Hacker News Reader

Comment by Galanwe | Hacker News Reader

> For downloads, s5cmd can saturate a 40Gbps link (~4.3 GB/s)

I'm surprised by these claims. I have worked pretty intimately with S3 for almost 10 years now, developed high performance tools to retrieve data from it, as well as used dedicated third party tools for performant file download tailored for S3.

My experience is that individual S3 connections are capped over the board at ~80MB/s, and the throughput of 1 file is capped at 1.6GB/s (at least per ec2 instance). At least I have never managed myself nor seen any tool capable of going beyond that.

My understanding is then that this benchmark's claims of 4.3GB/s are across multiple files, but then it would be rather meaningless, as it's free concurrency basically.

View on HN

I cant verify 40Gbps because I have never had access to a pipe that fast, but when I ran this tool on an AWS instance with a 20Gbps connection, it saturated that easily and maintained that speed for the duration of the transfer.

I just spawned a r6a.16xlarge with a 25gbps NIC, created a 10GB file which I uploaded to an S3 bucket in the same region, through a local S3 VPC endpoint.

Downloading that 10GB file to /dev/shm with s5cmd took 24s, all while spawning 20 or so threads which were all idling for IO.

The same test using a Python tool (http://github.com/NewbiZ/s3pd) with the same amount of workers took 10s.

Cranking up the worker count of the latter library until there is no more speedup, I can reach 6s with 80 workers. That is, 10/6 = 1.6GB/s, which seems to confirm my previous comment.

What am I doing wrong ?

Okay I found the trick, buried in the benchmark setup of s5cmd.

The claimed numbers are _not_ reached with S3, but rather from a custom server emulating the S3 API, hosted on the client machine.

I think this is very misleading, since these benchmark numbers are not reachable in any real life scenario. It also shows that there is very little point in using s5cmd compared to other tools, since beyond 1.6GB/s the throttling will be from S3, not from the client, so any tool able to saturate 1.6GB/s will be enough.

I think that's the point of this tool, that pipelining and parallelism are necessary to get high performance out of S3.

I pushed a very large file to S3 the other day from my local machine and I was barely seeing 90 megabytes/s with 5gbps of upstream available.

I wonder what the limit is for uploads inside AWS. I've never been able to afford EC2 instances with the requisite networking or I/O performance.

The S3 API allows requests to read a byte range of the file (sorry , object). So you could have multiple connections each reading a different byte range. Then the ranges would need to be written to the target local file using a random access pattern.

I know that already... and it is exactly what I tested and confirmed here https://news.ycombinator.com/item?id=44249137

You can spawn multiple connections to S3 to retrieve chunks of a file in parallel, but each of these connections is capped at 80MB/s, and the whole of these connections, while operating on a single file, to a single EC2 instance, is capped at 1.6GB/s.

It works with single files

Also you should up your chunk size to limit tps

Source: running s5cmd in prod for 1yr+

It is definitely possible. Depends on how many 503s you might need to hit and when there heuristic model allows you to increase throughput. As a customer, you can also push for higher dedicated throughput.

Reply on news.ycombinator.com