AWS Outperforms GCP in the 2018 Cloud Report
cockroachlabs.com
AWS Outperforms GCP in the 2018 Cloud Report
1–10 of 104 posts
Re: AWS Outperforms GCP in the 2018 Cloud Report
#2Is there anything open source so I can reproduce these results?
Re: AWS Outperforms GCP in the 2018 Cloud Report
#3> At first glance it appears that GCP has a tighter latency spread (when compared to the network throughput) centered on 0.2 ms
Comparing a distribution of two completely different metrics is not particularly meaningful. You can change the histogram buckets to a different size and it will look just as spread out. When I first read it, I thought it was saying GCP has a tighter spread than AWS. This was confusing, especially since the chart immediately above that seems to have AWS and GCP numbers flipped.
Re: AWS Outperforms GCP in the 2018 Cloud Report
#4I wonder if they will consider expanding the cloud report to things that are not necessarily relevant to Cockroach labs use-case. In my work, latency to the block store (especially outliers) is very relevant. It would be great to see latency distributions of various workloads (sequential/random and read/write/mixed) to the patform's distributed block store.
edit: I missed that 95th percentile latency for read and write was included. That is helpful; I also typically look at p99.99 and p100.
Re: AWS Outperforms GCP in the 2018 Cloud Report
#5Is there anything open source so I can reproduce these results?
All of the benchmarks we used to test are open source.
TPC-C https://www.cockroachlabs.com/docs/stable/performance-benchm... Sysbench https://github.com/akopytov/sysbench Stress-ng https://kernel.ubuntu.com/~cking/stress-ng/ iPerf https://github.com/esnet/iperf PING https://linux.die.net/man/8/ping
Re: AWS Outperforms GCP in the 2018 Cloud Report
#6Is there anything open source so I can reproduce these results?
The report states they are using iperf, ping, stress-ng, and sysbench; these are all open-source. There might not be enough details to reproduce exactly, but I think there is enough there that you should be able to produce similar results.
Re: AWS Outperforms GCP in the 2018 Cloud Report
#7I wonder if they will consider expanding the cloud report to things that are not necessarily relevant to Cockroach labs use-case. In my work, latency to the block store (especially outliers) is very relevant. It would be great to see latency distributions of various workloads (sequential/random and read/write/mixed) to the patform's distributed block store. edit: I missed that 95th percentile latency for read and wri…
We can consider expanding this in our testing next year! Glad you found it helpful
Re: AWS Outperforms GCP in the 2018 Cloud Report
#8I wonder if they will consider expanding the cloud report to things that are not necessarily relevant to Cockroach labs use-case. In my work, latency to the block store (especially outliers) is very relevant. It would be great to see latency distributions of various workloads (sequential/random and read/write/mixed) to the patform's distributed block store. edit: I missed that 95th percentile latency for read and wri…
You can tradeoff talk latency vs cost yourself easily.
For example, you could have two copies of your data in the block store, and issue reads to both simultaneously, and use whichever returns first. Suddenly, your 99% latency becomes your 99.99% latency...
You can do the same for writes (albeit a bit more complex).
Re: AWS Outperforms GCP in the 2018 Cloud Report
#9Is this table labeled wrong?
https://d33wubrfki0l68.cloudfront.net/f61cd6683f5c13f8d2b506...
All the text around it says GCP is worse, but the table shows GCP is better.
Re: AWS Outperforms GCP in the 2018 Cloud Report
#10Very promising results!Look forward to seeing what’s in store for 2019.