btrfs: read_policy type device
cover btrfs: read_policy type device
This patch set provides a read_policy type device and was part of the other read_policies before [1].
[1]
Re: [PATCH v4 0/3, full-cover-letter] btrfs: read_policy types latency, device and round-robin
https://lore.kernel.org/linux-btrfs/20210120123437.OVx7ybGaVfmOdZxtpp43qcB_ORHQQs5OzPSzr3ZUGbo@z/T/
I am sending them separately as they help to test the integrity of the mirrored RAID devices.
No change from the previous V4 except for the rebase conflict fixes.
Anand Jain (2):
btrfs: introduce new device-state read_preferred
btrfs: introduce new read_policy device
fs/btrfs/sysfs.c | 55 +++++++++++++++++++++++++++++++++++++++++++++- fs/btrfs/volumes.c | 23 +++++++++++++++++++ fs/btrfs/volumes.h | 3 +++ 3 files changed, 80 insertions(+), 1 deletion(-)
Signature · 1 line
2.33.1
PATCH 1/2 btrfs: introduce new device-state read_preferred
This is a preparatory patch and introduces a new device flag 'read_preferred', RW-able using sysfs interface.
--- fs/btrfs/sysfs.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/volumes.h | 1 + 2 files changed, 54 insertions(+)
fs/btrfs/sysfs.c +53 -0
@@ -1785,6 +1785,58 @@ static ssize_t btrfs_devinfo_error_stats_show(struct kobject *kobj, }BTRFS_ATTR (devid, error_stats, btrfs_devinfo_error_stats_show); +static ssize_t btrfs_devinfo_read_pref_show (struct kobject *kobj, +struct kobj_attribute *a,char *buf) +{ +int val; + struct btrfs_device *device = container_of(kobj, struct btrfs_device, + devid_kobj); + + val = !!test_bit (BTRFS_DEV_STATE_READ_PREFERRED , &device->dev_state); + +return snprintf (buf,PAGE_SIZE ,"%d\n" , val); +} + +static ssize_t btrfs_devinfo_read_pref_store (struct kobject *kobj, +struct kobj_attribute *a, +const char *buf,size_t len) +{ +int ret; +unsigned long val; +struct btrfs_device *device; + + ret =kstrtoul (skip_spaces (buf),0 , &val); +if (ret) +return ret; + +if (val !=0 && val !=1 ) +return -EINVAL ; + +/* +* lock is not required, the btrfs_device struct can't be freed while +* its kobject btrfs_device::devid_kobj is still open. +*/ + device = container_of(kobj, struct btrfs_device, devid_kobj); + +if (val && + !test_bit (BTRFS_DEV_STATE_READ_PREFERRED , &device->dev_state)) { +set_bit (BTRFS_DEV_STATE_READ_PREFERRED , &device->dev_state); +btrfs_info (device->fs_devices->fs_info, +"set read preferred on devid %llu (%d)" , + device->devid,task_pid_nr (current)); + }else if (!val && +test_bit (BTRFS_DEV_STATE_READ_PREFERRED , &device->dev_state)) { +clear_bit (BTRFS_DEV_STATE_READ_PREFERRED , &device->dev_state); +btrfs_info (device->fs_devices->fs_info, +"reset read preferred on devid %llu (%d)" , + device->devid,task_pid_nr (current)); + } + +return len; +} +BTRFS_ATTR_RW (devid, read_preferred, btrfs_devinfo_read_pref_show, + btrfs_devinfo_read_pref_store); +/* * Information about one device. *
@@ -1798,6 +1850,7 @@ static struct attribute *devid_attrs[] = {BTRFS_ATTR_PTR (devid, replace_target),BTRFS_ATTR_PTR (devid, scrub_speed_max),BTRFS_ATTR_PTR (devid, writeable), +BTRFS_ATTR_PTR (devid, read_preferred), NULL };ATTRIBUTE_GROUPS (devid);
fs/btrfs/volumes.h +1 -0
@@ -85,6 +85,7 @@ struct btrfs_io_geometry {#define BTRFS_DEV_STATE_REPLACE_TGT (3)#define BTRFS_DEV_STATE_FLUSH_SENT (4)#define BTRFS_DEV_STATE_NO_READA (5) +#define BTRFS_DEV_STATE_READ_PREFERRED (6)struct btrfs_zoned_device_info ;
Signature · 1 line
2.33.1
PATCH 2/2 btrfs: introduce new read_policy device
In reply to Anand JainRead-policy type 'device' and device flag 'read-preferred':
The read-policy type device picks the device(s) flagged as read-preferred for reading stripes of type raid1, raid10, raid1c3 and raid1c4.
A system might contain SSD, nvme, iscsi, or san lun, and which are all a non-rotational device, so it is not a good idea to set the read-preferred automatically. Instead, device read-policy along with the read-preferred flag provides an ability to do it manually. This advanced tuning is useful in more than one situation, for example,
- In heterogeneous-disk volume, it provides an ability to manually choose the low latency disks for reading.
- Useful for more accurate testing.
- Avoid known problematic device from reading the chunk until it is replaced (by marking the other good devices as read-preferred).
Note:
If the read-policy type is set to 'device', but there isn't any device which is flagged as read-preferred, then stripe 0 is used for reading.
The device replacement won't migrate the read-preferred flag to the new replace the target device.
As of now, this is an in-memory only feature.
It's pointless to set the read-preferred flag on the missing device, as IOs aren't submitted to the missing device.
If there is more than one read-preferred device in a chunk, the read IO shall go to the stripe 0 as of now.
Usage example:
Consider a typical two disks raid1.
Configure devid1 for reading.
$ echo 1 > devinfo/1/read_preferred $ cat devinfo/1/read_preferred 1 $ cat devinfo/2/read_preferred 0
$ pwd /sys/fs/btrfs/12345678-1234-1234-1234-123456789abc
$ cat read_policy [pid] device $ echo device > ./read_policy $ cat read_policy pid [device]
Now read IOs are sent to devid 1 (sdb).
$ echo 3 > /proc/sys/vm/drop_caches $ md5sum /btrfs/YkZI
$ iostat -zy 1 | egrep 'sdb|sdc' (from another terminal) sdb 50.00 40048.00 0.00 40048 0
Change the read-preferred device from devid 1 to devid 2 (sdc).
$ echo 0 > ./devinfo/1/read_preferred
[ 3343.918658] BTRFS info (device sdb): reset read preferred on devid 1 (1334)
$ echo 1 > ./devinfo/2/read_preferred
[ 3343.919876] BTRFS info (device sdb): set read preferred on devid 2 (1334)
$ echo 3 > /proc/sys/vm/drop_caches $ md5sum /btrfs/YkZI
Further read ios are sent to devid 2 (sdc).
$ iostat -zy 1 | egrep 'sdb|sdc' (from another terminal) sdc 49.00 40048.00 0.00 40048 0
--- fs/btrfs/sysfs.c | 2 +- fs/btrfs/volumes.c | 23 +++++++++++++++++++++++ fs/btrfs/volumes.h | 2 ++ 3 files changed, 26 insertions(+), 1 deletion(-)
fs/btrfs/sysfs.c +1 -1
@@ -1169,7 +1169,7 @@ static bool strmatch(const char *buffer, const char *string)return false; } -static const char *const btrfs_read_policy_name[] = {"pid" }; +static const char *const btrfs_read_policy_name[] = {"pid" ,"device" };static ssize_t btrfs_read_policy_show (struct kobject *kobj,struct kobj_attribute *a,char *buf)
fs/btrfs/volumes.c +23 -0
@@ -5793,6 +5793,25 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, u64 logical, u64 len)return ret; } +static int btrfs_find_read_preferred (struct map_lookup *map,int first,int num_stripe) +{ +int stripe_index; +int last = first + num_stripe; + +/* +* If there are more than one read preferred devices, then just pick the +* first found read preferred device as of now. +*/ +for (stripe_index = first; stripe_index < last; stripe_index++) { +if (test_bit (BTRFS_DEV_STATE_READ_PREFERRED , + &map->stripes[stripe_index].dev->dev_state)) +return stripe_index; + } + +/* If there is no read preferred device then just use the first stripe */ +return first; +} +static int find_live_mirror (struct btrfs_fs_info *fs_info,struct map_lookup *map,int first,int dev_replace_is_ongoing)
@@ -5822,6 +5841,10 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,case BTRFS_READ_POLICY_PID : preferred_mirror = first + (current->pid % num_stripes);break ; +case BTRFS_READ_POLICY_DEVICE : + preferred_mirror =btrfs_find_read_preferred (map, first, + num_stripes); +break ; } if (dev_replace_is_ongoing &&
fs/btrfs/volumes.h +2 -0
@@ -260,6 +260,8 @@ enum btrfs_chunk_allocation_policy {enum btrfs_read_policy {/* Use process PID to choose the stripe */ BTRFS_READ_POLICY_PID , +/* Use the device marked with READ_PREFERRED state */ +BTRFS_READ_POLICY_DEVICE ,BTRFS_NR_READ_POLICY , };
Signature · 1 line
2.33.1