glusterfs.git/xlators/cluster/afr/src/afr-inode-write.c, branch v7.8

cluster/afr: Delay post-op for fsync

2020-08-27T20:24:44+00:00

Problem:
AFR doesn't delay post-op for fsync fop. For fsync heavy workloads
this leads to un-necessary fxattrop/finodelk for every fsync leading
to bad performance.

Fix:
Have delayed post-op for fsync. Add special flag in xdata to indicate
that afr shouldn't delay post-op in cases where either the
process will terminate or graph-switch would happen. Otherwise it leads
to un-necessary heals when the graph-switch/process-termination
happens before delayed-post-op completes.

Fixes: #1253
Change-Id: I531940d13269a111c49e0510d49514dc169f4577
Signed-off-by: Pranith Kumar K

multiple files: another attempt to remove includes

2019-06-14T16:50:32+00:00

There are many include statements that are not needed.
A previous more ambitious attempt failed because of *BSD plafrom
(see https://review.gluster.org/#/c/glusterfs/+/21929/ )

Now trying a more conservative reduction.
It does not solve all circular deps that we have, but it
does reduce some of them. There is just too much to handle
reasonably (dht-common.h includes dht-lock.h which includes
dht-common.h ...), but it does reduce the overall number of lines
of include we need to look at in the future to understand and fix
the mess later one.

Change-Id: I550cd001bdefb8be0fe67632f783c0ef6bee3f9f
updates: bz#1193929
Signed-off-by: Yaniv Kaul

cluster/afr: Send inodelk/entrylk with non-zero lk-owner

2019-04-02T12:18:33+00:00

Found missing assignment of lk-owner for an inodelk/entrylk before winding
the fops. locks xlator at the moment allows this operation. This leads to
multiple threads in the same client being able to get locks on the inode
because lk-owner is same and transport is same. So isolation with locks can't
be achieved. To fix it, we need locks xlator change which will disallow
null-lk-owner based inodelk/entrylk/lk. To achieve that we need to first
fix all the places which do this mistake.

updates bz#1624701
Change-Id: Ic3431da3f451a1414f1f4fdcfc4cf41e555f69dd
Signed-off-by: Pranith Kumar K

cluster/afr: fix zerofill transaction.start

2019-01-14T03:20:11+00:00

This maybe one mistake when coding.

Fixes: bz#1665332
Change-Id: Ia8f8dadf4a71579240ff9950b141ca528bd342b3
Signed-off-by: Xiubo Li

cluster/afr: Allow lookup on root if it is from ADD_REPLICA_MOUNT

2018-12-18T10:30:19+00:00

Problem: When trying to convert a plain distribute volume to replica-3
or arbiter type it is failing with ENOTCONN error as the lookup on
the root will fail as there is no quorum.

Fix: Allow lookup on root if it is coming from the ADD_REPLICA_MOUNT
which is used while adding bricks to a volume. It will try to set the
pending xattrs for the newly added bricks to allow the heal to happen
in the right direction and avoid data loss scenarios.

Note: This fix will solve the problem of type conversion only in the
case where the volume was mounted at least once. The conversion of
non mounted volumes will still fail since the dht selfheal tries to
set the directory layout will fail as they do that with the PID
GF_CLIENT_PID_NO_ROOT_SQUASH set in the frame->root.

Change-Id: Ic511939981dad118cc946754341318b164954b3b
fixes: bz#1655854
Signed-off-by: karthik-us

AFR xlator: use dict_{setn|getn|deln|get_int32n|set_int32n|set_strn}

2018-12-17T11:39:14+00:00

In a previous patch (https://review.gluster.org/20769) we've
added the key length to be passed to dict_* funcs, to remove the need
to strlen() it. This patch moves some xlators to use it.

- In some cases, moved strlen() of the key length outside of locks,
which is usually a good thing. Please verify it's safe to do so.
- In some cases, created a prefix for the keys, replacing something like
"%d-%d" with a "%s" in snprintf(). Not sure it adds value, but improves
readability.

Please review carefully.

Compile-tested only!

Change-Id: I04f2a1eb2ecfc3283d849d150d10d088ae7aa7f1
updates: bz#1193929
Signed-off-by: Yaniv Kaul

libglusterfs: Move devel headers under glusterfs directory

2018-12-05T21:47:04+00:00

libglusterfs devel package headers are referenced in code using
include semantics for a program, this while it works can be better
especially when dealing with out of tree xlator builds or in
general out of tree devel package usage.

Towards this, the following changes are done,
- moved all devel headers under a glusterfs directory
- Included these headers using system header notation <> in all
code outside of libglusterfs
- Included these headers using own program notation "" within
libglusterfs

This change although big, is just moving around the headers and
making it correct when including these headers from other sources.

This helps us correctly include libglusterfs includes without
namespace conflicts.

Change-Id: Id2a98854e671a7ee5d73be44da5ba1a74252423b
Updates: bz#1193929
Signed-off-by: ShyamsundarR

libglusterfs/dict: Add sizeof()-1 variants of dict functions

2018-10-15T04:05:30+00:00

One needs to be very careful about giving same key for the key and
SLEN(key) arguments in dict_xxxn() functions. Writing macros that
would take care of passing the SLEN(key) would help reduce this
burden on the developer and reviewer.

updates: bz#1193929
Change-Id: I312c479b919826570b47ae2c219c53e2f9b2ddef
Signed-off-by: Pranith Kumar K

cluster/afr: Make data eager-lock decision based on number of locks

2018-09-21T04:42:43+00:00

For both Virt and block workloads the file is opened multiple times
leading to dynamically setting eager-lock to off for the workload.
Instead of depending on the number-of-open-fds, if we change the
logic to depend on number of inodelks, then it will give better
performance than the earlier logic. When there is an eager-lock
and number of inodelks is more than 1 we know that there is a
conflicting lock, so depend on that information to decide whether
to keep the current transaction go through delayed-post-op or not.

Locks xlator doesn't have implementation to query number of locks in
fxattrop in releases older than 3.10 so to keep things backward
compatible in 3.12, data transactions will use new logic where as
fxattrop transactions will use old logic. I am planning to send one
more patch which makes metadata domain locks also depend on
inodelk-count

Profile info for a dd of 500MB to a file with another fd opened
on the file using exec 250>filename

Without this patch:
 0.14      67.41 us      16.72 us    3870.82 us  892 FINODELK
 0.59     279.87 us      95.71 us    2085.89 us  898 FXATTROP
 3.46     366.43 us      81.75 us    6952.79 us 4000 WRITE
95.79  148733.99 us   50568.12 us  919127.86 us  273 FSYNC

With this patch:
 0.00      51.01 us      38.07 us      80.16 us    4 FINODELK
 0.00     235.43 us     235.43 us     235.43 us    1 TRUNCATE
 0.00     125.07 us      56.80 us     193.33 us    2 GETXATTR
 0.00     135.86 us      62.13 us     209.59 us    2  INODELK
 0.00     197.88 us     155.39 us     253.90 us    4 FXATTROP
 0.00     450.59 us     394.28 us     506.89 us    2  XATTROP
 0.00      56.96 us      19.06 us     406.59 us   23    FLUSH
37.81  273648.93 us      48.43 us 6017657.05 us   44   LOOKUP
62.18    4951.86 us      93.80 us 1143154.75 us 3999    WRITE

postgresql benchmark performance changed from ~1130 TPS to ~2300TPS
randio fio job inside Ovirt based VM went from ~600IOPs to ~2000IOPS

fixes bz#1630368
Change-Id: If7f7388d2f08cf7f17ca517a4ea222560661dc36
Signed-off-by: Pranith Kumar K

Land part 2 of clang-format changes

2018-09-12T12:22:45+00:00

Change-Id: Ia84cc24c8924e6d22d02ac15f611c10e26db99b4
Signed-off-by: Nigel Babu