有自己的mpls backbone。
超大的datacenter就我目前看到的几个好像对L2 extension的requirment不多。
这里有篇OTV vs vpls的whitepaper。
http://www.cisco.com/en/US/partner/prod/collateral/switches/ps9 |
|
|
h**********c
发帖数: 4120 | 22 这么说cloud和五年以前的datacenter区别就是datacenter不卖虚拟机的instance
datacenter 当了还能去把硬盘手蒿出来，
cloud down了回家发简历去吧。 |
|
|
|
s******n
发帖数: 3946 | 25 datacenter is not bad，but fb's data center is a tiny fraction of google's
datacenter |
|
b*******r
发帖数: 9 | 26 上个月投的netapp， 上周HR打电话说想让我做database相关的工作，就发了个职。 这
个是描述，下周电面，在网上也没看到有人面这个位置的， 想问下版里的前辈们，之
前面过这个位置吗？ 能说说具体这个职位面什么吗？十分感谢！
Description:
As a Database Administrator you work as part of a team that provides
operational support for databases in the Corporate Datacenter. The database
administration team is responsible for the overall planning of databases
accuracy and completeness of data in master files; establishing and
maintaining security, formulating and monitoring policies, procedures and
standards;... 阅读全帖 |
|
d*******8
发帖数: 23 | 27 版中大多数面经都是针对北美new graduate的, 在此贡献一下本人国内找北美工作的一
些经验吧, 也算是答谢mitbbs上分享面经的朋友对我的帮助. 更希望攒攒人品能够抽到
h1b签证 :)
[背景]
国内4年工作经验. 硕士毕业后一直在某做存储的外企工作.
14年7月份开始有出国打算并开始准备.
[准备]
在工作之余每天坚持至少刷3~4道算法题, 并关注各个公司的blog及github上的开源项
目.
1. 算法
Leetcode自然不必说, 必刷. 先是用了将近两个月的时间把leetcode刷了1.5遍, 然
后每次电面和onsite面之前挑一些觉得做得不好的题再刷.
其次就是看geeksforgeeks上题. 这是个老印host的网站, 但是上面的题目分类明晰
,有很多分类底下的题目非常好, 比如DP (印象最深的就是m个鸡蛋n层楼测在哪层楼鸡
蛋会被摔碎的问题)和graph (印象最深的就是单源/多源最短/最长路径和欧拉环). 每
天看一下还是能学到不少新鲜的知识的.
其他就没有了, career up和glass door也断断续续看了一些, ... 阅读全帖 |
|
d*******8
发帖数: 23 | 28 版中大多数面经都是针对北美new graduate的, 在此贡献一下本人国内找北美工作的一
些经验吧, 也算是答谢mitbbs上分享面经的朋友对我的帮助. 更希望攒攒人品能够抽到
h1b签证 :)
[背景]
国内4年工作经验. 硕士毕业后一直在某做存储的外企工作.
14年7月份开始有出国打算并开始准备.
[准备]
在工作之余每天坚持至少刷3~4道算法题, 并关注各个公司的blog及github上的开源项
目.
1. 算法
Leetcode自然不必说, 必刷. 先是用了将近两个月的时间把leetcode刷了1.5遍, 然
后每次电面和onsite面之前挑一些觉得做得不好的题再刷.
其次就是看geeksforgeeks上题. 这是个老印host的网站, 但是上面的题目分类明晰
,有很多分类底下的题目非常好, 比如DP (印象最深的就是m个鸡蛋n层楼测在哪层楼鸡
蛋会被摔碎的问题)和graph (印象最深的就是单源/多源最短/最长路径和欧拉环). 每
天看一下还是能学到不少新鲜的知识的.
其他就没有了, career up和glass door也断断续续看了一些, ... 阅读全帖 |
|
发帖数: 1 | 29 大家好，我有一个华为的工程师职位，有朋友感兴趣的可以推荐。 contract 长期职位
，地点在 Bridgewater,NJ
马上要截止了，有想申请的请尽快把简历发给我， [email protected]/* */
Title:Solution Product Network Engineer
Location: Bridgewater, NJ
Term: contract
Duration: long term
Description
1.Responsibilities
The CSP Sales team works in close partnership with sales, channel, vertical
solution to deliver a tailored solution to enterprise customer by using
Huawei solution.
We are seeking a technical professional who can understand key customers’
services env... 阅读全帖 |
|
k****i
发帖数: 353 | 30 会读,看,听中文,因为要report到总部,可以不会写.
要求绿卡.第二常驻地是加州santa clara.
有兴趣的朋友可以发简历到g*******[email protected]
GENERAL SUMMARY:
The primary role of the IT DC Manager is to ensure that the company’s
regional datacenter runs continually and steadily. The IT DC Manager is
responsible for DC infrastructure facilities administration and security,
systems operation and maintenance, related IT projects deployment and
support to meet leading enterprise datacenter business requirements and
industry’s rules, IT vendor mana... 阅读全帖 |
|
b******r
发帖数: 16603 | 31 Company Description
We have pioneered a next generation storage memory platform for data
decentralization. Our platform significantly improves the processing
capabilities within a datacenter by relocating process-critical, or “active
”, data from centralized storage to the server where it is being processed,
a methodology we refer to as data decentralization. Our integrated hardware
and software solutions leverage non-volatile memory to significantly
increase datacenter efficiency and offers ent... 阅读全帖 |
|
r****c
发帖数: 2585 | 32 不知道datacenter要花很多钱么，没有技术搞什么
facebook也在搞datacenter，学亚麻和谷歌
当时就像谷歌搞social晚一样，facebook搞这些也不行 |
|
O**l
发帖数: 12923 | 33 搞笑 你以为特斯拉卖datacenter电池 直接就是一堆18650裸露的堆在那
datacenter到底要求什么的稳定性？ |
|
O**l
发帖数: 12923 | 34 datacenters 不在乎省钱？？ 我过去一个月至少听了三个seminar 讲怎么schedule
CPU
降低能耗 给datacenter省电费
而且电池肯定比备用发电机更robust |
|
w**k
发帖数: 1455 | 35 外行话。。。日常用电费用和电池是两个问题。。datacenters日常用电费用当然要追
求最低，但是后备电源系统关键是要稳定，可靠，，可持续供电，和日常用电是两个问
题。电池因为需要充电，所以并不能独立于电网运作很长时间，但是generator是可以
独立于电网运作的，所以可以提供双保险，在电网不能恢复的情况下，可以依赖于另外
一个能源来发电。。。
客户要求就是在电网断电几天的情况下，datacenters依然可以正常运作。。。。柴油
可以用车运来，电池用完就只占地了。。。 |
|
w**k
发帖数: 1455 | 36 搞笑吧，你不知道datacenter现在都是专门的公司建造并管理吧？？？？？你可以
google去Digital Realty，coresite，equinix，现在大公司的系统都放在这些公司运
作的datacenters里面。。。 |
|
w**k
发帖数: 1455 | 37 我还告诉你， 现在越来越多的datacenters倾向于独立运作，在税收上有很大优势，现
在很多
REITs都是做datacenters，没有公司层面的税收，而且越来越多的公司希望把这部分业
务剥离出去，最大限度降低自己的税收。你可以搜他们的SEC filings都是公开的，你
可以了解这个产业的前沿信息 |
|
s****h
发帖数: 3979 | 38 从AMD hyper角度出发：
1)
现在不可能大打价格战。
Ryzen的性能如果真有最近leak的这么好。
Intel性能不占优势，价格高很多，降价是必然。
2)
而且对未来的Naples的市场预期也是重大利好。
Ryzen性能好，说明Naples性能也值得期待。
AMD的目标是10%的server市场，如果Intel Server降价8%，
差不多性能的AMD server CPU是Intel价格的80%。那么对于datacenter来说，AMD
server CPU其实就是free的。从平衡intel的市场垄断角度出发，datacenter们肯定会
买AMD server CPU。
而且AMD今后还可以号称GPU/加速器和CPU融合得更好。 |
|
p**f
发帖数: 3549 | 39 就看这个了。。。。其他独显，挖矿，自动驾驶都是扯蛋。。
Nvidia reports Q3 results that beat EPS and revenue estimates with an upside
guidance. The company showed a 25% growth on the year in Gaming and 109%
Datacenter growth, which were the platforms to watch.
Q4 guidance has revenue from $2.6B to $2.7B compared to the $2.44B consensus
.
Revenue by reportable segments (Y/Y): GPU Business $2.2B (+31%); Tegra
Processor Business, $419M (+26%).
Revenue by market platform (Y/Y): Gaming, $1.56B (+25%); Professional
Visualization,... 阅读全帖 |
|
s**********n
发帖数: 2343 | 40 索性再给你比一比 Juniper 吹得最凶的scaling 吧， 这里Qfabric 和 VDX 也是半斤
八两， 谁好谁坏
还很难说。 这个题目技术性有点强， 通俗地说， Qfabric 没有遵照标准，自己也不
明说是什么技术
细节， 但是效果好。 Vdx 遵照IEEE标准， 性能也还可以，不像juniper 认为得那样
什么都做不了。
具体可以看下面的讨论， ADAM = Juniper, BROOK = brocade.
http://blogs.forrester.com/andre_kindness/11-02-23-
junipers_qfabric_the_dark_horse_in_the_datacenter_fabric_race
ADAM->Well let's see, VDX can do very few switches in a "fabric" (I'm
thinking maybe 4,
correct me if i'm wrong)
BROOK-> Yeap, not close. On the first release we support... 阅读全帖 |
|
m**m
发帖数: 5500 | 41 断电说太搞了。狗家datacenter都有备用电源，不是大规模灾难，战争等，哪有那么容
易断电。
还有那个什么1000台计算机。。根本不懂的人胡扯。。datacenter谁说“计算机”这个
词。。 |
|
|
|
l*********r
发帖数: 80 | 44 why my sql server 2000 enterprise sp2 can't install on win2003 enterprise
trial version?
? SQL Server 2000 Enterprise Edition and Standard Edition can run on the fol
lowing operating systems:
Windows Server? 2003, Standard Edition1
Windows Server 2003, Enterprise Edition1
Windows Server 2003, Datacenter Edition1
Windows? 2000 Server
Windows 2000 Advanced Server
Windows 2000 Datacenter Server
Windows NT? Server version 4.0 with Service Pack 5 (SP5) or later
Windows NT Server 4.0, Enterprise Editi |
|
c*****i
发帖数: 631 | 45 50个人的公司能有啥datacenter？还是帮别的公司维护datacenter？ |
|
b****c
发帖数: 16 | 46 CCIE datacenter 基本上你就当个人认证吧，去INE买bootcamp，租rack学习，也不难
，我也正在弄。
下面你写的几个，基本算是公司的专业化认证吧，公司可以申请datacenter这块的合作
伙伴，然后折扣什么的项目什么的好说些，对个人来说用处不大，看你老板的真实意思
了。
-----------------------------------------------
是这样的，我这两天在网上查了些资料，发现现在有个CCIE DATA CENTER这个认证
Exam Number: 350-080
Associated Certifications: CCIE Data Center
但是之前我在网上也看到了另外几个认证：
Cisco Data Center Application Services Design Specialist
Cisco Data Center Application Services Support Specialist
Cisco Data Center Unified Computing Design Specialist... 阅读全帖 |
|
g*****g
发帖数: 34805 | 47 Netflix has 30M streaming users, way more than before the split. It also
uses 1/3 of bandwidth in North America
in peak hours, I wouldn't call that a failure. Sure it made mistakes, every
company does.
BTW, it's harder to host on EC2 than in datacenter at that scale. Coz no
other companies did it before. Cloud computing is about making operation
easier, in terms of not worrying about growth planning. The software
development part is actually harder. You don't magically write less code for
your b... 阅读全帖 |
|
c*********e
发帖数: 16335 | 48 We’re excited to announce the launch of our newest datacenter region: BLR1,
located in Bangalore, India.
BLR1 includes the same full range of features found in every other region,
including 40GbE networking and the latest model of SSDs.
Pricing will also remain consistent across all of our datacenters worldwide,
including Bangalore, with cloud servers starting at $5 USD per month.
Read more on the India launch announcement here.
digital ocean在大陆有data center吗？ |
|
