c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-22 10:37:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Illumos #3306, #3321

Browse Source 
3306 zdb should be able to issue reads in parallel
3321 'zpool reopen' command should be documented in the man
     page and help

Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Matt Ahrens <matthew.ahrens@delphix.com>
Reviewed by: Christopher Siden <chris.siden@delphix.com>
Approved by: Garrett D'Amore <garrett@damore.org>

References:
  illumos/illumos-gate@31d7e8fa33
  https://www.illumos.org/issues/3306
  https://www.illumos.org/issues/3321

The vdev_file.c implementation in this patch diverges significantly
from the upstream version.  For consistenty with the vdev_disk.c
code the upstream version leverages the Illumos bio interfaces.
This makes sense for Illumos but not for ZoL for two reasons.

1) The vdev_disk.c code in ZoL has been rewritten to use the
   Linux block device interfaces which differ significantly
   from those in Illumos.  Therefore, updating the vdev_file.c
   to use the Illumos interfaces doesn't get you consistency
   with vdev_disk.c.

2) Using the upstream patch as is would requiring implementing
   compatibility code for those Solaris block device interfaces
   in user and kernel space.  That additional complexity could
   lead to confusion and doesn't buy us anything.

For these reasons I've opted to simply move the existing vn_rdwr()
as is in to the taskq function.  This has the advantage of being
low risk and easy to understand.  Moving the vn_rdwr() function
in to its own taskq thread also neatly avoids the possibility of
a stack overflow.

Finally, because of the additional work which is being handled by
the free taskq the number of threads has been increased.  The
thread count under Illumos defaults to 100 but was decreased to 2
in commit 08d08e due to contention.  We increase it to 8 until
the contention can be address by porting Illumos #3581.

Ported-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #1354
This commit is contained in:
George Wilson
2013-05-02 16:36:32 -07:00
committed by Brian Behlendorf
parent 5165473737
commit 5853fe790d
7 changed files with 169 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/zdb/zdb.c
+77 -29
View File
@@ -86,6 +86,7 @@ extern void dump_intent_log(zilog_t *);
uint64_t *zopt_object = NULL;
int zopt_objects = 0;
libzfs_handle_t *g_zfs;
uint64_t max_inflight = 200;
/*
* These libumem hooks provide a reasonable set of defaults for the allocator's
@@ -108,13 +109,14 @@ usage(void)
{
(void) fprintf(stderr,
"Usage: %s [-CumdibcsDvhLXFPA] [-t txg] [-e [-p path...]] "
"poolname [object...]\n"
" %s [-divPA] [-e -p path...] dataset [object...]\n"
" %s -m [-LXFPA] [-t txg] [-e [-p path...]] "
"[-U config] [-M inflight I/Os] poolname [object...]\n"
" %s [-divPA] [-e -p path...] [-U config] dataset "
"[object...]\n"
" %s -m [-LXFPA] [-t txg] [-e [-p path...]] [-U config] "
"poolname [vdev [metaslab...]]\n"
" %s -R [-A] [-e [-p path...]] poolname "
"vdev:offset:size[:flags]\n"
" %s -S [-PA] [-e [-p path...]] poolname\n"
" %s -S [-PA] [-e [-p path...]] [-U config] poolname\n"
" %s -l [-uA] device\n"
" %s -C [-A] [-U config]\n\n",
cmdname, cmdname, cmdname, cmdname, cmdname, cmdname, cmdname);
@@ -161,6 +163,8 @@ usage(void)
(void) fprintf(stderr, " -P print numbers in parseable form\n");
(void) fprintf(stderr, " -t <txg> -- highest txg to use when "
"searching for uberblocks\n");
(void) fprintf(stderr, " -M <number of inflight I/Os> -- "
"specify the maximum number of checksumming I/Os [default is 200]");
(void) fprintf(stderr, "Specify an option more than once (e.g. -bb) "
"to make only that option verbose\n");
(void) fprintf(stderr, "Default is to dump everything non-verbosely\n");
@@ -2005,6 +2009,45 @@ zdb_count_block(zdb_cb_t *zcb, zilog_t *zilog, const blkptr_t *bp,
bp, NULL, NULL, ZIO_FLAG_CANFAIL)), ==, 0);
}
static void
zdb_blkptr_done(zio_t *zio)
{
spa_t *spa = zio->io_spa;
blkptr_t *bp = zio->io_bp;
int ioerr = zio->io_error;
zdb_cb_t *zcb = zio->io_private;
zbookmark_t *zb = &zio->io_bookmark;
zio_data_buf_free(zio->io_data, zio->io_size);
mutex_enter(&spa->spa_scrub_lock);
spa->spa_scrub_inflight--;
cv_broadcast(&spa->spa_scrub_io_cv);
if (ioerr && !(zio->io_flags & ZIO_FLAG_SPECULATIVE)) {
char blkbuf[BP_SPRINTF_LEN];
zcb->zcb_haderrors = 1;
zcb->zcb_errors[ioerr]++;
if (dump_opt['b'] >= 2)
sprintf_blkptr(blkbuf, bp);
else
blkbuf[0] = '\0';
(void) printf("zdb_blkptr_cb: "
"Got error %d reading "
"<%llu, %llu, %lld, %llx> %s -- skipping\n",
ioerr,
(u_longlong_t)zb->zb_objset,
(u_longlong_t)zb->zb_object,
(u_longlong_t)zb->zb_level,
(u_longlong_t)zb->zb_blkid,
blkbuf);
}
mutex_exit(&spa->spa_scrub_lock);
}
/* ARGSUSED */
static int
zdb_blkptr_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf,
@@ -2026,39 +2069,23 @@ zdb_blkptr_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf,
is_metadata = (BP_GET_LEVEL(bp) != 0 || DMU_OT_IS_METADATA(type));
if (dump_opt['c'] > 1 || (dump_opt['c'] && is_metadata)) {
int ioerr;
size_t size = BP_GET_PSIZE(bp);
void *data = malloc(size);
void *data = zio_data_buf_alloc(size);
int flags = ZIO_FLAG_CANFAIL | ZIO_FLAG_SCRUB | ZIO_FLAG_RAW;
/* If it's an intent log block, failure is expected. */
if (zb->zb_level == ZB_ZIL_LEVEL)
flags |= ZIO_FLAG_SPECULATIVE;
ioerr = zio_wait(zio_read(NULL, spa, bp, data, size,
NULL, NULL, ZIO_PRIORITY_ASYNC_READ, flags, zb));
mutex_enter(&spa->spa_scrub_lock);
while (spa->spa_scrub_inflight > max_inflight)
cv_wait(&spa->spa_scrub_io_cv, &spa->spa_scrub_lock);
spa->spa_scrub_inflight++;
mutex_exit(&spa->spa_scrub_lock);
free(data);
zio_nowait(zio_read(NULL, spa, bp, data, size,
zdb_blkptr_done, zcb, ZIO_PRIORITY_ASYNC_READ, flags, zb));
if (ioerr && !(flags & ZIO_FLAG_SPECULATIVE)) {
zcb->zcb_haderrors = 1;
zcb->zcb_errors[ioerr]++;
if (dump_opt['b'] >= 2)
sprintf_blkptr(blkbuf, bp);
else
blkbuf[0] = '\0';
(void) printf("zdb_blkptr_cb: "
"Got error %d reading "
"<%llu, %llu, %lld, %llx> %s -- skipping\n",
ioerr,
(u_longlong_t)zb->zb_objset,
(u_longlong_t)zb->zb_object,
(u_longlong_t)zb->zb_level,
(u_longlong_t)zb->zb_blkid,
blkbuf);
}
}
zcb->zcb_readfails = 0;
@@ -2266,6 +2293,18 @@ dump_block_stats(spa_t *spa)
zcb.zcb_haderrors |= traverse_pool(spa, 0, flags, zdb_blkptr_cb, &zcb);
/*
* If we've traversed the data blocks then we need to wait for those
* I/Os to complete. We leverage "The Godfather" zio to wait on
* all async I/Os to complete.
*/
if (dump_opt['c']) {
(void) zio_wait(spa->spa_async_zio_root);
spa->spa_async_zio_root = zio_root(spa, NULL, NULL,
ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE |
ZIO_FLAG_GODFATHER);
}
if (zcb.zcb_haderrors) {
(void) printf("\nError counts:\n\n");
(void) printf("\t%5s %s\n", "errno", "count");
@@ -3026,7 +3065,7 @@ main(int argc, char **argv)
dprintf_setup(&argc, argv);
while ((c = getopt(argc, argv, "bcdhilmsuCDRSAFLXevp:t:U:P")) != -1) {
while ((c = getopt(argc, argv, "bcdhilmM:suCDRSAFLXevp:t:U:P")) != -1) {
switch (c) {
case 'b':
case 'c':
@@ -3055,6 +3094,15 @@ main(int argc, char **argv)
case 'v':
verbose++;
break;
case 'M':
max_inflight = strtoull(optarg, NULL, 0);
if (max_inflight == 0) {
(void) fprintf(stderr, "maximum number "
"of inflight I/Os must be greater "
"than 0\n");
usage();
}
break;
case 'p':
if (searchdirs == NULL) {
searchdirs = umem_alloc(sizeof (char *),