qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Qemu-devel] [PATCH V3 5/6] migration: calculate downtime on dst side


From: Alexey Perevalov
Subject: [Qemu-devel] [PATCH V3 5/6] migration: calculate downtime on dst side
Date: Wed, 26 Apr 2017 08:06:19 +0300

This patch provides downtime calculation per vCPU,
as a summary and as a overlapped value for all vCPUs.

This approach was suggested by Peter Xu, as an improvements of
previous approch where QEMU kept tree with faulted page address and cpus bitmask
in it. Now QEMU is keeping array with faulted page address as value and vCPU
as index. It helps to find proper vCPU at UFFD_COPY time. Also it keeps
list for downtime per vCPU (could be traced with page_fault_addr)

For more details see comments for get_postcopy_total_downtime
implementation.

Downtime will not calculated if postcopy_downtime field of
MigrationIncomingState wasn't initialized.

Signed-off-by: Alexey Perevalov <address@hidden>
---
 include/migration/migration.h |   3 ++
 migration/migration.c         | 103 ++++++++++++++++++++++++++++++++++++++++++
 migration/postcopy-ram.c      |  20 +++++++-
 migration/trace-events        |   6 ++-
 4 files changed, 130 insertions(+), 2 deletions(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index b1759f7..137405b 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -139,6 +139,9 @@ void migration_incoming_state_destroy(void);
  * Functions to work with downtime context
  */
 struct DowntimeContext *downtime_context_new(void);
+void mark_postcopy_downtime_begin(uint64_t addr, int cpu);
+void mark_postcopy_downtime_end(uint64_t addr);
+uint64_t get_postcopy_total_downtime(void);
 
 /*
  * An outstanding page request, on the source, having been received
diff --git a/migration/migration.c b/migration/migration.c
index 0309c2b..b559dfe 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -2150,3 +2150,106 @@ PostcopyState postcopy_state_set(PostcopyState 
new_state)
     return atomic_xchg(&incoming_postcopy_state, new_state);
 }
 
+void mark_postcopy_downtime_begin(uint64_t addr, int cpu)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    DowntimeContext *dc;
+    if (!mis->downtime_ctx || cpu < 0) {
+        return;
+    }
+    dc = mis->downtime_ctx;
+    dc->vcpu_addr[cpu] = addr;
+    dc->last_begin = dc->page_fault_vcpu_time[cpu] =
+        qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+
+    trace_mark_postcopy_downtime_begin(addr, dc, dc->page_fault_vcpu_time[cpu],
+            cpu);
+}
+
+void mark_postcopy_downtime_end(uint64_t addr)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    DowntimeContext *dc;
+    int i;
+    bool all_vcpu_down = true;
+    int64_t now;
+
+    if (!mis->downtime_ctx) {
+        return;
+    }
+    dc = mis->downtime_ctx;
+    now = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+
+    /* check all vCPU down,
+     * QEMU has bitmap.h, but even with bitmap_and
+     * will be a cycle */
+    for (i = 0; i < smp_cpus; i++) {
+        if (dc->vcpu_addr[i]) {
+            continue;
+        }
+        all_vcpu_down = false;
+        break;
+    }
+
+    if (all_vcpu_down) {
+        dc->total_downtime += now - dc->last_begin;
+    }
+
+    /* lookup cpu, to clear it */
+    for (i = 0; i < smp_cpus; i++) {
+        uint64_t vcpu_downtime;
+
+        if (dc->vcpu_addr[i] != addr) {
+            continue;
+        }
+
+        vcpu_downtime = now - dc->page_fault_vcpu_time[i];
+
+        dc->vcpu_addr[i] = 0;
+        dc->vcpu_downtime[i] += vcpu_downtime;
+    }
+
+    trace_mark_postcopy_downtime_end(addr, dc, dc->total_downtime);
+}
+
+/*
+ * This function just provide calculated before downtime per cpu and trace it.
+ * Total downtime is calculated in mark_postcopy_downtime_end.
+ *
+ *
+ * Assume we have 3 CPU
+ *
+ *      S1        E1           S1               E1
+ * -----***********------------xxx***************------------------------> CPU1
+ *
+ *             S2                E2
+ * ------------****************xxx---------------------------------------> CPU2
+ *
+ *                         S3            E3
+ * ------------------------****xxx********-------------------------------> CPU3
+ *
+ * We have sequence S1,S2,E1,S3,S1,E2,E3,E1
+ * S2,E1 - doesn't match condition due to sequence S1,S2,E1 doesn't include 
CPU3
+ * S3,S1,E2 - sequence includes all CPUs, in this case overlap will be S1,E2 -
+ *            it's a part of total downtime.
+ * S1 - here is last_begin
+ * Legend of the picture is following:
+ *              * - means downtime per vCPU
+ *              x - means overlapped downtime (total downtime)
+ */
+uint64_t get_postcopy_total_downtime(void)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+
+    if (!mis->downtime_ctx) {
+        return 0;
+    }
+
+    if (trace_event_get_state(TRACE_DOWNTIME_PER_CPU)) {
+        int i;
+        for (i = 0; i < smp_cpus; i++) {
+            trace_downtime_per_cpu(i, mis->downtime_ctx->vcpu_downtime[i]);
+        }
+    }
+    return mis->downtime_ctx->total_downtime;
+}
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index ce1ea5d..03c2be7 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -23,6 +23,7 @@
 #include "migration/postcopy-ram.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/balloon.h"
+#include <sys/param.h>
 #include "qemu/error-report.h"
 #include "trace.h"
 
@@ -470,6 +471,19 @@ static int ram_block_enable_notify(const char *block_name, 
void *host_addr,
     return 0;
 }
 
+static int get_mem_fault_cpu_index(uint32_t pid)
+{
+    CPUState *cpu_iter;
+
+    CPU_FOREACH(cpu_iter) {
+        if (cpu_iter->thread_id == pid) {
+            return cpu_iter->cpu_index;
+        }
+    }
+    trace_get_mem_fault_cpu_index(pid);
+    return -1;
+}
+
 /*
  * Handle faults detected by the USERFAULT markings
  */
@@ -547,8 +561,11 @@ static void *postcopy_ram_fault_thread(void *opaque)
         rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
         trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
                                                 qemu_ram_get_idstr(rb),
-                                                rb_offset);
+                                                rb_offset,
+                                                msg.arg.pagefault.feat.ptid);
 
+        mark_postcopy_downtime_begin((uintptr_t)(msg.arg.pagefault.address),
+                         get_mem_fault_cpu_index(msg.arg.pagefault.feat.ptid));
         /*
          * Send the request to the source - we want to request one
          * of our host page sizes (which is >= TPS)
@@ -643,6 +660,7 @@ int postcopy_place_page(MigrationIncomingState *mis, void 
*host, void *from,
 
         return -e;
     }
+    mark_postcopy_downtime_end((uint64_t)host);
 
     trace_postcopy_place_page(host);
     return 0;
diff --git a/migration/trace-events b/migration/trace-events
index 7372ce2..19e7dc5 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -110,6 +110,9 @@ process_incoming_migration_co_end(int ret, int ps) "ret=%d 
postcopy-state=%d"
 process_incoming_migration_co_postcopy_end_main(void) ""
 migration_set_incoming_channel(void *ioc, const char *ioctype) "ioc=%p 
ioctype=%s"
 migration_set_outgoing_channel(void *ioc, const char *ioctype, const char 
*hostname)  "ioc=%p ioctype=%s hostname=%s"
+mark_postcopy_downtime_begin(uint64_t addr, void *dd, int64_t time, int cpu) 
"addr 0x%" PRIx64 " dd %p time %" PRId64 " cpu %d"
+mark_postcopy_downtime_end(uint64_t addr, void *dd, int64_t time) "addr 0x%" 
PRIx64 " dd %p time %" PRId64
+downtime_per_cpu(int cpu_index, int64_t downtime) "downtime cpu[%d]=%" PRId64
 
 # migration/rdma.c
 qemu_rdma_accept_incoming_migration(void) ""
@@ -186,7 +189,7 @@ postcopy_ram_enable_notify(void) ""
 postcopy_ram_fault_thread_entry(void) ""
 postcopy_ram_fault_thread_exit(void) ""
 postcopy_ram_fault_thread_quit(void) ""
-postcopy_ram_fault_thread_request(uint64_t hostaddr, const char *ramblock, 
size_t offset) "Request for HVA=%" PRIx64 " rb=%s offset=%zx"
+postcopy_ram_fault_thread_request(uint64_t hostaddr, const char *ramblock, 
size_t offset, uint32_t pid) "Request for HVA=%" PRIx64 " rb=%s offset=%zx %u"
 postcopy_ram_incoming_cleanup_closeuf(void) ""
 postcopy_ram_incoming_cleanup_entry(void) ""
 postcopy_ram_incoming_cleanup_exit(void) ""
@@ -195,6 +198,7 @@ save_xbzrle_page_skipping(void) ""
 save_xbzrle_page_overflow(void) ""
 ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" 
PRIu64 " milliseconds, %d iterations"
 ram_load_complete(int ret, uint64_t seq_iter) "exit_code %d seq iteration %" 
PRIu64
+get_mem_fault_cpu_index(uint32_t pid) "pid %u is not vCPU"
 
 # migration/exec.c
 migration_exec_outgoing(const char *cmd) "cmd=%s"
-- 
1.9.1




reply via email to

[Prev in Thread] Current Thread [Next in Thread]