09/03/2024 | Press release | Distributed by Public on 09/03/2024 10:49
When you think about cloud performance, metrics like latency and throughput are probably the first things that come to mind. We covered those metrics pretty extensively here and here. So, today, I'm walking through some factors that affect cloud performance that may not get talked about as often, including:
These factors may not be "surprising" per se especially if you remember the pain of trying to download The Matrix over dial up. But they are all things that you should consider (and that you have more control over) when thinking about cloud performance overall.
Let's dig in.
This one is pretty obvious. Larger files take longer because they require more data to be transferred. If you have a 10Mbps upload connection, a 1GB file will take approximately 800 seconds (13 minutes and 20 seconds) to upload, whereas a 100MB file will take about 80 seconds (a minute and 20 seconds). Most enterprise-grade internet connections offer higher upload speeds, but 10Mbps makes the math approachable for the sake of argument.
Small files-that is, those less than 5GB-can be uploaded in a single API call. (Note: this can vary based on cloud storage provider and configuration.) Larger files up to 10TB can be uploaded as "parts" in multiple API calls. Each part has to be a minimum of 5MB and a maximum of 5GB.
You'll notice that there is quite an overlap here! For uploading files between 5MB and 5GB, is it better to upload them in a single API call, or split them into parts? What is the optimum part size? For backup applications, which typically split all data into equally sized blocks, storing each block as a file, what is the optimum block size? As with many questions, the answer is: it depends.
Each API call incurs a more-or-less fixed overhead due to latency. For a 1GB file, assuming a single thread of execution, uploading all 1GB in a single API call will be faster than 10 API calls each uploading a 100MB part, since those additional nine API calls each incur some latency overhead. So, bigger is better, right?
Not necessarily, and that brings us to part size. Multi-threading, as mentioned above, affords us the opportunity to upload multiple parts simultaneously, which improves performance-but there are trade-offs. Typically, each part must be stored in memory as it is uploaded, so more threads means more memory consumption. If the number of threads multiplied by the part size exceeds available memory, then either the application will fail with an out of memory error, or data will be swapped to disk, reducing performance.
Downloading data offers even more flexibility, since applications can specify anyportion of the file to download in each API call. Whether uploading or downloading, there is a maximum number of threads that will drive throughput to consume all of the available bandwidth. Exceeding this maximum will consume more memory, but provide no performance benefit.
So, what to do to get the best performance possible for your use case?
Most backup and file transfer tools allow you to configure the number of threads and the amount of data to be transferred per API call, whether that's block size or part size. If you are writing your own application, you should allow for these parameters to be configured. When it comes to deployment, some experimentation may be required to achieve maximum throughput given available memory.
The big takeaway: When it comes to cloud performance, the metrics you need to care about and the performance you actually need are highly dependent on your use case, your own infrastructure, your workload, and all the network connections between your infrastructure and the cloud provider as well. So, when you're deciding how to store and use your data, it's worth taking some extra time to consider the above factors for optimum performance.