Hi all,
This is a test for this RFC patch.
Start vm as following:
cmdline="./x86_64-softmmu/qemu-system-x86_64 -m 2560 \
-drive if=none,file=/nfs/img/fedora.qcow2,format=qcow2,id=foo \
-netdev tap,id=hn0,queues=1 \
-device virtio-net-pci,id=net-pci0,netdev=hn0 \
-device virtio-blk,drive=foo \
-enable-kvm -M pc -cpu host \
-vnc :3 \
-monitor stdio"
Continue running benchmark program named himeno[*](modified base on
original source). The code is in the attach file, make it in MIDDLE.
It costs much cpu calculation and memory. Then migrate the guest.
The source host and target host are in one switch.
"before" means the upstream version, "after" means applying this patch.
"idpr" means "inst_dirty_pages_rate", a new variable in this RFC PATCH.
"count" is "dirty sync count" in "info migrate".
"time" is "total time" in "info migrate".
"ct pct" is "cpu throttle percentage" in "info migrate".
--------------------------------------------
| | before | after |
|-----|--------------|---------------------|
|count|time(s)|ct pct|time(s)| idpr |ct pct|
|-----|-------|------|-------|------|------|
| 1 | 3 | 0 | 4 | x | 0 |
| 2 | 53 | 0 | 53 | 14237| 0 |
| 3 | 97 | 0 | 95 | 3142| 0 |
| 4 | 109 | 0 | 105 | 11085| 0 |
| 5 | 117 | 0 | 113 | 12894| 0 |
| 6 | 125 | 20 | 121 | 13549| 67 |
| 7 | 133 | 20 | 130 | 13550| 67 |
| 8 | 141 | 20 | 136 | 13587| 67 |
| 9 | 149 | 30 | 144 | 13553| 99 |
| 10 | 156 | 30 | 152 | 1474| 99 |
| 11 | 164 | 30 | 152 | 1706| 99 |
| 12 | 172 | 40 | 153 | 0 | 99 |
| 13 | 180 | 40 | 153 | 0 | x |
| 14 | 188 | 40 |---------------------|
| 15 | 195 | 50 | completed |
| 16 | 203 | 50 | |
| 17 | 211 | 50 | |
| 18 | 219 | 60 | |
| 19 | 227 | 60 | |
| 20 | 235 | 60 | |
| 21 | 242 | 70 | |
| 22 | 250 | 70 | |
| 23 | 258 | 70 | |
| 24 | 266 | 80 | |
| 25 | 274 | 80 | |
| 26 | 281 | 80 | |
| 27 | 289 | 90 | |
| 28 | 297 | 90 | |
| 29 | 305 | 90 | |
| 30 | 315 | 99 | |
| 31 | 320 | 99 | |
| 32 | 320 | 99 | |
| 33 | 321 | 99 | |
| 34 | 321 | 99 | |
|--------------------| |
| completed | |
--------------------------------------------
And the "info migrate" when completed:
before:
capabilities: xbzrle: off rdma-pin-all: off auto-converge: on
zero-blocks: off compress: off events: off postcopy-ram: off x-colo: off
Migration status: completed
total time: 321091 milliseconds
downtime: 573 milliseconds
setup: 40 milliseconds
transferred ram: 10509346 kbytes
throughput: 268.13 mbps
remaining ram: 0 kbytes
total ram: 2638664 kbytes
duplicate: 362439 pages
skipped: 0 pages
normal: 2621414 pages
normal bytes: 10485656 kbytes
dirty sync count: 34
after:
capabilities: xbzrle: off rdma-pin-all: off auto-converge: on
zero-blocks: off compress: off events: off postcopy-ram: off x-colo: off
Migration status: completed
total time: 152652 milliseconds
downtime: 290 milliseconds
setup: 47 milliseconds
transferred ram: 4997452 kbytes
throughput: 268.20 mbps
remaining ram: 0 kbytes
total ram: 2638664 kbytes
duplicate: 359598 pages
skipped: 0 pages
normal: 1246136 pages
normal bytes: 4984544 kbytes
dirty sync count: 13
It's clear that the total time is much better(321s VS 153s).
The guest began cpu throttle in the 6th dirty sync. But at this time,
the dirty pages born too much in this guest. So the default
cpu throttle percentage(20 and 10) is too small for this condition. I
just use (inst_dirty_pages_rate / 200) to calculate the cpu throttle
value. This is just an adhoc algorithm, not supported by any theories.
Of course on the other hand, the cpu throttle percentage is higher, the
guest runs more slowly. But in the result, after applying this patch,
the guest spend 23s with the cpu throttle percentage is 67 (total time
from 121 to 144), and 9s with cpu throttle percentage is 99 (total time
from 144 to completed). But in the upstream version, the guest spend
73s with the cpu throttle percentage is 70.80.90 (total time from 21 to
30), 6s with the cpu throttle percentage is 99 (total time from 30 to
completed). So I think the influence to the guest performance after my
patch is fewer than the upstream version.
Any comments will be welcome.
[*]http://accc.riken.jp/en/supercom/himenobmt/
Thanks,
Chao FanOn Thu, Dec 29, 2016 at 05:16:19PM +0800, Chao Fan wrote:
>This RFC PATCH is my demo about the new feature, here is my POC mail:
>https://lists.gnu.org/archive/html/qemu-devel/2016-12/msg00646.html
>
>When migration_bitmap_sync executed, get the time and read bitmap to
>calculate how many dirty pages born between two sync.
>Use inst_dirty_pages / (time_now - time_prev) / ram_size to get
>inst_dirty_pages_rate. Then map from the inst_dirty_pages_rate
>to cpu throttle value. I have no idea how to map it. So I just do
>that in a simple way. The mapping way is just a guess and should
>be improved.
>
>This is just a demo. There are more methods.
>1.In another file, calculate the inst_dirty_pages_rate every second
> or two seconds or another fixed time. Then set the cpu throttle
> value according to the inst_dirty_pages_rate
>2.When inst_dirty_pages_rate gets a threshold, begin cpu throttle
> and set the throttle value.
>
>Any comments will be welcome.
>
>Signed-off-by: Chao Fan <fanc.f...@cn.fujitsu.com>
>---
> include/qemu/bitmap.h | 17 +++++++++++++++++
> migration/ram.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 66 insertions(+)
>
>diff --git a/include/qemu/bitmap.h b/include/qemu/bitmap.h
>index 63ea2d0..dc99f9b 100644
>--- a/include/qemu/bitmap.h
>+++ b/include/qemu/bitmap.h
>@@ -235,4 +235,21 @@ static inline unsigned long *bitmap_zero_extend(unsigned
>long *old,
> return new;
> }
>
>+static inline unsigned long bitmap_weight(const unsigned long *src, long
>nbits)
>+{
>+ unsigned long i, count = 0, nlong = nbits / BITS_PER_LONG;
>+
>+ if (small_nbits(nbits)) {
>+ return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
>+ }
>+ for (i = 0; i < nlong; i++) {
>+ count += hweight_long(src[i]);
>+ }
>+ if (nbits % BITS_PER_LONG) {
>+ count += hweight_long(src[i] & BITMAP_LAST_WORD_MASK(nbits));
>+ }
>+
>+ return count;
>+}
>+
> #endif /* BITMAP_H */
>diff --git a/migration/ram.c b/migration/ram.c
>index a1c8089..f96e3e3 100644
>--- a/migration/ram.c
>+++ b/migration/ram.c
>@@ -44,6 +44,7 @@
> #include "exec/ram_addr.h"
> #include "qemu/rcu_queue.h"
> #include "migration/colo.h"
>+#include "hw/boards.h"
>
> #ifdef DEBUG_MIGRATION_RAM
> #define DPRINTF(fmt, ...) \
>@@ -599,6 +600,9 @@ static int64_t num_dirty_pages_period;
> static uint64_t xbzrle_cache_miss_prev;
> static uint64_t iterations_prev;
>
>+static int64_t dirty_pages_time_prev;
>+static int64_t dirty_pages_time_now;
>+
> static void migration_bitmap_sync_init(void)
> {
> start_time = 0;
>@@ -606,6 +610,49 @@ static void migration_bitmap_sync_init(void)
> num_dirty_pages_period = 0;
> xbzrle_cache_miss_prev = 0;
> iterations_prev = 0;
>+
>+ dirty_pages_time_prev = 0;
>+ dirty_pages_time_now = 0;
>+}
>+
>+static void migration_inst_rate(void)
>+{
>+ RAMBlock *block;
>+ MigrationState *s = migrate_get_current();
>+ int64_t inst_dirty_pages_rate, inst_dirty_pages = 0;
>+ int64_t i;
>+ unsigned long *num;
>+ unsigned long len = 0;
>+
>+ dirty_pages_time_now = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
>+ if (dirty_pages_time_prev != 0) {
>+ rcu_read_lock();
>+ DirtyMemoryBlocks *blocks = atomic_rcu_read(
>+ &ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION]);
>+ QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
>+ if (len == 0) {
>+ len = block->offset;
>+ }
>+ len += block->used_length;
>+ }
>+ ram_addr_t idx = (len >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE;
>+ if (((len >> TARGET_PAGE_BITS) % DIRTY_MEMORY_BLOCK_SIZE) != 0) {
>+ idx++;
>+ }
>+ for (i = 0; i < idx; i++) {
>+ num = blocks->blocks[i];
>+ inst_dirty_pages += bitmap_weight(num, DIRTY_MEMORY_BLOCK_SIZE);
>+ }
>+ rcu_read_unlock();
>+
>+ inst_dirty_pages_rate = inst_dirty_pages * TARGET_PAGE_SIZE *
>+ 1024 * 1024 * 1000 /
>+ (dirty_pages_time_now - dirty_pages_time_prev) /
>+ current_machine->ram_size;
>+ s->parameters.cpu_throttle_initial = inst_dirty_pages_rate / 200;
>+ s->parameters.cpu_throttle_increment = inst_dirty_pages_rate / 200;
>+ }
>+ dirty_pages_time_prev = dirty_pages_time_now;
> }
>
> static void migration_bitmap_sync(void)
>@@ -629,6 +676,8 @@ static void migration_bitmap_sync(void)
> trace_migration_bitmap_sync_start();
> memory_global_dirty_log_sync();
>
>+ migration_inst_rate();
>+
> qemu_mutex_lock(&migration_bitmap_mutex);
> rcu_read_lock();
> QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
>--
>2.9.3
>
/********************************************************************
This benchmark test program is measuring a cpu performance
of floating point operation by a Poisson equation solver.
If you have any question, please ask me via email.
written by Ryutaro HIMENO, November 26, 2001.
Version 3.0
----------------------------------------------
Ryutaro Himeno, Dr. of Eng.
Head of Computer Information Division,
RIKEN (The Institute of Pysical and Chemical Research)
Email : him...@postman.riken.go.jp
---------------------------------------------------------------
You can adjust the size of this benchmark code to fit your target
computer. In that case, please chose following sets of
(mimax,mjmax,mkmax):
small : 33,33,65
small : 65,65,129
midium: 129,129,257
large : 257,257,513
ext.large: 513,513,1025
This program is to measure a computer performance in MFLOPS
by using a kernel which appears in a linear solver of pressure
Poisson eq. which appears in an incompressible Navier-Stokes solver.
A point-Jacobi method is employed in this solver as this method can
be easyly vectrized and be parallelized.
------------------
Finite-difference method, curvilinear coodinate system
Vectorizable and parallelizable on each grid point
No. of grid points : imax x jmax x kmax including boundaries
------------------
A,B,C:coefficient matrix, wrk1: source term of Poisson equation
wrk2 : working area, OMEGA : relaxation parameter
BND:control variable for boundaries and objects ( = 0 or 1)
P: pressure
********************************************************************/
#include <stdio.h>
#ifdef XSMALL
#define MIMAX 16
#define MJMAX 16
#define MKMAX 16
#endif
#ifdef SSSMALL
#define MIMAX 17
#define MJMAX 17
#define MKMAX 33
#endif
#ifdef SSMALL
#define MIMAX 33
#define MJMAX 33
#define MKMAX 65
#endif
#ifdef SMALL
#define MIMAX 65
#define MJMAX 65
#define MKMAX 129
#endif
#ifdef MIDDLE
#define MIMAX 129
#define MJMAX 129
#define MKMAX 257
#endif
#ifdef LARGE
#define MIMAX 257
#define MJMAX 257
#define MKMAX 513
#endif
#ifdef ELARGE
#define MIMAX 513
#define MJMAX 513
#define MKMAX 1025
#endif
double second();
float jacobi();
void initmt();
double fflop(int,int,int);
double mflops(int,double,double);
static float p[MIMAX][MJMAX][MKMAX];
static float a[4][MIMAX][MJMAX][MKMAX],
b[3][MIMAX][MJMAX][MKMAX],
c[3][MIMAX][MJMAX][MKMAX];
static float bnd[MIMAX][MJMAX][MKMAX];
static float wrk1[MIMAX][MJMAX][MKMAX],
wrk2[MIMAX][MJMAX][MKMAX];
static int imax, jmax, kmax;
static float omega;
int
main()
{
int i,j,k,nn;
float gosa;
double cpu,cpu0,cpu1,flop,target;
target= 3.0;
omega= 0.8;
imax = MIMAX-1;
jmax = MJMAX-1;
kmax = MKMAX-1;
/*
* Initializing matrixes
*/
initmt();
printf("mimax = %d mjmax = %d mkmax = %d\n",MIMAX, MJMAX, MKMAX);
printf("imax = %d jmax = %d kmax =%d\n",imax,jmax,kmax);
nn= 3;
printf(" Start rehearsal measurement process.\n");
printf(" Measure the performance in %d times.\n\n",nn);
cpu0= second();
gosa= jacobi(nn);
cpu1= second();
cpu= cpu1 - cpu0;
flop= fflop(imax,jmax,kmax);
printf(" MFLOPS: %f time(s): %f %e\n\n",
mflops(nn,cpu,flop),cpu,gosa);
nn= (int)(target/(cpu/3.0));
printf(" Now, start the actual measurement process.\n");
printf(" The loop will be excuted in %d times\n",nn);
printf(" This will take about one minute.\n");
printf(" Wait for a while\n\n");
/*
* Start measuring
*/
while (1)
{
cpu0 = second();
gosa = jacobi(nn);
cpu1 = second();
cpu= cpu1 - cpu0;
//printf(" Loop executed for %d times\n",nn);
//printf(" Gosa : %e \n",gosa);
printf(" MFLOPS measured : %f\tcpu : %f\n",mflops(nn,cpu,flop),cpu);
fflush(stdout);
//printf(" Score based on Pentium III 600MHz : %f\n",
// mflops(nn,cpu,flop)/82,84);
}
return (0);
}
void
initmt()
{
int i,j,k;
for(i=0 ; i<MIMAX ; i++)
for(j=0 ; j<MJMAX ; j++)
for(k=0 ; k<MKMAX ; k++){
a[0][i][j][k]=0.0;
a[1][i][j][k]=0.0;
a[2][i][j][k]=0.0;
a[3][i][j][k]=0.0;
b[0][i][j][k]=0.0;
b[1][i][j][k]=0.0;
b[2][i][j][k]=0.0;
c[0][i][j][k]=0.0;
c[1][i][j][k]=0.0;
c[2][i][j][k]=0.0;
p[i][j][k]=0.0;
wrk1[i][j][k]=0.0;
bnd[i][j][k]=0.0;
}
for(i=0 ; i<imax ; i++)
for(j=0 ; j<jmax ; j++)
for(k=0 ; k<kmax ; k++){
a[0][i][j][k]=1.0;
a[1][i][j][k]=1.0;
a[2][i][j][k]=1.0;
a[3][i][j][k]=1.0/6.0;
b[0][i][j][k]=0.0;
b[1][i][j][k]=0.0;
b[2][i][j][k]=0.0;
c[0][i][j][k]=1.0;
c[1][i][j][k]=1.0;
c[2][i][j][k]=1.0;
p[i][j][k]=(float)(i*i)/(float)((imax-1)*(imax-1));
wrk1[i][j][k]=0.0;
bnd[i][j][k]=1.0;
}
}
float
jacobi(int nn)
{
int i,j,k,n;
float gosa, s0, ss;
for(n=0 ; n<nn ; ++n){
gosa = 0.0;
for(i=1 ; i<imax-1 ; i++)
for(j=1 ; j<jmax-1 ; j++)
for(k=1 ; k<kmax-1 ; k++){
s0 = a[0][i][j][k] * p[i+1][j ][k ]
+ a[1][i][j][k] * p[i ][j+1][k ]
+ a[2][i][j][k] * p[i ][j ][k+1]
+ b[0][i][j][k] * ( p[i+1][j+1][k ] - p[i+1][j-1][k ]
- p[i-1][j+1][k ] + p[i-1][j-1][k ] )
+ b[1][i][j][k] * ( p[i ][j+1][k+1] - p[i ][j-1][k+1]
- p[i ][j+1][k-1] + p[i ][j-1][k-1] )
+ b[2][i][j][k] * ( p[i+1][j ][k+1] - p[i-1][j ][k+1]
- p[i+1][j ][k-1] + p[i-1][j ][k-1] )
+ c[0][i][j][k] * p[i-1][j ][k ]
+ c[1][i][j][k] * p[i ][j-1][k ]
+ c[2][i][j][k] * p[i ][j ][k-1]
+ wrk1[i][j][k];
ss = ( s0 * a[3][i][j][k] - p[i][j][k] ) * bnd[i][j][k];
gosa+= ss*ss;
/* gosa= (gosa > ss*ss) ? a : b; */
wrk2[i][j][k] = p[i][j][k] + omega * ss;
}
for(i=1 ; i<imax-1 ; ++i)
for(j=1 ; j<jmax-1 ; ++j)
for(k=1 ; k<kmax-1 ; ++k)
p[i][j][k] = wrk2[i][j][k];
} /* end n loop */
return(gosa);
}
double
fflop(int mx,int my, int mz)
{
return((double)(mz-2)*(double)(my-2)*(double)(mx-2)*34.0);
}
double
mflops(int nn,double cpu,double flop)
{
return(flop/cpu*1.e-6*(double)nn);
}
double
second()
{
#include <sys/time.h>
struct timeval tm;
double t ;
static int base_sec = 0,base_usec = 0;
gettimeofday(&tm, NULL);
if(base_sec == 0 && base_usec == 0)
{
base_sec = tm.tv_sec;
base_usec = tm.tv_usec;
t = 0.0;
} else {
t = (double) (tm.tv_sec-base_sec) +
((double) (tm.tv_usec-base_usec))/1.0e6 ;
}
return t ;
}
