Impact on NGS workflows - due to Vulnerabilities - Meltdown and Spectre ?

Question

[gsr9999]

Dear Biostar Leaders,

I built a exome pipeline with standard tools like fastQC + BWA-MEM align + GATK + samtools + Picard + freebayes + samblaster. My pipeline runs on a local Linux Server(HP) that runs "Red Hat Enterprise Linux 7.3"

Our IT staff has informed me about the recent news on a hardware-memory vulnerability called "Meltdown & Spectre" that affects servers containing Intel microprocessors. RedHat has released some patch upgrades to solve this vulnerability.

ReadHat has also indicated that this upgrade will cause a performance degrade (up to 30%). I am wondering if anyone of you has made similar upgrades and seen any performance hits at various stages of the ngs pipeline ? Which ngs related tools have got affected the most due to this patch upgrade ?

Redhat patch is : https://access.redhat.com/security/vulnerabilities/speculativeexecution?sc_cid=701f2000000tsLNAAY&; The 3 vulnerabilities are : CVE-2017-5754, CVE-2017-5753, & CVE-2017-5715 More information about these vulnerabilities are here : https://www.wired.com/story/meltdown-and-spectre-patches-take-toll/

Thanks, gsr

[gsr9999]

@genomax, thank you for your answer

Answer 1

[GenoMax]

Your admins are going to upgrade anyway so you don't have much of a choice but to take the hit when it shows up. Initial reports were a bit exaggerated though. It may be more like 5-10%.

I would suggest that you not worry about this. It may add hit% more time to your pipeline but on a job that may run for multiple hours/overnight you will likely not notice that difference. If you are paying for your compute by the cpu time then the provider should adjust their rates to account for this hit.