[Qemu-devel] [PATCHl] kqemu: Linux CPU accouting

[Laurent Vivier <Laurent.Vivier@bull.net>]

[-- Attachment #1: Type: text/plain, Size: 584 bytes --]

Hi,

Here is a patch allowing to register guest time to guest field
of /proc/stat and /proc/%pid/stat (it moves also this part of cpu time
from system time to user time). This field is available since linux
2.6.24.

To play with it, I provide a second patch which is a patch for
procps-3.2.7 allowing to display correctly this value (the per cpu "g"
field).

For more details, see:

http://kerneltrap.org/Linux/Virtual_Machine_Time_Accounting

Regards,
Laurent
-- 
------------- Laurent.Vivier@bull.net ---------------
"The best way to predict the future is to invent it."
- Alan Kay

[-- Attachment #2: kqemu-guest-time.patch --]
[-- Type: text/x-patch, Size: 647 bytes --]

Index: kqemu-1.4.0pre1/kqemu-linux.c
===================================================================
--- kqemu-1.4.0pre1.orig/kqemu-linux.c	2008-06-11 10:29:37.000000000 +0200
+++ kqemu-1.4.0pre1/kqemu-linux.c	2008-06-11 10:31:30.000000000 +0200
@@ -318,7 +318,13 @@ static int kqemu_ioctl(struct inode *ino
 #if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,10)
             unlock_kernel();
 #endif
+#ifdef PF_VCPU
+            current->flags |= PF_VCPU;
+#endif
             ret = kqemu_exec(s);
+#ifdef PF_VCPU
+            current->flags &= ~PF_VCPU;
+#endif
 #if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,10)
             lock_kernel();
 #endif

[-- Attachment #3: procps-3.2.7-guest-time.patch --]
[-- Type: text/x-patch, Size: 5049 bytes --]

Index: procps-3.2.7/top.c
===================================================================
--- procps-3.2.7.orig/top.c	2007-08-10 17:34:46.000000000 +0200
+++ procps-3.2.7/top.c	2007-08-13 13:14:43.000000000 +0200
@@ -935,7 +935,8 @@ static CPU_t *cpus_refresh (CPU_t *cpus)
    cpus[Cpu_tot].x = 0;  // FIXME: can't tell by kernel version number
    cpus[Cpu_tot].y = 0;  // FIXME: can't tell by kernel version number
    cpus[Cpu_tot].z = 0;  // FIXME: can't tell by kernel version number
-   num = sscanf(buf, "cpu %Lu %Lu %Lu %Lu %Lu %Lu %Lu %Lu",
+   cpus[Cpu_tot].g = 0;  // FIXME: can't tell by kernel version number
+   num = sscanf(buf, "cpu %Lu %Lu %Lu %Lu %Lu %Lu %Lu %Lu %Lu",
       &cpus[Cpu_tot].u,
       &cpus[Cpu_tot].n,
       &cpus[Cpu_tot].s,
@@ -943,7 +944,8 @@ static CPU_t *cpus_refresh (CPU_t *cpus)
       &cpus[Cpu_tot].w,
       &cpus[Cpu_tot].x,
       &cpus[Cpu_tot].y,
-      &cpus[Cpu_tot].z
+      &cpus[Cpu_tot].z,
+      &cpus[Cpu_tot].g
    );
    if (num < 4)
          std_err("failed /proc/stat read");
@@ -960,9 +962,10 @@ static CPU_t *cpus_refresh (CPU_t *cpus)
       cpus[i].x = 0;  // FIXME: can't tell by kernel version number
       cpus[i].y = 0;  // FIXME: can't tell by kernel version number
       cpus[i].z = 0;  // FIXME: can't tell by kernel version number
-      num = sscanf(buf, "cpu%u %Lu %Lu %Lu %Lu %Lu %Lu %Lu %Lu",
+      cpus[i].g = 0;  // FIXME: can't tell by kernel version number
+      num = sscanf(buf, "cpu%u %Lu %Lu %Lu %Lu %Lu %Lu %Lu %Lu %Lu",
          &cpus[i].id,
-         &cpus[i].u, &cpus[i].n, &cpus[i].s, &cpus[i].i, &cpus[i].w, &cpus[i].x, &cpus[i].y, &cpus[i].z
+         &cpus[i].u, &cpus[i].n, &cpus[i].s, &cpus[i].i, &cpus[i].w, &cpus[i].x, &cpus[i].y, &cpus[i].z, &cpus[i].g
       );
       if (num < 4)
             std_err("failed /proc/stat read");
@@ -2879,10 +2882,11 @@ static void summaryhlp (CPU_t *cpu, cons
    // we'll trim to zero if we get negative time ticks,
    // which has happened with some SMP kernels (pre-2.4?)
 #define TRIMz(x)  ((tz = (SIC_t)(x)) < 0 ? 0 : tz)
-   SIC_t u_frme, s_frme, n_frme, i_frme, w_frme, x_frme, y_frme, z_frme, tot_frme, tz;
+   SIC_t u_frme, s_frme, n_frme, i_frme, w_frme, x_frme, y_frme, z_frme, g_frme, tot_frme, tz, u_tmp;
    float scale;
 
-   u_frme = cpu->u - cpu->u_sav;
+   u_tmp = cpu->u - cpu->g;
+   u_frme = TRIMz(u_tmp - cpu->u_sav);
    s_frme = cpu->s - cpu->s_sav;
    n_frme = cpu->n - cpu->n_sav;
    i_frme = TRIMz(cpu->i - cpu->i_sav);
@@ -2890,7 +2894,8 @@ static void summaryhlp (CPU_t *cpu, cons
    x_frme = cpu->x - cpu->x_sav;
    y_frme = cpu->y - cpu->y_sav;
    z_frme = cpu->z - cpu->z_sav;
-   tot_frme = u_frme + s_frme + n_frme + i_frme + w_frme + x_frme + y_frme + z_frme;
+   g_frme = cpu->g - cpu->g_sav;
+   tot_frme = u_frme + s_frme + n_frme + i_frme + w_frme + x_frme + y_frme + z_frme + g_frme;
    if (tot_frme < 1) tot_frme = 1;
    scale = 100.0 / (float)tot_frme;
 
@@ -2908,13 +2913,14 @@ static void summaryhlp (CPU_t *cpu, cons
          (float)w_frme * scale,
          (float)x_frme * scale,
          (float)y_frme * scale,
-         (float)z_frme * scale
+         (float)z_frme * scale,
+         (float)g_frme * scale
       )
    );
    Msg_row += 1;
 
    // remember for next time around
-   cpu->u_sav = cpu->u;
+   cpu->u_sav = u_tmp;
    cpu->s_sav = cpu->s;
    cpu->n_sav = cpu->n;
    cpu->i_sav = cpu->i;
@@ -2922,6 +2928,7 @@ static void summaryhlp (CPU_t *cpu, cons
    cpu->x_sav = cpu->x;
    cpu->y_sav = cpu->y;
    cpu->z_sav = cpu->z;
+   cpu->g_sav = cpu->g;
 
 #undef TRIMz
 }
Index: procps-3.2.7/top.h
===================================================================
--- procps-3.2.7.orig/top.h	2007-08-10 17:34:46.000000000 +0200
+++ procps-3.2.7/top.h	2007-08-13 13:14:43.000000000 +0200
@@ -211,8 +211,8 @@ typedef struct HST_t {
 // calculations.  It exists primarily for SMP support but serves
 // all environments.
 typedef struct CPU_t {
-   TIC_t u, n, s, i, w, x, y, z; // as represented in /proc/stat
-   TIC_t u_sav, s_sav, n_sav, i_sav, w_sav, x_sav, y_sav, z_sav; // in the order of our display
+   TIC_t u, n, s, i, w, x, y, z, g; // as represented in /proc/stat
+   TIC_t u_sav, s_sav, n_sav, i_sav, w_sav, x_sav, y_sav, z_sav, g_sav; // in the order of our display
    unsigned id;  // the CPU ID number
 } CPU_t;
 
@@ -390,7 +390,7 @@ typedef struct WIN_t {
 #define STATES_line2x6  "%s\03" \
    " %#4.1f%% \02us,\03 %#4.1f%% \02sy,\03 %#4.1f%% \02ni,\03 %#4.1f%% \02id,\03 %#4.1f%% \02wa,\03 %#4.1f%% \02hi,\03 %#4.1f%% \02si\03\n"
 #define STATES_line2x7  "%s\03" \
-   "%#5.1f%%\02us,\03%#5.1f%%\02sy,\03%#5.1f%%\02ni,\03%#5.1f%%\02id,\03%#5.1f%%\02wa,\03%#5.1f%%\02hi,\03%#5.1f%%\02si,\03%#5.1f%%\02st\03\n"
+  "%#4.1f%%\02us,\03%#4.1f%%\02sy,\03%#4.1f%%\02ni,\03%#5.1f%%\02id,\03%#4.1f%%\02wa,\03%#4.1f%%\02hi,\03%#4.1f%%\02si,\03%#4.1f%%\02st\03,\02%#4.1f%%\02g\n"
 #ifdef CASEUP_SUMMK
 #define MEMORY_line1  "Mem: \03" \
    " %8luK \02total,\03 %8luK \02used,\03 %8luK \02free,\03 %8luK \02buffers\03\n"