From: Cliff Wickman <cpw@sgi.com>
To: linux-kernel@vger.kernel.org, mingo@elte.hu, x86@kernel.org
Cc: mingo@elte.hu, x86@kernel.org
Subject: [PATCH 6/6] x86, UV2: accounting for BAU strong nacks
Date: Mon, 16 Jan 2012 15:22:38 -0600 [thread overview]
Message-ID: <20120116212238.GF5767@sgi.com> (raw)
In-Reply-To: <20120116211617.GD5512@sgi.com>
This patch adds separate accounting of UV2 message "strong nack's" in
the BAU statistics.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
---
arch/x86/include/asm/uv/uv_bau.h | 1 +
arch/x86/platform/uv/tlb_uv.c | 12 +++++++-----
2 files changed, 8 insertions(+), 5 deletions(-)
Index: 120113.linux-3.2.1/arch/x86/include/asm/uv/uv_bau.h
===================================================================
--- 120113.linux-3.2.1.orig/arch/x86/include/asm/uv/uv_bau.h
+++ 120113.linux-3.2.1/arch/x86/include/asm/uv/uv_bau.h
@@ -483,6 +483,7 @@ struct ptc_stats {
requests */
unsigned long s_stimeout; /* source side timeouts */
unsigned long s_dtimeout; /* destination side timeouts */
+ unsigned long s_strongnacks; /* number of strong nack's */
unsigned long s_time; /* time spent in sending side */
unsigned long s_retriesok; /* successful retries */
unsigned long s_ntargcpu; /* total number of cpu's
Index: 120113.linux-3.2.1/arch/x86/platform/uv/tlb_uv.c
===================================================================
--- 120113.linux-3.2.1.orig/arch/x86/platform/uv/tlb_uv.c
+++ 120113.linux-3.2.1/arch/x86/platform/uv/tlb_uv.c
@@ -635,13 +635,15 @@ static int uv2_wait_completion(struct ba
* our message and its state will stay IDLE.
*/
if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) ||
- (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) ||
(descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) {
stat->s_stimeout++;
return FLUSH_GIVEUP;
+ } else if (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) {
+ stat->s_strongnacks++;
+ bcp->conseccompletes = 0;
+ return FLUSH_GIVEUP;
} else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) {
stat->s_dtimeout++;
- ttm = get_cycles();
bcp->conseccompletes = 0;
return FLUSH_RETRY_TIMEOUT;
} else {
@@ -1346,7 +1348,7 @@ static int ptc_seq_show(struct seq_file
seq_printf(file,
"remotehub numuvhubs numuvhubs16 numuvhubs8 ");
seq_printf(file,
- "numuvhubs4 numuvhubs2 numuvhubs1 dto retries rok ");
+ "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries rok ");
seq_printf(file,
"resetp resett giveup sto bz throt swack recv rtime ");
seq_printf(file,
@@ -1364,10 +1366,10 @@ static int ptc_seq_show(struct seq_file
stat->s_ntargremotes, stat->s_ntargcpu,
stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub,
stat->s_ntarguvhub, stat->s_ntarguvhub16);
- seq_printf(file, "%ld %ld %ld %ld %ld ",
+ seq_printf(file, "%ld %ld %ld %ld %ld %ld ",
stat->s_ntarguvhub8, stat->s_ntarguvhub4,
stat->s_ntarguvhub2, stat->s_ntarguvhub1,
- stat->s_dtimeout);
+ stat->s_dtimeout, stat->s_strongnacks);
seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld ",
stat->s_retry_messages, stat->s_retriesok,
stat->s_resets_plug, stat->s_resets_timeout,
next prev parent reply other threads:[~2012-01-16 21:22 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-01-16 21:16 [PATCH 0/6] x86, UV2: BAU fixes for UV version 2 Cliff Wickman
2012-01-16 21:17 ` [PATCH 1/6] x86, UV2: use native UV2 broadcast mode Cliff Wickman
2012-01-17 17:20 ` [tip:x86/urgent] x86/UV2: Fix new UV2 hardware by using " tip-bot for Cliff Wickman
2012-01-16 21:18 ` [PATCH 2/6] x86, UV2: calc BAU destination timeout Cliff Wickman
2012-01-17 17:20 ` [tip:x86/urgent] x86/UV2: Fix BAU destination timeout initialization tip-bot for Cliff Wickman
2012-01-16 21:19 ` [PATCH 3/6] x86: workaround for UV2 BAU bug Cliff Wickman
2012-01-17 17:21 ` [tip:x86/urgent] x86/UV2: Work around " tip-bot for Cliff Wickman
2012-01-16 21:20 ` [PATCH 4/6] x86 UV2: remove no-resources test for UV2 BAU Cliff Wickman
2012-01-17 17:22 ` [tip:x86/urgent] x86/UV2: Remove stale " tip-bot for Cliff Wickman
2012-01-16 21:21 ` [PATCH 5/6] x86, UV2: ack BAU interrupt earlier Cliff Wickman
2012-01-17 17:23 ` [tip:x86/urgent] x86/UV2: Ack " tip-bot for Cliff Wickman
2012-01-16 21:22 ` Cliff Wickman [this message]
2012-01-17 17:24 ` [tip:x86/urgent] x86/UV2: Add accounting for BAU strong nacks tip-bot for Cliff Wickman
2012-01-17 9:47 ` [PATCH 0/6] x86, UV2: BAU fixes for UV version 2 Ingo Molnar
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=20120116212238.GF5767@sgi.com \
--to=cpw@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=x86@kernel.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;
as well as URLs for NNTP newsgroup(s).