block: discard alignment fixes
cover block: discard alignment fixes
Two discard alignment issues were identified in
https://issues.redhat.com/browse/RHEL-86032:
1. pdiscard_alignment is not populated for host_device in file-posix.c.
2. Misaligned head/tail discard requests are not skipped when file-posix.c returns -EINVAL. This causes an undesired pause when guests are configured with werror=stop.
Stefan Hajnoczi (2):
file-posix: probe discard alignment on Linux block devices block/io: skip head/tail requests on EINVAL
block/file-posix.c | 56 +++++++++++++++++++++++++++++++++++++++++++++- block/io.c | 6 ++++- 2 files changed, 60 insertions(+), 2 deletions(-)
Signature · 1 line
2.49.0
PATCH 1/2 file-posix: probe discard alignment on Linux block devices
Populate the pdiscard_alignment block limit so the block layer is able align discard requests correctly.
--- block/file-posix.c | 56 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 55 insertions(+), 1 deletion(-)
block/file-posix.c +55 -1
@@ -1276,10 +1276,10 @@ static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned) }#endif /* defined(CONFIG_BLKZONED) */ +#ifdef CONFIG_LINUX /* * Get a sysfs attribute value as a long integer. */ -#ifdef CONFIG_LINUX static long get_sysfs_long_val (struct stat *st,const char *attribute) { g_autofree char *str = NULL;
@@ -1299,6 +1299,30 @@ static long get_sysfs_long_val(struct stat *st, const char *attribute) }return ret; } + +/* +* Get a sysfs attribute value as a uint32_t. +*/ +static int get_sysfs_u32_val (struct stat *st,const char *attribute, +uint32_t *u32) +{ + g_autofree char *str = NULL; +const char *end; +unsigned int val; +int ret; + + ret =get_sysfs_str_val (st, attribute, &str); +if (ret <0 ) { +return ret; + } + +/* The file is ended with '\n', pass 'end' to accept that. */ + ret =qemu_strtoui (str, &end,10 , &val); +if (ret ==0 && end && *end =='\0' ) { + *u32 = val; + } +return ret; +}#endif static int hdev_get_max_segments (int fd,struct stat *st)
@@ -1318,6 +1342,23 @@ static int hdev_get_max_segments(int fd, struct stat *st)#endif } +/* +* Fills in *dalign with the discard alignment and returns 0 on success, +* -errno otherwise. +*/ +static int hdev_get_pdiscard_alignment (struct stat *st,uint32_t *dalign) +{ +#ifdef CONFIG_LINUX +/* +* Note that Linux "discard_granularity" is QEMU "discard_alignment". Linux +* "discard_alignment" is something else. +*/ +return get_sysfs_u32_val (st,"discard_granularity" , dalign); +#else +return -ENOTSUP ; +#endif +} +#if defined(CONFIG_BLKZONED )/* * If the reset_all flag is true, then the wps of zone whose state is
@@ -1527,6 +1568,19 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) } } +if (S_ISBLK (st.st_mode)) { +uint32_t dalign =0 ; +int ret; + + ret =hdev_get_pdiscard_alignment (&st, &dalign); +if (ret ==0 ) { +/* Must be a multiple of request_alignment */ +assert (dalign % bs->bl.request_alignment ==0 ); + + bs->bl.pdiscard_alignment = dalign; + } + } +raw_refresh_zoned_limits (bs, &st, errp); }
Signature · 1 line
2.49.0
Re: [PATCH 1/2] file-posix: probe discard alignment on Linux block devices
Quoted 13 lines · Stefan Hajnoczi
Populate the
pdiscard_alignmentblock limit so the block layer is able align discard requests correctly.Signed-off-by Stefan Hajnoczi <[email protected]>--- block/file-posix.c | 56 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 55 insertions(+), 1 deletion(-)block/file-posix.c +0
-0
block/file-posix.c static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned) · line 1283
Quoted 9 lines
block/file-posix.c +1
-1@@ -1276,10 +1276,10 @@ static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned) }#endif /* defined(CONFIG_BLKZONED) */ +#ifdef CONFIG_LINUX /* * Get a sysfs attribute value as a long integer. */ -#ifdef CONFIG_LINUX static long get_sysfs_long_val (struct stat *st,const char *attribute)
Random change to pull the comment inside of the #if, but tangentially related so I don't mind keeping it here.
Quoted 21 lines
block/file-posix.c +15
-0{ g_autofree char *str = NULL;@@ -1299,6 +1299,30 @@ static long get_sysfs_long_val(struct stat *st, const char *attribute) }return ret; } + +/* +* Get a sysfs attribute value as a uint32_t. +*/ +static int get_sysfs_u32_val (struct stat *st,const char *attribute, +uint32_t *u32) +{ + g_autofree char *str = NULL; +const char *end; +unsigned int val; +int ret; + + ret =get_sysfs_str_val (st, attribute, &str); +if (ret <0 ) { +return ret;
block/file-posix.c static long get_sysfs_long_val(struct stat *st, const char *attribute) · line 1326
Quoted 10 lines
block/file-posix.c +9
-0+ } + +/* The file is ended with '\n', pass 'end' to accept that. */ + ret =qemu_strtoui (str, &end,10 , &val); +if (ret ==0 && end && *end =='\0' ) { + *u32 = val; + } +return ret; +}#endif
May be worth amending this line to "#endif /* CONFIG_LINUX */" now that it is further from the opening #if.
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. Virtualization: qemu.org | libguestfs.org
PATCH 2/2 block/io: skip head/tail requests on EINVAL
In reply to Stefan HajnocziWhen guests send misaligned discard requests, the block layer breaks them up into a misaligned head, an aligned main body, and a misaligned tail.
The file-posix block driver on Linux returns -EINVAL on misaligned discard requests. This causes bdrv_co_pdiscard() to fail and guests configured with werror=stop will pause.
Add a special case for misaligned head/tail requests. Simply continue when EINVAL is encountered so that the aligned main body of the request can be completed and the guest is not paused. This is the best we can do when guest discard limits do not match the host discard limits.
--- block/io.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
block/io.c +5 -1
@@ -3180,7 +3180,11 @@ int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, } }if (ret && ret != -ENOTSUP ) { - goto out; +if (ret == -EINVAL && (offset % align ==0 || num % align ==0 )) { +/* Silently skip rejected unaligned head/tail requests */ + }else { + goto out;/* bail out */ + } } offset += num;
Signature · 1 line
2.49.0