qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Denis V. Lunev" <den@openvz.org>
To: qemu-block@nongnu.org, qemu-devel@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>, "Denis V. Lunev" <den@openvz.org>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Max Reitz <mreitz@redhat.com>
Subject: [PATCH 2/3] block: add logging facility for long standing IO requests
Date: Wed,  5 Aug 2020 13:08:23 +0300	[thread overview]
Message-ID: <20200805100824.16817-3-den@openvz.org> (raw)
In-Reply-To: <20200805100824.16817-1-den@openvz.org>

There are severe delays with IO requests processing if QEMU is running in
virtual machine or over software defined storage. Such delays potentially
results in unpredictable guest behavior. For example, guests over IDE or
SATA drive could remount filesystem read-only if write is performed
longer than 10 seconds.

Such reports are very complex to process. Some good starting point for this
seems quite reasonable. This patch provides one. It adds logging of such
potentially dangerous long IO operations.

Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
CC: Stefan Hajnoczi <stefanha@redhat.com>
CC: Kevin Wolf <kwolf@redhat.com>
CC: Max Reitz <mreitz@redhat.com>
---
 block/accounting.c         | 59 +++++++++++++++++++++++++++++++++++++-
 blockdev.c                 |  7 ++++-
 include/block/accounting.h |  5 +++-
 slirp                      |  2 +-
 4 files changed, 69 insertions(+), 4 deletions(-)

diff --git a/block/accounting.c b/block/accounting.c
index 8d41c8a83a..24f48c84b8 100644
--- a/block/accounting.c
+++ b/block/accounting.c
@@ -27,7 +27,9 @@
 #include "block/accounting.h"
 #include "block/block_int.h"
 #include "qemu/timer.h"
+#include "qemu/log.h"
 #include "sysemu/qtest.h"
+#include "sysemu/block-backend.h"
 
 static QEMUClockType clock_type = QEMU_CLOCK_REALTIME;
 static const int qtest_latency_ns = NANOSECONDS_PER_SECOND / 1000;
@@ -41,10 +43,11 @@ void block_acct_init(BlockAcctStats *stats)
 }
 
 void block_acct_setup(BlockAcctStats *stats, bool account_invalid,
-                      bool account_failed)
+                      bool account_failed, unsigned latency_log_threshold_ms)
 {
     stats->account_invalid = account_invalid;
     stats->account_failed = account_failed;
+    stats->latency_log_threshold_ms = latency_log_threshold_ms;
 }
 
 void block_acct_cleanup(BlockAcctStats *stats)
@@ -182,6 +185,58 @@ void block_latency_histograms_clear(BlockAcctStats *stats)
     }
 }
 
+static const char *block_account_type(enum BlockAcctType type)
+{
+    switch (type) {
+    case BLOCK_ACCT_READ:
+        return "READ";
+    case BLOCK_ACCT_WRITE:
+        return "WRITE";
+    case BLOCK_ACCT_FLUSH:
+        return "DISCARD";
+    case BLOCK_ACCT_UNMAP:
+        return "TRUNCATE";
+    case BLOCK_ACCT_NONE:
+        return "NONE";
+    case BLOCK_MAX_IOTYPE:
+        break;
+    }
+    return "UNKNOWN";
+}
+
+static void block_acct_report_long(BlockAcctStats *stats,
+                                   BlockAcctCookie *cookie, int64_t latency_ns)
+{
+    unsigned latency_ms = latency_ns / SCALE_MS;
+    int64_t start_time_host_s;
+    char buf[64];
+    struct tm t;
+    BlockDriverState *bs;
+
+    if (cookie->type == BLOCK_ACCT_NONE) {
+        return;
+    }
+    if (stats->latency_log_threshold_ms == 0) {
+        return;
+    }
+    if (latency_ms < stats->latency_log_threshold_ms) {
+        return;
+    }
+
+    start_time_host_s = cookie->start_time_ns / NANOSECONDS_PER_SECOND;
+    strftime(buf, sizeof(buf), "%m-%d %H:%M:%S",
+             localtime_r(&start_time_host_s, &t));
+
+    bs = blk_bs(blk_stats2blk(stats));
+    qemu_log("long %s[%ld] IO request: %d.03%d since %s.%03d bs: %s(%s, %s)\n",
+             block_account_type(cookie->type), cookie->bytes,
+             (int)(latency_ms / 1000), (int)(latency_ms % 1000), buf,
+             (int)((cookie->start_time_ns / 1000000) % 1000),
+             bs == NULL ? "unknown" : bdrv_get_node_name(bs),
+             bs == NULL ? "unknown" : bdrv_get_format_name(bs),
+             bs == NULL ? "unknown" : bs->filename);
+}
+
 static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
                                  bool failed)
 {
@@ -222,6 +277,8 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
 
     qemu_mutex_unlock(&stats->lock);
 
+    block_acct_report_long(stats, cookie, latency_ns);
+
     cookie->type = BLOCK_ACCT_NONE;
 }
 
diff --git a/blockdev.c b/blockdev.c
index 3848a9c8ab..66158d1292 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -622,7 +622,8 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
 
         bs->detect_zeroes = detect_zeroes;
 
-        block_acct_setup(blk_get_stats(blk), account_invalid, account_failed);
+        block_acct_setup(blk_get_stats(blk), account_invalid, account_failed,
+                qemu_opt_get_number(opts, "latency-log-threshold", 0));
 
         if (!parse_stats_intervals(blk_get_stats(blk), interval_list, errp)) {
             blk_unref(blk);
@@ -3727,6 +3728,10 @@ QemuOptsList qemu_common_drive_opts = {
             .type = QEMU_OPT_BOOL,
             .help = "whether to account for failed I/O operations "
                     "in the statistics",
+        },{
+            .name = "latency-log-threshold",
+            .type = QEMU_OPT_NUMBER,
+            .help = "threshold for long I/O report (disabled if <=0), in ms",
         },
         { /* end of list */ }
     },
diff --git a/include/block/accounting.h b/include/block/accounting.h
index 878b4c3581..c3ea25f9aa 100644
--- a/include/block/accounting.h
+++ b/include/block/accounting.h
@@ -91,6 +91,9 @@ struct BlockAcctStats {
     bool account_invalid;
     bool account_failed;
     BlockLatencyHistogram latency_histogram[BLOCK_MAX_IOTYPE];
+
+    /* Threshold for long I/O detection, ms */
+    unsigned latency_log_threshold_ms;
 };
 
 typedef struct BlockAcctCookie {
@@ -101,7 +104,7 @@ typedef struct BlockAcctCookie {
 
 void block_acct_init(BlockAcctStats *stats);
 void block_acct_setup(BlockAcctStats *stats, bool account_invalid,
-                     bool account_failed);
+                      bool account_failed, unsigned latency_log_threshold_ms);
 void block_acct_cleanup(BlockAcctStats *stats);
 void block_acct_add_interval(BlockAcctStats *stats, unsigned interval_length);
 BlockAcctTimedStats *block_acct_interval_next(BlockAcctStats *stats,
diff --git a/slirp b/slirp
index ce94eba204..2faae0f778 160000
--- a/slirp
+++ b/slirp
@@ -1 +1 @@
-Subproject commit ce94eba2042d52a0ba3d9e252ebce86715e94275
+Subproject commit 2faae0f778f818fadc873308f983289df697eb93
-- 
2.17.1



  parent reply	other threads:[~2020-08-05 10:09 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-05 10:08 [PATCH v2 0/3] block: add logging facility for long standing IO requests Denis V. Lunev
2020-08-05 10:08 ` [PATCH 1/3] block/block-backend: add converter from BlockAcctStats to BlockBackend Denis V. Lunev
2020-08-05 10:08 ` Denis V. Lunev [this message]
2020-08-05 13:51   ` [PATCH 2/3] block: add logging facility for long standing IO requests Philippe Mathieu-Daudé
2020-08-05 14:00     ` Denis V. Lunev
2020-08-05 10:08 ` [PATCH 3/3] block: enable long IO requests report by default Denis V. Lunev
  -- strict thread matches above, loose matches on Subject: below --
2020-08-10 10:14 [PATCH v2 for 5.2 0/3] block: add logging facility for long standing IO requests Denis V. Lunev
2020-08-10 10:14 ` [PATCH 2/3] " Denis V. Lunev
2020-08-20  8:03   ` David Edmondson
2020-08-24  9:01     ` Denis V. Lunev
2020-09-17 13:56   ` Max Reitz
2020-09-17 15:27     ` Denis V. Lunev

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=20200805100824.16817-3-den@openvz.org \
    --to=den@openvz.org \
    --cc=kwolf@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.com \
    /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).