Paul Chen
Paul Chen
@JohnSully we tried with this fix and just let you know it works fine for us. Thanks.
@JohnSully @benschermel John and Ben, i found a crash which happens only where there are pending writes on the client, and it triggers an assert failure. Please review the fix....
@JohnSully @benschermel John and Ben, based on our discussion, I changed to using LL_DEBUG. Please merge it. Thank you.
@JohnSully @benschermel John and Ben, a reminder please review and merge this fix. Thank you.
[maxmemory eviction cpu starvation.docx](https://github.com/Snapchat/KeyDB/files/8748056/maxmemory.eviction.cpu.starvation.docx) Attached a screenshot of "0 qps" reported by the memtier client when running the maxmemory eviction process.
@JohnSully add John to the issue here. tx
@JohnSully here is the commit 118ae701f57897dfa7a47755d1983705ac94755a , please review it. Thanks.
@JohnSully fyi John.
Here is a workaround fix https://github.com/Snapchat/KeyDB/commit/fb0c8e475f02d1391ab5e93af68745e2fbee34f1
It sounds running out of the replication buffer hard limit and triggers a fast fullsync (check your log for confirmation). Increasing the replication hardlimit in your conf will help if...