d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
6ca636a152
freebsd-dev/cmd/zdb/zdb_il.c
Ned Bass 50c957f702 Implement large_dnode pool feature 
Justification
-------------

This feature adds support for variable length dnodes. Our motivation is
to eliminate the overhead associated with using spill blocks.  Spill
blocks are used to store system attribute data (i.e. file metadata) that
does not fit in the dnode's bonus buffer. By allowing a larger bonus
buffer area the use of a spill block can be avoided.  Spill blocks
potentially incur an additional read I/O for every dnode in a dnode
block. As a worst case example, reading 32 dnodes from a 16k dnode block
and all of the spill blocks could issue 33 separate reads. Now suppose
those dnodes have size 1024 and therefore don't need spill blocks.  Then
the worst case number of blocks read is reduced to from 33 to two--one
per dnode block. In practice spill blocks may tend to be co-located on
disk with the dnode blocks so the reduction in I/O would not be this
drastic. In a badly fragmented pool, however, the improvement could be
significant.

ZFS-on-Linux systems that make heavy use of extended attributes would
benefit from this feature. In particular, ZFS-on-Linux supports the
xattr=sa dataset property which allows file extended attribute data
to be stored in the dnode bonus buffer as an alternative to the
traditional directory-based format. Workloads such as SELinux and the
Lustre distributed filesystem often store enough xattr data to force
spill bocks when xattr=sa is in effect. Large dnodes may therefore
provide a performance benefit to such systems.

Other use cases that may benefit from this feature include files with
large ACLs and symbolic links with long target names. Furthermore,
this feature may be desirable on other platforms in case future
applications or features are developed that could make use of a
larger bonus buffer area.

Implementation
--------------

The size of a dnode may be a multiple of 512 bytes up to the size of
a dnode block (currently 16384 bytes). A dn_extra_slots field was
added to the current on-disk dnode_phys_t structure to describe the
size of the physical dnode on disk. The 8 bits for this field were
taken from the zero filled dn_pad2 field. The field represents how
many "extra" dnode_phys_t slots a dnode consumes in its dnode block.
This convention results in a value of 0 for 512 byte dnodes which
preserves on-disk format compatibility with older software.

Similarly, the in-memory dnode_t structure has a new dn_num_slots field
to represent the total number of dnode_phys_t slots consumed on disk.
Thus dn->dn_num_slots is 1 greater than the corresponding
dnp->dn_extra_slots. This difference in convention was adopted
because, unlike on-disk structures, backward compatibility is not a
concern for in-memory objects, so we used a more natural way to
represent size for a dnode_t.

The default size for newly created dnodes is determined by the value of
a new "dnodesize" dataset property. By default the property is set to
"legacy" which is compatible with older software. Setting the property
to "auto" will allow the filesystem to choose the most suitable dnode
size. Currently this just sets the default dnode size to 1k, but future
code improvements could dynamically choose a size based on observed
workload patterns. Dnodes of varying sizes can coexist within the same
dataset and even within the same dnode block. For example, to enable
automatically-sized dnodes, run

 # zfs set dnodesize=auto tank/fish

The user can also specify literal values for the dnodesize property.
These are currently limited to powers of two from 1k to 16k. The
power-of-2 limitation is only for simplicity of the user interface.
Internally the implementation can handle any multiple of 512 up to 16k,
and consumers of the DMU API can specify any legal dnode value.

The size of a new dnode is determined at object allocation time and
stored as a new field in the znode in-memory structure. New DMU
interfaces are added to allow the consumer to specify the dnode size
that a newly allocated object should use. Existing interfaces are
unchanged to avoid having to update every call site and to preserve
compatibility with external consumers such as Lustre. The new
interfaces names are given below. The versions of these functions that
don't take a dnodesize parameter now just call the _dnsize() versions
with a dnodesize of 0, which means use the legacy dnode size.

New DMU interfaces:
  dmu_object_alloc_dnsize()
  dmu_object_claim_dnsize()
  dmu_object_reclaim_dnsize()

New ZAP interfaces:
  zap_create_dnsize()
  zap_create_norm_dnsize()
  zap_create_flags_dnsize()
  zap_create_claim_norm_dnsize()
  zap_create_link_dnsize()

The constant DN_MAX_BONUSLEN is renamed to DN_OLD_MAX_BONUSLEN. The
spa_maxdnodesize() function should be used to determine the maximum
bonus length for a pool.

These are a few noteworthy changes to key functions:

* The prototype for dnode_hold_impl() now takes a "slots" parameter.
  When the DNODE_MUST_BE_FREE flag is set, this parameter is used to
  ensure the hole at the specified object offset is large enough to
  hold the dnode being created. The slots parameter is also used
  to ensure a dnode does not span multiple dnode blocks. In both of
  these cases, if a failure occurs, ENOSPC is returned. Keep in mind,
  these failure cases are only possible when using DNODE_MUST_BE_FREE.

  If the DNODE_MUST_BE_ALLOCATED flag is set, "slots" must be 0.
  dnode_hold_impl() will check if the requested dnode is already
  consumed as an extra dnode slot by an large dnode, in which case
  it returns ENOENT.

* The function dmu_object_alloc() advances to the next dnode block
  if dnode_hold_impl() returns an error for a requested object.
  This is because the beginning of the next dnode block is the only
  location it can safely assume to either be a hole or a valid
  starting point for a dnode.

* dnode_next_offset_level() and other functions that iterate
  through dnode blocks may no longer use a simple array indexing
  scheme. These now use the current dnode's dn_num_slots field to
  advance to the next dnode in the block. This is to ensure we
  properly skip the current dnode's bonus area and don't interpret it
  as a valid dnode.

zdb
---
The zdb command was updated to display a dnode's size under the
"dnsize" column when the object is dumped.

For ZIL create log records, zdb will now display the slot count for
the object.

ztest
-----
Ztest chooses a random dnodesize for every newly created object. The
random distribution is more heavily weighted toward small dnodes to
better simulate real-world datasets.

Unused bonus buffer space is filled with non-zero values computed from
the object number, dataset id, offset, and generation number.  This
helps ensure that the dnode traversal code properly skips the interior
regions of large dnodes, and that these interior regions are not
overwritten by data belonging to other dnodes. A new test visits each
object in a dataset. It verifies that the actual dnode size matches what
was stored in the ztest block tag when it was created. It also verifies
that the unused bonus buffer space is filled with the expected data
patterns.

ZFS Test Suite
--------------
Added six new large dnode-specific tests, and integrated the dnodesize
property into existing tests for zfs allow and send/recv.

Send/Receive
------------
ZFS send streams for datasets containing large dnodes cannot be received
on pools that don't support the large_dnode feature. A send stream with
large dnodes sets a DMU_BACKUP_FEATURE_LARGE_DNODE flag which will be
unrecognized by an incompatible receiving pool so that the zfs receive
will fail gracefully.

While not implemented here, it may be possible to generate a
backward-compatible send stream from a dataset containing large
dnodes. The implementation may be tricky, however, because the send
object record for a large dnode would need to be resized to a 512
byte dnode, possibly kicking in a spill block in the process. This
means we would need to construct a new SA layout and possibly
register it in the SA layout object. The SA layout is normally just
sent as an ordinary object record. But if we are constructing new
layouts while generating the send stream we'd have to build the SA
layout object dynamically and send it at the end of the stream.

For sending and receiving between pools that do support large dnodes,
the drr_object send record type is extended with a new field to store
the dnode slot count. This field was repurposed from unused padding
in the structure.

ZIL Replay
----------
The dnode slot count is stored in the uppermost 8 bits of the lr_foid
field. The bits were unused as the object id is currently capped at
48 bits.

Resizing Dnodes
---------------
It should be possible to resize a dnode when it is dirtied if the
current dnodesize dataset property differs from the dnode's size, but
this functionality is not currently implemented. Clearly a dnode can
only grow if there are sufficient contiguous unused slots in the
dnode block, but it should always be possible to shrink a dnode.
Growing dnodes may be useful to reduce fragmentation in a pool with
many spill blocks in use. Shrinking dnodes may be useful to allow
sending a dataset to a pool that doesn't support the large_dnode
feature.

Feature Reference Counting
--------------------------
The reference count for the large_dnode pool feature tracks the
number of datasets that have ever contained a dnode of size larger
than 512 bytes. The first time a large dnode is created in a dataset
the dataset is converted to an extensible dataset. This is a one-way
operation and the only way to decrement the feature count is to
destroy the dataset, even if the dataset no longer contains any large
dnodes. The complexity of reference counting on a per-dnode basis was
too high, so we chose to track it on a per-dataset basis similarly to
the large_block feature.

Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3542
2016-06-24 13:13:21 -07:00

397 lines
11 KiB
C
Raw Blame History

/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
* Copyright (c) 2012 Cyril Plisko. All rights reserved.
* Use is subject to license terms.
*/
/*
* Copyright (c) 2013, 2014 by Delphix. All rights reserved.
*/
/*
* Print intent log header and statistics.
*/
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/dmu.h>
#include <sys/stat.h>
#include <sys/resource.h>
#include <sys/zil.h>
#include <sys/zil_impl.h>
extern uint8_t dump_opt[256];
static char prefix[4] = "\t\t\t";
static void
print_log_bp(const blkptr_t *bp, const char *prefix)
{
char blkbuf[BP_SPRINTF_LEN];
snprintf_blkptr(blkbuf, sizeof (blkbuf), bp);
(void) printf("%s%s\n", prefix, blkbuf);
}
/* ARGSUSED */
static void
zil_prt_rec_create(zilog_t *zilog, int txtype, lr_create_t *lr)
{
time_t crtime = lr->lr_crtime[0];
char *name, *link;
lr_attr_t *lrattr;
name = (char *)(lr + 1);
if (lr->lr_common.lrc_txtype == TX_CREATE_ATTR ||
lr->lr_common.lrc_txtype == TX_MKDIR_ATTR) {
lrattr = (lr_attr_t *)(lr + 1);
name += ZIL_XVAT_SIZE(lrattr->lr_attr_masksize);
}
if (txtype == TX_SYMLINK) {
link = name + strlen(name) + 1;
(void) printf("%s%s -> %s\n", prefix, name, link);
} else if (txtype != TX_MKXATTR) {
(void) printf("%s%s\n", prefix, name);
}
(void) printf("%s%s", prefix, ctime(&crtime));
(void) printf("%sdoid %llu, foid %llu, slots %llu, mode %llo\n", prefix,
(u_longlong_t)lr->lr_doid,
(u_longlong_t)LR_FOID_GET_OBJ(lr->lr_foid),
(u_longlong_t)LR_FOID_GET_SLOTS(lr->lr_foid),
(longlong_t)lr->lr_mode);
(void) printf("%suid %llu, gid %llu, gen %llu, rdev 0x%llx\n", prefix,
(u_longlong_t)lr->lr_uid, (u_longlong_t)lr->lr_gid,
(u_longlong_t)lr->lr_gen, (u_longlong_t)lr->lr_rdev);
}
/* ARGSUSED */
static void
zil_prt_rec_remove(zilog_t *zilog, int txtype, lr_remove_t *lr)
{
(void) printf("%sdoid %llu, name %s\n", prefix,
(u_longlong_t)lr->lr_doid, (char *)(lr + 1));
}
/* ARGSUSED */
static void
zil_prt_rec_link(zilog_t *zilog, int txtype, lr_link_t *lr)
{
(void) printf("%sdoid %llu, link_obj %llu, name %s\n", prefix,
(u_longlong_t)lr->lr_doid, (u_longlong_t)lr->lr_link_obj,
(char *)(lr + 1));
}
/* ARGSUSED */
static void
zil_prt_rec_rename(zilog_t *zilog, int txtype, lr_rename_t *lr)
{
char *snm = (char *)(lr + 1);
char *tnm = snm + strlen(snm) + 1;
(void) printf("%ssdoid %llu, tdoid %llu\n", prefix,
(u_longlong_t)lr->lr_sdoid, (u_longlong_t)lr->lr_tdoid);
(void) printf("%ssrc %s tgt %s\n", prefix, snm, tnm);
}
/* ARGSUSED */
static void
zil_prt_rec_write(zilog_t *zilog, int txtype, lr_write_t *lr)
{
char *data, *dlimit;
blkptr_t *bp = &lr->lr_blkptr;
zbookmark_phys_t zb;
char *buf;
int verbose = MAX(dump_opt['d'], dump_opt['i']);
int error;
(void) printf("%sfoid %llu, offset %llx, length %llx\n", prefix,
(u_longlong_t)lr->lr_foid, (u_longlong_t)lr->lr_offset,
(u_longlong_t)lr->lr_length);
if (txtype == TX_WRITE2 || verbose < 5)
return;
if ((buf = malloc(SPA_MAXBLOCKSIZE)) == NULL)
return;
if (lr->lr_common.lrc_reclen == sizeof (lr_write_t)) {
(void) printf("%shas blkptr, %s\n", prefix,
!BP_IS_HOLE(bp) &&
bp->blk_birth >= spa_first_txg(zilog->zl_spa) ?
"will claim" : "won't claim");
print_log_bp(bp, prefix);
if (BP_IS_HOLE(bp)) {
(void) printf("\t\t\tLSIZE 0x%llx\n",
(u_longlong_t)BP_GET_LSIZE(bp));
bzero(buf, SPA_MAXBLOCKSIZE);
(void) printf("%s<hole>\n", prefix);
goto exit;
}
if (bp->blk_birth < zilog->zl_header->zh_claim_txg) {
(void) printf("%s<block already committed>\n", prefix);
goto exit;
}
SET_BOOKMARK(&zb, dmu_objset_id(zilog->zl_os),
lr->lr_foid, ZB_ZIL_LEVEL,
lr->lr_offset / BP_GET_LSIZE(bp));
error = zio_wait(zio_read(NULL, zilog->zl_spa,
bp, buf, BP_GET_LSIZE(bp), NULL, NULL,
ZIO_PRIORITY_SYNC_READ, ZIO_FLAG_CANFAIL, &zb));
if (error)
goto exit;
data = buf;
} else {
data = (char *)(lr + 1);
}
dlimit = data + MIN(lr->lr_length,
(verbose < 6 ? 20 : SPA_MAXBLOCKSIZE));
(void) printf("%s", prefix);
while (data < dlimit) {
if (isprint(*data))
(void) printf("%c ", *data);
else
(void) printf("%2hhX", *data);
data++;
}
(void) printf("\n");
exit:
free(buf);
}
/* ARGSUSED */
static void
zil_prt_rec_truncate(zilog_t *zilog, int txtype, lr_truncate_t *lr)
{
(void) printf("%sfoid %llu, offset 0x%llx, length 0x%llx\n", prefix,
(u_longlong_t)lr->lr_foid, (longlong_t)lr->lr_offset,
(u_longlong_t)lr->lr_length);
}
/* ARGSUSED */
static void
zil_prt_rec_setattr(zilog_t *zilog, int txtype, lr_setattr_t *lr)
{
time_t atime = (time_t)lr->lr_atime[0];
time_t mtime = (time_t)lr->lr_mtime[0];
(void) printf("%sfoid %llu, mask 0x%llx\n", prefix,
(u_longlong_t)lr->lr_foid, (u_longlong_t)lr->lr_mask);
if (lr->lr_mask & AT_MODE) {
(void) printf("%sAT_MODE %llo\n", prefix,
(longlong_t)lr->lr_mode);
}
if (lr->lr_mask & AT_UID) {
(void) printf("%sAT_UID %llu\n", prefix,
(u_longlong_t)lr->lr_uid);
}
if (lr->lr_mask & AT_GID) {
(void) printf("%sAT_GID %llu\n", prefix,
(u_longlong_t)lr->lr_gid);
}
if (lr->lr_mask & AT_SIZE) {
(void) printf("%sAT_SIZE %llu\n", prefix,
(u_longlong_t)lr->lr_size);
}
if (lr->lr_mask & AT_ATIME) {
(void) printf("%sAT_ATIME %llu.%09llu %s", prefix,
(u_longlong_t)lr->lr_atime[0],
(u_longlong_t)lr->lr_atime[1],
ctime(&atime));
}
if (lr->lr_mask & AT_MTIME) {
(void) printf("%sAT_MTIME %llu.%09llu %s", prefix,
(u_longlong_t)lr->lr_mtime[0],
(u_longlong_t)lr->lr_mtime[1],
ctime(&mtime));
}
}
/* ARGSUSED */
static void
zil_prt_rec_acl(zilog_t *zilog, int txtype, lr_acl_t *lr)
{
(void) printf("%sfoid %llu, aclcnt %llu\n", prefix,
(u_longlong_t)lr->lr_foid, (u_longlong_t)lr->lr_aclcnt);
}
typedef void (*zil_prt_rec_func_t)(zilog_t *, int, void *);
typedef struct zil_rec_info {
zil_prt_rec_func_t zri_print;
char *zri_name;
uint64_t zri_count;
} zil_rec_info_t;
static zil_rec_info_t zil_rec_info[TX_MAX_TYPE] = {
{ NULL, "Total " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_CREATE " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_MKDIR " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_MKXATTR " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_SYMLINK " },
{ (zil_prt_rec_func_t)zil_prt_rec_remove, "TX_REMOVE " },
{ (zil_prt_rec_func_t)zil_prt_rec_remove, "TX_RMDIR " },
{ (zil_prt_rec_func_t)zil_prt_rec_link, "TX_LINK " },
{ (zil_prt_rec_func_t)zil_prt_rec_rename, "TX_RENAME " },
{ (zil_prt_rec_func_t)zil_prt_rec_write, "TX_WRITE " },
{ (zil_prt_rec_func_t)zil_prt_rec_truncate, "TX_TRUNCATE " },
{ (zil_prt_rec_func_t)zil_prt_rec_setattr, "TX_SETATTR " },
{ (zil_prt_rec_func_t)zil_prt_rec_acl, "TX_ACL_V0 " },
{ (zil_prt_rec_func_t)zil_prt_rec_acl, "TX_ACL_ACL " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_CREATE_ACL " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_CREATE_ATTR " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_CREATE_ACL_ATTR " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_MKDIR_ACL " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_MKDIR_ATTR " },
{ (zil_prt_rec_func_t)zil_prt_rec_create, "TX_MKDIR_ACL_ATTR " },
{ (zil_prt_rec_func_t)zil_prt_rec_write, "TX_WRITE2 " },
};
/* ARGSUSED */
static int
print_log_record(zilog_t *zilog, lr_t *lr, void *arg, uint64_t claim_txg)
{
int txtype;
int verbose = MAX(dump_opt['d'], dump_opt['i']);
/* reduce size of txtype to strip off TX_CI bit */
txtype = lr->lrc_txtype;
ASSERT(txtype != 0 && (uint_t)txtype < TX_MAX_TYPE);
ASSERT(lr->lrc_txg);
(void) printf("\t\t%s%s len %6llu, txg %llu, seq %llu\n",
(lr->lrc_txtype & TX_CI) ? "CI-" : "",
zil_rec_info[txtype].zri_name,
(u_longlong_t)lr->lrc_reclen,
(u_longlong_t)lr->lrc_txg,
(u_longlong_t)lr->lrc_seq);
if (txtype && verbose >= 3)
zil_rec_info[txtype].zri_print(zilog, txtype, lr);
zil_rec_info[txtype].zri_count++;
zil_rec_info[0].zri_count++;
return (0);
}
/* ARGSUSED */
static int
print_log_block(zilog_t *zilog, blkptr_t *bp, void *arg, uint64_t claim_txg)
{
char blkbuf[BP_SPRINTF_LEN + 10];
int verbose = MAX(dump_opt['d'], dump_opt['i']);
char *claim;
if (verbose <= 3)
return (0);
if (verbose >= 5) {
(void) strcpy(blkbuf, ", ");
snprintf_blkptr(blkbuf + strlen(blkbuf),
sizeof (blkbuf) - strlen(blkbuf), bp);
} else {
blkbuf[0] = '\0';
}
if (claim_txg != 0)
claim = "already claimed";
else if (bp->blk_birth >= spa_first_txg(zilog->zl_spa))
claim = "will claim";
else
claim = "won't claim";
(void) printf("\tBlock seqno %llu, %s%s\n",
(u_longlong_t)bp->blk_cksum.zc_word[ZIL_ZC_SEQ], claim, blkbuf);
return (0);
}
static void
print_log_stats(int verbose)
{
int i, w, p10;
if (verbose > 3)
(void) printf("\n");
if (zil_rec_info[0].zri_count == 0)
return;
for (w = 1, p10 = 10; zil_rec_info[0].zri_count >= p10; p10 *= 10)
w++;
for (i = 0; i < TX_MAX_TYPE; i++)
if (zil_rec_info[i].zri_count || verbose >= 3)
(void) printf("\t\t%s %*llu\n",
zil_rec_info[i].zri_name, w,
(u_longlong_t)zil_rec_info[i].zri_count);
(void) printf("\n");
}
/* ARGSUSED */
void
dump_intent_log(zilog_t *zilog)
{
const zil_header_t *zh = zilog->zl_header;
int verbose = MAX(dump_opt['d'], dump_opt['i']);
int i;
if (BP_IS_HOLE(&zh->zh_log) || verbose < 1)
return;
(void) printf("\n ZIL header: claim_txg %llu, "
"claim_blk_seq %llu, claim_lr_seq %llu",
(u_longlong_t)zh->zh_claim_txg,
(u_longlong_t)zh->zh_claim_blk_seq,
(u_longlong_t)zh->zh_claim_lr_seq);
(void) printf(" replay_seq %llu, flags 0x%llx\n",
(u_longlong_t)zh->zh_replay_seq, (u_longlong_t)zh->zh_flags);
for (i = 0; i < TX_MAX_TYPE; i++)
zil_rec_info[i].zri_count = 0;
if (verbose >= 2) {
(void) printf("\n");
(void) zil_parse(zilog, print_log_block, print_log_record, NULL,
zh->zh_claim_txg);
print_log_stats(verbose);
}
}
Reference in New Issue View Git Blame Copy Permalink