[PATCH] Perfquery can be too noisy.

[PATCH] Perfquery can be too noisy.

[Mike Heinz]

When perfquery is run against fabrics that do not support PortXmitWait, it emits this warning for every port:

ibwarn: [23225] dump_perfcounters: PortXmitWait not indicated so ignore this counter

When running ibcheckerrors on a large fabric, this leads to a flood of warnings.

The proposed patch reduces the warning to a verbose message and, on fabrics that do not support PortXmitWait, it suppresses the output of the XmitWait attribute.

Signed-off-by: Michael Heinz <michaelheinz-h88ZbnxC6KDQT0dZR+AlfA@public.gmane.org>

diff --git a/infiniband-diags/src/perfquery.c b/infiniband-diags/src/perfquery.c
index 3ae692c..812b4c2 100644
--- a/infiniband-diags/src/perfquery.c
+++ b/infiniband-diags/src/perfquery.c
@@ -282,6 +282,25 @@ static void output_aggregate_perfcounters_ext(ib_portid_t * portid)
               ALL_PORTS, buf);
 }

+static int dump_fields(char *buf, int bufsz, void *data, int start, int end)
+{
+       char val[64];
+       char *s = buf;
+       int n, field;
+       for (field = start; field <= end && bufsz > 0; field++) {
+               mad_decode_field(data, field, val);
+               if (!mad_dump_field(field, s, bufsz, val))
+                       return -1;
+               n = strlen(s);
+               s += n;
+               *s++ = '\n';
+               *s = 0;
+               n++;
+               bufsz -= n;
+       }
+       return (int)(s - buf);
+}
+
 static void dump_perfcounters(int extended, int timeout, uint16_t cap_mask,
                              ib_portid_t * portid, int port, int aggregate)
 {
@@ -293,8 +312,7 @@ static void dump_perfcounters(int extended, int timeout, uint16_t cap_mask,
                        IBERROR("perfquery");
                if (!(cap_mask & 0x1000)) {
                        /* if PortCounters:PortXmitWait not supported clear this counter */
-                       IBWARN
-                           ("PortXmitWait not indicated so ignore this counter");
+                       VERBOSE("PortXmitWait not indicated so ignore this counter");
                        perf_count.xmtwait = 0;
                        mad_encode_field(pc, IB_PC_XMT_WAIT_F,
                                         &perf_count.xmtwait);
@@ -302,7 +320,8 @@ static void dump_perfcounters(int extended, int timeout, uint16_t cap_mask,
                if (aggregate)
                        aggregate_perfcounters();
                else
-                       mad_dump_perfcounters(buf, sizeof buf, pc, sizeof pc);
+                       dump_fields(buf, sizeof buf, pc, IB_PC_FIRST_F,
+                               (cap_mask & 0x1000)?IB_PC_LAST_F:IB_PC_RCV_PKTS_F);
        } else {
                if (!(cap_mask & 0x200))        /* 1.2 errata: bit 9 is extended counter support */
                        IBWARN

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] Perfquery can be too noisy.

[Sasha Khapyorsky]

Hi Mike,

On 15:01 Thu 04 Mar     , Mike Heinz wrote:
> When perfquery is run against fabrics that do not support PortXmitWait, it emits this warning for every port:
> 
> ibwarn: [23225] dump_perfcounters: PortXmitWait not indicated so ignore this counter

Tee patch is malformed (white space mangled).

> 
> When running ibcheckerrors on a large fabric, this leads to a flood of warnings.
> 
> The proposed patch reduces the warning to a verbose message

So I'm applying this verbosity reducing part by hands.

> and, on fabrics that do not support PortXmitWait, it suppresses the output of the XmitWait attribute.

This could be done, but see the comment below.

> 
> Signed-off-by: Michael Heinz <michaelheinz-h88ZbnxC6KDQT0dZR+AlfA@public.gmane.org>
> 
> diff --git a/infiniband-diags/src/perfquery.c b/infiniband-diags/src/perfquery.c
> index 3ae692c..812b4c2 100644
> --- a/infiniband-diags/src/perfquery.c
> +++ b/infiniband-diags/src/perfquery.c
> @@ -282,6 +282,25 @@ static void output_aggregate_perfcounters_ext(ib_portid_t * portid)
>                ALL_PORTS, buf);
>  }
> 
> +static int dump_fields(char *buf, int bufsz, void *data, int start, int end)
> +{
> +       char val[64];
> +       char *s = buf;
> +       int n, field;
> +       for (field = start; field <= end && bufsz > 0; field++) {
> +               mad_decode_field(data, field, val);
> +               if (!mad_dump_field(field, s, bufsz, val))
> +                       return -1;
> +               n = strlen(s);
> +               s += n;
> +               *s++ = '\n';
> +               *s = 0;
> +               n++;
> +               bufsz -= n;
> +       }
> +       return (int)(s - buf);
> +}

Seems that this low level stuf is copied from libibmad. Wouldn't it be
better just to add appropriate function there (if needed).

Sasha

> +
>  static void dump_perfcounters(int extended, int timeout, uint16_t cap_mask,
>                               ib_portid_t * portid, int port, int aggregate)
>  {
> @@ -293,8 +312,7 @@ static void dump_perfcounters(int extended, int timeout, uint16_t cap_mask,
>                         IBERROR("perfquery");
>                 if (!(cap_mask & 0x1000)) {
>                         /* if PortCounters:PortXmitWait not supported clear this counter */
> -                       IBWARN
> -                           ("PortXmitWait not indicated so ignore this counter");
> +                       VERBOSE("PortXmitWait not indicated so ignore this counter");
>                         perf_count.xmtwait = 0;
>                         mad_encode_field(pc, IB_PC_XMT_WAIT_F,
>                                          &perf_count.xmtwait);
> @@ -302,7 +320,8 @@ static void dump_perfcounters(int extended, int timeout, uint16_t cap_mask,
>                 if (aggregate)
>                         aggregate_perfcounters();
>                 else
> -                       mad_dump_perfcounters(buf, sizeof buf, pc, sizeof pc);
> +                       dump_fields(buf, sizeof buf, pc, IB_PC_FIRST_F,
> +                               (cap_mask & 0x1000)?IB_PC_LAST_F:IB_PC_RCV_PKTS_F);
>         } else {
>                 if (!(cap_mask & 0x200))        /* 1.2 errata: bit 9 is extended counter support */
>                         IBWARN
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html