Animesh Trivedi
contact information




links
profile
About Me
I am a Research Staff Member (RSM) in the Cloud and Computing Infrastructure group at the IBM Research Lab, Zurich. Earlier in 2016, I graduated with a PhD from ETH, Zurich.
My primary research areas are distributed systems, networking, operating systems, and storage. Broadly speaking, I am interested in the performance aspect of systems, spanning from multi-core CPUs to distributed environments. Currently I am investigating how to leverage high-performance network (e.g., 100+ Gbps network) and storage (10+ GBps, e.g., NVMe flash) devices in modern open-source analytics stacks such as Apache Spark. These efforts are parts of the Apache Crail (Incubating) project (www.crail.io).
Occasionally, I put stuff on my technical blog that can be reached here: https://animeshtrivedi.github.io/blog/. My github profile is at https://github.com/animeshtrivedi.
News:
- 2018: I am looking for talented students who like to hack distributed systems. Have a look at our group's git repo https://github.com/zrlio to get a flavour for the type of work we do.
- November, 2017: Crail features in the FLOSS weekly podcast. Have a look here.
Projects
Many of the projects that I am involved in, are open sourced :
- Apache Crail (Incubating): Crail is an open source user-level I/O architecture for the Apache data processing ecosystem designed from ground up for high-performance storage and networking hardware, www.crail.io
- DiSNI: High-performance devices (e.g., RDMA, NVMeF, etc.) integration for Java (previosuly called jVerbs), github.com/zrlio/disni
- DaRPC: High-performance RPC library for RDMA/Java built using DiSNI, https://github.com/zrlio/disni
- SoftiWARP: A fully functional software RDMA device for Linux : https://github.com/zrlio/softiwarp
More work from the group can be found at : https://github.com/zrlio
Recent Publications
Full list is [here]
- FlashNet: Flash/Network Stack Co-Design (Best paper award!). Animesh Trivedi, Nikolas Ioannou, Bernard Metzler, Patrick Stuedi, Jonas Pfefferle, Ioannis Koltsidas, Kornilios Kourtis, Thomas R. Gross, in the 10th ACM International Systems and Storage Conference (SYSTOR'17), Haifa, Israel, May 22-24, 2017. [ACM].
- Crail: A High-Performance I/O Architecture for Distributed Data Processing. Patrick Stuedi, Animesh Trivedi, Jonas Pfefferle, Radu Stoica, Bernard Metzler, Nikolas Ioannou, Ioannis Koltsidas, in the IEEE Bulletin of the Technical Committee on Data Engineering, Special Issue on Distributed Data Management with RDMA, Volume 40, pages 40-52, March, 2017. [PDF]
- On The [Ir]relevance of Network Performance for Data Processing. Animesh Trivedi, Patrick Stuedi, Jonas Pfefferle, Radu Stoica, Bernard Metzler, Ioannis Koltsidas, Nikolas Ioannou, in the 8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud '16), Denver, Colorado, USA, June 20–21, 2016. [PDF] [ACM]
- RStore: A Direct-Access DRAM-based Data Store. Animesh Trivedi, Patrick Stuedi, Bernard Metzler, Clemens Lutz, Martin Schmatz, Thomas R. Gross, in the 35th IEEE International Conference on Distributed Computing Systems (ICDCS'15), Columbus, Ohio, USA, June 29th - July 2nd, 2015.
Thesis
- [PhD] Animesh Trivedi, End-to-End Considerations in Unification of High-Performance IO, PhD thesis, ETH Zurich, January, 2016. https://doi.org/10.3929/ethz-a-010651949 [PDF]
- [Master] Animesh Trivedi, Hotplug in a multikernel operating system, Master's thesis, Department of Computer Science, ETH Zurich, August, 2009. https://doi.org/10.3929/ethz-a-005881972 [PDF]