-
Welcome
-
Subscribe to
Proposals
Proportional IO Controller
*Excerpt
The Proportional IO controller allows to distribute disk time to tasks/cgroups in proportion to their assigned weights. It leverages existing cgroup infrastructure for task grouping and supports
specification of weights hierarchically.
Description
The Proportional IO controller allows to distribute disk time to tasks/cgroups in proportion to their assigned weights. It leverages existing cgroup infrastructure for task grouping and supports
specification of weights hierarchically.
The IO controller uses hierarchical weighted fair queuing logic, which builds upon the Budget Fair Queuing (BFQ) scheduler proposed by Fabio Checconi and Paolo Valente. This logic is implemented at the common
elevator layer that allows this approach to work with all four IO schedulers. Having this logic at the IO scheduler level and only one level of queuing makes sense as we can support existing IO priority class semantics.
We plan to present/discuss goals and design overview of this io controller. A basic set of working patches are ready and we also plan to provide some test results and numbers.
Tags
storage, IO scheduler, IO controller, cgroups
Speakers
-
Vivek Goyal
Red Hat Inc.Biography
Vivek Goyal works as a kernel developer at RedHat in Westford, MA, USA. An electronics and communication engineer from Institute of technology, B.H.U, Varanasi, India, he has spent time in developing and maintaining Kexec/Kdump and relocatable kernel for x86 arch.
He is currently working on implementing IO controller so that different group of tasks in different cgroups can receive differentiated services.
-
Nauman Rafique
Google Inc.Biography
Nauman Rafique is a software engineer at Google where he works with kernel team on resource management issues. Prior to joining Google, he obtained his PhD degree from the department of Electrical and Computer Engineering at Purdue University. He did research on the management of low level shared resources in multicore processors like lower-level caches and DRAM bandwidth. He has published papers in conferences (Parallel Architecture and Compilation Techniques, PACT, International Symposium on Computer Architecture) and journal (Transactions on VLSI). He has also reviewed papers for PACT and HiPC.
He is currently working on cgroup based block layer IO controller.
-
Divyesh Shah
Google IncBiography
Divyesh Shah works as a Linux kernel developer at Google. He works mainly on resource management issues, mostly centered around block IO and storage related things for now.
Prior to joining Google, Divyesh graduated with a Masters degree in Computer Science from University at Buffalo, SUNY.