| Message ID | 63676f15fe9b1ca6c10eb9021829b4666db6d021.1727368214.git.anand.jain@oracle.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | raid1 balancing methods | expand |
在 2024/9/27 19:25, Anand Jain 写道: > This feature balances I/O across the striped devices when reading from > RAID1 blocks. > > Signed-off-by: Anand Jain <anand.jain@oracle.com> > --- > fs/btrfs/sysfs.c | 4 ++++ > fs/btrfs/volumes.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++ > fs/btrfs/volumes.h | 7 ++++++ > 3 files changed, 64 insertions(+) > > diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c > index 03926ad467c9..18fb35a887c6 100644 > --- a/fs/btrfs/sysfs.c > +++ b/fs/btrfs/sysfs.c > @@ -1305,7 +1305,11 @@ static ssize_t btrfs_temp_fsid_show(struct kobject *kobj, > } > BTRFS_ATTR(, temp_fsid, btrfs_temp_fsid_show); > > +#ifdef CONFIG_BTRFS_DEBUG > +static const char * const btrfs_read_policy_name[] = { "pid", "rotation" }; > +#else > static const char * const btrfs_read_policy_name[] = { "pid" }; > +#endif > > static ssize_t btrfs_read_policy_show(struct kobject *kobj, > struct kobj_attribute *a, char *buf) > diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c > index 995b0647f538..c130a27386a7 100644 > --- a/fs/btrfs/volumes.c > +++ b/fs/btrfs/volumes.c > @@ -5859,6 +5859,54 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, u64 logical, u64 len) > return ret; > } > > +#ifdef CONFIG_BTRFS_DEBUG It would be much better to utilize CONFIG_BTRFS_EXPERIMENTAL. CONFIG_BTRFS_DEBUG is now for pure debug purposes. Thanks, Qu > +struct stripe_mirror { > + u64 devid; > + int map; > +}; > + > +static int btrfs_cmp_devid(const void *a, const void *b) > +{ > + struct stripe_mirror *s1 = (struct stripe_mirror *)a; > + struct stripe_mirror *s2 = (struct stripe_mirror *)b; > + > + if (s1->devid < s2->devid) > + return -1; > + if (s1->devid > s2->devid) > + return 1; > + return 0; > +} > + > +static int btrfs_read_rotation(struct btrfs_chunk_map *map, int first, > + int num_stripe) > +{ > + struct stripe_mirror stripes[4] = {0}; //4: for testing, works for now. > + struct btrfs_fs_devices *fs_devices; > + u64 devid; > + int index, j, cnt; > + int next_stripe; > + > + index = 0; > + for (j = first; j < first + num_stripe; j++) { > + devid = map->stripes[j].dev->devid; > + > + stripes[index].devid = devid; > + stripes[index].map = j; > + > + index++; > + } > + > + sort(stripes, num_stripe, sizeof(struct stripe_mirror), > + btrfs_cmp_devid, NULL); > + > + fs_devices = map->stripes[first].dev->fs_devices; > + cnt = atomic_inc_return(&fs_devices->total_reads); > + next_stripe = stripes[cnt % num_stripe].map; > + > + return next_stripe; > +} > +#endif > + > static int find_live_mirror(struct btrfs_fs_info *fs_info, > struct btrfs_chunk_map *map, int first, > int dev_replace_is_ongoing) > @@ -5888,6 +5936,11 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, > case BTRFS_READ_POLICY_PID: > preferred_mirror = first + (current->pid % num_stripes); > break; > +#ifdef CONFIG_BTRFS_DEBUG > + case BTRFS_READ_POLICY_ROTATION: > + preferred_mirror = btrfs_read_rotation(map, first, num_stripes); > + break; > +#endif > } > > if (dev_replace_is_ongoing && > diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h > index 4481575dd70f..81701217dbb9 100644 > --- a/fs/btrfs/volumes.h > +++ b/fs/btrfs/volumes.h > @@ -303,6 +303,10 @@ enum btrfs_chunk_allocation_policy { > enum btrfs_read_policy { > /* Use process PID to choose the stripe */ > BTRFS_READ_POLICY_PID, > +#ifdef CONFIG_BTRFS_DEBUG > + /* Balancing raid1 reads across all striped devices */ > + BTRFS_READ_POLICY_ROTATION, > +#endif > BTRFS_NR_READ_POLICY, > }; > > @@ -431,6 +435,9 @@ struct btrfs_fs_devices { > enum btrfs_read_policy read_policy; > > #ifdef CONFIG_BTRFS_DEBUG > + /* read counter for the filesystem */ > + atomic_t total_reads; > + > /* Checksum mode - offload it or do it synchronously. */ > enum btrfs_offload_csum_mode offload_csum_mode; > #endif
>> +#ifdef CONFIG_BTRFS_DEBUG > > It would be much better to utilize CONFIG_BTRFS_EXPERIMENTAL. > CONFIG_BTRFS_DEBUG is now for pure debug purposes. Yes, I noticed the recent patch that changed that. Fixed in v2. Thanks, Anand
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 03926ad467c9..18fb35a887c6 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1305,7 +1305,11 @@ static ssize_t btrfs_temp_fsid_show(struct kobject *kobj, } BTRFS_ATTR(, temp_fsid, btrfs_temp_fsid_show); +#ifdef CONFIG_BTRFS_DEBUG +static const char * const btrfs_read_policy_name[] = { "pid", "rotation" }; +#else static const char * const btrfs_read_policy_name[] = { "pid" }; +#endif static ssize_t btrfs_read_policy_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 995b0647f538..c130a27386a7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5859,6 +5859,54 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, u64 logical, u64 len) return ret; } +#ifdef CONFIG_BTRFS_DEBUG +struct stripe_mirror { + u64 devid; + int map; +}; + +static int btrfs_cmp_devid(const void *a, const void *b) +{ + struct stripe_mirror *s1 = (struct stripe_mirror *)a; + struct stripe_mirror *s2 = (struct stripe_mirror *)b; + + if (s1->devid < s2->devid) + return -1; + if (s1->devid > s2->devid) + return 1; + return 0; +} + +static int btrfs_read_rotation(struct btrfs_chunk_map *map, int first, + int num_stripe) +{ + struct stripe_mirror stripes[4] = {0}; //4: for testing, works for now. + struct btrfs_fs_devices *fs_devices; + u64 devid; + int index, j, cnt; + int next_stripe; + + index = 0; + for (j = first; j < first + num_stripe; j++) { + devid = map->stripes[j].dev->devid; + + stripes[index].devid = devid; + stripes[index].map = j; + + index++; + } + + sort(stripes, num_stripe, sizeof(struct stripe_mirror), + btrfs_cmp_devid, NULL); + + fs_devices = map->stripes[first].dev->fs_devices; + cnt = atomic_inc_return(&fs_devices->total_reads); + next_stripe = stripes[cnt % num_stripe].map; + + return next_stripe; +} +#endif + static int find_live_mirror(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map, int first, int dev_replace_is_ongoing) @@ -5888,6 +5936,11 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, case BTRFS_READ_POLICY_PID: preferred_mirror = first + (current->pid % num_stripes); break; +#ifdef CONFIG_BTRFS_DEBUG + case BTRFS_READ_POLICY_ROTATION: + preferred_mirror = btrfs_read_rotation(map, first, num_stripes); + break; +#endif } if (dev_replace_is_ongoing && diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 4481575dd70f..81701217dbb9 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -303,6 +303,10 @@ enum btrfs_chunk_allocation_policy { enum btrfs_read_policy { /* Use process PID to choose the stripe */ BTRFS_READ_POLICY_PID, +#ifdef CONFIG_BTRFS_DEBUG + /* Balancing raid1 reads across all striped devices */ + BTRFS_READ_POLICY_ROTATION, +#endif BTRFS_NR_READ_POLICY, }; @@ -431,6 +435,9 @@ struct btrfs_fs_devices { enum btrfs_read_policy read_policy; #ifdef CONFIG_BTRFS_DEBUG + /* read counter for the filesystem */ + atomic_t total_reads; + /* Checksum mode - offload it or do it synchronously. */ enum btrfs_offload_csum_mode offload_csum_mode; #endif
This feature balances I/O across the striped devices when reading from RAID1 blocks. Signed-off-by: Anand Jain <anand.jain@oracle.com> --- fs/btrfs/sysfs.c | 4 ++++ fs/btrfs/volumes.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/volumes.h | 7 ++++++ 3 files changed, 64 insertions(+)