[PATCH 2/2][KVM] modify account_system_time() to add cputime to cpustat->guest

[PATCH 2/2][KVM] modify account_system_time() to add cputime to cpustat->guest

[Laurent Vivier]

[-- Attachment #1: Type: text/plain, Size: 636 bytes --]

modify account_system_time() to add cputime to cpustat->guest if we are running
a VCPU. We add this cputime to cpustat->user too instead of cpustat->system
because this part of KVM code is in fact user code although it is executed in
the kernel. We duplicate VCPU time between guest and user to allow an unmodified
"top(1)" to display correct value. A modified "top(1)" is able to display good
cpu user time and cpu guest time by subtracting cpu guest time from cpu user time.

Signed-Off-by: Laurent Vivier <Laurent.Vivier@bull.net>
-- 
------------- Laurent.Vivier@bull.net  --------------
          "Software is hard" - Donald Knuth

[-- Attachment #2: kvm_stat_guest --]
[-- Type: text/plain, Size: 2318 bytes --]

Index: kvm/drivers/kvm/vmx.c
===================================================================
--- kvm.orig/drivers/kvm/vmx.c	2007-08-10 16:49:40.000000000 +0200
+++ kvm/drivers/kvm/vmx.c	2007-08-10 17:21:46.000000000 +0200
@@ -2078,6 +2078,7 @@
 	local_irq_disable();
 
 	vcpu->guest_mode = 1;
+	current->flags |= PF_VCPU;
 	if (vcpu->requests)
 		if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests))
 		    vmx_flush_tlb(vcpu);
Index: kvm/drivers/kvm/svm.c
===================================================================
--- kvm.orig/drivers/kvm/svm.c	2007-08-10 16:49:40.000000000 +0200
+++ kvm/drivers/kvm/svm.c	2007-08-10 16:52:29.000000000 +0200
@@ -1404,6 +1404,7 @@
 	clgi();
 
 	vcpu->guest_mode = 1;
+	current->flags |= PF_VCPU;
 	if (vcpu->requests)
 		if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests))
 		    svm_flush_tlb(vcpu);
Index: kvm/include/linux/sched.h
===================================================================
--- kvm.orig/include/linux/sched.h	2007-08-10 16:49:40.000000000 +0200
+++ kvm/include/linux/sched.h	2007-08-10 16:52:29.000000000 +0200
@@ -1310,6 +1310,7 @@
 #define PF_STARTING	0x00000002	/* being created */
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
+#define PF_VCPU		0x00000010	/* I'm virtual CPU */
 #define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
 #define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
 #define PF_DUMPCORE	0x00000200	/* dumped core */
Index: kvm/kernel/sched.c
===================================================================
--- kvm.orig/kernel/sched.c	2007-08-10 16:49:40.000000000 +0200
+++ kvm/kernel/sched.c	2007-08-10 17:21:30.000000000 +0200
@@ -3246,10 +3246,18 @@
 	struct rq *rq = this_rq();
 	cputime64_t tmp;
 
+	tmp = cputime_to_cputime64(cputime);
+	if (p->flags & PF_VCPU) {
+		p->utime = cputime_add(p->utime, cputime);
+		cpustat->user = cputime64_add(cpustat->user, tmp);
+		cpustat->guest = cputime64_add(cpustat->guest, tmp);
+		p->flags &= ~PF_VCPU;
+		return;
+	}
+
 	p->stime = cputime_add(p->stime, cputime);
 
 	/* Add system time to cpustat. */
-	tmp = cputime_to_cputime64(cputime);
 	if (hardirq_count() - hardirq_offset)
 		cpustat->irq = cputime64_add(cpustat->irq, tmp);
 	else if (softirq_count())

Re: [PATCH 2/2][KVM] modify account_system_time() to add cputime to cpustat->guest

[Laurent Vivier]

[-- Attachment #1: Type: text/plain, Size: 287 bytes --]

You can find attached to this email the patch to apply to procps-3.2.7[1] to
allow "top(1)" to display the cpu guest time.

Laurent
[1] http://procps.sf.net/procps-3.2.7.tar.gz
-- 
------------- Laurent.Vivier@bull.net  --------------
          "Software is hard" - Donald Knuth

[-- Attachment #2: procps-proc_stat_guest --]
[-- Type: text/plain, Size: 4716 bytes --]

Index: procps-3.2.7/top.c
===================================================================
--- procps-3.2.7.orig/top.c	2007-08-08 16:13:17.000000000 +0200
+++ procps-3.2.7/top.c	2007-08-10 16:46:01.000000000 +0200
@@ -935,7 +935,8 @@
    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 @@
       &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 @@
       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 @@
    // 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 @@
    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 @@
          (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 @@
    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	2007-08-08 16:14:47.000000000 +0200
+++ procps-3.2.7/top.h	2007-08-08 17:01:45.000000000 +0200
@@ -211,8 +211,8 @@
 // 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 @@
 #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"