From nobody Sun May 5 04:19:27 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zoho.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 148700196362780.15719327612169; Mon, 13 Feb 2017 08:06:03 -0800 (PST) Received: from localhost ([::1]:57846 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cdJ8Y-0004EH-I6 for importer@patchew.org; Mon, 13 Feb 2017 11:05:58 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:33729) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cdJ6x-0003Fk-Au for qemu-devel@nongnu.org; Mon, 13 Feb 2017 11:04:21 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cdJ6u-0006WW-Ir for qemu-devel@nongnu.org; Mon, 13 Feb 2017 11:04:19 -0500 Received: from mx-v6.kamp.de ([2a02:248:0:51::16]:50475 helo=mx01.kamp.de) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1cdJ6u-0006WA-AW for qemu-devel@nongnu.org; Mon, 13 Feb 2017 11:04:16 -0500 Received: (qmail 31057 invoked by uid 89); 13 Feb 2017 16:04:10 -0000 Received: from [195.62.97.28] by client-16-kamp (envelope-from , uid 89) with qmail-scanner-2010/03/19-MF (clamdscan: 0.99.2/23055. avast: 1.2.2/17010300. spamassassin: 3.4.1. Clear:RC:1(195.62.97.28):. Processed in 0.066388 secs); 13 Feb 2017 16:04:10 -0000 Received: from smtp.kamp.de (HELO submission.kamp.de) ([195.62.97.28]) by mx01.kamp.de with ESMTPS (DHE-RSA-AES256-GCM-SHA384 encrypted); 13 Feb 2017 16:04:09 -0000 Received: (qmail 5528 invoked from network); 13 Feb 2017 16:04:09 -0000 Received: from lieven-pc.kamp-intra.net (HELO lieven-pc) (relay@kamp.de@::ffff:172.21.12.60) by submission.kamp.de with ESMTPS (DHE-RSA-AES256-GCM-SHA384 encrypted) ESMTPA; 13 Feb 2017 16:04:09 -0000 Received: by lieven-pc (Postfix, from userid 1000) id 7994620A61; Mon, 13 Feb 2017 17:04:09 +0100 (CET) X-GL_Whitelist: yes From: Peter Lieven To: qemu-devel@nongnu.org Date: Mon, 13 Feb 2017 17:04:07 +0100 Message-Id: <1487001847-19082-1-git-send-email-pl@kamp.de> X-Mailer: git-send-email 1.9.1 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] X-Received-From: 2a02:248:0:51::16 Subject: [Qemu-devel] [RFC PATCH V2] qemu-img: make convert async X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: kwolf@redhat.com, Peter Lieven , famz@redhat.com, qemu-block@nongnu.org, mreitz@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" this is something I have been thinking about for almost 2 years now. we heavily have the following two use cases when using qemu-img convert. a) reading from NFS and writing to iSCSI for deploying templates b) reading from iSCSI and writing to NFS for backups In both processes we use libiscsi and libnfs so we have no kernel pagecache. As qemu-img convert is implemented with sync operations that means we read one buffer and then write it. No parallelism and each sync request takes as long as it takes until it is completed. This is version 2 of the approach using coroutine worker "threads". The code is far from clean or complete, but I would appreaciate comments and thoughts from you. So far I have the following runtimes when reading an uncompressed QCOW2 from NFS and writing it to iSCSI (raw): qemu-img (master) nfs -> iscsi 33 secs nfs -> ram 19 secs ram -> iscsi 14 secs qemu-img-async nfs -> iscsi 23 secs nfs -> ram 17 secs ram -> iscsi 14 secs Its visible that on master the runtimes add up as expected. The async branch is faster, but not as fast as I would have expected. I would expect the run= time to be as slow as the slowest of the two involved transfers. Thank you, Peter Signed-off-by: Peter Lieven --- v1->v2: - using coroutine as worker "threads". [Max] - keeping the request queue as otherwise it happens that we wait on BLK_ZERO chunks while keeping the write order. it also avoids redundant calls to get_block_status and helps to skip some conditions for fully allocated imaged (!s->min_spars= e) qemu-img.c | 187 ++++++++++++++++++++++++++++++++++++++++-----------------= ---- 1 file changed, 123 insertions(+), 64 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index cff22e3..e623188 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1448,6 +1448,16 @@ enum ImgConvertBlockStatus { BLK_BACKING_FILE, }; =20 +typedef struct ImgConvertQueueElt { + int64_t sector_num; + enum ImgConvertBlockStatus status; + int nb_sectors; + QSIMPLEQ_ENTRY(ImgConvertQueueElt) next; +} ImgConvertQueueElt; + +//XXX: this should be a cmdline parameter +#define NUM_COROUTINES 8 + typedef struct ImgConvertState { BlockBackend **src; int64_t *src_sectors; @@ -1455,6 +1465,8 @@ typedef struct ImgConvertState { int64_t src_cur_offset; int64_t total_sectors; int64_t allocated_sectors; + int64_t allocated_done; + int64_t wr_offs; enum ImgConvertBlockStatus status; int64_t sector_next_status; BlockBackend *target; @@ -1464,11 +1476,16 @@ typedef struct ImgConvertState { int min_sparse; size_t cluster_sectors; size_t buf_sectors; + bool locked; + int ret; + Coroutine *co[NUM_COROUTINES]; + QSIMPLEQ_HEAD(, ImgConvertQueueElt) queue; } ImgConvertState; =20 static void convert_select_part(ImgConvertState *s, int64_t sector_num) { - assert(sector_num >=3D s->src_cur_offset); + s->src_cur_offset =3D 0; + s->src_cur =3D 0; while (sector_num - s->src_cur_offset >=3D s->src_sectors[s->src_cur])= { s->src_cur_offset +=3D s->src_sectors[s->src_cur]; s->src_cur++; @@ -1545,7 +1562,7 @@ static int convert_iteration_sectors(ImgConvertState = *s, int64_t sector_num) } =20 static int convert_read(ImgConvertState *s, int64_t sector_num, int nb_sec= tors, - uint8_t *buf) + uint8_t *buf, QEMUIOVector *qiov) { int n; int ret; @@ -1562,10 +1579,12 @@ static int convert_read(ImgConvertState *s, int64_t= sector_num, int nb_sectors, blk =3D s->src[s->src_cur]; bs_sectors =3D s->src_sectors[s->src_cur]; =20 + qemu_iovec_reset(qiov); n =3D MIN(nb_sectors, bs_sectors - (sector_num - s->src_cur_offset= )); - ret =3D blk_pread(blk, - (sector_num - s->src_cur_offset) << BDRV_SECTOR_BI= TS, - buf, n << BDRV_SECTOR_BITS); + qemu_iovec_add(qiov, buf, n << BDRV_SECTOR_BITS); + + ret =3D blk_co_preadv(blk, (sector_num - s->src_cur_offset) << BDR= V_SECTOR_BITS, + n << BDRV_SECTOR_BITS, qiov, 0); if (ret < 0) { return ret; } @@ -1578,15 +1597,17 @@ static int convert_read(ImgConvertState *s, int64_t= sector_num, int nb_sectors, return 0; } =20 + static int convert_write(ImgConvertState *s, int64_t sector_num, int nb_se= ctors, - const uint8_t *buf) + uint8_t *buf, QEMUIOVector *qiov, + enum ImgConvertBlockStatus status) { int ret; =20 while (nb_sectors > 0) { int n =3D nb_sectors; - - switch (s->status) { + qemu_iovec_reset(qiov); + switch (status) { case BLK_BACKING_FILE: /* If we have a backing file, leave clusters unallocated that = are * unallocated in the source image, so that the backing file is @@ -1607,9 +1628,9 @@ static int convert_write(ImgConvertState *s, int64_t = sector_num, int nb_sectors, break; } =20 - ret =3D blk_pwrite_compressed(s->target, - sector_num << BDRV_SECTOR_BITS, - buf, n << BDRV_SECTOR_BITS); + qemu_iovec_add(qiov, buf, n << BDRV_SECTOR_BITS); + ret =3D blk_co_pwritev(s->target, sector_num << BDRV_SECTO= R_BITS, + n << BDRV_SECTOR_BITS, qiov, BDRV_REQ= _WRITE_COMPRESSED); if (ret < 0) { return ret; } @@ -1622,8 +1643,9 @@ static int convert_write(ImgConvertState *s, int64_t = sector_num, int nb_sectors, if (!s->min_sparse || is_allocated_sectors_min(buf, n, &n, s->min_sparse)) { - ret =3D blk_pwrite(s->target, sector_num << BDRV_SECTOR_BI= TS, - buf, n << BDRV_SECTOR_BITS, 0); + qemu_iovec_add(qiov, buf, n << BDRV_SECTOR_BITS); + ret =3D blk_co_pwritev(s->target, sector_num << BDRV_SECTO= R_BITS, + n << BDRV_SECTOR_BITS, qiov, 0); if (ret < 0) { return ret; } @@ -1635,8 +1657,8 @@ static int convert_write(ImgConvertState *s, int64_t = sector_num, int nb_sectors, if (s->has_zero_init) { break; } - ret =3D blk_pwrite_zeroes(s->target, sector_num << BDRV_SECTOR= _BITS, - n << BDRV_SECTOR_BITS, 0); + ret =3D blk_co_pwrite_zeroes(s->target, sector_num << BDRV_SEC= TOR_BITS, + n << BDRV_SECTOR_BITS, 0); if (ret < 0) { return ret; } @@ -1651,12 +1673,75 @@ static int convert_write(ImgConvertState *s, int64_= t sector_num, int nb_sectors, return 0; } =20 -static int convert_do_copy(ImgConvertState *s) +static void convert_do_copy_co(void *opaque) { + ImgConvertState *s =3D opaque; uint8_t *buf =3D NULL; - int64_t sector_num, allocated_done; + int ret, i; + int64_t next_sector; + ImgConvertQueueElt *elt, *elt2; + QEMUIOVector qiov; + qemu_iovec_init(&qiov, 1); + + buf =3D blk_blockalign(s->target, s->buf_sectors * BDRV_SECTOR_SIZE); + + while (!s->ret && (elt =3D QSIMPLEQ_FIRST(&s->queue))) { + QSIMPLEQ_REMOVE_HEAD(&s->queue, next); + if ((elt2 =3D QSIMPLEQ_FIRST(&s->queue))) { + next_sector =3D elt2->sector_num; + } else { + next_sector =3D s->total_sectors; + } + + s->allocated_done +=3D elt->nb_sectors; + qemu_progress_print(100.0 * s->allocated_done / s->allocated_secto= rs, + 0); + + if (elt->status =3D=3D BLK_DATA) { + ret =3D convert_read(s, elt->sector_num, elt->nb_sectors, buf,= &qiov); + if (ret < 0) { + error_report("error while reading sector %" PRId64 + ": %s", elt->sector_num, strerror(-ret)); + s->ret =3D ret; + goto out; + } + } + + //~ //XXX: in-order write on/off could be a switch + while (s->wr_offs !=3D elt->sector_num) { + if (s->ret) { + goto out; + } + qemu_coroutine_yield(); + } + + ret =3D convert_write(s, elt->sector_num, elt->nb_sectors, buf, &q= iov, elt->status); + if (ret < 0) { + error_report("error while writing sector %" PRId64 + ": %s", elt->sector_num, strerror(-ret)); + s->ret =3D ret; + goto out; + } + + s->wr_offs =3D next_sector; + g_free(elt); + } + +out: + qemu_iovec_destroy(&qiov); + qemu_vfree(buf); + for (i =3D 0; i < NUM_COROUTINES; i++) { + if (s->co[i] =3D=3D qemu_coroutine_self()) { + s->co[i] =3D NULL; + } + } +} + +static int convert_do_copy(ImgConvertState *s) +{ int ret; - int n; + int i, n, running =3D -1; + int64_t sector_num =3D 0; =20 /* Check whether we have zero initialisation or can get it efficiently= */ s->has_zero_init =3D s->min_sparse && !s->target_has_backing @@ -1682,69 +1767,44 @@ static int convert_do_copy(ImgConvertState *s) } s->buf_sectors =3D s->cluster_sectors; } - buf =3D blk_blockalign(s->target, s->buf_sectors * BDRV_SECTOR_SIZE); =20 - /* Calculate allocated sectors for progress */ - s->allocated_sectors =3D 0; - sector_num =3D 0; + QSIMPLEQ_INIT(&s->queue); while (sector_num < s->total_sectors) { n =3D convert_iteration_sectors(s, sector_num); if (n < 0) { ret =3D n; goto fail; } + if (s->status =3D=3D BLK_DATA || (!s->min_sparse && s->status =3D= =3D BLK_ZERO)) { + ImgConvertQueueElt *elt =3D g_malloc(sizeof(ImgConvertQueueElt= )); + elt->sector_num =3D sector_num; + elt->status =3D s->status; + elt->nb_sectors =3D n; s->allocated_sectors +=3D n; + QSIMPLEQ_INSERT_TAIL(&s->queue, elt, next); } sector_num +=3D n; } =20 - /* Do the copy */ - s->src_cur =3D 0; - s->src_cur_offset =3D 0; - s->sector_next_status =3D 0; - - sector_num =3D 0; - allocated_done =3D 0; - - while (sector_num < s->total_sectors) { - n =3D convert_iteration_sectors(s, sector_num); - if (n < 0) { - ret =3D n; - goto fail; - } - if (s->status =3D=3D BLK_DATA || (!s->min_sparse && s->status =3D= =3D BLK_ZERO)) - { - allocated_done +=3D n; - qemu_progress_print(100.0 * allocated_done / s->allocated_sect= ors, - 0); - } + for (i =3D 0; i < NUM_COROUTINES; i++) { + s->co[i] =3D qemu_coroutine_create(convert_do_copy_co, s); + qemu_coroutine_enter(s->co[i]); + } =20 - if (s->status =3D=3D BLK_DATA) { - ret =3D convert_read(s, sector_num, n, buf); - if (ret < 0) { - error_report("error while reading sector %" PRId64 - ": %s", sector_num, strerror(-ret)); - goto fail; + while (!s->ret && running) { + running =3D 0; + for (i =3D 0; i < NUM_COROUTINES; i++) { + if (s->co[i] !=3D NULL) { + qemu_coroutine_enter_if_inactive(s->co[i]); + running++; } - } else if (!s->min_sparse && s->status =3D=3D BLK_ZERO) { - n =3D MIN(n, s->buf_sectors); - memset(buf, 0, n * BDRV_SECTOR_SIZE); - s->status =3D BLK_DATA; - } - - ret =3D convert_write(s, sector_num, n, buf); - if (ret < 0) { - error_report("error while writing sector %" PRId64 - ": %s", sector_num, strerror(-ret)); - goto fail; } - - sector_num +=3D n; + main_loop_wait(false); } =20 - if (s->compressed) { + if (s->compressed && !s->ret) { /* signal EOF to align */ ret =3D blk_pwrite_compressed(s->target, 0, NULL, 0); if (ret < 0) { @@ -1752,9 +1812,8 @@ static int convert_do_copy(ImgConvertState *s) } } =20 - ret =3D 0; + ret =3D s->ret; fail: - qemu_vfree(buf); return ret; } =20 --=20 1.9.1