From 3a7804c3065ac79ff6e609e75ff2765d79f64f85 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 2 May 2018 18:47:22 +0800 Subject: migration: allow fault thread to pause Allows the fault thread to stop handling page faults temporarily. When network failure happened (and if we expect a recovery afterwards), we should not allow the fault thread to continue sending things to source, instead, it should halt for a while until the connection is rebuilt. When the dest main thread noticed the failure, it kicks the fault thread to switch to pause state. Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Peter Xu Message-Id: <20180502104740.12123-7-peterx@redhat.com> Signed-off-by: Juan Quintela --- migration/postcopy-ram.c | 54 ++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 50 insertions(+), 4 deletions(-) (limited to 'migration/postcopy-ram.c') diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 8ceeaa2a93..658b750a8e 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -830,6 +830,17 @@ static void mark_postcopy_blocktime_end(uintptr_t addr) affected_cpu); } +static bool postcopy_pause_fault_thread(MigrationIncomingState *mis) +{ + trace_postcopy_pause_fault_thread(); + + qemu_sem_wait(&mis->postcopy_pause_sem_fault); + + trace_postcopy_pause_fault_thread_continued(); + + return true; +} + /* * Handle faults detected by the USERFAULT markings */ @@ -880,6 +891,22 @@ static void *postcopy_ram_fault_thread(void *opaque) break; } + if (!mis->to_src_file) { + /* + * Possibly someone tells us that the return path is + * broken already using the event. We should hold until + * the channel is rebuilt. + */ + if (postcopy_pause_fault_thread(mis)) { + mis->last_rb = NULL; + /* Continue to read the userfaultfd */ + } else { + error_report("%s: paused but don't allow to continue", + __func__); + break; + } + } + if (pfd[1].revents) { uint64_t tmp64 = 0; @@ -942,18 +969,37 @@ static void *postcopy_ram_fault_thread(void *opaque) (uintptr_t)(msg.arg.pagefault.address), msg.arg.pagefault.feat.ptid, rb); +retry: /* * Send the request to the source - we want to request one * of our host page sizes (which is >= TPS) */ if (rb != mis->last_rb) { mis->last_rb = rb; - migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb), - rb_offset, qemu_ram_pagesize(rb)); + ret = migrate_send_rp_req_pages(mis, + qemu_ram_get_idstr(rb), + rb_offset, + qemu_ram_pagesize(rb)); } else { /* Save some space */ - migrate_send_rp_req_pages(mis, NULL, - rb_offset, qemu_ram_pagesize(rb)); + ret = migrate_send_rp_req_pages(mis, + NULL, + rb_offset, + qemu_ram_pagesize(rb)); + } + + if (ret) { + /* May be network failure, try to wait for recovery */ + if (ret == -EIO && postcopy_pause_fault_thread(mis)) { + /* We got reconnected somehow, try to continue */ + mis->last_rb = NULL; + goto retry; + } else { + /* This is a unavoidable fault */ + error_report("%s: migrate_send_rp_req_pages() get %d", + __func__, ret); + break; + } } } -- cgit v1.2.3-59-g8ed1b