On 22.01.20 19:38, Michal Hocko wrote: > On Wed 22-01-20 19:15:47, David Hildenbrand wrote: >> On 22.01.20 17:46, Michal Hocko wrote: >>> On Wed 22-01-20 12:58:16, David Hildenbrand wrote: > [...] >>>> Especially interesting for IBM z Systems, whereby memory >>>> onlining/offlining will trigger the actual population of memory in the >>>> hypervisor. So if an admin wants to offline some memory (to give it back >>>> to the hypervisor), it would use lsmem to identify such blocks first, >>>> instead of trying random blocks until one offlining request succeeds. >>> >>> I am sorry for being dense here but I still do not understand why s390 >> >> It's good that we talk about it :) It's hard to reconstruct actual use >> cases from tools and some documentation only ... >> >> Side note (just FYI): One difference on s390x compared to other >> architectures (AFAIKS) is that once memory is offline, you might not be >> allowed (by the hypervisor) to online it again - because it was >> effectively unplugged. Such memory is not removed via remove_memory(), >> it's simply kept offline. > > I have a very vague understanding of s390 specialities but this is not > really relevant to the discussion AFAICS because this happens _after_ > offlining. Jep, that's why I flagged it as a side note. > >>> and the way how it does the hotremove matters here. Afterall there are >>> no arch specific operations done until the memory is offlined. Also >>> randomly checking memory blocks and then hoping that the offline will >>> succeed is not way much different from just trying the offline the >>> block. Both have to crawl through the pfn range and bail out on the >>> unmovable memory. >> >> I think in general we have to approaches to memory unplugging. >> >> 1. Know explicitly what you want to unplug (e.g., a DIMM spanning >> multiple memory blocks). >> >> 2. Find random memory blocks you can offline/unplug. >> >> >> For 1, I think we both agree that we don't need this. Just try to >> offline and you know if it worked. >> >> Now of course, for 2 you can try random blocks until you succeeded. From >> a sysadmin point of view that's very inefficient. From a powerpc-utils >> point of view, that's inefficient. > > How exactly is check + offline more optimal then offline which makes > check as its first step? I will get to your later points after this is > clarified. Scanning (almost) lockless is more efficient than bouncing back and forth with the device_hotplug_lock, mem_hotplug_lock, cpu_hotplug_lock and zone locks - as far as I understand. And as far as I understood, that was the whole reason of the original commit. Anyhow, you should have read until the end of my mail to find what you were looking for :) -- Thanks, David / dhildenb
