TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Why libvirt supports only 14 PCIe hotplugged devices on x86-64

249 pointsby andreyvitalmost 2 years ago

7 comments

josephcsiblealmost 2 years ago
&gt; It already supports a number of obscure options (you can make QEMU claim to support a CPU feature regardless of whether the host CPU supports it, really?), so adding one more woild fit in just fine.<p>&gt; Nope. “there are no plans to address it further or fix it in an upcoming release”.<p>&lt;<a href="https:&#x2F;&#x2F;bugzilla.redhat.com&#x2F;show_bug.cgi?id=1408810" rel="nofollow noreferrer">https:&#x2F;&#x2F;bugzilla.redhat.com&#x2F;show_bug.cgi?id=1408810</a>&gt;<p>I could see that being the response of an individual open-source developer working for free. But that was IBM saying that, and people pay big bucks to IBM to fix things like this.
评论 #37026741 未加载
评论 #37024841 未加载
评论 #37024990 未加载
评论 #37035825 未加载
评论 #37031684 未加载
formerly_provenalmost 2 years ago
&gt; So if you wish to have more than 14 PCIe slots in your VM, you’ll have to use QEMU directly.<p>No need, libvirt can pass arbitrary options to QEMU.<p><a href="https:&#x2F;&#x2F;libvirt.org&#x2F;kbase&#x2F;qemu-passthrough-security.html" rel="nofollow noreferrer">https:&#x2F;&#x2F;libvirt.org&#x2F;kbase&#x2F;qemu-passthrough-security.html</a>
评论 #37025070 未加载
评论 #37031285 未加载
tedunangstalmost 2 years ago
I&#x27;m curious to know more about the VM host machine that they plugged 15 e1000 cards into to test this limitation. And even more curious about the non-test environment in which somebody ran into this limitation.<p>I can only imagine trying to passthrough 20 nvme devices to a guest, but it seems like a very weird configuration.
评论 #37025365 未加载
评论 #37025228 未加载
评论 #37031213 未加载
EmilioPeJualmost 2 years ago
If I&#x27;m not wrong, the pre-allocation of I&#x2F;O ranges in PCIe bridges is needed only if you intend to hot-plug devices that were not present in the first enumeration.. but in VMs the hardware is known from the start and the PCIe enumeration can assign I&#x2F;O ranges only if devices underneath actually needs them... is there a reason why hot-plugging is needed in VMs?
评论 #37025484 未加载
评论 #37025500 未加载
评论 #37031253 未加载
评论 #37025513 未加载
评论 #37026968 未加载
评论 #37025502 未加载
magicalhippoalmost 2 years ago
I ran into this on FreeNAS which uses Bhyve. Not sure if it&#x27;s FreeNAS&#x27; way of doing things, but adding a virtual disk using VirtIO creates a separate SATA controller.<p>I tried forwarding quad NVMe&#x27;s and couldn&#x27;t get it working until I discovered I was hitting this limitation between the existing disks and VirtIO network card.
评论 #37035862 未加载
mixmastamykalmost 2 years ago
Would like to hear more about why i&#x2F;o ports stayed fixed and &quot;usage decreased over time.&quot; USB&#x2F;TB devices must not use them, right?
评论 #37027764 未加载
评论 #37025229 未加载
评论 #37031348 未加载
joelhaasnootalmost 2 years ago
But this doesn&#x27;t answer the question why 14 and not 16. There&#x27;s a diff of two there...
评论 #37036267 未加载