summary refs log tree commit diff stats
path: root/results/classifier/gemma3:12b/kernel/1813045
diff options
context:
space:
mode:
Diffstat (limited to 'results/classifier/gemma3:12b/kernel/1813045')
-rw-r--r--results/classifier/gemma3:12b/kernel/181304517
1 files changed, 17 insertions, 0 deletions
diff --git a/results/classifier/gemma3:12b/kernel/1813045 b/results/classifier/gemma3:12b/kernel/1813045
new file mode 100644
index 00000000..b265cdc5
--- /dev/null
+++ b/results/classifier/gemma3:12b/kernel/1813045
@@ -0,0 +1,17 @@
+
+qemu-ga fsfreeze crashes the kernel
+
+We use mainly Cloudlinux, Debian and Centos.
+We experienced many crashes on our qemu instances based on Cloudlinux during a snapshot.
+The issue is not related to CloudLinux directly, but to Qemu agent, which does not freeze the file system(s) correctly. What is actually happening:
+
+When VM backup is invoked, Qemu agent freezes the file systems, so no single change will be made during the backup. But Qemu agent does not respect the loop* devices in freezing order (we have checked its sources), which leads to the next situation: 
+1) freeze loopback fs
+              ---> send async reqs to loopback thread
+2) freeze main fs
+3) loopback thread wakes up and trying to write data to the main fs, which is still frozen, and this finally leads to the hung task and kernel crash. 
+
+I believe this is the culprit: 
+
+/dev/loop0 /tmp ext3 rw,nosuid,noexec,relatime,data=ordered 0 0
+/dev/loop0 /var/tmp ext3 rw,nosuid,noexec,relatime,data=ordered 0 0
\ No newline at end of file