Looking for books & other references mentioned in this video? Check out the video description for all the links! Want early access to videos & exclusive perks? Join our channel membership today: th-cam.com/channels/s_tLP3AiwYKwdUHpltJPuA.htmljoin Question for you: What’s your greatest takeaway from this video? Let us know in the comments! ⬇
Great talk, Great organisational perspective, and an amazing takeaway: 'Every engineering decision is a buying decision.' One note: G1 -> ZGC is simple, but likely not an ideal solution. The issue here was probably that autoscaling had an overly sensitive configuration, which caused the losses. ZDC is a solution for latency, but it requires more CPU and memory. So for the same resources G1 would have a better max throughput (and more options to tune). Large pause time for G1 may also indicate that instances were not properly rightsized (like unnecessary too much memory per instance).
Looking for books & other references mentioned in this video?
Check out the video description for all the links!
Want early access to videos & exclusive perks?
Join our channel membership today: th-cam.com/channels/s_tLP3AiwYKwdUHpltJPuA.htmljoin
Question for you: What’s your greatest takeaway from this video? Let us know in the comments! ⬇
From this kind of dedication, lots of organizations can learn a lot.
Great talk, Great organisational perspective, and an amazing takeaway: 'Every engineering decision is a buying decision.'
One note: G1 -> ZGC is simple, but likely not an ideal solution. The issue here was probably that autoscaling had an overly sensitive configuration, which caused the losses. ZDC is a solution for latency, but it requires more CPU and memory. So for the same resources G1 would have a better max throughput (and more options to tune). Large pause time for G1 may also indicate that instances were not properly rightsized (like unnecessary too much memory per instance).