Home » Posts tagged "direct"

AWS 公開了在台北的 Direct Connect 接口

也是個很久前就聽到傳言的消息... AWS 剛剛公佈了在台北的 Direct Connect 接口,用戶可以在台北內租用線路進機房就連上 Direct Connect:「New AWS Direct Connect sites land in Paris and Taipei」。

AWS Direct Connect also launched its first site in Taiwan at Chief Telecom LY, Taipei. In the Management Console, Taipei is located in the Asia Pacific (Tokyo) Region. With global access enabled for AWS Direct Connect, these sites can reach AWS resources in any global AWS region using global public VIFs and Direct Connect Gateway.

以往需要透過像 GCX 這樣的公司租用國際頻寬,再從 GCX 在台北的機房拉到自家機房 (通常是市內專線),現在只需要在台北對接的這段就可以了。

台北的接點在 AWS 上寫的是 Chief Telecom LY, Taipei, Taiwan,查了一下是是方電訊的「是方麗源大樓 (台北市內湖區陽光街250號)」,也就是之前有發生過火災而大斷線的那棟。對接的 AWS Home Region 是 Asia Pacific (Tokyo),所以使用 ap-northeast-1 的人可以規劃...

Amazon Device Farm 支援讓使用者直接連上去 debug 了...

Amazon Device Farm 推出這樣的功能又朝著設備租賃服務更進一步了:「Amazon Device Farm Launches Direct Device Access for Private Devices」。

Now, with direct device access, mobile applications developers can use individual devices in their private test set as if they were directly connected to their local machine via USB. Developers can now test against a wide array of devices just like they would as if the devices were sitting on their desk.


AWS Direct Connect 可以多條線路綁在一起用了

AWS Direct Connect 支援 Link Aggregation Group (LAG),將多條線路綁在一起了:「AWS Direct Connect enables Link Aggregation Group for additional AWS regions」。

We are excited to announce support for 1G and 10G Link Aggregation Groups (LAG). Customers in AWS GovCloud (US), Europe (Frankfurt), Europe (London), Europe (Ireland), Asia Pacific (Tokyo), Asia Pacific (Singapore), Asia Pacific (Sydney) regions can start using LAG to link existing connections on the same AWS device, or request new connections.

主要還是對於超大量的用戶會變方便 (都是使用 10Gbps 線路接上去的使用者),尤其是 load balancing 這塊會好做不少。

多條 1Gbps 的當然也是有幫助,不過剛好只會落在一個微妙的範圍 (到 8Gbps 的時候,直接換 10Gbps 成本說不定其實差不多...)。

PostgreSQL 上,直接將 SSD 的內容送到 GPU 上,加速讀取速度

PostgreSQL 上針對讀取檔案到 GPU 上的成果:「GpuScan + SSD-to-GPU Direct DMA」(日文版)、「(EN) GpuScan + SSD-to-GPU Direct DMA」(英文版)。

主要的原因在於雖然已經有 PGStorm 讓 PostgreSQL 把運算丟到 GPU 上加速,但從 disk 讀到 GPU 這段還是有改善的空間:

PG-Strom that is an extension of PostgreSQL to off-load multiple SQL workloads on GPU devices, transparently. It has been developed for four years, and now supports simple scan, tables join, aggregation and projection.
Its prime focus is CPU intensive workloads, on the other hands, it didn't touch storage subsystem of PostgreSQL because the earlier version of PG-Strom assumes all the data set shall be pre-loaded onto physical memory. No need to say, we had a problem when we want to process a data-set larger than physical RAM.


這對資料量超過 RAM 大小時的處理會非常有幫助 (因為會有大量的 disk i/o 發生)。

Instagram 從 AWS 搬到 Facebook 機房

InstagramInstagram Engineering Blog 上宣佈的消息:「Migrating From AWS to FB」。

整個 migration 的過程是採取不停機轉移,所以 effort 比直接停機轉移高很多:

The main blocker to this easy migration was that Facebook’s private IP space conflicts with that of EC2. We had but one route: migrate to Amazon’s Virtual Private Cloud (VPC) first, followed by a subsequent migration to Facebook using Amazon Direct Connect. Amazon’s VPC offered the addressing flexibility necessary to avoid conflicts with Facebook’s private network.

先把整個系統轉移到 Amazon VPC 裡,然後再拉 AWS Direct Connect 串起來,接下來才是慢慢把 instance 轉移到 Facebook 的機房內。


To provide portability for our provisioning tools, all of the Instagram-specific software now runs inside of a Linux Container (LXC) on the servers in Facebook’s data centers.

所以已經導入 LXC 了...

AWS Direct Connect 向下提供 50Mbps 的連線頻寬...

在「AWS Direct Connect - More Connection Speeds, New Console, Multiple Accounts」這篇文章裡面提到了 AWS Direct Connect 可以接受 50Mbps~500Mbps 的頻寬了,而先前只接受 1Gbps 與 10Gbps...

不過 500Mbps 的頻寬與 1Gbps 頻寬的 port 價錢是相同的,都是 USD$0.3/hour,其他較低的速度就依照 500Mbps 的比率計算。

比較特別的是 50Mbps,是用 QoS 限制頻寬嗎?這樣的速度還蠻特別的...