summary refs log tree commit diff stats
path: root/results/classifier/118/network/1054180
diff options
context:
space:
mode:
authorChristian Krinitsin <mail@krinitsin.com>2025-06-16 16:59:00 +0000
committerChristian Krinitsin <mail@krinitsin.com>2025-06-16 16:59:33 +0000
commit9aba81d8eb048db908c94a3c40c25a5fde0caee6 (patch)
treeb765e7fb5e9a3c2143c68b0414e0055adb70e785 /results/classifier/118/network/1054180
parentb89a938452613061c0f1f23e710281cf5c83cb29 (diff)
downloadqemu-analysis-9aba81d8eb048db908c94a3c40c25a5fde0caee6.tar.gz
qemu-analysis-9aba81d8eb048db908c94a3c40c25a5fde0caee6.zip
add 18th iteration of classifier
Diffstat (limited to 'results/classifier/118/network/1054180')
-rw-r--r--results/classifier/118/network/105418053
1 files changed, 53 insertions, 0 deletions
diff --git a/results/classifier/118/network/1054180 b/results/classifier/118/network/1054180
new file mode 100644
index 000000000..af937e7e0
--- /dev/null
+++ b/results/classifier/118/network/1054180
@@ -0,0 +1,53 @@
+network: 0.951
+virtual: 0.899
+performance: 0.869
+graphic: 0.835
+device: 0.778
+files: 0.728
+user-level: 0.721
+vnc: 0.641
+semantic: 0.558
+ppc: 0.522
+socket: 0.476
+hypervisor: 0.418
+architecture: 0.394
+kernel: 0.340
+i386: 0.338
+PID: 0.332
+debug: 0.312
+register: 0.311
+x86: 0.310
+risc-v: 0.294
+peripherals: 0.282
+boot: 0.263
+mistranslation: 0.225
+TCG: 0.198
+permissions: 0.176
+VMM: 0.161
+arm: 0.156
+KVM: 0.155
+assembly: 0.102
+
+DNS activity in slirp (user networking) mode quickly depletes file descriptors and crashes qemu
+
+Hi, we have encountered quite some trouble with filedescriptor depletion of the qemu process. We have figured out that it can be demonstrated easily by doing a lot of DNS queries inside the VM -- in our real world scenario this is caused by running centos network install with a fast mirror.
+
+This situation is further problematic because qemu can't handle fd depletion very well:
+1) if ulimit is 1024 then qemu hangs in infinite loop whenever it tries to open the 1025th fd
+2) setting ulimit >1024 does not help that much because qemu uses select and max. fd set size is 1024 per default => qemu crashes because of buffer overflow in select()
+3) setting ulimit > 1024 AND recompiling with large enough fd set size AND disabling gcc's fortify source seems to work, but that's really just a hot-fix
+
+The problem can be replicated quite easily by running something like
+
+while :; do echo >/dev/udp/10.0.2.3/53; done
+
+inside a Linux VM -- crash comes very soon.
+
+This problem is present in current qemu (1.2.0) and in earlier as well.
+
+Triaging old bug tickets ... can you still reproduce this problem with the latest version of QEMU (currently v2.9 or a release candidate of 2.10)?
+
+Also could you please provide the exact command line that you use to start QEMU?
+
+[Expired for QEMU because there has been no activity for 60 days.]
+