Linux Storage Filesystem/MM Summit 2014からの便り
Linux Storage Filesystem/MM Summit 2014からの便り：Linux Kernel Watch（1/2 ページ） お久しぶりです、Linux Kernel Watchが帰ってきました。3月に行われた「Linux Storage Filesystem/MM Summit 2014」の主なトピックを紹介します。 皆さん、お久しぶりです。私は今ボストンで、米レッドハット常駐という立場でRed Hat Enterprise Linux（RHEL）開発に携わっています。 今回はサンフランシスコ近郊のナパバレーで2014年3月24～25日に行われた「Linux Storage Filesystem/MM Summit 2014」（以下LSF/MM）の中から面白かったトピックをピックアップしてお届けしたいと思います。 LSF/MMはLinux Foundation主催で行
Optimizing Linux Memory Management for Low-latency / High-throughput Databases
Optimizing Linux Memory Management for Low-latency / High-throughput Databases Co-author: Cuong Tran Table of Contents Introduction Setting up the context Reproducing and understanding Linux's zone reclaim behavior NUMA memory rebalancing also triggers direct page scans Lessons learned Introduction GraphDB is the storage layer of LinkedIn's real-time distributed social graph service. Our service h
Free Programmer's Blog | Linux 3.9 introduced new way of writing socket servers
Try Monique.io for free and save 93% of the time needed to set up dashboards and alerts. Linux kernel 3.9 came with an interesting feature: ability to bind multiple listening sockets to the same port on the same host, by unrelated processes or threads. The socket option is called SO_REUSEPORT and here is an article by Michael Kerrisk describing the feature. The article makes SO_REUSEPORT look like
Linux_3.5 - Linux Kernel Newbies
Linux 3.5 has been released on 21 Jul 2012. Summary: This release includes support for metadata checksums in ext4, userspace probes for performance profiling with tools like Systemtap or perf, a sandboxing mechanism that allows to filters syscalls, a new network queue management algorithm designed to fight bufferbloat, support for checkpointing and restoring TCP connections, support for TCP Early
debian - Anyone else experiencing high rates of linux server crashes today? - Server Fault
*NOTE: if your server still has issues due to confused kernels, and you can't reboot - the simplest solution proposed with gnu date installed on your system is: date -s now. This will reset the kernel's internal "time_was_set" variable and fix the CPU hogging futex loops in java and other userspace tools. I have straced this command on my own system an confirmed it's doing what it says on the tin
What's new in Linux 3.2 - The H Open: News and Features
by Thorsten Leemhuis Improvements to the Ext4 filesystem, network code optimisations and thin provisioning support in the Device Mapper are some of the major improvements in Linux 3.2. Further additions include new and improved drivers – for example, for graphics hardware by Intel and NVIDIA, as well as Wi-Fi components by Atheros and Broadcom. After just over two months of development, Linus Torv
시스템 엔지니어 공동 관리 구역 :: Guide to Optimizing GlusterFS
Block Device Tuning One problem which could manifest itself in older kernels (2.6.9 which for example is the stock kernel in Scientific Linux 4) is the size of io requests which are buffered before they are communicated to the disk. In 2.6.9 the default value of that for every block device is 8192. In the newer kernels it is 128. One can see that the change in default value is substantial. The tro
mcelog -- the linux hardware error daemon
mcelog logs and accounts machine checks (in particular memory, IO, and CPU hardware errors) on modern x86 Linux systems. mcelog is required by both 32bit x86 Linux kernels (since 2.6.30) and 64bit Linux kernels (since early 2.6 kernel releases) to log machine checks and should run on all Linux systems that need error handling. The mcelog daemon accounts memory and some other errors errors in vario
Software receive packet steering [LWN.net]
netdev@vger.kernel.org, David Miller <davem@davemloft.net> This patch implements software receive side packet steering (RPS). RPS distributes the load of received packet processing across multiple CPUs. Problem statement: Protocol processing done in the NAPI context for received packets is serialized per device queue and becomes a bottleneck under high packet load. This substantially limits pps th
VIOPS06で「RPS・RFS等最新Linux Kernel事例」と題してお話してきました - syuu1228's blog
はじめに 第一回カーネル／VM探検隊＠関西、第二回日本Vyattaユーザ会ミーティングで行った発表のダイジェスト版です。 詳しく知りたい人はこちらの内容ではなく、第二回日本Vyattaユーザ会ミーティングの動画、資料をみる事をお勧めします。 あと、最新って書いてあるけど割と古い話題です。すんません。 発表資料 従来型のNICとネットワークスタックの組み合わせでは、マルチコア環境においても１つのNICの受信処理は１つのCPUでしか行えません。 これは、NIC上に受信のキューと受信を通知する割り込みが１つしか存在せず、ハードウェアからデバイスドライバまでのレイヤーでは受信処理を並列に行う事が本質的に出来ない事が原因でした。 これが原因で、通信量が多い時にパケット処理の負荷が特定のCPUへ偏ってしまい、CPU数を増やしても性能がスケールしないという問題が発生します。 この問題を解決する為に、１つ
lxc Linux Containers | IBM MCR Home
Linux Containers (LXC), provides the ability to group and isolate of a set of processes in a jail by virtualizing and accounting the kernel resources. It is similar to Linux-Vserver or Openvz. Please note that LXC is no longer using SourceForge for most of its resources. Instead, we're now using github at http://github.com/lxc Mailing-lists are still hosted here for the time being.
fsync() on a different thread: apparently a useless trick
fsync() is the kind of system call you love and hate at the same time. In many applications it's nice to know that kernel buffers are flushed to disk (even if this alone does not necessarily guarantees data is actually written to the disk, as the disk itself can have caching layers), but unfortunately fsync() tends to be monkey assess slow. As I like numbers, slow is, for instance, 55 milliseconds
iostat: (r/s + w/s) * svctm = %util on Linux
iostat -x is very useful to check disk i/o activities. Sometimes it is said that "check %util is less than 100%" or "check svctm is less than 50ms", but please do not fully trust these numbers. For example, the following two cases (DBT-2 load on MySQL) used same disks (two HDD disks, RAID1) and reached almost 100% util, but performance numbers were very different (no.2 was about twice as fast as n
RCUの全面書き直しも！ 2.6.29は何が変わった？（1/2） － ＠IT
4月版 RCUの全面書き直しも！ 2.6.29は何が変わった？ 小崎資広 2009/5/8 いやあ、文字数の都合で書けませんでしたが、4月最終週はIngoがいい出した「カーネル専用コンパイラを作ろうぜ！」スレッドが大盛り上がり。おバカな話題ほどスレッドが伸びるのは、全世界共通ですね。 それでは予告どおり、今回はカーネル2.6.29についてのよもやま話をお送りいたします。どうぞ。 カーネル2.6.29の主な変更点 ■ランダムシード受け渡し方法の変更によるアプリケーション起動の高速化 最近のgccには、glibcと連携してスタック破壊を検知するSSP（Stack Smashing Protector）という機構が実装されています（-fstack-protectorオプション）。これはスタックに「カナリア値」と呼ばれる特殊な値を埋め込み、関数リターン時に、その値が無変更であることを確認することで
Understanding the Linux Virtual Memory Manager | InformIT
Description Copyright 2004 Dimensions: 7" x 9-1/4" Pages: 752 Edition: 1st Book ISBN-10: 0-13-145348-3 ISBN-13: 978-0-13-145348-7 A programmer wanting to understand the workings of the Linux VM today literally has no choice but to study the kernel source code, line-by-line - an excruciatingly difficult and time-consuming task. This book dedicates itself to explaining, in detail, how the memory man
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Transparent hugepages [LWN.net]
レッドハット マガジン 64ビットコンピューティング: 32ビット環境での共存
美女LINUX bijo-linux.com
http://www.makelinux.net/kernel_map/
IBM Developer
