Skip to contentSkip to conversation

Documentation: add description of dirty_background_time

PATCH Superseded Namjae Jeon 2 participants 3 messages Aug 27, 2012 – Sep 11, 2012

v1 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH 2/2 Documentation: add description of dirty_background_time

From: Namjae Jeon <[email protected]>

This commit adds dirty_background_time description in bdi sysfs documentation.

---
 Documentation/ABI/testing/sysfs-class-bdi |   13 +++++++++++++
 1 file changed, 13 insertions(+)
Documentation/ABI/testing/sysfs-class-bdi +13 -0
index 5f50097..018e26a 100644
@@ -48,3 +48,16 @@ max_ratio (read-write)
 	most of the write-back cache.  For example in case of an NFS
 	mount that is prone to get stuck, or a FUSE mount which cannot
 	be trusted to play fair.
+
+dirty_background_time (read-write)
+
+	It is used to start early writeback of given bdi once bdi dirty
+	data exceeds product of average write bandwidth and
+	dirty_background_time. It is mainly useful for tuning writeback
+	speed at 'NFS Server' so that NFS client could see better write speed.
+
+	However, sometimes it may not match user expectations as it is based
+	on bdi write bandwidth estimation. Write bandwidth estimation is a
+	best effort to estimate bdi write speed bandwidth. But it can be
+	wildly wrong in certain situations.
+	dirty_background_time is expressed in msec.
Signature · 1 line
1.7.9.5
#1 lore raw
Quoted 16 lines · Namjae Jeon

From: Namjae Jeon <[email protected]>

This commit adds dirty_background_time description in bdi sysfs documentation.

---
 Documentation/ABI/testing/sysfs-class-bdi |   13 +++++++++++++
 1 file changed, 13 insertions(+)
Documentation/ABI/testing/sysfs-class-bdi +0 -0
index 5f50097..018e26a 100644

Documentation/ABI/testing/sysfs-class-bdi max_ratio (read-write) · line 56

Quoted 9 lines
Documentation/ABI/testing/sysfs-class-bdi +6 -0
@@ -48,3 +48,16 @@ max_ratio (read-write)
 	most of the write-back cache.  For example in case of an NFS
 	mount that is prone to get stuck, or a FUSE mount which cannot
 	be trusted to play fair.
+
+dirty_background_time (read-write)
+
+	It is used to start early writeback of given bdi once bdi dirty
+	data exceeds product of average write bandwidth and
+	dirty_background_time.

It may be worth to note that it works _in parallel with_ the global background writeback threshold rather than replacing it.

Documentation/ABI/testing/sysfs-class-bdi max_ratio (read-write) · line 57

Quoted 2 lines

It is mainly useful for tuning writeback

Documentation/ABI/testing/sysfs-class-bdi +1 -0
+	speed at 'NFS Server' so that NFS client could see better write speed.

Hopefully more clear:

A good use case is setting it to around 100 (1 second) in the NFS server for improving NFS write performance. Note that it's not recommended to set it to a too small value, which might lead to small IO size. Setting it to 0 disables the feature.

Documentation/ABI/testing/sysfs-class-bdi

Quoted 2 lines
Documentation/ABI/testing/sysfs-class-bdi +2 -0
+	However, sometimes it may not match user expectations as it is based
+	on bdi write bandwidth estimation.

The users should not expect this threshold to work accurately.

Documentation/ABI/testing/sysfs-class-bdi max_ratio (read-write) · line 62

Quoted 3 lines

Write bandwidth estimation is a

Documentation/ABI/testing/sysfs-class-bdi +2 -0
+	best effort to estimate bdi write speed bandwidth. But it can be
+	wildly wrong in certain situations.

such as sudden change of workload (including the workload startup stage), or if there are no heavy writes since boot, in which case there is no reasonable estimation yet.

Documentation/ABI/testing/sysfs-class-bdi max_ratio (read-write) · line 63

Quoted 1 line
Documentation/ABI/testing/sysfs-class-bdi +1 -0
+	dirty_background_time is expressed in msec.

That can be eliminated if changing to dirty_background_centisecs.

Thanks,
Fengguang

#2 lore raw

Hi. Wu.

I will update documentation as per your suggestion. Thank you.

2012/9/11, Fengguang Wu <[email protected]>:

Quoted 61 lines · Namjae Jeon
Quoted 17 lines

From: Namjae Jeon <[email protected]>

This commit adds dirty_background_time description in bdi sysfs documentation.

---
 Documentation/ABI/testing/sysfs-class-bdi |   13 +++++++++++++
 1 file changed, 13 insertions(+)
Documentation/ABI/testing/sysfs-class-bdi +0 -0
index 5f50097..018e26a 100644

Documentation/ABI/testing/sysfs-class-bdi max_ratio (read-write) · line 56

Quoted 9 lines
Documentation/ABI/testing/sysfs-class-bdi +6 -0
@@ -48,3 +48,16 @@ max_ratio (read-write)
 	most of the write-back cache.  For example in case of an NFS
 	mount that is prone to get stuck, or a FUSE mount which cannot
 	be trusted to play fair.
+
+dirty_background_time (read-write)
+
+	It is used to start early writeback of given bdi once bdi dirty
+	data exceeds product of average write bandwidth and
+	dirty_background_time.

It may be worth to note that it works _in parallel with_ the global background writeback threshold rather than replacing it.

Documentation/ABI/testing/sysfs-class-bdi max_ratio (read-write) · line 57

Quoted 2 lines

It is mainly useful for tuning writeback

Documentation/ABI/testing/sysfs-class-bdi +1 -0
+	speed at 'NFS Server' so that NFS client could see better write speed.

Hopefully more clear:

A good use case is setting it to around 100 (1 second) in the NFS server for improving NFS write performance. Note that it's not recommended to set it to a too small value, which might lead to small IO size. Setting it to 0 disables the feature.

Documentation/ABI/testing/sysfs-class-bdi

Quoted 2 lines
Documentation/ABI/testing/sysfs-class-bdi +2 -0
+	However, sometimes it may not match user expectations as it is based
+	on bdi write bandwidth estimation.

The users should not expect this threshold to work accurately.

Documentation/ABI/testing/sysfs-class-bdi max_ratio (read-write) · line 62

Quoted 3 lines

Write bandwidth estimation is a

Documentation/ABI/testing/sysfs-class-bdi +2 -0
+	best effort to estimate bdi write speed bandwidth. But it can be
+	wildly wrong in certain situations.

such as sudden change of workload (including the workload startup stage), or if there are no heavy writes since boot, in which case there is no reasonable estimation yet.

Documentation/ABI/testing/sysfs-class-bdi max_ratio (read-write) · line 63

Quoted 1 line
Documentation/ABI/testing/sysfs-class-bdi +1 -0
+	dirty_background_time is expressed in msec.

That can be eliminated if changing to dirty_background_centisecs.

Thanks,
Fengguang