UChicago systems research on
Availability, Reliability and Efficiency
    Home     People     Publications     Projects/Downloads     Sponsors    


  • We are recruiting graduate students! If you are interested in our projects, please contact Haryadi Gunawi. We are also open to local undergraduate students who would like to perform undergraduate research / independent study (local means you are enrolled in our CS department).

  • Tiny-Tail Flash is accepted to FAST '17, congrats Shiqin, Huaicheng, Mingzhe, and Michael!
  • DCatch (with Shan Lu's team) is accepted to ASPLOS '17, congrats Jeffrey!
  • Three posters at OSDI '16 (Tiny-Tail Flash, PBSE, and SCk) by the entire team
  • Internship time! Tanakorn will go to Microsoft Rsch, Riza to Samsung Rsch, and Shiqin and Michael to EMC AD
  • Haryadi received 2015 Google Research Award (Thanks Google!)
  • Thanks to EMC and Huawei for supporting our research!
  • Haryadi received 2015 NetApp Faculty Fellowship (Thanks NetApp!)
  • The Tail at Store is accepted to FAST '16, congrats to Mingzhe!
  • TaxDC is accepted to ASPLOS '16, congrats to Jeffrey and Tanakorn!
  • (Old news)

Publication and Download Links

For a complete list, please go to our publications page.

Selected papers: TaxDC [ASPLOS '16], Tail at Store [FAST '16], ManyLogs [MSST '16], SAMC [OSDI '14], CBS [SoCC '14], Drill [SoCC '14], Limplock/Limpware [SoCC '13], Fate/Destini [NSDI '11]

Project/download links: tinyTailFlash, SAMC, Cloud Bug Study (CBS)


The "Cloud" era is here. As more and more computing tasks depend on cloud computing, the availability, reliability, and efficiency of cloud-scale systems are becoming more and more important. Unfortunately, major dependability problems (outages, data loss, etc.) still take place even recently. To sum up, today's computing forecast is "cloudy with a chance of failure."

In UCARE lab (U of C systems research on Availability, Reliability and Efficiency), we are improving the dependability of storage and cloud-scale distributed systems in the context of (1) performance stability, specifically on the handling and management of "limpware", (2) reliability, specifically on combating distributed concurrency bugs, and (3) scalability, specifically about finding and reproducing latent scalability bugs easily.


We would like to thank:

  • National Science Foundation, Grants# CNS-1350499, CCF-1336580, and CCF-1321958
  • CERES: Center for Unstoppable Computing
  • EMC
  • Google
  • Huawei
  • NetApp

  • Infrastructures: