Linux 3.13 Improves Networking, Memory Performance

 
 
By Sean Michael Kerner  |  Posted 2014-01-21 Email Print this article Print
 
 
 
 
 
 
 

The first new Linux kernel of 2014 arrives with new features and performance enhancements for the open-source operating system.

The Linux 3.13 kernel is now available, providing users of the open-source Linux operating system with the first major update of 2014. The Linux 3.13 kernel follows the Linux 3.12 kernel that was released in November of 2013. Among the new capabilities and features are a packet filtering technology, improved solid-state disk (SSD) storage capabilities and integrated support for near-field communications (NFC) payments.

One of the biggest changes in the Linux 3.13 release is the inclusion of the new nftables packet filtering technology, which is intended to be a successor to the widely deployed iptables technology. Iptables are typically used for security, access and firewall configuration on Linux servers and systems.

The basic idea with nftables is that it is a more robust and easier to use than iptables while offering similar functionality that is backward-compatible with existing iptables rules.

"We are supportive of nftables and what it means for the Linux community moving forward," Denise Dumas, senior director of Platform Engineering at Red Hat, told eWEEK. "iptables has always been difficult for customers to use successfully, and we have high hopes that nftables will provide a much more user-friendly experience."

In addition, Linux 3.13 gains automatic non-uniform memory access (NUMA) balancing, which Dumas said should be very helpful for enterprise users.

There is now also a new storage block layer for SSDs that is part of the Linux 3.13 kernel.

"With drivers being written for new high IOPS (Input/Output Per Second) devices, the classic request_fn based driver doesn't work well enough," Linux developer Jens Axobe wrote in his code commit message. "It has problems with scaling to bigger machines, and runs into scaling issues even on smaller machines when you have IOPS in the hundreds of thousands per device."

The new block layer approach, called "blk-mq," introduces block multi-queue support, which is intended to meet the high IOPS requirements of SSDs.

"The design is centered around per-cpu queues for queueing IO, which then funnel down into x number of hardware submission queues," Axboe wrote.

Networking also gets a boost in Linux 3.13 with a pair of innovations, including the High-Availability Seamless Redundancy (HSR) standard that is now supported in Linux, enabling a new approach for failover.

"It [HSR] requires a special network topology where all nodes are connected in a ring (each node having two physical network interfaces)," Linux developer Arvid Brodin wrote in his code commit message. "It is suited for applications that demand high availability and very short reaction time."

In addition to HSR, Linux 3.13 benefits from the TCP Fast Open specification, which is intended to accelerate the ability of a system to open up multiple Transmission Control Protocol (TCP) connections. The technology first landed in the Linux 3.7 kernel  at the end of 2012 and is now enabled by default in the Linux 3.13 release.

"Applications have started to use Fast Open (e.g., Chrome browser has such an optional flag) and the feature has gone through several generations of kernels since 3.7 with many real network tests," Linux kernel developer Yuchung Cheng wrote in his code commit message. "It's time to enable this flag by default for applications to test more conveniently and extensively."

Sean Michael Kerner is a senior editor at eWEEK and InternetNews.com. Follow him on Twitter @TechJournalist.

 
 
 
 
 
 
 
 
 
 
 
 
 

Submit a Comment

Loading Comments...
 
Manage your Newsletters: Login   Register My Newsletters























 
 
 
 
 
 
 
 
 
 
 
Thanks for your registration, follow us on our social networks to keep up-to-date
Rocket Fuel