Home » Posts tagged "connection"

Happy Eyeballs (RFC 6555)

在「PChome 24h 連線會慢的原因...」這篇的 comment 有讀者提到了 Happy Eyeballs 應該可以解決這個問題:

除了可以在維基百科上面看到外,比較正式的說明可以參考 RFC 6555:「Happy Eyeballs: Success with Dual-Stack Hosts」,其中在「6. Example Algorithm」就有提到 Google ChromeMozilla Firefox 怎麼實做 Happy Eyeballs:

What follows is the algorithm implemented in Google Chrome and Mozilla Firefox.

  1. Call getaddinfo(), which returns a list of IP addresses sorted by the host's address preference policy.
  2. Initiate a connection attempt with the first address in that list (e.g., IPv6).
  3. If that connection does not complete within a short period of time (Firefox and Chrome use 300 ms), initiate a connection attempt with the first address belonging to the other address family (e.g., IPv4).
  4. The first connection that is established is used. The other connection is discarded.

If an algorithm were to cache connection success/failure, the caching would occur after step 4 determined which connection was successful.

Other example algorithms include [Perreault] and [Andrews].

可以看到 Happy Eyeballs 的演算法是要避免 IPv6 network 不通的情況卡住很慢 (如果在 300ms 內連線沒有建起來,就會儘快往另外一個 address family 嘗試),而不是在 DNS 層避免問題 (也就是 getaddinfo() 觸發的 DNS query)。

這次的情況是 DNS query 很慢,就會導致還是一開始就很慢,Happy Eyeballs 沒辦法解決這個問題。

不過話說回來,我是有印象知道有這個演算法,但不知道有「Happy Eyeballs」這個這麼逗趣的名字... (掩面)

有 Lazy Connection 功能的 PDO object

在「Aura.Sql」這邊看到有提供 Lazy Connection 的 PDO object,而且是繼承自本來的 PDO object:

Provides an extension to the native PDO along with a profiler and connection locator. Because ExtendedPdo is an extension of the native PDO, code already using the native PDO or typehinted to the native PDO can use ExtendedPdo without any changes.

Lazy connection. ExtendedPdo connects to the database only on method calls that require a connection. This means you can create an instance and not incur the cost of a connection if you never make a query.

之後可以拿來跟 LaravelEloquent 一起用看看。本來的 PDO 物件在建立時就會建立連線,對於連線的開銷其實蠻大的,用這個應該是個方向...

另外是 Profiler 的能力,需要用的時候應該會很好用:

Profiler. An optional query profiler is provided, along with an interface for other implementations, that logs to any PSR-3 interface.

引一下來源,當初是從「Atlas.Orm 2.0 Is Now Stable」這邊在看文件時一路看到的。

VPN 保留連線記錄幫助 FBI 抓犯人

這應該是這幾天鬧得蠻大的事情:「PureVPN Logs Helped FBI Net Alleged Cyberstalker」。

起因在於 PureVPN 的廣告寫著他們不會記錄:

但在證詞裡卻提到 PureVPN 有記錄:

“Significantly, PureVPN was able to determine that their service was accessed by the same customer from two originating IP addresses: the RCN IP address from the home Lin was living in at the time, and the software company where Lin was employed at the time,” the agent’s affidavit reads.

然後回頭看 PureVPN 的 Privacy 條款發現他們在條款裡面寫著他們會記錄連線資訊:

Our servers automatically record the time at which you connect to any of our servers. From here on forward, we do not keep any records of anything that could associate any specific activity to a specific user. The time when a successful connection is made with our servers is counted as a ‘connection’ and the total bandwidth used during this connection is called ‘bandwidth’. Connection and bandwidth are kept in record to maintain the quality of our service. This helps us understand the flow of traffic to specific servers so we could optimize them better.

然後被告 Ryan S. Lin 就幹剿了:

“There is no such thing as a VPN that doesn’t keep logs,” Lin said. “If they can limit your connections or track bandwidth usage, they keep logs.”

以後挑 VPN 還得仔細看條款裡面留 log 的部份啊...

PS4 下載速度很慢的原因

在「Why PS4 downloads are so slow」這篇作者花了不少力氣找出原因,發現 PS4 下載速度很慢是故意的... 另外討論了在什麼情況下會變慢,以及要怎麼避免的方式。

懶得看的人可以直接看 Conculsions 那段,主要的原因是 PS4 會因為背景程式而調整 TCP window size (就算背景程式在 idle 也會影響到下載的 TCP window size),進而影響速度:

If any applications are running, the PS4 appears to change the settings for PSN store downloads, artificially restricting their speed. Closing the other applications will remove the limit.

用 TCP window size 來調整速度也算是頗有「創意」的方法...

Anyway,遇到時的解決方法就是把所有在跑的程式都完整關掉,再下載就會正常多了...

CloudFlare 正式推出 HTTP/2,可以與 SPDY 同時混搭

CloudFlare 推出了 HTTP/2 服務,與其他 CDN 業者不一樣的地方在於,他可以同時接受 HTTP/2 與 SPDY:「HTTP/2 is here! Goodbye SPDY? Not quite yet」。

CloudFlare 拿自家的 www.cloudflare.com 官網測試,顯示 HTTP/2 的效能比 SPDY 又好了不少:

Access via HTTP Protocol VersionAverage Page Load time
HTTP 1.x9.07 sec.
SPDY/3.17.06 sec.
HTTP/24.27 sec.

在正式上 HTTP/2 前,有 80.38% 對 www.cloudflare.com 的 SSL/TLS 連線是 SPDY:

During the week before our HTTP/2 launch, 80.38% of all SSL/TLS connections to our own website at www.cloudflare.com were made over SPDY/3.1.

上線後其實沒有想像中的高:

Protocol VersionPercentage of Hits
HTTP 1.x19.36%
SPDY/3.157.02%
HTTP/223.62%

這也說明了為什麼 CloudFlare 要推出 SPDY + HTTP/2 的服務:

Why choose, if you can have both? Today CloudFlare is introducing HTTP/2 support for all customers using SSL/TLS connections, while still supporting SPDY. There is no need to make a decision between SPDY or HTTP/2. Both are automatically there for you and your customers.

剛剛連到後台確認,由於本來已經打開 SPDY 的使用者會自動開啟 HTTP/2,這表示全球 HTTP/2 的使用率會馬上拉高很多,有太多資源掛在 CloudFlare 上:(像是 cdnjs.com,剛剛確認也已經是 HTTP/2 了)

If you are a customer on the Free or Pro plan, there is no need to do anything at all. Both SPDY and HTTP/2 are already enabled for you.

Customers on Business and Enterprise plans can enable HTTP/2 within the "Network" application of the CloudFlare Dashboard.

Facebook 因為 Connection Pool 選擇機制,加上系統的複雜性而導致的慘案...

Facebook 的 engineer 寫了一篇文章,說明他們花了超過兩年的時間找到一個 bug:「Solving the Mystery of Link Imbalance: A Metastable Failure State at Scale」。

整個故事是個通靈的故事...

Facebook 在底層的架構使用了 Link Aggregation 的規劃,多條線路 channel bonding 在一起連到骨幹上。但發現有時候會卡在某一條線路壅塞而導致 system failure。

於是就一路追下去,從 switch 本身開始懷疑,最後去組織跨部門的研究小組跳下去分析 (通靈)。後來才觀察到是因為 connection pool 的機制本身用的演算法在 Facebook 這個複雜的系統架構下造成的慘案...

當 query burst 發生時,Facebook 的系統會同時到 50~100 組資料庫撈資料出來寫入 cache,而 connection pool 的機制用的是 MRU (Most Recently Used),從 congestion link 回來的 connection 會在 pool 裡面的最上方,於是就愈來愈塞...

知道問題後,解決的方法就簡單多了。只是把 connection 選擇演算法從 MRU 換成 LRU 後就解決了,但中間用了超過兩年的時間,以及至少 30 個人的努力才把問題找出來並且解決。

可以看到最後銘謝的對象一卡車:

Thanks to all of the engineers who helped us manage and then fix this bug, including James Paussa, Ernesto Ovcharenko, Mark Drayton, Peter Hoose, Ankur Agrawal, Alexey Andreyev, Billy Choe, Brendan Cleary, JJ Crawford, Rodrigo Curado, Tim Eberhard, Kevin Federation, Hans Fugal, Mayuresh Gaitonde, CJ Infantino, Mark Marchukov, Chinmay Mehta, Murat Mugan, Austin Myzk, Gaya Nagarajan, Dmitri Petrov, Marco Rizzi, Rafael Rodriguez, Steve Shaw, Adam Simpkins, David Swafford, Wendy Tobagus, Thomas Tobin, TJ Trask, Diego Veca, Kaushik Veeraraghavan, Callahan Warlick, Jason Wilbanks, Jimmy Williams, and Keith Wright.

最後附上 Facebook 解釋的圖:

AWS Elastic Load Balancing 服務支援 Connection Draining

AWS Elastic Load Balancing 支援 Connection Draining 功能了:「ELB Connection Draining - Remove Instances From Service With Care」。

由於 Connection Draining 是自創名詞,所以 AWS 的人解釋了一大堆。其實對比較熟悉的人用「graceful shutdown」就應該能了解 Connection Draining 想要做什麼事情。

技術上的細節是,當 instance 從 ELB 內被移除 (無論是暫時性的還是永久性的),新的 request 將不會被送到該 instance 裡,而既有的連線將不會斷掉,直到 client 完成或是超時 (timeout)。

這個功能在一般商用的 load balancing solution 都會提供,而且是對於服務品質其實還蠻重要的功能。

話說回來,這陣子 ELB 動了不少東西?不查資料可以直接想到的就包括了:

  • HTTPS 支援 PFS
  • 支援 access log 下載。

再加上今天的 graceful shutdown。每次都改善一些東西,累積起來就是驚人的財產...

Archives