QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
To: qemu-block@nongnu.org
Cc: kwolf@redhat.com, vsementsov@virtuozzo.com,
	wencongyang2@huawei.com, xiechanglong.d@gmail.com,
	qemu-devel@nongnu.org, armbru@redhat.com, jsnow@redhat.com,
	den@openvz.org, mreitz@redhat.com
Subject: [PATCH v4 17/23] backup: move to block-copy
Date: Sun, 17 Jan 2021 00:46:59 +0300
Message-ID: <20210116214705.822267-18-vsementsov@virtuozzo.com> (raw)
In-Reply-To: <20210116214705.822267-1-vsementsov@virtuozzo.com>

This brings async request handling and block-status driven chunk sizes
to backup out of the box, which improves backup performance.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
---
 block/backup.c | 187 +++++++++++++++++++++++++++++++------------------
 1 file changed, 120 insertions(+), 67 deletions(-)

diff --git a/block/backup.c b/block/backup.c
index 466608ee55..cc525d5544 100644
--- a/block/backup.c
+++ b/block/backup.c
@@ -22,7 +22,6 @@
 #include "block/block-copy.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
-#include "qemu/ratelimit.h"
 #include "qemu/cutils.h"
 #include "sysemu/block-backend.h"
 #include "qemu/bitmap.h"
@@ -44,41 +43,17 @@ typedef struct BackupBlockJob {
     BlockdevOnError on_source_error;
     BlockdevOnError on_target_error;
     uint64_t len;
-    uint64_t bytes_read;
     int64_t cluster_size;
     BackupPerf perf;
 
     BlockCopyState *bcs;
+
+    bool wait;
+    BlockCopyCallState *bg_bcs_call;
 } BackupBlockJob;
 
 static const BlockJobDriver backup_job_driver;
 
-static void backup_progress_bytes_callback(int64_t bytes, void *opaque)
-{
-    BackupBlockJob *s = opaque;
-
-    s->bytes_read += bytes;
-}
-
-static int coroutine_fn backup_do_cow(BackupBlockJob *job,
-                                      int64_t offset, uint64_t bytes,
-                                      bool *error_is_read)
-{
-    int ret = 0;
-    int64_t start, end; /* bytes */
-
-    start = QEMU_ALIGN_DOWN(offset, job->cluster_size);
-    end = QEMU_ALIGN_UP(bytes + offset, job->cluster_size);
-
-    trace_backup_do_cow_enter(job, start, offset, bytes);
-
-    ret = block_copy(job->bcs, start, end - start, true, error_is_read);
-
-    trace_backup_do_cow_return(job, offset, bytes, ret);
-
-    return ret;
-}
-
 static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
 {
     BdrvDirtyBitmap *bm;
@@ -158,53 +133,96 @@ static BlockErrorAction backup_error_action(BackupBlockJob *job,
     }
 }
 
-static bool coroutine_fn yield_and_check(BackupBlockJob *job)
+static void coroutine_fn backup_block_copy_callback(void *opaque)
 {
-    uint64_t delay_ns;
-
-    if (job_is_cancelled(&job->common.job)) {
-        return true;
-    }
-
-    /*
-     * We need to yield even for delay_ns = 0 so that bdrv_drain_all() can
-     * return. Without a yield, the VM would not reboot.
-     */
-    delay_ns = block_job_ratelimit_get_delay(&job->common, job->bytes_read);
-    job->bytes_read = 0;
-    job_sleep_ns(&job->common.job, delay_ns);
+    BackupBlockJob *s = opaque;
 
-    if (job_is_cancelled(&job->common.job)) {
-        return true;
+    if (s->wait) {
+        s->wait = false;
+        aio_co_wake(s->common.job.co);
+    } else {
+        job_enter(&s->common.job);
     }
-
-    return false;
 }
 
 static int coroutine_fn backup_loop(BackupBlockJob *job)
 {
-    bool error_is_read;
-    int64_t offset;
-    BdrvDirtyBitmapIter *bdbi;
+    BlockCopyCallState *s = NULL;
     int ret = 0;
+    bool error_is_read;
+    BlockErrorAction act;
+
+    while (true) { /* retry loop */
+        job->bg_bcs_call = s = block_copy_async(job->bcs, 0,
+                QEMU_ALIGN_UP(job->len, job->cluster_size),
+                job->perf.max_workers, job->perf.max_chunk,
+                backup_block_copy_callback, job);
+
+        while (!block_copy_call_finished(s) &&
+               !job_is_cancelled(&job->common.job))
+        {
+            job_yield(&job->common.job);
+        }
 
-    bdbi = bdrv_dirty_iter_new(block_copy_dirty_bitmap(job->bcs));
-    while ((offset = bdrv_dirty_iter_next(bdbi)) != -1) {
-        do {
-            if (yield_and_check(job)) {
-                goto out;
-            }
-            ret = backup_do_cow(job, offset, job->cluster_size, &error_is_read);
-            if (ret < 0 && backup_error_action(job, error_is_read, -ret) ==
-                           BLOCK_ERROR_ACTION_REPORT)
-            {
-                goto out;
-            }
-        } while (ret < 0);
+        if (!block_copy_call_finished(s)) {
+            assert(job_is_cancelled(&job->common.job));
+            /*
+             * Note that we can't use job_yield() here, as it doesn't work for
+             * cancelled job.
+             */
+            block_copy_call_cancel(s);
+            job->wait = true;
+            qemu_coroutine_yield();
+            assert(block_copy_call_finished(s));
+            ret = 0;
+            goto out;
+        }
+
+        if (job_is_cancelled(&job->common.job) ||
+            block_copy_call_succeeded(s))
+        {
+            ret = 0;
+            goto out;
+        }
+
+        if (block_copy_call_cancelled(s)) {
+            /*
+             * Job is not cancelled but only block-copy call. This is possible
+             * after job pause. Now the pause is finished, start new block-copy
+             * iteration.
+             */
+            block_copy_call_free(s);
+            continue;
+        }
+
+        /* The only remaining case is failed block-copy call. */
+        assert(block_copy_call_failed(s));
+
+        ret = block_copy_call_status(s, &error_is_read);
+        act = backup_error_action(job, error_is_read, -ret);
+        switch (act) {
+        case BLOCK_ERROR_ACTION_REPORT:
+            goto out;
+        case BLOCK_ERROR_ACTION_STOP:
+            /*
+             * Go to pause prior to starting new block-copy call on the next
+             * iteration.
+             */
+            job_pause_point(&job->common.job);
+            break;
+        case BLOCK_ERROR_ACTION_IGNORE:
+            /* Proceed to new block-copy call to retry. */
+            break;
+        default:
+            abort();
+        }
+
+        block_copy_call_free(s);
     }
 
- out:
-    bdrv_dirty_iter_free(bdbi);
+out:
+    block_copy_call_free(s);
+    job->bg_bcs_call = NULL;
     return ret;
 }
 
@@ -245,7 +263,13 @@ static int coroutine_fn backup_run(Job *job, Error **errp)
         int64_t count;
 
         for (offset = 0; offset < s->len; ) {
-            if (yield_and_check(s)) {
+            if (job_is_cancelled(job)) {
+                return -ECANCELED;
+            }
+
+            job_pause_point(job);
+
+            if (job_is_cancelled(job)) {
                 return -ECANCELED;
             }
 
@@ -278,6 +302,33 @@ static int coroutine_fn backup_run(Job *job, Error **errp)
     return 0;
 }
 
+static void coroutine_fn backup_pause(Job *job)
+{
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
+
+    if (s->bg_bcs_call && !block_copy_call_finished(s->bg_bcs_call)) {
+        block_copy_call_cancel(s->bg_bcs_call);
+        s->wait = true;
+        qemu_coroutine_yield();
+    }
+}
+
+static void coroutine_fn backup_set_speed(BlockJob *job, int64_t speed)
+{
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+
+    /*
+     * block_job_set_speed() is called first from block_job_create(), when we
+     * don't yet have s->bcs.
+     */
+    if (s->bcs) {
+        block_copy_set_speed(s->bcs, speed);
+        if (s->bg_bcs_call) {
+            block_copy_kick(s->bg_bcs_call);
+        }
+    }
+}
+
 static const BlockJobDriver backup_job_driver = {
     .job_driver = {
         .instance_size          = sizeof(BackupBlockJob),
@@ -288,7 +339,9 @@ static const BlockJobDriver backup_job_driver = {
         .commit                 = backup_commit,
         .abort                  = backup_abort,
         .clean                  = backup_clean,
-    }
+        .pause                  = backup_pause,
+    },
+    .set_speed = backup_set_speed,
 };
 
 static int64_t backup_calculate_cluster_size(BlockDriverState *target,
@@ -485,8 +538,8 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
     job->len = len;
     job->perf = *perf;
 
-    block_copy_set_progress_callback(bcs, backup_progress_bytes_callback, job);
     block_copy_set_progress_meter(bcs, &job->common.job.progress);
+    block_copy_set_speed(bcs, speed);
 
     /* Required permissions are already taken by backup-top target */
     block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
-- 
2.29.2



  parent reply index

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-16 21:46 [PATCH v4 00/23] backup performance: block_status + async Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 01/23] qapi: backup: add perf.use-copy-range parameter Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 02/23] block/block-copy: More explicit call_state Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 03/23] block/block-copy: implement block_copy_async Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 04/23] block/block-copy: add max_chunk and max_workers parameters Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 05/23] block/block-copy: add list of all call-states Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 06/23] block/block-copy: add ratelimit to block-copy Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 07/23] block/block-copy: add block_copy_cancel Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 08/23] blockjob: add set_speed to BlockJobDriver Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 09/23] job: call job_enter from job_pause Vladimir Sementsov-Ogievskiy
2021-01-18 13:45   ` Max Reitz
2021-01-18 14:20     ` Max Reitz
2021-04-07 11:19   ` Max Reitz
2021-04-07 11:38     ` Vladimir Sementsov-Ogievskiy
2021-04-21  8:31       ` Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 10/23] qapi: backup: add max-chunk and max-workers to x-perf struct Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 11/23] iotests: 56: prepare for backup over block-copy Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 12/23] iotests: 185: " Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 13/23] iotests: 219: " Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 14/23] iotests: 257: " Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 15/23] block/block-copy: make progress_bytes_callback optional Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` [PATCH v4 16/23] block/backup: drop extra gotos from backup_run() Vladimir Sementsov-Ogievskiy
2021-01-16 21:46 ` Vladimir Sementsov-Ogievskiy [this message]
2021-01-16 21:47 ` [PATCH v4 18/23] qapi: backup: disable copy_range by default Vladimir Sementsov-Ogievskiy
2021-01-16 21:47 ` [PATCH v4 19/23] block/block-copy: drop unused block_copy_set_progress_callback() Vladimir Sementsov-Ogievskiy
2021-01-16 21:47 ` [PATCH v4 20/23] block/block-copy: drop unused argument of block_copy() Vladimir Sementsov-Ogievskiy
2021-01-16 21:47 ` [PATCH v4 21/23] simplebench/bench_block_job: use correct shebang line with python3 Vladimir Sementsov-Ogievskiy
2021-01-16 21:47 ` [PATCH v4 22/23] simplebench: bench_block_job: add cmd_options argument Vladimir Sementsov-Ogievskiy
2021-01-16 21:47 ` [PATCH v4 23/23] simplebench: add bench-backup.py Vladimir Sementsov-Ogievskiy
2021-01-18 14:01   ` Max Reitz
2021-01-18 15:07 ` [PATCH v4 00/23] backup performance: block_status + async Max Reitz
2021-01-18 17:04   ` Vladimir Sementsov-Ogievskiy
2021-01-19 18:40 ` Max Reitz
2021-01-19 19:22   ` Vladimir Sementsov-Ogievskiy
2021-01-19 19:29     ` Vladimir Sementsov-Ogievskiy
2021-01-20 10:39     ` Max Reitz
2021-01-20 13:50       ` Max Reitz
2021-01-20 14:34         ` Max Reitz
2021-01-20 14:44           ` Max Reitz
2021-01-20 15:53             ` Max Reitz
2021-01-20 16:00               ` Max Reitz
2021-01-20 16:04               ` Daniel P. Berrangé
2021-01-20 16:40                 ` Max Reitz
2021-01-20 10:20 ` [PATCH v4 11.5/23] iotests/129: Limit backup's max-chunk/max-workers Max Reitz
2021-01-20 11:24   ` Vladimir Sementsov-Ogievskiy

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=20210116214705.822267-18-vsementsov@virtuozzo.com \
    --to=vsementsov@virtuozzo.com \
    --cc=armbru@redhat.com \
    --cc=den@openvz.org \
    --cc=jsnow@redhat.com \
    --cc=kwolf@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=wencongyang2@huawei.com \
    --cc=xiechanglong.d@gmail.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

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git
	git clone --mirror https://lore.kernel.org/qemu-devel/2 qemu-devel/git/2.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git