On 09/09/19 12:49, Yury Kotov wrote: > Hi, > > V6: > * Fix "Add qemu_cond_timedwait" patch: > - Changed return type for qemu_cond_timedwait (void -> bool) > - Added details in commit message > > V5: > * Updated sleep loop in throttle_thread at the suggestion of Paolo Bonzini > * Fixed hanging of test > > V4: > * The test was simplified to prevent false fails. > > V3: > * Rebase fixes (migrate_set_parameter -> migrate_set_parameter_int) > > V2: > * Added a test > * Fixed qemu_cond_timedwait for qsp > > I wrote a test for migration auto converge and found out a strange thing: > 1. Enable auto converge > 2. Set max-bandwidth 1Gb/s > 3. Set downtime-limit 1ms > 4. Run standard test (just writes a byte per page) > 5. Wait for converge > 6. It's converged with 99% throttle percentage > 7. The result downtime was about 300-600ms <<<< > > It's much higher than expected 1ms. I figured out that cpu_throttle_thread() > function sleeps for 100ms+ for high throttle percentage (>=95%) in VCPU > thread. > And it sleeps even after a cpu kick. > > Fixed it by using timedwait for ms part of sleep. > E.g timedwait(halt_cond, 1ms) + usleep(500).
Queued, thanks. Paolo
