From: Ira Weiny <weiny2-i2BcT+NCU+M@public.gmane.org>
To: Hal Rosenstock <hal-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
Cc: "linux-rdma
(linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org)"
<linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: Re: [PATCHv2 2/2] infiniband-diags/perfquery.c: Fix reset for PortExtendedSpeedsCounters
Date: Thu, 1 Dec 2011 11:58:08 -0800 [thread overview]
Message-ID: <20111201115808.28ad5c08.weiny2@llnl.gov> (raw)
In-Reply-To: <4ED7B005.3040908-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
On Thu, 1 Dec 2011 08:49:09 -0800
Hal Rosenstock <hal-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org> wrote:
> infiniband-diags/perfquery.c: Fix reset for PortExtendedSpeedsCounters
>
> Signed-off-by: Hal Rosenstock <hal-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Thanks applied,
Ira
> ---
> Changes since v1:
> Patch now against separated/recent infiniband-diags tree
>
> diff --git a/src/perfquery.c b/src/perfquery.c
> index 859ddbb..3ebf1cc 100644
> --- a/src/perfquery.c
> +++ b/src/perfquery.c
> @@ -401,12 +401,56 @@ static void rcv_err_query(ib_portid_t * portid, int port, int mask)
> mad_dump_perfcounters_rcv_err);
> }
>
> -static void extended_speeds_query(ib_portid_t * portid, int port, int mask)
> +static uint8_t *ext_speeds_reset_via(void *rcvbuf, ib_portid_t * dest,
> + int port, uint64_t mask, unsigned timeout,
> + const struct ibmad_port * srcport)
> {
> - common_func(portid, port, mask, !reset_only, (reset_only || reset),
> - "PortExtendedSpeedsCounters",
> - IB_GSI_PORT_EXT_SPEEDS_COUNTERS,
> - mad_dump_port_ext_speeds_counters);
> + ib_rpc_t rpc = { 0 };
> + int lid = dest->lid;
> +
> + DEBUG("lid %u port %d mask 0x%" PRIx64, lid, port, mask);
> +
> + if (lid == -1) {
> + IBWARN("only lid routed is supported");
> + return NULL;
> + }
> +
> + if (!mask)
> + mask = ~0;
> +
> + rpc.mgtclass = IB_PERFORMANCE_CLASS;
> + rpc.method = IB_MAD_METHOD_SET;
> + rpc.attr.id = IB_GSI_PORT_EXT_SPEEDS_COUNTERS;
> +
> + memset(rcvbuf, 0, IB_MAD_SIZE);
> +
> + mad_set_field(rcvbuf, 0, IB_PESC_PORT_SELECT_F, port);
> + mad_set_field64(rcvbuf, 0, IB_PESC_COUNTER_SELECT_F, mask);
> + rpc.attr.mod = 0;
> + rpc.timeout = timeout;
> + rpc.datasz = IB_PC_DATA_SZ;
> + rpc.dataoffs = IB_PC_DATA_OFFS;
> + if (!dest->qp)
> + dest->qp = 1;
> + if (!dest->qkey)
> + dest->qkey = IB_DEFAULT_QP1_QKEY;
> +
> + return mad_rpc(srcport, &rpc, dest, rcvbuf, rcvbuf);
> +}
> +
> +static void extended_speeds_query(ib_portid_t * portid, int port, uint64_t ext_mask)
> +{
> + int mask = ext_mask;
> +
> + if (!reset_only)
> + common_func(portid, port, mask, 1, 0,
> + "PortExtendedSpeedsCounters",
> + IB_GSI_PORT_EXT_SPEEDS_COUNTERS,
> + mad_dump_port_ext_speeds_counters);
> +
> + if ((reset_only || reset) &&
> + !ext_speeds_reset_via(pc, portid, port, ext_mask, ibd_timeout, srcport))
> + IBERROR("cannot reset PortExtendedSpeedsCounters");
> }
>
> void dump_portsamples_control(ib_portid_t * portid, int port)
> @@ -472,6 +516,7 @@ int main(int argc, char **argv)
> };
> ib_portid_t portid = { 0 };
> int mask = 0xffff;
> + uint64_t ext_mask = 0xffffffffffffffff;
> uint16_t cap_mask;
> int all_ports_loop = 0;
> int node_type, num_ports = 0;
> @@ -518,8 +563,10 @@ int main(int argc, char **argv)
>
> if (argc > 1)
> port = strtoul(argv[1], 0, 0);
> - if (argc > 2)
> - mask = strtoul(argv[2], 0, 0);
> + if (argc > 2) {
> + ext_mask = strtoull(argv[2], 0, 0);
> + mask = ext_mask;
> + }
>
> srcport = mad_rpc_open_port(ibd_ca, ibd_ca_port, mgmt_classes, 4);
> if (!srcport)
> @@ -569,7 +618,7 @@ int main(int argc, char **argv)
> }
>
> if (extended_speeds) {
> - extended_speeds_query(&portid, port, mask);
> + extended_speeds_query(&portid, port, ext_mask);
> goto done;
> }
>
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
weiny2-i2BcT+NCU+M@public.gmane.org
--
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
prev parent reply other threads:[~2011-12-01 19:58 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-12-01 16:49 [PATCHv2 2/2] infiniband-diags/perfquery.c: Fix reset for PortExtendedSpeedsCounters Hal Rosenstock
[not found] ` <4ED7B005.3040908-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2011-12-01 19:58 ` Ira Weiny [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20111201115808.28ad5c08.weiny2@llnl.gov \
--to=weiny2-i2bct+ncu+m@public.gmane.org \
--cc=hal-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox